[PATCHv11.1,5/9] efi: Add unaccepted memory support

efi_config_parse_tables() reserves memory that holds unaccepted memory
configuration table so it won't be reused by page allocator.

Core-mm requires few helpers to support unaccepted memory:

 - accept_memory() checks the range of addresses against the bitmap and
   accept memory if needed.

 - range_contains_unaccepted_memory() checks if anything within the
   range requires acceptance.

Architectural code has to provide efi_get_unaccepted_table() that
returns pointer to the unaccepted memory configuration table.

arch_accept_memory() handles arch-specific part of memory acceptance.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>

v11.1:
 - Add missing memblock_reserve() for the unaccepted memory
   configuration table.

---
 drivers/firmware/efi/Makefile            |   1 +
 drivers/firmware/efi/efi.c               |  25 ++++++
 drivers/firmware/efi/unaccepted_memory.c | 103 +++++++++++++++++++++++
 include/linux/efi.h                      |   1 +
 4 files changed, 130 insertions(+)
 create mode 100644 drivers/firmware/efi/unaccepted_memory.c

On Tue, 16 May 2023 at 14:07, Kirill A. Shutemov
<kirill.shutemov@linux.intel.com> wrote:
>
> efi_config_parse_tables() reserves memory that holds unaccepted memory
> configuration table so it won't be reused by page allocator.
>
> Core-mm requires few helpers to support unaccepted memory:
>
>  - accept_memory() checks the range of addresses against the bitmap and
>    accept memory if needed.
>
>  - range_contains_unaccepted_memory() checks if anything within the
>    range requires acceptance.
>
> Architectural code has to provide efi_get_unaccepted_table() that
> returns pointer to the unaccepted memory configuration table.
>
> arch_accept_memory() handles arch-specific part of memory acceptance.
>
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
>

Reviewed-by: Ard Biesheuvel <ardb@kernel.org>

> v11.1:
>  - Add missing memblock_reserve() for the unaccepted memory
>    configuration table.
>
> ---
>  drivers/firmware/efi/Makefile            |   1 +
>  drivers/firmware/efi/efi.c               |  25 ++++++
>  drivers/firmware/efi/unaccepted_memory.c | 103 +++++++++++++++++++++++
>  include/linux/efi.h                      |   1 +
>  4 files changed, 130 insertions(+)
>  create mode 100644 drivers/firmware/efi/unaccepted_memory.c
>
> diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
> index b51f2a4c821e..e489fefd23da 100644
> --- a/drivers/firmware/efi/Makefile
> +++ b/drivers/firmware/efi/Makefile
> @@ -41,3 +41,4 @@ obj-$(CONFIG_EFI_CAPSULE_LOADER)      += capsule-loader.o
>  obj-$(CONFIG_EFI_EARLYCON)             += earlycon.o
>  obj-$(CONFIG_UEFI_CPER_ARM)            += cper-arm.o
>  obj-$(CONFIG_UEFI_CPER_X86)            += cper-x86.o
> +obj-$(CONFIG_UNACCEPTED_MEMORY)                += unaccepted_memory.o
> diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
> index 7dce06e419c5..d817e7afd266 100644
> --- a/drivers/firmware/efi/efi.c
> +++ b/drivers/firmware/efi/efi.c
> @@ -50,6 +50,9 @@ struct efi __read_mostly efi = {
>  #ifdef CONFIG_EFI_COCO_SECRET
>         .coco_secret            = EFI_INVALID_TABLE_ADDR,
>  #endif
> +#ifdef CONFIG_UNACCEPTED_MEMORY
> +       .unaccepted             = EFI_INVALID_TABLE_ADDR,
> +#endif
>  };
>  EXPORT_SYMBOL(efi);
>
> @@ -605,6 +608,9 @@ static const efi_config_table_type_t common_tables[] __initconst = {
>  #ifdef CONFIG_EFI_COCO_SECRET
>         {LINUX_EFI_COCO_SECRET_AREA_GUID,       &efi.coco_secret,       "CocoSecret"    },
>  #endif
> +#ifdef CONFIG_UNACCEPTED_MEMORY
> +       {LINUX_EFI_UNACCEPTED_MEM_TABLE_GUID,   &efi.unaccepted,        "Unaccepted"    },
> +#endif
>  #ifdef CONFIG_EFI_GENERIC_STUB
>         {LINUX_EFI_SCREEN_INFO_TABLE_GUID,      &screen_info_table                      },
>  #endif
> @@ -759,6 +765,25 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables,
>                 }
>         }
>
> +       if (IS_ENABLED(CONFIG_UNACCEPTED_MEMORY) &&
> +           efi.unaccepted != EFI_INVALID_TABLE_ADDR) {
> +               struct efi_unaccepted_memory *unaccepted;
> +
> +               unaccepted = early_memremap(efi.unaccepted, sizeof(*unaccepted));
> +               if (unaccepted) {
> +                       unsigned long size;
> +
> +                       if (unaccepted->version == 1) {
> +                               size = sizeof(*unaccepted) + unaccepted->size;
> +                               memblock_reserve(efi.unaccepted, size);
> +                       } else {
> +                               efi.unaccepted = EFI_INVALID_TABLE_ADDR;
> +                       }
> +
> +                       early_memunmap(unaccepted, sizeof(*unaccepted));
> +               }
> +       }
> +
>         return 0;
>  }
>
> diff --git a/drivers/firmware/efi/unaccepted_memory.c b/drivers/firmware/efi/unaccepted_memory.c
> new file mode 100644
> index 000000000000..bb91c41f76fb
> --- /dev/null
> +++ b/drivers/firmware/efi/unaccepted_memory.c
> @@ -0,0 +1,103 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +
> +#include <linux/efi.h>
> +#include <linux/memblock.h>
> +#include <linux/spinlock.h>
> +#include <asm/unaccepted_memory.h>
> +
> +/* Protects unaccepted memory bitmap */
> +static DEFINE_SPINLOCK(unaccepted_memory_lock);
> +
> +void accept_memory(phys_addr_t start, phys_addr_t end)
> +{
> +       struct efi_unaccepted_memory *unaccepted;
> +       unsigned long range_start, range_end;
> +       unsigned long flags;
> +       u64 unit_size;
> +
> +       if (efi.unaccepted == EFI_INVALID_TABLE_ADDR)
> +               return;
> +
> +       unaccepted = efi_get_unaccepted_table();
> +       if (!unaccepted)
> +               return;
> +
> +       unit_size = unaccepted->unit_size;
> +
> +       /*
> +        * Only care for the part of the range that is represented
> +        * in the bitmap.
> +        */
> +       if (start < unaccepted->phys_base)
> +               start = unaccepted->phys_base;
> +       if (end < unaccepted->phys_base)
> +               return;
> +
> +       /* Translate to offsets from the beginning of the bitmap */
> +       start -= unaccepted->phys_base;
> +       end -= unaccepted->phys_base;
> +
> +       /* Make sure not to overrun the bitmap */
> +       if (end > unaccepted->size * unit_size * BITS_PER_BYTE)
> +               end = unaccepted->size * unit_size * BITS_PER_BYTE;
> +
> +       range_start = start / unit_size;
> +
> +       spin_lock_irqsave(&unaccepted_memory_lock, flags);
> +       for_each_set_bitrange_from(range_start, range_end, unaccepted->bitmap,
> +                                  DIV_ROUND_UP(end, unit_size)) {
> +               unsigned long phys_start, phys_end;
> +               unsigned long len = range_end - range_start;
> +
> +               phys_start = range_start * unit_size + unaccepted->phys_base;
> +               phys_end = range_end * unit_size + unaccepted->phys_base;
> +
> +               arch_accept_memory(phys_start, phys_end);
> +               bitmap_clear(unaccepted->bitmap, range_start, len);
> +       }
> +       spin_unlock_irqrestore(&unaccepted_memory_lock, flags);
> +}
> +
> +bool range_contains_unaccepted_memory(phys_addr_t start, phys_addr_t end)
> +{
> +       struct efi_unaccepted_memory *unaccepted;
> +       unsigned long flags;
> +       bool ret = false;
> +       u64 unit_size;
> +
> +       unaccepted = efi_get_unaccepted_table();
> +       if (!unaccepted)
> +               return false;
> +
> +       unit_size = unaccepted->unit_size;
> +
> +       /*
> +        * Only care for the part of the range that is represented
> +        * in the bitmap.
> +        */
> +       if (start < unaccepted->phys_base)
> +               start = unaccepted->phys_base;
> +       if (end < unaccepted->phys_base)
> +               return false;
> +
> +       /* Translate to offsets from the beginning of the bitmap */
> +       start -= unaccepted->phys_base;
> +       end -= unaccepted->phys_base;
> +
> +       /* Make sure not to overrun the bitmap */
> +       if (end > unaccepted->size * unit_size * BITS_PER_BYTE)
> +               end = unaccepted->size * unit_size * BITS_PER_BYTE;
> +
> +       spin_lock_irqsave(&unaccepted_memory_lock, flags);
> +       while (start < end) {
> +               if (test_bit(start / unit_size, unaccepted->bitmap)) {
> +                       ret = true;
> +                       break;
> +               }
> +
> +               start += unit_size;
> +       }
> +       spin_unlock_irqrestore(&unaccepted_memory_lock, flags);
> +
> +       return ret;
> +}
> diff --git a/include/linux/efi.h b/include/linux/efi.h
> index 29cc622910da..9864f9c00da2 100644
> --- a/include/linux/efi.h
> +++ b/include/linux/efi.h
> @@ -646,6 +646,7 @@ extern struct efi {
>         unsigned long                   tpm_final_log;          /* TPM2 Final Events Log table */
>         unsigned long                   mokvar_table;           /* MOK variable config table */
>         unsigned long                   coco_secret;            /* Confidential computing secret table */
> +       unsigned long                   unaccepted;             /* Unaccepted memory table */
>
>         efi_get_time_t                  *get_time;
>         efi_set_time_t                  *set_time;
> --
> 2.39.3
>

On 5/16/23 07:06, Kirill A. Shutemov wrote:
> efi_config_parse_tables() reserves memory that holds unaccepted memory
> configuration table so it won't be reused by page allocator.
> 
> Core-mm requires few helpers to support unaccepted memory:
> 
>   - accept_memory() checks the range of addresses against the bitmap and
>     accept memory if needed.
> 
>   - range_contains_unaccepted_memory() checks if anything within the
>     range requires acceptance.
> 
> Architectural code has to provide efi_get_unaccepted_table() that
> returns pointer to the unaccepted memory configuration table.
> 
> arch_accept_memory() handles arch-specific part of memory acceptance.
> 
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>

Can you also add the efi.unaccepted table to the efi_tables array in 
arch/x86/platform/efi/efi.c?

With that...

Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>

> 
> v11.1:
>   - Add missing memblock_reserve() for the unaccepted memory
>     configuration table.
> 
> ---
>   drivers/firmware/efi/Makefile            |   1 +
>   drivers/firmware/efi/efi.c               |  25 ++++++
>   drivers/firmware/efi/unaccepted_memory.c | 103 +++++++++++++++++++++++
>   include/linux/efi.h                      |   1 +
>   4 files changed, 130 insertions(+)
>   create mode 100644 drivers/firmware/efi/unaccepted_memory.c
> 
> diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
> index b51f2a4c821e..e489fefd23da 100644
> --- a/drivers/firmware/efi/Makefile
> +++ b/drivers/firmware/efi/Makefile
> @@ -41,3 +41,4 @@ obj-$(CONFIG_EFI_CAPSULE_LOADER)	+= capsule-loader.o
>   obj-$(CONFIG_EFI_EARLYCON)		+= earlycon.o
>   obj-$(CONFIG_UEFI_CPER_ARM)		+= cper-arm.o
>   obj-$(CONFIG_UEFI_CPER_X86)		+= cper-x86.o
> +obj-$(CONFIG_UNACCEPTED_MEMORY)		+= unaccepted_memory.o
> diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
> index 7dce06e419c5..d817e7afd266 100644
> --- a/drivers/firmware/efi/efi.c
> +++ b/drivers/firmware/efi/efi.c
> @@ -50,6 +50,9 @@ struct efi __read_mostly efi = {
>   #ifdef CONFIG_EFI_COCO_SECRET
>   	.coco_secret		= EFI_INVALID_TABLE_ADDR,
>   #endif
> +#ifdef CONFIG_UNACCEPTED_MEMORY
> +	.unaccepted		= EFI_INVALID_TABLE_ADDR,
> +#endif
>   };
>   EXPORT_SYMBOL(efi);
>   
> @@ -605,6 +608,9 @@ static const efi_config_table_type_t common_tables[] __initconst = {
>   #ifdef CONFIG_EFI_COCO_SECRET
>   	{LINUX_EFI_COCO_SECRET_AREA_GUID,	&efi.coco_secret,	"CocoSecret"	},
>   #endif
> +#ifdef CONFIG_UNACCEPTED_MEMORY
> +	{LINUX_EFI_UNACCEPTED_MEM_TABLE_GUID,	&efi.unaccepted,	"Unaccepted"	},
> +#endif
>   #ifdef CONFIG_EFI_GENERIC_STUB
>   	{LINUX_EFI_SCREEN_INFO_TABLE_GUID,	&screen_info_table			},
>   #endif
> @@ -759,6 +765,25 @@ int __init efi_config_parse_tables(const efi_config_table_t *config_tables,
>   		}
>   	}
>   
> +	if (IS_ENABLED(CONFIG_UNACCEPTED_MEMORY) &&
> +	    efi.unaccepted != EFI_INVALID_TABLE_ADDR) {
> +		struct efi_unaccepted_memory *unaccepted;
> +
> +		unaccepted = early_memremap(efi.unaccepted, sizeof(*unaccepted));
> +		if (unaccepted) {
> +			unsigned long size;
> +
> +			if (unaccepted->version == 1) {
> +				size = sizeof(*unaccepted) + unaccepted->size;
> +				memblock_reserve(efi.unaccepted, size);
> +			} else {
> +				efi.unaccepted = EFI_INVALID_TABLE_ADDR;
> +			}
> +
> +			early_memunmap(unaccepted, sizeof(*unaccepted));
> +		}
> +	}
> +
>   	return 0;
>   }
>   
> diff --git a/drivers/firmware/efi/unaccepted_memory.c b/drivers/firmware/efi/unaccepted_memory.c
> new file mode 100644
> index 000000000000..bb91c41f76fb
> --- /dev/null
> +++ b/drivers/firmware/efi/unaccepted_memory.c
> @@ -0,0 +1,103 @@
> +// SPDX-License-Identifier: GPL-2.0-only
> +
> +#include <linux/efi.h>
> +#include <linux/memblock.h>
> +#include <linux/spinlock.h>
> +#include <asm/unaccepted_memory.h>
> +
> +/* Protects unaccepted memory bitmap */
> +static DEFINE_SPINLOCK(unaccepted_memory_lock);
> +
> +void accept_memory(phys_addr_t start, phys_addr_t end)
> +{
> +	struct efi_unaccepted_memory *unaccepted;
> +	unsigned long range_start, range_end;
> +	unsigned long flags;
> +	u64 unit_size;
> +
> +	if (efi.unaccepted == EFI_INVALID_TABLE_ADDR)
> +		return;
> +
> +	unaccepted = efi_get_unaccepted_table();
> +	if (!unaccepted)
> +		return;
> +
> +	unit_size = unaccepted->unit_size;
> +
> +	/*
> +	 * Only care for the part of the range that is represented
> +	 * in the bitmap.
> +	 */
> +	if (start < unaccepted->phys_base)
> +		start = unaccepted->phys_base;
> +	if (end < unaccepted->phys_base)
> +		return;
> +
> +	/* Translate to offsets from the beginning of the bitmap */
> +	start -= unaccepted->phys_base;
> +	end -= unaccepted->phys_base;
> +
> +	/* Make sure not to overrun the bitmap */
> +	if (end > unaccepted->size * unit_size * BITS_PER_BYTE)
> +		end = unaccepted->size * unit_size * BITS_PER_BYTE;
> +
> +	range_start = start / unit_size;
> +
> +	spin_lock_irqsave(&unaccepted_memory_lock, flags);
> +	for_each_set_bitrange_from(range_start, range_end, unaccepted->bitmap,
> +				   DIV_ROUND_UP(end, unit_size)) {
> +		unsigned long phys_start, phys_end;
> +		unsigned long len = range_end - range_start;
> +
> +		phys_start = range_start * unit_size + unaccepted->phys_base;
> +		phys_end = range_end * unit_size + unaccepted->phys_base;
> +
> +		arch_accept_memory(phys_start, phys_end);
> +		bitmap_clear(unaccepted->bitmap, range_start, len);
> +	}
> +	spin_unlock_irqrestore(&unaccepted_memory_lock, flags);
> +}
> +
> +bool range_contains_unaccepted_memory(phys_addr_t start, phys_addr_t end)
> +{
> +	struct efi_unaccepted_memory *unaccepted;
> +	unsigned long flags;
> +	bool ret = false;
> +	u64 unit_size;
> +
> +	unaccepted = efi_get_unaccepted_table();
> +	if (!unaccepted)
> +		return false;
> +
> +	unit_size = unaccepted->unit_size;
> +
> +	/*
> +	 * Only care for the part of the range that is represented
> +	 * in the bitmap.
> +	 */
> +	if (start < unaccepted->phys_base)
> +		start = unaccepted->phys_base;
> +	if (end < unaccepted->phys_base)
> +		return false;
> +
> +	/* Translate to offsets from the beginning of the bitmap */
> +	start -= unaccepted->phys_base;
> +	end -= unaccepted->phys_base;
> +
> +	/* Make sure not to overrun the bitmap */
> +	if (end > unaccepted->size * unit_size * BITS_PER_BYTE)
> +		end = unaccepted->size * unit_size * BITS_PER_BYTE;
> +
> +	spin_lock_irqsave(&unaccepted_memory_lock, flags);
> +	while (start < end) {
> +		if (test_bit(start / unit_size, unaccepted->bitmap)) {
> +			ret = true;
> +			break;
> +		}
> +
> +		start += unit_size;
> +	}
> +	spin_unlock_irqrestore(&unaccepted_memory_lock, flags);
> +
> +	return ret;
> +}
> diff --git a/include/linux/efi.h b/include/linux/efi.h
> index 29cc622910da..9864f9c00da2 100644
> --- a/include/linux/efi.h
> +++ b/include/linux/efi.h
> @@ -646,6 +646,7 @@ extern struct efi {
>   	unsigned long			tpm_final_log;		/* TPM2 Final Events Log table */
>   	unsigned long			mokvar_table;		/* MOK variable config table */
>   	unsigned long			coco_secret;		/* Confidential computing secret table */
> +	unsigned long			unaccepted;		/* Unaccepted memory table */
>   
>   	efi_get_time_t			*get_time;
>   	efi_set_time_t			*set_time;