When KHO (Kexec HandOver) is enabled, it sets up scratch memory regions
early during device tree scanning. After kexec, the new kernel
exclusively uses this region for memory allocations during boot up to
the initialization of the page allocator

However, when booting with EFI, EFI's reserve_regions() uses
memblock_remove(0, PHYS_ADDR_MAX) to clear all memory regions before
rebuilding them from EFI data. This destroys KHO scratch regions and
their flags, thus causing a kernel panic, as there are no scratch
memory regions.

Instead of wholesale removal, iterate through memory regions and only
remove non-KHO ones. This preserves KHO scratch regions, which are
good known memory, while still allowing EFI to rebuild its memory map.

Signed-off-by: Evangelos Petrongonas <epetron@amazon.de>
---
Changes in v2:
	- Replaced the for loop with for_each_mem_region
	- Fixed comment indentation
	- Amended commit message to specify that scratch regions
	are known good regions

 drivers/firmware/efi/efi-init.c | 28 ++++++++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)

diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c
index a00e07b853f2..99f7eecc320f 100644
--- a/drivers/firmware/efi/efi-init.c
+++ b/drivers/firmware/efi/efi-init.c
@@ -12,6 +12,7 @@
 #include <linux/efi.h>
 #include <linux/fwnode.h>
 #include <linux/init.h>
+#include <linux/kexec_handover.h>
 #include <linux/memblock.h>
 #include <linux/mm_types.h>
 #include <linux/of.h>
@@ -164,12 +165,31 @@ static __init void reserve_regions(void)
 		pr_info("Processing EFI memory map:\n");
 
 	/*
-	 * Discard memblocks discovered so far: if there are any at this
-	 * point, they originate from memory nodes in the DT, and UEFI
-	 * uses its own memory map instead.
+	 * Discard memblocks discovered so far except for KHO scratch
+	 * regions. Most memblocks at this point originate from memory nodes
+	 * in the DT and UEFI uses its own memory map instead. However, if
+	 * KHO is enabled, scratch regions must be preserved.
 	 */
 	memblock_dump_all();
-	memblock_remove(0, PHYS_ADDR_MAX);
+
+	if (is_kho_boot()) {
+		struct memblock_region *r;
+
+		/* Remove all non-KHO regions */
+		for_each_mem_region(r) {
+			if (!memblock_is_kho_scratch(r)) {
+				memblock_remove(r->base, r->size);
+				r--;
+			}
+		}
+	} else {
+		/*
+		 * KHO is disabled. Discard memblocks discovered so far:
+		 * if there are any at this point, they originate from memory
+		 * nodes in the DT, and UEFI uses its own memory map instead.
+		 */
+		memblock_remove(0, PHYS_ADDR_MAX);
+	}
 
 	for_each_efi_memory_desc(md) {
 		paddr = md->phys_addr;
-- 
2.47.3




Amazon Web Services Development Center Germany GmbH
Tamara-Danz-Str. 13
10243 Berlin
Geschaeftsfuehrung: Christian Schlaeger, Jonathan Weiss
Eingetragen am Amtsgericht Charlottenburg unter HRB 257764 B
Sitz: Berlin
Ust-ID: DE 365 538 597

On Tue, Aug 19, 2025 at 11:22:46PM +0000, Evangelos Petrongonas wrote:
> When KHO (Kexec HandOver) is enabled, it sets up scratch memory regions
> early during device tree scanning. After kexec, the new kernel
> exclusively uses this region for memory allocations during boot up to
> the initialization of the page allocator
> 
> However, when booting with EFI, EFI's reserve_regions() uses
> memblock_remove(0, PHYS_ADDR_MAX) to clear all memory regions before
> rebuilding them from EFI data. This destroys KHO scratch regions and
> their flags, thus causing a kernel panic, as there are no scratch
> memory regions.
> 
> Instead of wholesale removal, iterate through memory regions and only
> remove non-KHO ones. This preserves KHO scratch regions, which are
> good known memory, while still allowing EFI to rebuild its memory map.
> 
> Signed-off-by: Evangelos Petrongonas <epetron@amazon.de>
> ---
> Changes in v2:
> 	- Replaced the for loop with for_each_mem_region
> 	- Fixed comment indentation
> 	- Amended commit message to specify that scratch regions
> 	are known good regions
> 
>  drivers/firmware/efi/efi-init.c | 28 ++++++++++++++++++++++++----
>  1 file changed, 24 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c
> index a00e07b853f2..99f7eecc320f 100644
> --- a/drivers/firmware/efi/efi-init.c
> +++ b/drivers/firmware/efi/efi-init.c
> @@ -12,6 +12,7 @@
>  #include <linux/efi.h>
>  #include <linux/fwnode.h>
>  #include <linux/init.h>
> +#include <linux/kexec_handover.h>
>  #include <linux/memblock.h>
>  #include <linux/mm_types.h>
>  #include <linux/of.h>
> @@ -164,12 +165,31 @@ static __init void reserve_regions(void)
>  		pr_info("Processing EFI memory map:\n");
>  
>  	/*
> -	 * Discard memblocks discovered so far: if there are any at this
> -	 * point, they originate from memory nodes in the DT, and UEFI
> -	 * uses its own memory map instead.
> +	 * Discard memblocks discovered so far except for KHO scratch
> +	 * regions. Most memblocks at this point originate from memory nodes
> +	 * in the DT and UEFI uses its own memory map instead. However, if
> +	 * KHO is enabled, scratch regions must be preserved.

I'd add that KHO scratch regions are good know memory here as well. With
that

Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>

>  	 */
>  	memblock_dump_all();
> -	memblock_remove(0, PHYS_ADDR_MAX);
> +
> +	if (is_kho_boot()) {
> +		struct memblock_region *r;
> +
> +		/* Remove all non-KHO regions */
> +		for_each_mem_region(r) {
> +			if (!memblock_is_kho_scratch(r)) {
> +				memblock_remove(r->base, r->size);
> +				r--;
> +			}
> +		}
> +	} else {
> +		/*
> +		 * KHO is disabled. Discard memblocks discovered so far:
> +		 * if there are any at this point, they originate from memory
> +		 * nodes in the DT, and UEFI uses its own memory map instead.
> +		 */
> +		memblock_remove(0, PHYS_ADDR_MAX);
> +	}
>  
>  	for_each_efi_memory_desc(md) {
>  		paddr = md->phys_addr;
> -- 
> 2.47.3

-- 
Sincerely yours,
Mike.