kexec: add KHO support to kexec file loads

Kexec has 2 modes: A user space driven mode and a kernel driven mode.  For
the kernel driven mode, kernel code determines the physical addresses of
all target buffers that the payload gets copied into.

With KHO, we can only safely copy payloads into the "scratch area".  Teach
the kexec file loader about it, so it only allocates for that area.  In
addition, enlighten it with support to ask the KHO subsystem for its
respective payloads to copy into target memory.  Also teach the KHO
subsystem how to fill the images for file loads.

Link: https://lkml.kernel.org/r/20250509074635.3187114-8-changyuanl@google.com
Signed-off-by: Alexander Graf <graf@amazon.com>
Co-developed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Co-developed-by: Changyuan Lyu <changyuanl@google.com>
Signed-off-by: Changyuan Lyu <changyuanl@google.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Anthony Yznaga <anthony.yznaga@oracle.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Ashish Kalra <ashish.kalra@amd.com>
Cc: Ben Herrenschmidt <benh@kernel.crashing.org>
Cc: Borislav Betkov <bp@alien8.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Gowans <jgowans@amazon.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Krzysztof Kozlowski <krzk@kernel.org>
Cc: Marc Rutland <mark.rutland@arm.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Pratyush Yadav <ptyadav@amazon.de>
Cc: Rob Herring <robh@kernel.org>
Cc: Saravana Kannan <saravanak@google.com>
Cc: Stanislav Kinsburskii <skinsburskii@linux.microsoft.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleinxer <tglx@linutronix.de>
Cc: Thomas Lendacky <thomas.lendacky@amd.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

include/linux/kexec.h

@@ -371,6 +371,11 @@ struct kimage {
 	size_t ima_buffer_size;
 #endif
 
+	struct {
+		struct kexec_segment *scratch;
+		phys_addr_t fdt;
+	} kho;
+
 	/* Core ELF header buffer */
 	void *elf_headers;
 	unsigned long elf_headers_sz;

kernel/kexec_file.c

@@ -253,6 +253,11 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 	/* IMA needs to pass the measurement list to the next kernel. */
 	ima_add_kexec_buffer(image);
 
+	/* If KHO is active, add its images to the list */
+	ret = kho_fill_kimage(image);
+	if (ret)
+		goto out;
+
 	/* Call image load handler */
 	ldata = kexec_image_load_default(image);
 
@@ -648,6 +653,14 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf)
 	if (kbuf->mem != KEXEC_BUF_MEM_UNKNOWN)
 		return 0;
 
+	/*
+	 * If KHO is active, only use KHO scratch memory. All other memory
+	 * could potentially be handed over.
+	 */
+	ret = kho_locate_mem_hole(kbuf, locate_mem_hole_callback);
+	if (ret <= 0)
+		return ret;
+
 	if (!IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
 		ret = kexec_walk_resources(kbuf, locate_mem_hole_callback);
 	else

kernel/kexec_handover.c

@@ -26,6 +26,7 @@
  * internal APIs.
  */
 #include "../mm/internal.h"
+#include "kexec_internal.h"
 
 #define KHO_FDT_COMPATIBLE "kho-v1"
 #define PROP_PRESERVED_MEMORY_MAP "preserved-memory-map"
@@ -1197,3 +1198,69 @@ out:
 	if (err)
 		pr_warn("disabling KHO revival: %d\n", err);
 }
+
+/* Helper functions for kexec_file_load */
+
+int kho_fill_kimage(struct kimage *image)
+{
+	ssize_t scratch_size;
+	int err = 0;
+	struct kexec_buf scratch;
+
+	if (!kho_enable)
+		return 0;
+
+	image->kho.fdt = page_to_phys(kho_out.ser.fdt);
+
+	scratch_size = sizeof(*kho_scratch) * kho_scratch_cnt;
+	scratch = (struct kexec_buf){
+		.image = image,
+		.buffer = kho_scratch,
+		.bufsz = scratch_size,
+		.mem = KEXEC_BUF_MEM_UNKNOWN,
+		.memsz = scratch_size,
+		.buf_align = SZ_64K, /* Makes it easier to map */
+		.buf_max = ULONG_MAX,
+		.top_down = true,
+	};
+	err = kexec_add_buffer(&scratch);
+	if (err)
+		return err;
+	image->kho.scratch = &image->segment[image->nr_segments - 1];
+
+	return 0;
+}
+
+static int kho_walk_scratch(struct kexec_buf *kbuf,
+			    int (*func)(struct resource *, void *))
+{
+	int ret = 0;
+	int i;
+
+	for (i = 0; i < kho_scratch_cnt; i++) {
+		struct resource res = {
+			.start = kho_scratch[i].addr,
+			.end = kho_scratch[i].addr + kho_scratch[i].size - 1,
+		};
+
+		/* Try to fit the kimage into our KHO scratch region */
+		ret = func(&res, kbuf);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+int kho_locate_mem_hole(struct kexec_buf *kbuf,
+			int (*func)(struct resource *, void *))
+{
+	int ret;
+
+	if (!kho_enable || kbuf->image->type == KEXEC_TYPE_CRASH)
+		return 1;
+
+	ret = kho_walk_scratch(kbuf, func);
+
+	return ret == 1 ? 0 : -EADDRNOTAVAIL;
+}

kernel/kexec_internal.h

@@ -39,4 +39,20 @@ extern size_t kexec_purgatory_size;
 #else /* CONFIG_KEXEC_FILE */
 static inline void kimage_file_post_load_cleanup(struct kimage *image) { }
 #endif /* CONFIG_KEXEC_FILE */
+
+struct kexec_buf;
+
+#ifdef CONFIG_KEXEC_HANDOVER
+int kho_locate_mem_hole(struct kexec_buf *kbuf,
+			int (*func)(struct resource *, void *));
+int kho_fill_kimage(struct kimage *image);
+#else
+static inline int kho_locate_mem_hole(struct kexec_buf *kbuf,
+				      int (*func)(struct resource *, void *))
+{
+	return 1;
+}
+
+static inline int kho_fill_kimage(struct kimage *image) { return 0; }
+#endif /* CONFIG_KEXEC_HANDOVER */
 #endif /* LINUX_KEXEC_INTERNAL_H */