RISC-V: Support separate firmware and kernel payload

Support for separate firmware and kernel payload is added
by updating BBL to read optional preloaded kernel address
attributes from device-tree using a similar mechanism to
that used to pass init ramdisk addresses to linux kernel.

    chosen {
        riscv,kernel-start = <0x00000000 0x80200000>;
        riscv,kernel-end = <0x00000000 0x80590634>;
    };

These attributes are added by QEMU and read by BBL when combining
-bios <firmware-image> and -kernel <kernel-image> options. e.g.

$ qemu-system-riscv64 -machine virt -bios bbl -kernel vmlinux

With this change, bbl can be compiled without --with-payload
and the dummy payload alignment is altered to make the memory
footprint of the firmware-only bbl smaller. The dummy payload
message is updated to indicate the alternative load method.

This load method could also be supported by a first stage boot
loader that reads seperate firmware and kernel from SPI flash.
The main advantage of this new mechanism is that it eases kernel
development by avoiding the riscv-pk packaging step after kernel
builds, makes building per repository artefacts for CI simpler,
and mimics bootloaders on other platforms that can load a kernel
image file directly. Ultimately BBL should use an SPI driver to
load the kernel image however this mechanism supports use cases
such such as QEMU's -bios, -kernel and -initrd options following
examples from other platforms that pass kernel entry to firmware
via device-tree.

Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Alistair Francis <Alistair.Francis@wdc.com>
Signed-off-by: Michael Clark <mjc@sifive.com>

3 files changed, 27 insertions, 6 deletions

diff --git a/bbl/bbl.ac b/bbl/bbl.ac
index 80d3b06..55ff50b 100644
--- a/bbl/bbl.ac
+++ b/bbl/bbl.ac
@@ -4,8 +4,13 @@ AS_IF([test "x$enable_logo" == "xyes"], [
 ])
 
 AC_ARG_WITH([payload], AS_HELP_STRING([--with-payload], [Set ELF payload for bbl]),
-  [AC_SUBST([BBL_PAYLOAD], $with_payload, [Kernel payload for bbl])],
-  [AC_SUBST([BBL_PAYLOAD], [dummy_payload], [Kernel payload for bbl])])
+  [
+   AC_SUBST([BBL_PAYLOAD], $with_payload, [Kernel payload for bbl])
+   AC_DEFINE(RELAXED_ALIGNMENT,[0],[Use relaxed payload alignment])
+  ], [
+   AC_SUBST([BBL_PAYLOAD], [dummy_payload], [Kernel payload for bbl])
+   AC_DEFINE(RELAXED_ALIGNMENT,[1],[Use relaxed payload alignment])
+  ])
 
 AC_ARG_WITH([logo], AS_HELP_STRING([--with-logo], [Specify a better logo]),
   [AC_SUBST([BBL_LOGO_FILE], $with_logo, [Logo for bbl])],
diff --git a/bbl/bbl.c b/bbl/bbl.c
index 1b96a9d..93746ff 100644
--- a/bbl/bbl.c
+++ b/bbl/bbl.c
@@ -7,13 +7,21 @@
 #include "fdt.h"
 #include <string.h>
 
+extern char _payload_start, _payload_end; /* internal payload */
 static const void* entry_point;
 long disabled_hart_mask;
 
 static uintptr_t dtb_output()
 {
-  extern char _payload_end;
-  uintptr_t end = (uintptr_t) &_payload_end;
+  /*
+   * Place DTB after the payload, either the internal payload or a
+   * preloaded external payload specified in device-tree, if present.
+   *
+   * Note: linux kernel calls __va(dtb) to get the device-tree virtual
+   * address. The kernel's virtual mapping begins at its load address,
+   * thus mandating device-tree is in physical memory after the kernel.
+   */
+  uintptr_t end = kernel_end ? (uintptr_t)kernel_end : (uintptr_t)&_payload_end;
   return (end + MEGAPAGE_SIZE - 1) / MEGAPAGE_SIZE * MEGAPAGE_SIZE;
 }
 
@@ -53,7 +61,6 @@ void boot_other_hart(uintptr_t unused __attribute__((unused)))
 
 void boot_loader(uintptr_t dtb)
 {
-  extern char _payload_start;
   filter_dtb(dtb);
 #ifdef PK_ENABLE_LOGO
   print_logo();
@@ -62,6 +69,7 @@ void boot_loader(uintptr_t dtb)
   fdt_print(dtb_output());
 #endif
   mb();
-  entry_point = &_payload_start;
+  /* Use optional FDT preloaded external payload if present */
+  entry_point = kernel_start ? kernel_start : &_payload_start;
   boot_other_hart(0);
 }
diff --git a/bbl/payload.S b/bbl/payload.S
index 6a175aa..b6797aa 100644
--- a/bbl/payload.S
+++ b/bbl/payload.S
@@ -1,7 +1,15 @@
+#include "config.h"
 #include "encoding.h"
 
   .section ".payload","a",@progbits
+
+#if RELAXED_ALIGNMENT
+  /* align payload minimally */
+  .align 3
+#else
+  /* align payload to megapage */
   .align RISCV_PGSHIFT + RISCV_PGLEVEL_BITS
+#endif
 
   .globl _payload_start, _payload_end
 _payload_start: