Merge patch series "remove size limit on XIP kernel"

Nam Cao <namcao@linutronix.de> says:

Hi,

For XIP kernel, the writable data section is always at offset specified in
XIP_OFFSET, which is hard-coded to 32MB.

Unfortunately, this means the read-only section (placed before the
writable section) is restricted in size. This causes build failure if the
kernel gets too large.

This series remove the use of XIP_OFFSET one by one, then remove this
macro entirely at the end, with the goal of lifting this size restriction.

Also some cleanup and documentation along the way.

* b4-shazam-merge
  riscv: remove limit on the size of read-only section for XIP kernel
  riscv: drop the use of XIP_OFFSET in create_kernel_page_table()
  riscv: drop the use of XIP_OFFSET in kernel_mapping_va_to_pa()
  riscv: drop the use of XIP_OFFSET in XIP_FIXUP_FLASH_OFFSET
  riscv: drop the use of XIP_OFFSET in XIP_FIXUP_OFFSET
  riscv: replace misleading va_kernel_pa_offset on XIP kernel
  riscv: don't export va_kernel_pa_offset in vmcoreinfo for XIP kernel
  riscv: cleanup XIP_FIXUP macro
  riscv: change XIP's kernel_map.size to be size of the entire kernel
  ...

Link: https://lore.kernel.org/r/cover.1717789719.git.namcao@linutronix.de
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>

4 files changed, 53 insertions, 26 deletions

diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
index 7ede2111c591..32d308a3355f 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -112,11 +112,13 @@ struct kernel_mapping {
 	/* Offset between linear mapping virtual address and kernel load address */
 	unsigned long va_pa_offset;
 	/* Offset between kernel mapping virtual address and kernel load address */
-	unsigned long va_kernel_pa_offset;
-	unsigned long va_kernel_xip_pa_offset;
 #ifdef CONFIG_XIP_KERNEL
+	unsigned long va_kernel_xip_text_pa_offset;
+	unsigned long va_kernel_xip_data_pa_offset;
 	uintptr_t xiprom;
 	uintptr_t xiprom_sz;
+#else
+	unsigned long va_kernel_pa_offset;
 #endif
 };
 
@@ -134,12 +136,18 @@ extern phys_addr_t phys_ram_base;
 #else
 void *linear_mapping_pa_to_va(unsigned long x);
 #endif
+
+#ifdef CONFIG_XIP_KERNEL
 #define kernel_mapping_pa_to_va(y)	({					\
 	unsigned long _y = (unsigned long)(y);					\
-	(IS_ENABLED(CONFIG_XIP_KERNEL) && _y < phys_ram_base) ?			\
-		(void *)(_y + kernel_map.va_kernel_xip_pa_offset) :		\
-		(void *)(_y + kernel_map.va_kernel_pa_offset + XIP_OFFSET);	\
+	(_y < phys_ram_base) ?							\
+		(void *)(_y + kernel_map.va_kernel_xip_text_pa_offset) :	\
+		(void *)(_y + kernel_map.va_kernel_xip_data_pa_offset);		\
 	})
+#else
+#define kernel_mapping_pa_to_va(y) ((void *)((unsigned long)(y) + kernel_map.va_kernel_pa_offset))
+#endif
+
 #define __pa_to_va_nodebug(x)		linear_mapping_pa_to_va(x)
 
 #ifndef CONFIG_DEBUG_VIRTUAL
@@ -147,12 +155,17 @@ void *linear_mapping_pa_to_va(unsigned long x);
 #else
 phys_addr_t linear_mapping_va_to_pa(unsigned long x);
 #endif
+
+#ifdef CONFIG_XIP_KERNEL
 #define kernel_mapping_va_to_pa(y) ({						\
 	unsigned long _y = (unsigned long)(y);					\
-	(IS_ENABLED(CONFIG_XIP_KERNEL) && _y < kernel_map.virt_addr + XIP_OFFSET) ? \
-		(_y - kernel_map.va_kernel_xip_pa_offset) :			\
-		(_y - kernel_map.va_kernel_pa_offset - XIP_OFFSET);		\
+	(_y < kernel_map.virt_addr + kernel_map.xiprom_sz) ?			\
+		(_y - kernel_map.va_kernel_xip_text_pa_offset) :		\
+		(_y - kernel_map.va_kernel_xip_data_pa_offset);			\
 	})
+#else
+#define kernel_mapping_va_to_pa(y) ((unsigned long)(y) - kernel_map.va_kernel_pa_offset)
+#endif
 
 #define __va_to_pa_nodebug(x)	({						\
 	unsigned long _x = x;							\
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 089f3c9f56a3..ede2f921967c 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -107,13 +107,6 @@
 
 #endif
 
-#ifdef CONFIG_XIP_KERNEL
-#define XIP_OFFSET		SZ_32M
-#define XIP_OFFSET_MASK		(SZ_32M - 1)
-#else
-#define XIP_OFFSET		0
-#endif
-
 #ifndef __ASSEMBLY__
 
 #include <asm/page.h>
@@ -142,11 +135,14 @@
 
 #ifdef CONFIG_XIP_KERNEL
 #define XIP_FIXUP(addr) ({							\
+	extern char _sdata[], _start[], _end[];					\
+	uintptr_t __rom_start_data = CONFIG_XIP_PHYS_ADDR			\
+				+ (uintptr_t)&_sdata - (uintptr_t)&_start;	\
+	uintptr_t __rom_end_data = CONFIG_XIP_PHYS_ADDR				\
+				+ (uintptr_t)&_end - (uintptr_t)&_start;	\
 	uintptr_t __a = (uintptr_t)(addr);					\
-	(__a >= CONFIG_XIP_PHYS_ADDR && \
-	 __a < CONFIG_XIP_PHYS_ADDR + XIP_OFFSET * 2) ?	\
-		__a - CONFIG_XIP_PHYS_ADDR + CONFIG_PHYS_RAM_BASE - XIP_OFFSET :\
-		__a;								\
+	(__a >= __rom_start_data && __a < __rom_end_data) ?			\
+		__a - __rom_start_data + CONFIG_PHYS_RAM_BASE :	__a;		\
 	})
 #else
 #define XIP_FIXUP(addr)		(addr)
diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h
index ec11001c3fe0..ab92fc84e1fc 100644
--- a/arch/riscv/include/asm/set_memory.h
+++ b/arch/riscv/include/asm/set_memory.h
@@ -46,7 +46,7 @@ bool kernel_page_present(struct page *page);
 
 #endif /* __ASSEMBLY__ */
 
-#ifdef CONFIG_STRICT_KERNEL_RWX
+#if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_XIP_KERNEL)
 #ifdef CONFIG_64BIT
 #define SECTION_ALIGN (1 << 21)
 #else
diff --git a/arch/riscv/include/asm/xip_fixup.h b/arch/riscv/include/asm/xip_fixup.h
index b65bf6306f69..f3d56299bc22 100644
--- a/arch/riscv/include/asm/xip_fixup.h
+++ b/arch/riscv/include/asm/xip_fixup.h
@@ -9,18 +9,36 @@
 
 #ifdef CONFIG_XIP_KERNEL
 .macro XIP_FIXUP_OFFSET reg
-        REG_L t0, _xip_fixup
+	/* Fix-up address in Flash into address in RAM early during boot before
+	 * MMU is up. Because generated code "thinks" data is in Flash, but it
+	 * is actually in RAM (actually data is also in Flash, but Flash is
+	 * read-only, thus we need to use the data residing in RAM).
+	 *
+	 * The start of data in Flash is _sdata and the start of data in RAM is
+	 * CONFIG_PHYS_RAM_BASE. So this fix-up essentially does this:
+	 * reg += CONFIG_PHYS_RAM_BASE - _start
+	 */
+	li t0, CONFIG_PHYS_RAM_BASE
         add \reg, \reg, t0
+	la t0, _sdata
+	sub \reg, \reg, t0
 .endm
 .macro XIP_FIXUP_FLASH_OFFSET reg
+	/* In linker script, at the transition from read-only section to
+	 * writable section, the VMA is increased while LMA remains the same.
+	 * (See in linker script how _sdata, __data_loc and LOAD_OFFSET is
+	 * changed)
+	 *
+	 * Consequently, early during boot before MMU is up, the generated code
+	 * reads the "writable" section at wrong addresses, because VMA is used
+	 * by compiler to generate code, but the data is located in Flash using
+	 * LMA.
+	 */
+	la t0, _sdata
+	sub \reg, \reg, t0
 	la t0, __data_loc
-	REG_L t1, _xip_phys_offset
-	sub \reg, \reg, t1
 	add \reg, \reg, t0
 .endm
-
-_xip_fixup: .dword CONFIG_PHYS_RAM_BASE - CONFIG_XIP_PHYS_ADDR - XIP_OFFSET
-_xip_phys_offset: .dword CONFIG_XIP_PHYS_ADDR + XIP_OFFSET
 #else
 .macro XIP_FIXUP_OFFSET reg
 .endm