1 files changed, 88 insertions, 81 deletions

diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index ed4a82948002..f62c284db9eb 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -21,8 +21,8 @@
 /*
  * High loaded stuff by Hans Lermen & Werner Almesberger, Feb. 1996
  */
-.code32
-.text
+        .code32
+        .text
 
 #include <linux/linkage.h>
 #include <asm/segment.h>
@@ -33,12 +33,14 @@
 #include <asm/processor-flags.h>
 #include <asm/asm-offsets.h>
 
-.section ".text.head"
+        .section ".text.head"
         .code32
 ENTRY(startup_32)
         cld
-        /* test KEEP_SEGMENTS flag to see if the bootloader is asking
-         * us to not reload segments */
+        /*
+         * Test KEEP_SEGMENTS flag to see if the bootloader is asking
+         * us to not reload segments
+         */
         testb $(1<<6), BP_loadflags(%esi)
         jnz 1f
 
@@ -49,14 +51,15 @@ ENTRY(startup_32)
         movl    %eax, %ss
 1:
 
-/* Calculate the delta between where we were compiled to run
+/*
+ * Calculate the delta between where we were compiled to run
  * at and where we were actually loaded at.  This can only be done
  * with a short local call on x86.  Nothing  else will tell us what
  * address we are running at.  The reserved chunk of the real-mode
  * data at 0x1e4 (defined as a scratch field) are used as the stack
  * for this calculation. Only 4 bytes are needed.
  */
-        leal    (0x1e4+4)(%esi), %esp
+        leal    (BP_scratch+4)(%esi), %esp
         call    1f
 1:      popl    %ebp
         subl    $1b, %ebp
@@ -70,32 +73,28 @@ ENTRY(startup_32)
         testl   %eax, %eax
         jnz     no_longmode
 
-/* Compute the delta between where we were compiled to run at
+/*
+ * Compute the delta between where we were compiled to run at
  * and where the code will actually run at.
- */
-/* %ebp contains the address we are loaded at by the boot loader and %ebx
+ *
+ * %ebp contains the address we are loaded at by the boot loader and %ebx
  * contains the address where we should move the kernel image temporarily
  * for safe in-place decompression.
  */
 
 #ifdef CONFIG_RELOCATABLE
         movl    %ebp, %ebx
-        addl    $(PMD_PAGE_SIZE -1), %ebx
-        andl    $PMD_PAGE_MASK, %ebx
+        movl    BP_kernel_alignment(%esi), %eax
+        decl    %eax
+        addl    %eax, %ebx
+        notl    %eax
+        andl    %eax, %ebx
 #else
-        movl    $CONFIG_PHYSICAL_START, %ebx
+        movl    $LOAD_PHYSICAL_ADDR, %ebx
 #endif
 
-        /* Replace the compressed data size with the uncompressed size */
-        subl    input_len(%ebp), %ebx
-        movl    output_len(%ebp), %eax
-        addl    %eax, %ebx
-        /* Add 8 bytes for every 32K input block */
-        shrl    $12, %eax
-        addl    %eax, %ebx
-        /* Add 32K + 18 bytes of extra slack and align on a 4K boundary */
-        addl    $(32768 + 18 + 4095), %ebx
-        andl    $~4095, %ebx
+        /* Target address to relocate to for decompression */
+        addl    $z_extract_offset, %ebx
 
 /*
  * Prepare for entering 64 bit mode
@@ -114,7 +113,7 @@ ENTRY(startup_32)
  /*
   * Build early 4G boot pagetable
   */
-        /* Initialize Page tables to 0*/
+        /* Initialize Page tables to 0 */
         leal    pgtable(%ebx), %edi
         xorl    %eax, %eax
         movl    $((4096*6)/4), %ecx
@@ -155,7 +154,8 @@ ENTRY(startup_32)
         btsl    $_EFER_LME, %eax
         wrmsr
 
-        /* Setup for the jump to 64bit mode
+        /*
+         * Setup for the jump to 64bit mode
          *
          * When the jump is performend we will be in long mode but
          * in 32bit compatibility mode with EFER.LME = 1, CS.L = 0, CS.D = 1
@@ -184,7 +184,8 @@ no_longmode:
 
 #include "../../kernel/verify_cpu_64.S"
 
-        /* Be careful here startup_64 needs to be at a predictable
+        /*
+         * Be careful here startup_64 needs to be at a predictable
          * address so I can export it in an ELF header.  Bootloaders
          * should look at the ELF header to find this address, as
          * it may change in the future.
@@ -192,7 +193,8 @@ no_longmode:
         .code64
         .org 0x200
 ENTRY(startup_64)
-        /* We come here either from startup_32 or directly from a
+        /*
+         * We come here either from startup_32 or directly from a
          * 64bit bootloader.  If we come here from a bootloader we depend on
          * an identity mapped page table being provied that maps our
          * entire text+data+bss and hopefully all of memory.
@@ -209,50 +211,54 @@ ENTRY(startup_64)
         movl    $0x20, %eax
         ltr     %ax
 
-        /* Compute the decompressed kernel start address.  It is where
+        /*
+         * Compute the decompressed kernel start address.  It is where
          * we were loaded at aligned to a 2M boundary. %rbp contains the
          * decompressed kernel start address.
          *
          * If it is a relocatable kernel then decompress and run the kernel
          * from load address aligned to 2MB addr, otherwise decompress and
-         * run the kernel from CONFIG_PHYSICAL_START
+         * run the kernel from LOAD_PHYSICAL_ADDR
+         *
+         * We cannot rely on the calculation done in 32-bit mode, since we
+         * may have been invoked via the 64-bit entry point.
          */
 
         /* Start with the delta to where the kernel will run at. */
 #ifdef CONFIG_RELOCATABLE
         leaq    startup_32(%rip) /* - $startup_32 */, %rbp
-        addq    $(PMD_PAGE_SIZE - 1), %rbp
-        andq    $PMD_PAGE_MASK, %rbp
-        movq    %rbp, %rbx
+        movl    BP_kernel_alignment(%rsi), %eax
+        decl    %eax
+        addq    %rax, %rbp
+        notq    %rax
+        andq    %rax, %rbp
 #else
-        movq    $CONFIG_PHYSICAL_START, %rbp
-        movq    %rbp, %rbx
+        movq    $LOAD_PHYSICAL_ADDR, %rbp
 #endif
 
-        /* Replace the compressed data size with the uncompressed size */
-        movl    input_len(%rip), %eax
-        subq    %rax, %rbx
-        movl    output_len(%rip), %eax
-        addq    %rax, %rbx
-        /* Add 8 bytes for every 32K input block */
-        shrq    $12, %rax
-        addq    %rax, %rbx
-        /* Add 32K + 18 bytes of extra slack and align on a 4K boundary */
-        addq    $(32768 + 18 + 4095), %rbx
-        andq    $~4095, %rbx
-
-/* Copy the compressed kernel to the end of our buffer
+        /* Target address to relocate to for decompression */
+        leaq    z_extract_offset(%rbp), %rbx
+
+        /* Set up the stack */
+        leaq    boot_stack_end(%rbx), %rsp
+
+        /* Zero EFLAGS */
+        pushq   $0
+        popfq
+
+/*
+ * Copy the compressed kernel to the end of our buffer
  * where decompression in place becomes safe.
  */
-        leaq    _end_before_pgt(%rip), %r8
-        leaq    _end_before_pgt(%rbx), %r9
-        movq    $_end_before_pgt /* - $startup_32 */, %rcx
-1:      subq    $8, %r8
-        subq    $8, %r9
-        movq    0(%r8), %rax
-        movq    %rax, 0(%r9)
-        subq    $8, %rcx
-        jnz     1b
+        pushq   %rsi
+        leaq    (_bss-8)(%rip), %rsi
+        leaq    (_bss-8)(%rbx), %rdi
+        movq    $_bss /* - $startup_32 */, %rcx
+        shrq    $3, %rcx
+        std
+        rep     movsq
+        cld
+        popq    %rsi
 
 /*
  * Jump to the relocated address.
@@ -260,37 +266,28 @@ ENTRY(startup_64)
         leaq    relocated(%rbx), %rax
         jmp     *%rax
 
-.section ".text"
+        .text
 relocated:
 
 /*
- * Clear BSS
+ * Clear BSS (stack is currently empty)
  */
-        xorq    %rax, %rax
-        leaq    _edata(%rbx), %rdi
-        leaq    _end_before_pgt(%rbx), %rcx
+        xorl    %eax, %eax
+        leaq    _bss(%rip), %rdi
+        leaq    _ebss(%rip), %rcx
         subq    %rdi, %rcx
-        cld
-        rep
-        stosb
-
-        /* Setup the stack */
-        leaq    boot_stack_end(%rip), %rsp
-
-        /* zero EFLAGS after setting rsp */
-        pushq   $0
-        popfq
+        shrq    $3, %rcx
+        rep     stosq
 
 /*
  * Do the decompression, and jump to the new kernel..
  */
-        pushq   %rsi                    # Save the real mode argument
-        movq    %rsi, %rdi              # real mode address
-        leaq    boot_heap(%rip), %rsi   # malloc area for uncompression
-        leaq    input_data(%rip), %rdx  # input_data
-        movl    input_len(%rip), %eax
-        movq    %rax, %rcx              # input_len
-        movq    %rbp, %r8               # output
+        pushq   %rsi                    /* Save the real mode argument */
+        movq    %rsi, %rdi              /* real mode address */
+        leaq    boot_heap(%rip), %rsi   /* malloc area for uncompression */
+        leaq    input_data(%rip), %rdx  /* input_data */
+        movl    $z_input_len, %ecx      /* input_len */
+        movq    %rbp, %r8               /* output target address */
         call    decompress_kernel
         popq    %rsi
 
@@ -311,11 +308,21 @@ gdt:
         .quad   0x0000000000000000      /* TS continued */
 gdt_end:
 
-.bss
-/* Stack and heap for uncompression */
-.balign 4
+/*
+ * Stack and heap for uncompression
+ */
+        .bss
+        .balign 4
 boot_heap:
         .fill BOOT_HEAP_SIZE, 1, 0
 boot_stack:
         .fill BOOT_STACK_SIZE, 1, 0
 boot_stack_end:
+
+/*
+ * Space for page tables (not in .bss so not zeroed)
+ */
+        .section ".pgtable","a",@nobits
+        .balign 4096
+pgtable:
+        .fill 6*4096, 1, 0