/* VGA framebuffer row copy: rep movsl optimized for P5 USWC write-combining. * * void vga_fb_copy_row(void *dst, void *src, unsigned int dwords); * * On Pentium (P5), rep movsl to UC memory (PCI framebuffer) uses the * 64-byte USWC write-combining buffer. Writes are batched and flushed * as burst transfers to VRAM, avoiding per-dword PCI bus stalls. */ .code32 .text .globl vga_fb_copy_row vga_fb_copy_row: pushl %esi pushl %edi movl 12(%esp), %edi /* dst */ movl 16(%esp), %esi /* src */ movl 20(%esp), %ecx /* dword count */ cld rep movsl popl %edi popl %esi ret /* void vga_fb_fill_row_sse2(void *dst, unsigned int value, unsigned int dwords); * * 16 bytes of the (broadcast) dword per iteration, then the remaining dwords. * Only called when cpuid reported SSE2; unaligned-safe (movdqu). */ .globl vga_fb_fill_row_sse2 vga_fb_fill_row_sse2: pushl %edi movl 8(%esp), %edi /* dst */ movl 12(%esp), %eax /* value */ movl 16(%esp), %ecx /* dword count */ movd %eax, %xmm0 pshufd $0, %xmm0, %xmm0 movl %ecx, %edx shrl $2, %edx jz 2f 1: movdqu %xmm0, (%edi) addl $16, %edi decl %edx jnz 1b 2: andl $3, %ecx jz 4f 3: movl %eax, (%edi) addl $4, %edi decl %ecx jnz 3b 4: popl %edi ret /* void vga_fb_fill_row_nt(void *dst, unsigned int value, unsigned int dwords); * * Streaming (non-temporal) store version for long rows: avoids the * read-for-ownership traffic of a cached fill, which is what makes large * fills DRAM-bound on the Atom. Aligns to 16 bytes with normal stores, then * movntdq. The caller must sfence before the data is read back. */ .globl vga_fb_fill_row_nt vga_fb_fill_row_nt: pushl %edi movl 8(%esp), %edi /* dst */ movl 12(%esp), %eax /* value */ movl 16(%esp), %ecx /* dword count */ movd %eax, %xmm0 pshufd $0, %xmm0, %xmm0 1: testl $15, %edi jz 2f testl %ecx, %ecx jz 9f movl %eax, (%edi) addl $4, %edi decl %ecx jmp 1b 2: movl %ecx, %edx shrl $2, %edx jz 4f 3: movntdq %xmm0, (%edi) addl $16, %edi decl %edx jnz 3b 4: andl $3, %ecx jz 9f 5: movl %eax, (%edi) addl $4, %edi decl %ecx jnz 5b 9: popl %edi ret /* void vga_fb_copy_row_nt(void *dst, const void *src, unsigned int dwords); * * Same as vga_fb_copy_row, but with streaming (non-temporal) stores: WC * destinations combine them into bursts, which rep movsl does not do here. * The destination is aligned with normal stores first; the caller sfences. */ .globl vga_fb_copy_row_nt vga_fb_copy_row_nt: pushl %esi pushl %edi movl 12(%esp), %edi /* dst */ movl 16(%esp), %esi /* src */ movl 20(%esp), %ecx /* dword count */ 1: testl $15, %edi jz 2f testl %ecx, %ecx jz 9f movl (%esi), %eax movl %eax, (%edi) addl $4, %esi addl $4, %edi decl %ecx jmp 1b 2: movl %ecx, %edx shrl $2, %edx jz 4f 3: movdqu (%esi), %xmm0 movntdq %xmm0, (%edi) addl $16, %esi addl $16, %edi decl %edx jnz 3b 4: andl $3, %ecx jz 9f 5: movl (%esi), %eax movl %eax, (%edi) addl $4, %esi addl $4, %edi decl %ecx jnz 5b 9: popl %edi popl %esi ret