Todo List - Revision history

Ralf: /* BPF JIT */

2012-10-17T22:45:49Z

‎BPF JIT

Ralf at 22:41, 17 October 2012

2012-10-17T22:41:01Z

Ralf at 10:02, 8 October 2012

2012-10-08T10:02:51Z

Ralf: More kexec for the to do list.

2011-06-22T11:17:52Z

More kexec for the to do list.

XP1 at 05:39, 5 June 2011

2011-06-05T05:39:08Z

Ralf: /* Prefetch handling */

2010-11-21T23:59:07Z

‎Prefetch handling

Ralf at 20:53, 21 November 2010

2010-11-21T20:53:54Z

Ralf at 12:03, 10 November 2010

2010-11-10T12:03:44Z

Ralf at 13:53, 8 November 2010

2010-11-08T13:53:43Z

Ralf at 13:13, 8 November 2010

2010-11-08T13:13:09Z

@@ Line 32: / Line 32: @@
 == BPF JIT ==
-[[wikipedia:Berkeley_Filter BPF]] code is normally interpreted.  Significant performance advantage can be obtained by compiling it into native machine code.
+[[wikipedia:Berkeley_Filter|BPF]] code is normally interpreted.  Significant performance advantage can be obtained by compiling it into native machine code.
 == EDAC Drivers ==

@@ Line 33: / Line 33: @@
 == BPF JIT ==
 [[wikipedia:Berkeley_Filter BPF]] code is normally interpreted.  Significant performance advantage can be obtained by compiling it into native machine code.
 == See also ==
 * http://lists.freedesktop.org/archives/pixman/2010-November/000749.html
 * http://www.gsp.com/cgi-bin/man.cgi?section=4&topic=bpf FreeBSD BPF documentation

@@ Line 30: / Line 30: @@
 * Something like <tt>kexec /mnt/kernels/rescue/vmlinux --initrd=/mnt/initrds/rescue</tt> but --initrd seems not to be implemented for MIPS.
 * kexec: add kexec jump support
 == See also ==
 * http://lists.freedesktop.org/archives/pixman/2010-November/000749.html

@@ Line 3: / Line 3: @@
 * Implement a backtracer based on the DWARF debug information
 * Implement stack protector
 * Improve non-executable support
 * Add latencytop support
@@ Line 27: / Line 26: @@
 Prefetching needs to know the cache line size to be effective. Right now, <code>RDHWR&nbsp;$reg,&nbsp;$</code> only gives access to the stride size to be used for <code>SYNCI</code>, which may be a different value than the number to be used for prefetching. And with <code>PrepareForStore</code>, you better get that right or&nbsp;...
 We may also take a fresh look at if we can safely implement <code>cachectl(2)</code>, not necessarily as originally defined by Risc/OS or IRIX but with more control over available cache modes.
 == See also ==
 * http://lists.freedesktop.org/archives/pixman/2010-November/000749.html

@@ Line 1: / Line 1: @@
-The list below gives an overview of some missing features in the current Mips port. This list is far from being completed.  If you want to undertake one of these items (or perhaps all of them), don't hesitate to ask on the linux-mips mailing list the status or clarification of the point you're interested in.
+The list below gives an overview of some missing features in the current MIPS port. This list is far from being completed.  If you want to undertake one of these items (or perhaps all of them), don't hesitate to ask on the linux-mips mailing list the status or clarification of the point you're interested in.
 * Implement a backtracer based on the DWARF debug information
@@ Line 12: / Line 12: @@
 See http://sourceware.org/systemtap/wiki/utrace/arch/HowTo
-== Binary compat code ==
+== Binary-compatible code ==
-The 32-bit binary compat code should be rewritten to use the generic compatibility code in fs/compat_binfmt_elf.c.  Brownie points for providing a more elegant N32 compat binfmt as well.
+The 32-bit binary-compatible code should be rewritten to use the generic compatibility code in <code>fs/compat_binfmt_elf.c</code>. Brownie points for providing a more elegant N32 compat binfmt as well.
-== module loader ==
+== Module loader ==
-Memory fragmentation permitting modules should be loaded into unmapped space, not vmalloc space.  An old patch doing 90% of the work was written by Andrea Arcangeli for 2.4.22 in http://ftp.kernel.org/pub/linux/kernel/people/andrea/kernels/v2.4/2.4.22aa1/00_module-gfp-7 but now that there is alloc_pages_exact() this would need reimplementation.
+Memory fragmentation permitting modules should be loaded into unmapped space, not vmalloc space.  An old patch doing 90% of the work was written by Andrea Arcangeli for 2.4.22 in [http://ftp.kernel.org/pub/linux/kernel/people/andrea/kernels/v2.4/2.4.22aa1/00_module-gfp-7 http://ftp.kernel.org/pub/linux/kernel/people/andrea/kernels/v2.4/2.4.22aa1/00_module-gfp-7], but now, that there is <code>alloc_pages_exact()</code>, which would need reimplementation.
 == syscall return code ==
-MIPS needs an implementation of force_successful_syscall_return() to handle a few corner cases.
+MIPS needs an implementation of <code>force_successful_syscall_return()</code> to handle a few corner cases.
-== virtual alias handling ==
+== Virtual alias handling ==
-In <tt>include/linux/highmem.h</tt> the non-definition of <tt>ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE</tt> leads to the use of broken default functions which break XFS on non-coherent CPUs with aliases, amongst other things.
+In <code>include/linux/highmem.h</code>, the non-definition of <code>ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE</code> leads to the use of broken default functions, which break XFS on non-coherent CPUs with aliases, amongst other things.
 == Prefetch handling ==
-Prefetching needs to know the cache line size to be effective.  Right now <tt>RDHWR&nbsp;$reg,&nbsp;$</tt> only gives access to the stride size to be used for <tt>SYNCI</tt> which may be a different value than the number to be used for prefetching.  And with <tt>PrepareForStore</tt> you better get that right or&nbsp;...
+Prefetching needs to know the cache line size to be effective. Right now, <code>RDHWR&nbsp;$reg,&nbsp;$</code> only gives access to the stride size to be used for <code>SYNCI</code>, which may be a different value than the number to be used for prefetching. And with <code>PrepareForStore</code>, you better get that right or&nbsp;...
-We may also take a fresh look at if we can safely implement cachectl(2).  Not necessarily as originally defined by Risc/OS or IRIX but with more control over available cache modes.
+We may also take a fresh look at if we can safely implement <code>cachectl(2)</code>, not necessarily as originally defined by Risc/OS or IRIX but with more control over available cache modes.
-=== See also ===
 * http://lists.freedesktop.org/archives/pixman/2010-November/000749.html

← Older revision		Revision as of 23:59, 21 November 2010
Line 26:		Line 26:
	== Prefetch handling ==		== Prefetch handling ==
	Prefetching needs to know the cache line size to be effective. Right now <tt>RDHWR $reg, $</tt> only gives access to the stride size to be used for <tt>SYNCI</tt> which may be a different value than the number to be used for prefetching. And with <tt>PrepareForStore</tt> you better get that right or ...		Prefetching needs to know the cache line size to be effective. Right now <tt>RDHWR $reg, $</tt> only gives access to the stride size to be used for <tt>SYNCI</tt> which may be a different value than the number to be used for prefetching. And with <tt>PrepareForStore</tt> you better get that right or ...
		+	We may also take a fresh look at if we can safely implement cachectl(2). Not necessarily as originally defined by Risc/OS or IRIX but with more control over available cache modes.
		+	=== See also ===
		+	* http://lists.freedesktop.org/archives/pixman/2010-November/000749.html

← Older revision		Revision as of 20:53, 21 November 2010
Line 23:		Line 23:
	== virtual alias handling ==		== virtual alias handling ==
	In <tt>include/linux/highmem.h</tt> the non-definition of <tt>ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE</tt> leads to the use of broken default functions which break XFS on non-coherent CPUs with aliases, amongst other things.		In <tt>include/linux/highmem.h</tt> the non-definition of <tt>ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE</tt> leads to the use of broken default functions which break XFS on non-coherent CPUs with aliases, amongst other things.
		+
		+	== Prefetch handling ==
		+	Prefetching needs to know the cache line size to be effective. Right now <tt>RDHWR $reg, $</tt> only gives access to the stride size to be used for <tt>SYNCI</tt> which may be a different value than the number to be used for prefetching. And with <tt>PrepareForStore</tt> you better get that right or ...

← Older revision		Revision as of 12:03, 10 November 2010
Line 20:		Line 20:
	== syscall return code ==		== syscall return code ==
	MIPS needs an implementation of force_successful_syscall_return() to handle a few corner cases.		MIPS needs an implementation of force_successful_syscall_return() to handle a few corner cases.
		+
		+	== virtual alias handling ==
		+	In <tt>include/linux/highmem.h</tt> the non-definition of <tt>ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE</tt> leads to the use of broken default functions which break XFS on non-coherent CPUs with aliases, amongst other things.

← Older revision		Revision as of 13:53, 8 November 2010
Line 17:		Line 17:
	== module loader ==		== module loader ==
	Memory fragmentation permitting modules should be loaded into unmapped space, not vmalloc space. An old patch doing 90% of the work was written by Andrea Arcangeli for 2.4.22 in http://ftp.kernel.org/pub/linux/kernel/people/andrea/kernels/v2.4/2.4.22aa1/00_module-gfp-7 but now that there is alloc_pages_exact() this would need reimplementation.		Memory fragmentation permitting modules should be loaded into unmapped space, not vmalloc space. An old patch doing 90% of the work was written by Andrea Arcangeli for 2.4.22 in http://ftp.kernel.org/pub/linux/kernel/people/andrea/kernels/v2.4/2.4.22aa1/00_module-gfp-7 but now that there is alloc_pages_exact() this would need reimplementation.
		+
		+	== syscall return code ==
		+	MIPS needs an implementation of force_successful_syscall_return() to handle a few corner cases.

← Older revision		Revision as of 13:13, 8 November 2010
Line 14:		Line 14:
	== Binary compat code ==		== Binary compat code ==
	The 32-bit binary compat code should be rewritten to use the generic compatibility code in fs/compat_binfmt_elf.c. Brownie points for providing a more elegant N32 compat binfmt as well.		The 32-bit binary compat code should be rewritten to use the generic compatibility code in fs/compat_binfmt_elf.c. Brownie points for providing a more elegant N32 compat binfmt as well.
		+
		+	== module loader ==
		+	Memory fragmentation permitting modules should be loaded into unmapped space, not vmalloc space. An old patch doing 90% of the work was written by Andrea Arcangeli for 2.4.22 in http://ftp.kernel.org/pub/linux/kernel/people/andrea/kernels/v2.4/2.4.22aa1/00_module-gfp-7 but now that there is alloc_pages_exact() this would need reimplementation.