x86, ptrace: regset extensions to support xstate

Add the xstate regset support which helps extend the kernel ptrace and the
core-dump interfaces to support AVX state etc.

This regset interface is designed to support all the future state that gets
supported using xsave/xrstor infrastructure.

Looking at the memory layout saved by "xsave", one can't say which state
is represented in the memory layout. This is because if a particular state is
in init state, in the xsave hdr it can be represented by bit '0'. And hence
we can't really say by the xsave header wether a state is in init state or
the state is not saved in the memory layout.

And hence the xsave memory layout available through this regset
interface uses SW usable bytes [464..511] to convey what state is represented
in the memory layout.

First 8 bytes of the sw_usable_bytes[464..467] will be set to OS enabled xstate
mask(which is same as the 64bit mask returned by the xgetbv's xCR0).

The note NT_X86_XSTATE represents the extended state information in the
core file, using the above mentioned memory layout.

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
LKML-Reference: <20100211195614.802495327@sbs-t61.sc.intel.com>
Signed-off-by: Hongjiu Lu <hjl.tools@gmail.com>
Cc: Roland McGrath <roland@redhat.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

3 files changed, 70 insertions, 2 deletions

diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index ebfb8a9e11f7..da2930924501 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -33,8 +33,16 @@ extern void init_thread_xstate(void);
 extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
 
 extern user_regset_active_fn fpregs_active, xfpregs_active;
-extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get;
-extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set;
+extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
+				xstateregs_get;
+extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
+				 xstateregs_set;
+
+/*
+ * xstateregs_active == fpregs_active. Please refer to the comment
+ * at the definition of fpregs_active.
+ */
+#define xstateregs_active	fpregs_active
 
 extern struct _fpx_sw_bytes fx_sw_reserved;
 #ifdef CONFIG_IA32_EMULATION
diff --git a/arch/x86/include/asm/user.h b/arch/x86/include/asm/user.h
index 999873b22e7f..24532c7da3d6 100644
--- a/arch/x86/include/asm/user.h
+++ b/arch/x86/include/asm/user.h
@@ -1,5 +1,63 @@
+#ifndef _ASM_X86_USER_H
+#define _ASM_X86_USER_H
+
 #ifdef CONFIG_X86_32
 # include "user_32.h"
 #else
 # include "user_64.h"
 #endif
+
+#include <asm/types.h>
+
+struct user_ymmh_regs {
+	/* 16 * 16 bytes for each YMMH-reg */
+	__u32 ymmh_space[64];
+};
+
+struct user_xsave_hdr {
+	__u64 xstate_bv;
+	__u64 reserved1[2];
+	__u64 reserved2[5];
+};
+
+/*
+ * The structure layout of user_xstateregs, used for exporting the
+ * extended register state through ptrace and core-dump (NT_X86_XSTATE note)
+ * interfaces will be same as the memory layout of xsave used by the processor
+ * (except for the bytes 464..511, which can be used by the software) and hence
+ * the size of this structure varies depending on the features supported by the
+ * processor and OS. The size of the structure that users need to use can be
+ * obtained by doing:
+ *     cpuid_count(0xd, 0, &eax, &ptrace_xstateregs_struct_size, &ecx, &edx);
+ * i.e., cpuid.(eax=0xd,ecx=0).ebx will be the size that user (debuggers, etc.)
+ * need to use.
+ *
+ * For now, only the first 8 bytes of the software usable bytes[464..471] will
+ * be used and will be set to OS enabled xstate mask (which is same as the
+ * 64bit mask returned by the xgetbv's xCR0).  Users (analyzing core dump
+ * remotely, etc.) can use this mask as well as the mask saved in the
+ * xstate_hdr bytes and interpret what states the processor/OS supports
+ * and what states are in modified/initialized conditions for the
+ * particular process/thread.
+ *
+ * Also when the user modifies certain state FP/SSE/etc through the
+ * ptrace interface, they must ensure that the xsave_hdr.xstate_bv
+ * bytes[512..519] of the memory layout are updated correspondingly.
+ * i.e., for example when FP state is modified to a non-init state,
+ * xsave_hdr.xstate_bv's bit 0 must be set to '1', when SSE is modified to
+ * non-init state, xsave_hdr.xstate_bv's bit 1 must to be set to '1', etc.
+ */
+#define USER_XSTATE_FX_SW_WORDS 6
+#define USER_XSTATE_XCR0_WORD	0
+
+struct user_xstateregs {
+	struct {
+		__u64 fpx_space[58];
+		__u64 xstate_fx_sw[USER_XSTATE_FX_SW_WORDS];
+	} i387;
+	struct user_xsave_hdr xsave_hdr;
+	struct user_ymmh_regs ymmh;
+	/* further processor state extensions go here */
+};
+
+#endif /* _ASM_X86_USER_H */
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 727acc152344..ddc04ccad03b 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -27,9 +27,11 @@
 extern unsigned int xstate_size;
 extern u64 pcntxt_mask;
 extern struct xsave_struct *init_xstate_buf;
+extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 
 extern void xsave_cntxt_init(void);
 extern void xsave_init(void);
+extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
 extern int init_fpu(struct task_struct *child);
 extern int check_for_xstate(struct i387_fxsave_struct __user *buf,
 			    void __user *fpstate,