From 5b3efd500854d45d305b53c54c97db5970959980 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Thu, 11 Feb 2010 11:50:59 -0800 Subject: 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 LKML-Reference: <20100211195614.802495327@sbs-t61.sc.intel.com> Signed-off-by: Hongjiu Lu Cc: Roland McGrath Signed-off-by: H. Peter Anvin --- arch/x86/kernel/i387.c | 83 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 83 insertions(+) (limited to 'arch/x86/kernel/i387.c') diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index f2f8540a7f3d..7a8a193b5144 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -164,6 +164,11 @@ int init_fpu(struct task_struct *tsk) return 0; } +/* + * The xstateregs_active() routine is the same as the fpregs_active() routine, + * as the "regset->n" for the xstate regset will be updated based on the feature + * capabilites supported by the xsave. + */ int fpregs_active(struct task_struct *target, const struct user_regset *regset) { return tsk_used_math(target) ? regset->n : 0; @@ -224,6 +229,84 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, return ret; } +int xstateregs_get(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + void *kbuf, void __user *ubuf) +{ + int ret; + + if (!cpu_has_xsave) + return -ENODEV; + + ret = init_fpu(target); + if (ret) + return ret; + + /* + * First copy the fxsave bytes 0..463. + */ + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.xstate->xsave, 0, + offsetof(struct user_xstateregs, + i387.xstate_fx_sw)); + if (ret) + return ret; + + /* + * Copy the 48bytes defined by software. + */ + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + xstate_fx_sw_bytes, + offsetof(struct user_xstateregs, + i387.xstate_fx_sw), + offsetof(struct user_xstateregs, + xsave_hdr)); + if (ret) + return ret; + + /* + * Copy the rest of xstate memory layout. + */ + ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, + &target->thread.xstate->xsave.xsave_hdr, + offsetof(struct user_xstateregs, + xsave_hdr), -1); + return ret; +} + +int xstateregs_set(struct task_struct *target, const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + struct xsave_hdr_struct *xsave_hdr; + + if (!cpu_has_xsave) + return -ENODEV; + + ret = init_fpu(target); + if (ret) + return ret; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &target->thread.xstate->xsave, 0, -1); + + /* + * mxcsr reserved bits must be masked to zero for security reasons. + */ + target->thread.xstate->fxsave.mxcsr &= mxcsr_feature_mask; + + xsave_hdr = &target->thread.xstate->xsave.xsave_hdr; + + xsave_hdr->xstate_bv &= pcntxt_mask; + /* + * These bits must be zero. + */ + xsave_hdr->reserved1[0] = xsave_hdr->reserved1[1] = 0; + + return ret; +} + #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION /* -- cgit v1.2.3 From ff7fbc72e0c3ef7e94a27a3a918fd09ec9a30204 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Mon, 22 Feb 2010 14:51:33 -0800 Subject: x86, ptrace: Simplify xstateregs_get() 48 bytes (bytes 464..511) of the xstateregs payload come from the kernel defined structure (xstate_fx_sw_bytes). Rest comes from the xstate regs structure in the thread struct. Instead of having multiple user_regset_copyout()'s, simplify the xstateregs_get() by first copying the SW bytes into the xstate regs structure in the thread structure and then using one user_regset_copyout() to copyout the xstateregs. Requested-by: Roland McGrath Signed-off-by: Suresh Siddha LKML-Reference: <20100222225240.494688491@sbs-t61.sc.intel.com> Acked-by: Roland McGrath Signed-off-by: H. Peter Anvin Cc: Oleg Nesterov --- arch/x86/kernel/i387.c | 30 +++++++----------------------- 1 file changed, 7 insertions(+), 23 deletions(-) (limited to 'arch/x86/kernel/i387.c') diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 7a8a193b5144..81e23bf12c12 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -243,34 +243,18 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset, return ret; /* - * First copy the fxsave bytes 0..463. + * Copy the 48bytes defined by the software first into the xstate + * memory layout in the thread struct, so that we can copy the entire + * xstateregs to the user using one user_regset_copyout(). */ - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.xstate->xsave, 0, - offsetof(struct user_xstateregs, - i387.xstate_fx_sw)); - if (ret) - return ret; - - /* - * Copy the 48bytes defined by software. - */ - ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - xstate_fx_sw_bytes, - offsetof(struct user_xstateregs, - i387.xstate_fx_sw), - offsetof(struct user_xstateregs, - xsave_hdr)); - if (ret) - return ret; + memcpy(&target->thread.xstate->fxsave.sw_reserved, + xstate_fx_sw_bytes, sizeof(xstate_fx_sw_bytes)); /* - * Copy the rest of xstate memory layout. + * Copy the xstate memory layout. */ ret = user_regset_copyout(&pos, &count, &kbuf, &ubuf, - &target->thread.xstate->xsave.xsave_hdr, - offsetof(struct user_xstateregs, - xsave_hdr), -1); + &target->thread.xstate->xsave, 0, -1); return ret; } -- cgit v1.2.3 From 6dbbe14f21368a45aedba7eab0221857b8ad8d16 Mon Sep 17 00:00:00 2001 From: Suresh Siddha Date: Mon, 22 Feb 2010 14:51:34 -0800 Subject: x86, ptrace: Remove set_stopped_child_used_math() in [x]fpregs_set init_fpu() already ensures that the used_math() is set for the stopped child. Remove the redundant set_stopped_child_used_math() in [x]fpregs_set() Reported-by: Oleg Nesterov Signed-off-by: Suresh Siddha LKML-Reference: <20100222225240.642169080@sbs-t61.sc.intel.com> Acked-by: Rolan McGrath Signed-off-by: H. Peter Anvin --- arch/x86/kernel/i387.c | 4 ---- 1 file changed, 4 deletions(-) (limited to 'arch/x86/kernel/i387.c') diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index 81e23bf12c12..c01a2b846d47 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -209,8 +209,6 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; - set_stopped_child_used_math(target); - ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.xstate->fxsave, 0, -1); @@ -471,8 +469,6 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset, if (ret) return ret; - set_stopped_child_used_math(target); - if (!HAVE_HWFP) return fpregs_soft_set(target, regset, pos, count, kbuf, ubuf); -- cgit v1.2.3 From 5a0e3ad6af8660be21ca98a971cd00f331318c05 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 24 Mar 2010 17:04:11 +0900 Subject: include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo Guess-its-ok-by: Christoph Lameter Cc: Ingo Molnar Cc: Lee Schermerhorn --- arch/x86/kernel/i387.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/kernel/i387.c') diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c index c01a2b846d47..54c31c285488 100644 --- a/arch/x86/kernel/i387.c +++ b/arch/x86/kernel/i387.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include -- cgit v1.2.3