Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755829AbYHGWlb (ORCPT ); Thu, 7 Aug 2008 18:41:31 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754267AbYHGWkn (ORCPT ); Thu, 7 Aug 2008 18:40:43 -0400 Received: from e36.co.us.ibm.com ([32.97.110.154]:46365 "EHLO e36.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754143AbYHGWkl (ORCPT ); Thu, 7 Aug 2008 18:40:41 -0400 Subject: [RFC][PATCH 2/4] checkpoint/restart: x86 support To: Oren Laadan Cc: containers@lists.linux-foundation.org, linux-kernel@vger.kernel.org, Theodore Tso , "Serge E. Hallyn" , Dave Hansen From: Dave Hansen Date: Thu, 07 Aug 2008 15:40:35 -0700 References: <20080807224033.FFB3A2C1@kernel> In-Reply-To: <20080807224033.FFB3A2C1@kernel> Message-Id: <20080807224035.E56663BF@kernel> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 11012 Lines: 412 The original version of Oren's patch contained a good hunk of #ifdefs. I've extracted all of those and created a bit of an API for new architectures to follow. Leaving Oren's sign-off because this is all still his code, even though he hasn't seen it mangled like this before. Signed-off-by: Oren Laadan --- linux-2.6.git-dave/ckpt/Makefile | 1 linux-2.6.git-dave/ckpt/checkpoint.c | 7 linux-2.6.git-dave/ckpt/ckpt_arch.h | 6 linux-2.6.git-dave/ckpt/restart.c | 7 linux-2.6.git-dave/ckpt/x86.c | 269 ++++++++++++++++++++++++++++++ linux-2.6.git-dave/include/asm-x86/ckpt.h | 46 +++++ 6 files changed, 336 insertions(+) diff -puN ckpt/checkpoint.c~x86_part ckpt/checkpoint.c --- linux-2.6.git/ckpt/checkpoint.c~x86_part 2008-08-04 13:29:59.000000000 -0700 +++ linux-2.6.git-dave/ckpt/checkpoint.c 2008-08-04 13:29:59.000000000 -0700 @@ -19,6 +19,7 @@ #include "ckpt.h" #include "ckpt_hdr.h" +#include "ckpt_arch.h" /** * cr_get_fname - return pathname of a given file @@ -183,6 +184,12 @@ static int cr_write_task(struct cr_ctx * ret = cr_write_task_struct(ctx, t); CR_PRINTK("ret (task_struct) %d\n", ret); + if (!ret) + ret = cr_write_thread(ctx, t); + CR_PRINTK("ret (thread) %d\n", ret); + if (!ret) + ret = cr_write_cpu(ctx, t); + CR_PRINTK("ret (cpu) %d\n", ret); return ret; } diff -puN /dev/null ckpt/ckpt_arch.h --- /dev/null 2007-04-11 11:48:27.000000000 -0700 +++ linux-2.6.git-dave/ckpt/ckpt_arch.h 2008-08-04 13:29:59.000000000 -0700 @@ -0,0 +1,6 @@ +#include "ckpt.h" + +int cr_write_thread(struct cr_ctx *ctx, struct task_struct *t); +int cr_write_cpu(struct cr_ctx *ctx, struct task_struct *t); +int cr_read_thread(struct cr_ctx *ctx); +int cr_read_cpu(struct cr_ctx *ctx); diff -puN ckpt/Makefile~x86_part ckpt/Makefile --- linux-2.6.git/ckpt/Makefile~x86_part 2008-08-04 13:29:59.000000000 -0700 +++ linux-2.6.git-dave/ckpt/Makefile 2008-08-04 13:29:59.000000000 -0700 @@ -1 +1,2 @@ obj-y += sys.o checkpoint.o restart.o +obj-$(CONFIG_X86) += x86.o diff -puN ckpt/restart.c~x86_part ckpt/restart.c --- linux-2.6.git/ckpt/restart.c~x86_part 2008-08-04 13:29:59.000000000 -0700 +++ linux-2.6.git-dave/ckpt/restart.c 2008-08-04 13:29:59.000000000 -0700 @@ -21,6 +21,7 @@ #include "ckpt.h" #include "ckpt_hdr.h" +#include "ckpt_arch.h" /** * cr_hbuf_get - reserve space on the hbuf @@ -171,6 +172,12 @@ static int cr_read_task(struct cr_ctx *c ret = cr_read_task_struct(ctx); CR_PRINTK("ret (task_struct) %d\n", ret); + if (!ret) + ret = cr_read_thread(ctx); + CR_PRINTK("ret (thread) %d\n", ret); + if (!ret) + ret = cr_read_cpu(ctx); + CR_PRINTK("ret (cpu) %d\n", ret); return ret; } diff -puN /dev/null ckpt/x86.c --- /dev/null 2007-04-11 11:48:27.000000000 -0700 +++ linux-2.6.git-dave/ckpt/x86.c 2008-08-04 13:29:59.000000000 -0700 @@ -0,0 +1,269 @@ +#include +#include +#include + +#include "ckpt.h" +#include "ckpt_hdr.h" + +/* dump the thread_struct of a given task */ +int cr_write_thread(struct cr_ctx *ctx, struct task_struct *t) +{ + struct cr_hdr h; + struct cr_hdr_thread *hh = ctx->tbuf; + struct thread_struct *thread; + struct desc_struct *desc; + int ntls = 0; + int n, ret; + + h.type = CR_HDR_THREAD; + h.len = sizeof(*hh); + h.id = ctx->pid; + + thread = &t->thread; + + /* calculate no. of TLS entries that follow */ + desc = thread->tls_array; + for (n = GDT_ENTRY_TLS_ENTRIES; n > 0; n--, desc++) { + if (desc->a || desc->b) + ntls++; + } + + hh->gdt_entry_tls_entries = GDT_ENTRY_TLS_ENTRIES; + hh->sizeof_tls_array = sizeof(thread->tls_array); + hh->ntls = ntls; + + if ((ret = cr_write_obj(ctx, &h, hh)) < 0) + return ret; + + /* for simplicity dump the entire array, cherry-pick upon restart */ + ret = cr_kwrite(ctx, thread->tls_array, sizeof(thread->tls_array)); + + CR_PRINTK("ntls %d\n", ntls); + + /* IGNORE RESTART BLOCKS FOR NOW ... */ + + return ret; +} + +/* dump the cpu state and registers of a given task */ +int cr_write_cpu(struct cr_ctx *ctx, struct task_struct *t) +{ + struct cr_hdr h; + struct cr_hdr_cpu *hh = ctx->tbuf; + struct thread_struct *thread; + struct thread_info *thread_info; + struct pt_regs *regs; + + h.type = CR_HDR_CPU; + h.len = sizeof(*hh); + h.id = ctx->pid; + + thread = &t->thread; + thread_info = task_thread_info(t); + regs = task_pt_regs(t); + + hh->bx = regs->bx; + hh->cx = regs->cx; + hh->dx = regs->dx; + hh->si = regs->si; + hh->di = regs->di; + hh->bp = regs->bp; + hh->ax = regs->ax; + hh->ds = regs->ds; + hh->es = regs->es; + hh->orig_ax = regs->orig_ax; + hh->ip = regs->ip; + hh->cs = regs->cs; + hh->flags = regs->flags; + hh->sp = regs->sp; + hh->ss = regs->ss; + + /* for checkpoint in process context (from within a container) + the GS and FS registers should be saved from the hardware; + otherwise they are already sabed on the thread structure */ + if (t == current) { + savesegment(gs, hh->gs); + savesegment(fs, hh->fs); + } else { + hh->gs = thread->gs; + hh->fs = thread->fs; + } + + /* + * for checkpoint in process context (from within a container), + * the actual syscall is taking place at this very moment; so + * we (optimistically) subtitute the future return value (0) of + * this syscall into the orig_eax, so that upon restart it will + * succeed (or it will endlessly retry checkpoint...) + */ + if (t == current) { + BUG_ON(hh->orig_ax < 0); + hh->ax = 0; + } + + preempt_disable(); + + /* i387 + MMU + SSE logic */ + hh->used_math = tsk_used_math(t) ? 1 : 0; + if (hh->used_math) { + /* normally, no need to unlazy_fpu(), since TS_USEDFPU flag + * have been cleared when task was conexted-switched out... + * except if we are in process context, in which case we do */ + if (thread_info->status & TS_USEDFPU) + unlazy_fpu(current); + + hh->has_fxsr = cpu_has_fxsr; + memcpy(&hh->xstate, &thread->xstate, sizeof(thread->xstate)); + } + + /* debug regs */ + + /* + * for checkpoint in process context (from within a container), + * get the actual registers; otherwise get the saved values. + */ + if (t == current) { + get_debugreg(hh->debugreg0, 0); + get_debugreg(hh->debugreg1, 1); + get_debugreg(hh->debugreg2, 2); + get_debugreg(hh->debugreg3, 3); + get_debugreg(hh->debugreg6, 6); + get_debugreg(hh->debugreg7, 7); + } else { + hh->debugreg0 = thread->debugreg0; + hh->debugreg1 = thread->debugreg1; + hh->debugreg2 = thread->debugreg2; + hh->debugreg3 = thread->debugreg3; + hh->debugreg6 = thread->debugreg6; + hh->debugreg7 = thread->debugreg7; + } + + hh->uses_debug = !!(thread_info->flags & TIF_DEBUG); + + preempt_enable(); + + CR_PRINTK("math %d debug %d\n", hh->used_math, hh->uses_debug); + + return cr_write_obj(ctx, &h, hh); +} + +/* read the thread_struct into the current task */ +int cr_read_thread(struct cr_ctx *ctx) +{ + struct cr_hdr_thread *hh = cr_hbuf_get(ctx, sizeof(*hh)); + struct task_struct *t = current; + struct thread_struct *thread = &t->thread; + int ret; + + ret = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_THREAD); + if (ret < 0) + return ret; + + CR_PRINTK("ntls %d\n", hh->ntls); + + if (hh->gdt_entry_tls_entries != GDT_ENTRY_TLS_ENTRIES || + hh->sizeof_tls_array != sizeof(thread->tls_array) || + hh->ntls < 0 || hh->ntls > GDT_ENTRY_TLS_ENTRIES) + return -EINVAL; + + if (hh->ntls > 0) { + + /* restore TLS by hand: why convert to struct user_desc if + * sys_set_thread_entry() will convert it back ? */ + + struct desc_struct *buf = ctx->tbuf; + int size = sizeof(*buf) * GDT_ENTRY_TLS_ENTRIES; + int cpu; + + BUG_ON(size > CR_TBUF_TOTAL); + + ret = cr_kread(ctx, buf, size); + if (ret < 0) + return ret; + + /* FIX: add sanity checks (eg. that values makes sense, that + * that we don't overwrite old values, etc */ + + cpu = get_cpu(); + memcpy(thread->tls_array, buf, size); + load_TLS(thread, cpu); + put_cpu(); + } + + return 0; +} + +/* read the cpu state nad registers for the current task */ +int cr_read_cpu(struct cr_ctx *ctx) +{ + struct cr_hdr_cpu *hh = cr_hbuf_get(ctx, sizeof(*hh)); + struct task_struct *t = current; + struct thread_struct *thread; + struct thread_info *thread_info; + struct pt_regs *regs; + int ret; + + ret = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_CPU); + if (ret < 0) + return ret; + + /* FIX: sanity check for sensitive registers (eg. eflags) */ + + thread = &t->thread; + thread_info = task_thread_info(t); + regs = task_pt_regs(t); + + regs->bx = hh->bx; + regs->cx = hh->cx; + regs->dx = hh->dx; + regs->si = hh->si; + regs->di = hh->di; + regs->bp = hh->bp; + regs->ax = hh->ax; + regs->ds = hh->ds; + regs->es = hh->es; + regs->orig_ax = hh->orig_ax; + regs->ip = hh->ip; + regs->cs = hh->cs; + regs->flags = hh->flags; + regs->sp = hh->sp; + regs->ss = hh->ss; + + thread->gs = hh->gs; + thread->fs = hh->fs; + loadsegment(gs, hh->gs); + loadsegment(fs, hh->fs); + + CR_PRINTK("math %d debug %d\n", hh->used_math, hh->uses_debug); + + /* FIX: this should work ... (someone double check !) */ + + preempt_disable(); + + /* i387 + MMU + SSE */ + __clear_fpu(t); /* in case we used FPU in user mode */ + if (!hh->used_math) + clear_used_math(); + else { + if (hh->has_fxsr != cpu_has_fxsr) { + force_sig(SIGFPE, t); + return -EINVAL; + } + memcpy(&thread->xstate, &hh->xstate, sizeof(thread->xstate)); + set_used_math(); + } + + /* debug regs */ + if (hh->uses_debug) { + set_debugreg(hh->debugreg0, 0); + set_debugreg(hh->debugreg1, 1); + set_debugreg(hh->debugreg2, 2); + set_debugreg(hh->debugreg3, 3); + set_debugreg(hh->debugreg6, 6); + set_debugreg(hh->debugreg7, 7); + } + + preempt_enable(); + + return 0; +} diff -puN /dev/null include/asm-x86/ckpt.h --- /dev/null 2007-04-11 11:48:27.000000000 -0700 +++ linux-2.6.git-dave/include/asm-x86/ckpt.h 2008-08-04 13:29:59.000000000 -0700 @@ -0,0 +1,46 @@ +#ifndef __ASM_X86_CKPT_H +#define __ASM_X86_CKPT_H + +#include + +struct cr_hdr_thread { + /* NEED: restart blocks */ + __s16 gdt_entry_tls_entries; + __s16 sizeof_tls_array; + __s16 ntls; /* number of TLS entries to follow */ +}; + +struct cr_hdr_cpu { + __u64 bx; + __u64 cx; + __u64 dx; + __u64 si; + __u64 di; + __u64 bp; + __u64 ax; + __u64 ds; + __u64 es; + __u64 orig_ax; + __u64 ip; + __u64 cs; + __u64 flags; + __u64 sp; + __u64 ss; + __u64 fs; + __u64 gs; + + __u64 debugreg0; + __u64 debugreg1; + __u64 debugreg2; + __u64 debugreg3; + __u64 debugreg6; + __u64 debugreg7; + + __u8 uses_debug; + + __u8 used_math; + __u8 has_fxsr; + union thread_xstate xstate; /* i387 */ +}; + +#endif /* __ASM_X86_CKPT_H */ _ -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/