From 671312304ec73059a0128ff3ac7a5ced459098ae Mon Sep 17 00:00:00 2001 From: Honggang Li Date: Thu, 5 Jun 2014 12:15:24 +0800 Subject: [PATCH 1/5] um: remove csum_partial_copy_generic_i386 to clean up exception table arch/x86/um/checksum_32.S had been copy & paste from x86. When build x86 uml, csum_partial_copy_generic_i386 mess up the exception table. In fact, exception table dose not work in uml kernel. And csum_partial_copy_generic_i386 never been called. So, delete it. Signed-off-by: Honggang Li Signed-off-by: Richard Weinberger --- arch/x86/um/checksum_32.S | 239 -------------------------------------- 1 file changed, 239 deletions(-) diff --git a/arch/x86/um/checksum_32.S b/arch/x86/um/checksum_32.S index 8d0c420465cc..fa4b8b9841ff 100644 --- a/arch/x86/um/checksum_32.S +++ b/arch/x86/um/checksum_32.S @@ -214,242 +214,3 @@ csum_partial: ret #endif - -/* -unsigned int csum_partial_copy_generic (const char *src, char *dst, - int len, int sum, int *src_err_ptr, int *dst_err_ptr) - */ - -/* - * Copy from ds while checksumming, otherwise like csum_partial - * - * The macros SRC and DST specify the type of access for the instruction. - * thus we can call a custom exception handler for all access types. - * - * FIXME: could someone double-check whether I haven't mixed up some SRC and - * DST definitions? It's damn hard to trigger all cases. I hope I got - * them all but there's no guarantee. - */ - -#define SRC(y...) \ - 9999: y; \ - _ASM_EXTABLE(9999b, 6001f) - -#define DST(y...) \ - 9999: y; \ - _ASM_EXTABLE(9999b, 6002f) - -.align 4 - -#ifndef CONFIG_X86_USE_PPRO_CHECKSUM - -#define ARGBASE 16 -#define FP 12 - -csum_partial_copy_generic_i386: - subl $4,%esp - pushl %edi - pushl %esi - pushl %ebx - movl ARGBASE+16(%esp),%eax # sum - movl ARGBASE+12(%esp),%ecx # len - movl ARGBASE+4(%esp),%esi # src - movl ARGBASE+8(%esp),%edi # dst - - testl $2, %edi # Check alignment. - jz 2f # Jump if alignment is ok. - subl $2, %ecx # Alignment uses up two bytes. - jae 1f # Jump if we had at least two bytes. - addl $2, %ecx # ecx was < 2. Deal with it. - jmp 4f -SRC(1: movw (%esi), %bx ) - addl $2, %esi -DST( movw %bx, (%edi) ) - addl $2, %edi - addw %bx, %ax - adcl $0, %eax -2: - movl %ecx, FP(%esp) - shrl $5, %ecx - jz 2f - testl %esi, %esi -SRC(1: movl (%esi), %ebx ) -SRC( movl 4(%esi), %edx ) - adcl %ebx, %eax -DST( movl %ebx, (%edi) ) - adcl %edx, %eax -DST( movl %edx, 4(%edi) ) - -SRC( movl 8(%esi), %ebx ) -SRC( movl 12(%esi), %edx ) - adcl %ebx, %eax -DST( movl %ebx, 8(%edi) ) - adcl %edx, %eax -DST( movl %edx, 12(%edi) ) - -SRC( movl 16(%esi), %ebx ) -SRC( movl 20(%esi), %edx ) - adcl %ebx, %eax -DST( movl %ebx, 16(%edi) ) - adcl %edx, %eax -DST( movl %edx, 20(%edi) ) - -SRC( movl 24(%esi), %ebx ) -SRC( movl 28(%esi), %edx ) - adcl %ebx, %eax -DST( movl %ebx, 24(%edi) ) - adcl %edx, %eax -DST( movl %edx, 28(%edi) ) - - lea 32(%esi), %esi - lea 32(%edi), %edi - dec %ecx - jne 1b - adcl $0, %eax -2: movl FP(%esp), %edx - movl %edx, %ecx - andl $0x1c, %edx - je 4f - shrl $2, %edx # This clears CF -SRC(3: movl (%esi), %ebx ) - adcl %ebx, %eax -DST( movl %ebx, (%edi) ) - lea 4(%esi), %esi - lea 4(%edi), %edi - dec %edx - jne 3b - adcl $0, %eax -4: andl $3, %ecx - jz 7f - cmpl $2, %ecx - jb 5f -SRC( movw (%esi), %cx ) - leal 2(%esi), %esi -DST( movw %cx, (%edi) ) - leal 2(%edi), %edi - je 6f - shll $16,%ecx -SRC(5: movb (%esi), %cl ) -DST( movb %cl, (%edi) ) -6: addl %ecx, %eax - adcl $0, %eax -7: -5000: - -# Exception handler: -.section .fixup, "ax" - -6001: - movl ARGBASE+20(%esp), %ebx # src_err_ptr - movl $-EFAULT, (%ebx) - - # zero the complete destination - computing the rest - # is too much work - movl ARGBASE+8(%esp), %edi # dst - movl ARGBASE+12(%esp), %ecx # len - xorl %eax,%eax - rep ; stosb - - jmp 5000b - -6002: - movl ARGBASE+24(%esp), %ebx # dst_err_ptr - movl $-EFAULT,(%ebx) - jmp 5000b - -.previous - - popl %ebx - popl %esi - popl %edi - popl %ecx # equivalent to addl $4,%esp - ret - -#else - -/* Version for PentiumII/PPro */ - -#define ROUND1(x) \ - SRC(movl x(%esi), %ebx ) ; \ - addl %ebx, %eax ; \ - DST(movl %ebx, x(%edi) ) ; - -#define ROUND(x) \ - SRC(movl x(%esi), %ebx ) ; \ - adcl %ebx, %eax ; \ - DST(movl %ebx, x(%edi) ) ; - -#define ARGBASE 12 - -csum_partial_copy_generic_i386: - pushl %ebx - pushl %edi - pushl %esi - movl ARGBASE+4(%esp),%esi #src - movl ARGBASE+8(%esp),%edi #dst - movl ARGBASE+12(%esp),%ecx #len - movl ARGBASE+16(%esp),%eax #sum -# movl %ecx, %edx - movl %ecx, %ebx - movl %esi, %edx - shrl $6, %ecx - andl $0x3c, %ebx - negl %ebx - subl %ebx, %esi - subl %ebx, %edi - lea -1(%esi),%edx - andl $-32,%edx - lea 3f(%ebx,%ebx), %ebx - testl %esi, %esi - jmp *%ebx -1: addl $64,%esi - addl $64,%edi - SRC(movb -32(%edx),%bl) ; SRC(movb (%edx),%bl) - ROUND1(-64) ROUND(-60) ROUND(-56) ROUND(-52) - ROUND (-48) ROUND(-44) ROUND(-40) ROUND(-36) - ROUND (-32) ROUND(-28) ROUND(-24) ROUND(-20) - ROUND (-16) ROUND(-12) ROUND(-8) ROUND(-4) -3: adcl $0,%eax - addl $64, %edx - dec %ecx - jge 1b -4: movl ARGBASE+12(%esp),%edx #len - andl $3, %edx - jz 7f - cmpl $2, %edx - jb 5f -SRC( movw (%esi), %dx ) - leal 2(%esi), %esi -DST( movw %dx, (%edi) ) - leal 2(%edi), %edi - je 6f - shll $16,%edx -5: -SRC( movb (%esi), %dl ) -DST( movb %dl, (%edi) ) -6: addl %edx, %eax - adcl $0, %eax -7: -.section .fixup, "ax" -6001: movl ARGBASE+20(%esp), %ebx # src_err_ptr - movl $-EFAULT, (%ebx) - # zero the complete destination (computing the rest is too much work) - movl ARGBASE+8(%esp),%edi # dst - movl ARGBASE+12(%esp),%ecx # len - xorl %eax,%eax - rep; stosb - jmp 7b -6002: movl ARGBASE+24(%esp), %ebx # dst_err_ptr - movl $-EFAULT, (%ebx) - jmp 7b -.previous - - popl %esi - popl %edi - popl %ebx - ret - -#undef ROUND -#undef ROUND1 - -#endif From 9e6a57d2cdee36a6d9c5d5cc3db85713dd416719 Mon Sep 17 00:00:00 2001 From: Honggang Li Date: Tue, 3 Jun 2014 13:30:45 +0800 Subject: [PATCH 2/5] um: delete unnecessary bootmem struct page array 1) uml kernel bootmem managed through bootmem_data->node_bootmem_map, not the struct page array, so the array is unnecessary. 2) the bootmem struct page array has been pointed by a *local* pointer, struct page *map, in init_maps function. The array can be accessed only in init_maps's scope. As a result, uml kernel wastes about 1% of total memory. Signed-off-by: Honggang Li Signed-off-by: Richard Weinberger --- arch/um/include/shared/mem_user.h | 2 +- arch/um/kernel/physmem.c | 32 ++++++------------------------- arch/um/kernel/um_arch.c | 7 +------ 3 files changed, 8 insertions(+), 33 deletions(-) diff --git a/arch/um/include/shared/mem_user.h b/arch/um/include/shared/mem_user.h index 46384acd547b..cb84414e3e66 100644 --- a/arch/um/include/shared/mem_user.h +++ b/arch/um/include/shared/mem_user.h @@ -49,7 +49,7 @@ extern int iomem_size; extern int init_mem_user(void); extern void setup_memory(void *entry); extern unsigned long find_iomem(char *driver, unsigned long *len_out); -extern int init_maps(unsigned long physmem, unsigned long iomem, +extern void mem_total_pages(unsigned long physmem, unsigned long iomem, unsigned long highmem); extern unsigned long get_vm(unsigned long len); extern void setup_physmem(unsigned long start, unsigned long usable, diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c index 30fdd5d0067b..549ecf3f5857 100644 --- a/arch/um/kernel/physmem.c +++ b/arch/um/kernel/physmem.c @@ -22,39 +22,19 @@ EXPORT_SYMBOL(high_physmem); extern unsigned long long physmem_size; -int __init init_maps(unsigned long physmem, unsigned long iomem, +void __init mem_total_pages(unsigned long physmem, unsigned long iomem, unsigned long highmem) { - struct page *p, *map; - unsigned long phys_len, phys_pages, highmem_len, highmem_pages; - unsigned long iomem_len, iomem_pages, total_len, total_pages; - int i; - - phys_pages = physmem >> PAGE_SHIFT; - phys_len = phys_pages * sizeof(struct page); - - iomem_pages = iomem >> PAGE_SHIFT; - iomem_len = iomem_pages * sizeof(struct page); + unsigned long phys_pages, highmem_pages; + unsigned long iomem_pages, total_pages; + phys_pages = physmem >> PAGE_SHIFT; + iomem_pages = iomem >> PAGE_SHIFT; highmem_pages = highmem >> PAGE_SHIFT; - highmem_len = highmem_pages * sizeof(struct page); - total_pages = phys_pages + iomem_pages + highmem_pages; - total_len = phys_len + iomem_len + highmem_len; - - map = alloc_bootmem_low_pages(total_len); - if (map == NULL) - return -ENOMEM; - - for (i = 0; i < total_pages; i++) { - p = &map[i]; - memset(p, 0, sizeof(struct page)); - SetPageReserved(p); - INIT_LIST_HEAD(&p->lru); - } + total_pages = phys_pages + iomem_pages + highmem_pages; max_mapnr = total_pages; - return 0; } void map_memory(unsigned long virt, unsigned long phys, unsigned long len, diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 016adf0985d5..9274eae6ae7b 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -348,12 +348,7 @@ int __init linux_main(int argc, char **argv) start_vm = VMALLOC_START; setup_physmem(uml_physmem, uml_reserved, physmem_size, highmem); - if (init_maps(physmem_size, iomem_size, highmem)) { - printf("Failed to allocate mem_map for %Lu bytes of physical " - "memory and %Lu bytes of highmem\n", physmem_size, - highmem); - exit(1); - } + mem_total_pages(physmem_size, iomem_size, highmem); virtmem_size = physmem_size; stack = (unsigned long) argv; From 2a2361228c5e6d8c1733f00653481de918598e50 Mon Sep 17 00:00:00 2001 From: Thorsten Knabe Date: Sat, 23 Aug 2014 15:47:38 +0200 Subject: [PATCH 3/5] um: ubd: Fix for processes stuck in D state forever Starting with Linux 3.12 processes get stuck in D state forever in UserModeLinux under sync heavy workloads. This bug was introduced by commit 805f11a0d5 (um: ubd: Add REQ_FLUSH suppport). Fix bug by adding a check if FLUSH request was successfully submitted to the I/O thread and keeping the FLUSH request on the request queue on submission failures. Fixes: 805f11a0d5 (um: ubd: Add REQ_FLUSH suppport) Signed-off-by: Thorsten Knabe Cc: stable@kernel.org # >= 3.12 Signed-off-by: Richard Weinberger --- arch/um/drivers/ubd_kern.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 3716e6952554..e8ab93c3e638 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1277,7 +1277,7 @@ static void do_ubd_request(struct request_queue *q) while(1){ struct ubd *dev = q->queuedata; - if(dev->end_sg == 0){ + if(dev->request == NULL){ struct request *req = blk_fetch_request(q); if(req == NULL) return; @@ -1299,7 +1299,8 @@ static void do_ubd_request(struct request_queue *q) return; } prepare_flush_request(req, io_req); - submit_request(io_req, dev); + if (submit_request(io_req, dev) == false) + return; } while(dev->start_sg < dev->end_sg){ From 970e51feaddbc33ed0e7d187af7f69d1a12c7b6a Mon Sep 17 00:00:00 2001 From: Daniel Walter Date: Wed, 20 Aug 2014 10:56:00 +0100 Subject: [PATCH 4/5] um: Add support for CONFIG_STACKTRACE Add stacktrace support for User Mode Linux Signed-off-by: Daniel Walter Signed-off-by: Richard Weinberger --- arch/um/Kconfig.common | 3 +- arch/um/include/asm/stacktrace.h | 42 +++++++++++++++++ arch/um/kernel/Makefile | 1 + arch/um/kernel/stacktrace.c | 80 ++++++++++++++++++++++++++++++++ arch/um/kernel/sysrq.c | 73 ++++++++--------------------- 5 files changed, 144 insertions(+), 55 deletions(-) create mode 100644 arch/um/include/asm/stacktrace.h create mode 100644 arch/um/kernel/stacktrace.c diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common index 6915d28cf118..87bc86821bc9 100644 --- a/arch/um/Kconfig.common +++ b/arch/um/Kconfig.common @@ -39,7 +39,8 @@ config LOCKDEP_SUPPORT config STACKTRACE_SUPPORT bool - default n + default y + select STACKTRACE config GENERIC_CALIBRATE_DELAY bool diff --git a/arch/um/include/asm/stacktrace.h b/arch/um/include/asm/stacktrace.h new file mode 100644 index 000000000000..9a864328c67f --- /dev/null +++ b/arch/um/include/asm/stacktrace.h @@ -0,0 +1,42 @@ +#ifndef _ASM_UML_STACKTRACE_H +#define _ASM_UML_STACKTRACE_H + +#include +#include + +struct stack_frame { + struct stack_frame *next_frame; + unsigned long return_address; +}; + +struct stacktrace_ops { + void (*address)(void *data, unsigned long address, int reliable); +}; + +#ifdef CONFIG_FRAME_POINTER +static inline unsigned long +get_frame_pointer(struct task_struct *task, struct pt_regs *segv_regs) +{ + if (!task || task == current) + return segv_regs ? PT_REGS_BP(segv_regs) : current_bp(); + return KSTK_EBP(task); +} +#else +static inline unsigned long +get_frame_pointer(struct task_struct *task, struct pt_regs *segv_regs) +{ + return 0; +} +#endif + +static inline unsigned long +*get_stack_pointer(struct task_struct *task, struct pt_regs *segv_regs) +{ + if (!task || task == current) + return segv_regs ? (unsigned long *)PT_REGS_SP(segv_regs) : current_sp(); + return (unsigned long *)KSTK_ESP(task); +} + +void dump_trace(struct task_struct *tsk, const struct stacktrace_ops *ops, void *data); + +#endif /* _ASM_UML_STACKTRACE_H */ diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile index d8b78a03855c..2d840a070c8b 100644 --- a/arch/um/kernel/Makefile +++ b/arch/um/kernel/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_BLK_DEV_INITRD) += initrd.o obj-$(CONFIG_GPROF) += gprof_syms.o obj-$(CONFIG_GCOV) += gmon_syms.o obj-$(CONFIG_EARLY_PRINTK) += early_printk.o +obj-$(CONFIG_STACKTRACE) += stacktrace.o USER_OBJS := config.o diff --git a/arch/um/kernel/stacktrace.c b/arch/um/kernel/stacktrace.c new file mode 100644 index 000000000000..ebe7bcf62684 --- /dev/null +++ b/arch/um/kernel/stacktrace.c @@ -0,0 +1,80 @@ +/* + * Copyright (C) 2001 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com) + * Copyright (C) 2013 Richard Weinberger + * Copyright (C) 2014 Google Inc., Author: Daniel Walter + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include + +void dump_trace(struct task_struct *tsk, + const struct stacktrace_ops *ops, + void *data) +{ + int reliable = 0; + unsigned long *sp, bp, addr; + struct pt_regs *segv_regs = tsk->thread.segv_regs; + struct stack_frame *frame; + + bp = get_frame_pointer(tsk, segv_regs); + sp = get_stack_pointer(tsk, segv_regs); + + frame = (struct stack_frame *)bp; + while (((long) sp & (THREAD_SIZE-1)) != 0) { + addr = *sp; + if (__kernel_text_address(addr)) { + reliable = 0; + if ((unsigned long) sp == bp + sizeof(long)) { + frame = frame ? frame->next_frame : NULL; + bp = (unsigned long)frame; + reliable = 1; + } + ops->address(data, addr, reliable); + } + sp++; + } +} + +static void save_addr(void *data, unsigned long address, int reliable) +{ + struct stack_trace *trace = data; + + if (!reliable) + return; + if (trace->nr_entries >= trace->max_entries) + return; + + trace->entries[trace->nr_entries++] = address; +} + +static const struct stacktrace_ops dump_ops = { + .address = save_addr +}; + +static void __save_stack_trace(struct task_struct *tsk, struct stack_trace *trace) +{ + dump_trace(tsk, &dump_ops, trace); + if (trace->nr_entries < trace->max_entries) + trace->entries[trace->nr_entries++] = ULONG_MAX; +} + +void save_stack_trace(struct stack_trace *trace) +{ + __save_stack_trace(current, trace); +} +EXPORT_SYMBOL_GPL(save_stack_trace); + +void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +{ + __save_stack_trace(tsk, trace); +} +EXPORT_SYMBOL_GPL(save_stack_trace_tsk); diff --git a/arch/um/kernel/sysrq.c b/arch/um/kernel/sysrq.c index 799d7e413bf5..894c8d303cda 100644 --- a/arch/um/kernel/sysrq.c +++ b/arch/um/kernel/sysrq.c @@ -12,58 +12,21 @@ #include #include #include +#include #include -struct stack_frame { - struct stack_frame *next_frame; - unsigned long return_address; +static void _print_addr(void *data, unsigned long address, int reliable) +{ + pr_info(" [<%08lx>]", address); + pr_cont(" %s", reliable ? "" : "? "); + print_symbol("%s", address); + pr_cont("\n"); +} + +static const struct stacktrace_ops stackops = { + .address = _print_addr }; -static void do_stack_trace(unsigned long *sp, unsigned long bp) -{ - int reliable; - unsigned long addr; - struct stack_frame *frame = (struct stack_frame *)bp; - - printk(KERN_INFO "Call Trace:\n"); - while (((long) sp & (THREAD_SIZE-1)) != 0) { - addr = *sp; - if (__kernel_text_address(addr)) { - reliable = 0; - if ((unsigned long) sp == bp + sizeof(long)) { - frame = frame ? frame->next_frame : NULL; - bp = (unsigned long)frame; - reliable = 1; - } - - printk(KERN_INFO " [<%08lx>]", addr); - printk(KERN_CONT " %s", reliable ? "" : "? "); - print_symbol(KERN_CONT "%s", addr); - printk(KERN_CONT "\n"); - } - sp++; - } - printk(KERN_INFO "\n"); -} - -static unsigned long get_frame_pointer(struct task_struct *task, - struct pt_regs *segv_regs) -{ - if (!task || task == current) - return segv_regs ? PT_REGS_BP(segv_regs) : current_bp(); - else - return KSTK_EBP(task); -} - -static unsigned long *get_stack_pointer(struct task_struct *task, - struct pt_regs *segv_regs) -{ - if (!task || task == current) - return segv_regs ? (unsigned long *)PT_REGS_SP(segv_regs) : current_sp(); - else - return (unsigned long *)KSTK_ESP(task); -} - void show_stack(struct task_struct *task, unsigned long *stack) { unsigned long *sp = stack, bp = 0; @@ -71,7 +34,7 @@ void show_stack(struct task_struct *task, unsigned long *stack) int i; if (!segv_regs && os_is_signal_stack()) { - printk(KERN_ERR "Received SIGSEGV in SIGSEGV handler," + pr_err("Received SIGSEGV in SIGSEGV handler," " aborting stack trace!\n"); return; } @@ -83,16 +46,18 @@ void show_stack(struct task_struct *task, unsigned long *stack) if (!stack) sp = get_stack_pointer(task, segv_regs); - printk(KERN_INFO "Stack:\n"); + pr_info("Stack:\n"); stack = sp; for (i = 0; i < 3 * STACKSLOTS_PER_LINE; i++) { if (kstack_end(stack)) break; if (i && ((i % STACKSLOTS_PER_LINE) == 0)) - printk(KERN_CONT "\n"); - printk(KERN_CONT " %08lx", *stack++); + pr_cont("\n"); + pr_cont(" %08lx", *stack++); } - printk(KERN_CONT "\n"); + pr_cont("\n"); - do_stack_trace(sp, bp); + pr_info("Call Trace:\n"); + dump_trace(current, &stackops, NULL); + pr_info("\n"); } From 5f786595a291092d20fafe10c5a30378971a8cc3 Mon Sep 17 00:00:00 2001 From: Himangi Saraogi Date: Sat, 19 Jul 2014 17:04:05 +0530 Subject: [PATCH 5/5] um: net: Eliminate NULL test after alloc_bootmem alloc_bootmem and related functions never return NULL. Thus a NULL test or memset after calls to these functions is unnecessary. The following Coccinelle semantic patch was used for making the change: @@ expression E; statement S; @@ E = \(alloc_bootmem\|alloc_bootmem_low\|alloc_bootmem_pages\|alloc_bootmem_low_pages\)(...) ... when != E - if (E == NULL) S Signed-off-by: Himangi Saraogi Acked-by: Julia Lawall Signed-off-by: Richard Weinberger --- arch/um/drivers/net_kern.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 7d26d9c0b2fb..f70dd540655d 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -659,10 +659,6 @@ static int __init eth_setup(char *str) } new = alloc_bootmem(sizeof(*new)); - if (new == NULL) { - printk(KERN_ERR "eth_init : alloc_bootmem failed\n"); - return 1; - } INIT_LIST_HEAD(&new->list); new->index = n;