From 4f1933620f57145212cdbb1ac6ce099eeeb21c5a Mon Sep 17 00:00:00 2001 From: Paul Smith Date: Sun, 5 Mar 2006 17:14:10 -0500 Subject: kbuild: change kbuild to not rely on incorrect GNU make behavior The kbuild system takes advantage of an incorrect behavior in GNU make. Once this behavior is fixed, all files in the kernel rebuild every time, even if nothing has changed. This patch ensures kbuild works with both the incorrect and correct behaviors of GNU make. For more details on the incorrect behavior, see: http://lists.gnu.org/archive/html/bug-make/2006-03/msg00003.html Changes in this patch: - Keep all targets that are to be marked .PHONY in a variable, PHONY. - Add .PHONY: $(PHONY) to mark them properly. - Remove any $(PHONY) files from the $? list when determining whether targets are up-to-date or not. Signed-off-by: Paul Smith Signed-off-by: Sam Ravnborg --- arch/um/Makefile | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'arch/um') diff --git a/arch/um/Makefile b/arch/um/Makefile index c58b657f0097..8d14c7a831be 100644 --- a/arch/um/Makefile +++ b/arch/um/Makefile @@ -1,4 +1,7 @@ -# +# +# This file is included by the global makefile so that you can add your own +# architecture-specific flags and dependencies. +# # Copyright (C) 2002 Jeff Dike (jdike@karaya.com) # Licensed under the GPL # @@ -88,7 +91,7 @@ CONFIG_KERNEL_HALF_GIGS ?= 0 SIZE = (($(CONFIG_NEST_LEVEL) + $(CONFIG_KERNEL_HALF_GIGS)) * 0x20000000) -.PHONY: linux +PHONY += linux all: linux -- cgit v1.2.3 From 70dc991d66cac40fdb07346dba2b5d862d732c34 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 22 Mar 2006 00:08:35 -0800 Subject: [PATCH] remove set_page_count(page, 0) users (outside mm) A couple of places set_page_count(page, 1) that don't need to. Signed-off-by: Nick Piggin Cc: Paul Mackerras Cc: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/kernel/physmem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/um') diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c index 544665e04513..0e65340eee33 100644 --- a/arch/um/kernel/physmem.c +++ b/arch/um/kernel/physmem.c @@ -279,7 +279,7 @@ int init_maps(unsigned long physmem, unsigned long iomem, unsigned long highmem) for(i = 0; i < total_pages; i++){ p = &map[i]; - set_page_count(p, 0); + memset(p, 0, sizeof(struct page)); SetPageReserved(p); INIT_LIST_HEAD(&p->lru); } -- cgit v1.2.3 From 7835e98b2e3c66dba79cb0ff8ebb90a2fe030c29 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 22 Mar 2006 00:08:40 -0800 Subject: [PATCH] remove set_page_count() outside mm/ set_page_count usage outside mm/ is limited to setting the refcount to 1. Remove set_page_count from outside mm/, and replace those users with init_page_count() and set_page_refcounted(). This allows more debug checking, and tighter control on how code is allowed to play around with page->_count. Signed-off-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/kernel/mem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/um') diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index fa4f915be5c5..92cce96b5e24 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -57,7 +57,7 @@ static void setup_highmem(unsigned long highmem_start, for(i = 0; i < highmem_len >> PAGE_SHIFT; i++){ page = &mem_map[highmem_pfn + i]; ClearPageReserved(page); - set_page_count(page, 1); + init_page_count(page); __free_page(page); } } @@ -296,7 +296,7 @@ void free_initrd_mem(unsigned long start, unsigned long end) (end - start) >> 10); for (; start < end; start += PAGE_SIZE) { ClearPageReserved(virt_to_page(start)); - set_page_count(virt_to_page(start), 1); + init_page_count(virt_to_page(start)); free_page(start); totalram_pages++; } -- cgit v1.2.3 From 9a0b5817ad97bb718ab85322759d19a238712b47 Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Thu, 23 Mar 2006 02:59:32 -0800 Subject: [PATCH] x86: SMP alternatives Implement SMP alternatives, i.e. switching at runtime between different code versions for UP and SMP. The code can patch both SMP->UP and UP->SMP. The UP->SMP case is useful for CPU hotplug. With CONFIG_CPU_HOTPLUG enabled the code switches to UP at boot time and when the number of CPUs goes down to 1, and switches to SMP when the number of CPUs goes up to 2. Without CONFIG_CPU_HOTPLUG or on non-SMP-capable systems the code is patched once at boot time (if needed) and the tables are released afterwards. The changes in detail: * The current alternatives bits are moved to a separate file, the SMP alternatives code is added there. * The patch adds some new elf sections to the kernel: .smp_altinstructions like .altinstructions, also contains a list of alt_instr structs. .smp_altinstr_replacement like .altinstr_replacement, but also has some space to save original instruction before replaving it. .smp_locks list of pointers to lock prefixes which can be nop'ed out on UP. The first two are used to replace more complex instruction sequences such as spinlocks and semaphores. It would be possible to deal with the lock prefixes with that as well, but by handling them as special case the table sizes become much smaller. * The sections are page-aligned and padded up to page size, so they can be free if they are not needed. * Splitted the code to release init pages to a separate function and use it to release the elf sections if they are unused. Signed-off-by: Gerd Hoffmann Signed-off-by: Chuck Ebbert <76306.1226@compuserve.com> Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/kernel/um_arch.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) (limited to 'arch/um') diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 27cdf9164422..80c9c18aae94 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -491,6 +491,16 @@ void __init check_bugs(void) check_devanon(); } -void apply_alternatives(void *start, void *end) +void apply_alternatives(struct alt_instr *start, struct alt_instr *end) +{ +} + +void alternatives_smp_module_add(struct module *mod, char *name, + void *locks, void *locks_end, + void *text, void *text_end) +{ +} + +void alternatives_smp_module_del(struct module *mod) { } -- cgit v1.2.3 From f214ef3e193dea10a7b527d4f4b0c15d2d98c984 Mon Sep 17 00:00:00 2001 From: Akinobu Mita Date: Sun, 26 Mar 2006 01:38:59 -0800 Subject: [PATCH] um: fix undefined reference to hweight32 Build fix for user mode linux. Signed-off-by: Akinobu Mita Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/Kconfig.i386 | 5 +++++ arch/um/Kconfig.x86_64 | 5 +++++ 2 files changed, 10 insertions(+) (limited to 'arch/um') diff --git a/arch/um/Kconfig.i386 b/arch/um/Kconfig.i386 index ef79ed25aecd..85e6a55b3b59 100644 --- a/arch/um/Kconfig.i386 +++ b/arch/um/Kconfig.i386 @@ -52,3 +52,8 @@ config ARCH_HAS_SC_SIGNALS config ARCH_REUSE_HOST_VSYSCALL_AREA bool default y + +config GENERIC_HWEIGHT + bool + default y + diff --git a/arch/um/Kconfig.x86_64 b/arch/um/Kconfig.x86_64 index aae19bc4b06a..f60e9e506424 100644 --- a/arch/um/Kconfig.x86_64 +++ b/arch/um/Kconfig.x86_64 @@ -46,3 +46,8 @@ config ARCH_REUSE_HOST_VSYSCALL_AREA config SMP_BROKEN bool default y + +config GENERIC_HWEIGHT + bool + default y + -- cgit v1.2.3 From c90e12b86595dbd9996336ac9d762487c638d934 Mon Sep 17 00:00:00 2001 From: Jeff Dike Date: Mon, 27 Mar 2006 01:14:29 -0800 Subject: [PATCH] uml: fix declaration of exit() This fixes a conflict between a header and what gcc "knows" the declaration' to be. Signed-off-by: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/include/kern.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/um') diff --git a/arch/um/include/kern.h b/arch/um/include/kern.h index 7d223beccbc0..4ce3fc650e57 100644 --- a/arch/um/include/kern.h +++ b/arch/um/include/kern.h @@ -29,7 +29,7 @@ extern int getuid(void); extern int getgid(void); extern int pause(void); extern int write(int, const void *, int); -extern int exit(int); +extern void exit(int); extern int close(int); extern int read(unsigned int, char *, int); extern int pipe(int *); -- cgit v1.2.3 From d9f8b62a6b033fe7226d7c2b2efdd164ca1aa07c Mon Sep 17 00:00:00 2001 From: Jeff Dike Date: Mon, 27 Mar 2006 01:14:29 -0800 Subject: [PATCH] uml: fix some printf formats Some printf formats are incorrect for large memory sizes. Signed-off-by: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/kernel/um_arch.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/um') diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 80c9c18aae94..0c5b9dcfbe2e 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -421,7 +421,7 @@ int linux_main(int argc, char **argv) #ifndef CONFIG_HIGHMEM highmem = 0; printf("CONFIG_HIGHMEM not enabled - physical memory shrunk " - "to %lu bytes\n", physmem_size); + "to %Lu bytes\n", physmem_size); #endif } @@ -433,8 +433,8 @@ int linux_main(int argc, char **argv) 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, + printf("Failed to allocate mem_map for %Lu bytes of physical " + "memory and %Lu bytes of highmem\n", physmem_size, highmem); exit(1); } -- cgit v1.2.3 From 63ae2a94d98dd9d94163918539ec80df33f44a69 Mon Sep 17 00:00:00 2001 From: Jeff Dike Date: Mon, 27 Mar 2006 01:14:30 -0800 Subject: [PATCH] uml: move libc-dependent irq code to os-Linux The serial UML OS-abstraction layer patch (um/kernel dir). This moves all systemcalls from irq_user.c file under os-Linux dir Signed-off-by: Gennady Sharapov Signed-off-by: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/include/irq_user.h | 15 ++- arch/um/include/misc_constants.h | 6 ++ arch/um/include/os.h | 16 +++ arch/um/kernel/irq_user.c | 204 +++++++++++--------------------------- arch/um/kernel/smp.c | 14 +-- arch/um/os-Linux/Makefile | 6 +- arch/um/os-Linux/irq.c | 162 ++++++++++++++++++++++++++++++ arch/um/os-Linux/tt.c | 10 ++ arch/um/sys-i386/user-offsets.c | 10 +- arch/um/sys-x86_64/user-offsets.c | 6 ++ 10 files changed, 288 insertions(+), 161 deletions(-) create mode 100644 arch/um/include/misc_constants.h create mode 100644 arch/um/os-Linux/irq.c (limited to 'arch/um') diff --git a/arch/um/include/irq_user.h b/arch/um/include/irq_user.h index b61deb8b362a..69a93c804f0e 100644 --- a/arch/um/include/irq_user.h +++ b/arch/um/include/irq_user.h @@ -1,4 +1,4 @@ -/* +/* * Copyright (C) 2001, 2002 Jeff Dike (jdike@karaya.com) * Licensed under the GPL */ @@ -6,6 +6,17 @@ #ifndef __IRQ_USER_H__ #define __IRQ_USER_H__ +struct irq_fd { + struct irq_fd *next; + void *id; + int fd; + int type; + int irq; + int pid; + int events; + int current_events; +}; + enum { IRQ_READ, IRQ_WRITE }; extern void sigio_handler(int sig, union uml_pt_regs *regs); @@ -16,8 +27,6 @@ extern void reactivate_fd(int fd, int irqnum); extern void deactivate_fd(int fd, int irqnum); extern int deactivate_all_fds(void); extern void forward_interrupts(int pid); -extern void init_irq_signals(int on_sigstack); -extern void forward_ipi(int fd, int pid); extern int activate_ipi(int fd, int pid); extern unsigned long irq_lock(void); extern void irq_unlock(unsigned long flags); diff --git a/arch/um/include/misc_constants.h b/arch/um/include/misc_constants.h new file mode 100644 index 000000000000..989bc08de36e --- /dev/null +++ b/arch/um/include/misc_constants.h @@ -0,0 +1,6 @@ +#ifndef __MISC_CONSTANT_H_ +#define __MISC_CONSTANT_H_ + +#include + +#endif diff --git a/arch/um/include/os.h b/arch/um/include/os.h index 2a1c64d8d0bf..efae3e6acb5b 100644 --- a/arch/um/include/os.h +++ b/arch/um/include/os.h @@ -12,6 +12,7 @@ #include "sysdep/ptrace.h" #include "kern_util.h" #include "skas/mm_id.h" +#include "irq_user.h" #define OS_TYPE_FILE 1 #define OS_TYPE_DIR 2 @@ -198,6 +199,8 @@ extern void os_flush_stdout(void); /* tt.c * for tt mode only (will be deleted in future...) */ +extern void forward_ipi(int fd, int pid); +extern void kill_child_dead(int pid); extern void stop(void); extern int wait_for_stop(int pid, int sig, int cont_type, void *relay); extern int protect_memory(unsigned long addr, unsigned long len, @@ -294,4 +297,17 @@ extern void initial_thread_cb_skas(void (*proc)(void *), extern void halt_skas(void); extern void reboot_skas(void); +/* irq.c */ +extern int os_waiting_for_events(struct irq_fd *active_fds); +extern int os_isatty(int fd); +extern int os_create_pollfd(int fd, int events, void *tmp_pfd, int size_tmpfds); +extern void os_free_irq_by_cb(int (*test)(struct irq_fd *, void *), void *arg, + struct irq_fd *active_fds, struct irq_fd ***last_irq_ptr2); +extern void os_free_irq_later(struct irq_fd *active_fds, + int irq, void *dev_id); +extern int os_get_pollfd(int i); +extern void os_set_pollfd(int i, int fd); +extern void os_set_ioignore(void); +extern void init_irq_signals(int on_sigstack); + #endif diff --git a/arch/um/kernel/irq_user.c b/arch/um/kernel/irq_user.c index 0e32f5f4a887..483e79c5ab98 100644 --- a/arch/um/kernel/irq_user.c +++ b/arch/um/kernel/irq_user.c @@ -1,4 +1,4 @@ -/* +/* * Copyright (C) 2000 Jeff Dike (jdike@karaya.com) * Licensed under the GPL */ @@ -18,53 +18,25 @@ #include "sigio.h" #include "irq_user.h" #include "os.h" +#include "misc_constants.h" -struct irq_fd { - struct irq_fd *next; - void *id; - int fd; - int type; - int irq; - int pid; - int events; - int current_events; -}; - -static struct irq_fd *active_fds = NULL; +struct irq_fd *active_fds = NULL; static struct irq_fd **last_irq_ptr = &active_fds; -static struct pollfd *pollfds = NULL; -static int pollfds_num = 0; -static int pollfds_size = 0; - -extern int io_count, intr_count; - extern void free_irqs(void); void sigio_handler(int sig, union uml_pt_regs *regs) { struct irq_fd *irq_fd; - int i, n; + int n; if(smp_sigio_handler()) return; while(1){ - n = poll(pollfds, pollfds_num, 0); - if(n < 0){ - if(errno == EINTR) continue; - printk("sigio_handler : poll returned %d, " - "errno = %d\n", n, errno); - break; - } - if(n == 0) break; - - irq_fd = active_fds; - for(i = 0; i < pollfds_num; i++){ - if(pollfds[i].revents != 0){ - irq_fd->current_events = pollfds[i].revents; - pollfds[i].fd = -1; - } - irq_fd = irq_fd->next; - } + n = os_waiting_for_events(active_fds); + if (n <= 0) { + if(n == -EINTR) continue; + else break; + } for(irq_fd = active_fds; irq_fd != NULL; irq_fd = irq_fd->next){ if(irq_fd->current_events != 0){ @@ -77,14 +49,9 @@ void sigio_handler(int sig, union uml_pt_regs *regs) free_irqs(); } -int activate_ipi(int fd, int pid) -{ - return(os_set_fd_async(fd, pid)); -} - static void maybe_sigio_broken(int fd, int type) { - if(isatty(fd)){ + if(os_isatty(fd)){ if((type == IRQ_WRITE) && !pty_output_sigio){ write_sigio_workaround(); add_sigio_fd(fd, 0); @@ -96,12 +63,13 @@ static void maybe_sigio_broken(int fd, int type) } } + int activate_fd(int irq, int fd, int type, void *dev_id) { struct pollfd *tmp_pfd; struct irq_fd *new_fd, *irq_fd; unsigned long flags; - int pid, events, err, n, size; + int pid, events, err, n; pid = os_getpid(); err = os_set_fd_async(fd, pid); @@ -113,8 +81,8 @@ int activate_fd(int irq, int fd, int type, void *dev_id) if(new_fd == NULL) goto out; - if(type == IRQ_READ) events = POLLIN | POLLPRI; - else events = POLLOUT; + if(type == IRQ_READ) events = UM_POLLIN | UM_POLLPRI; + else events = UM_POLLOUT; *new_fd = ((struct irq_fd) { .next = NULL, .id = dev_id, .fd = fd, @@ -125,12 +93,12 @@ int activate_fd(int irq, int fd, int type, void *dev_id) .current_events = 0 } ); /* Critical section - locked by a spinlock because this stuff can - * be changed from interrupt handlers. The stuff above is done + * be changed from interrupt handlers. The stuff above is done * outside the lock because it allocates memory. */ /* Actually, it only looks like it can be called from interrupt - * context. The culprit is reactivate_fd, which calls + * context. The culprit is reactivate_fd, which calls * maybe_sigio_broken, which calls write_sigio_workaround, * which calls activate_fd. However, write_sigio_workaround should * only be called once, at boot time. That would make it clear that @@ -147,40 +115,42 @@ int activate_fd(int irq, int fd, int type, void *dev_id) } } - n = pollfds_num; - if(n == pollfds_size){ - while(1){ - /* Here we have to drop the lock in order to call - * kmalloc, which might sleep. If something else - * came in and changed the pollfds array, we free - * the buffer and try again. - */ - irq_unlock(flags); - size = (pollfds_num + 1) * sizeof(pollfds[0]); - tmp_pfd = um_kmalloc(size); - flags = irq_lock(); - if(tmp_pfd == NULL) - goto out_unlock; - if(n == pollfds_size) - break; + /*-------------*/ + if(type == IRQ_WRITE) + fd = -1; + + tmp_pfd = NULL; + n = 0; + + while(1){ + n = os_create_pollfd(fd, events, tmp_pfd, n); + if (n == 0) + break; + + /* n > 0 + * It means we couldn't put new pollfd to current pollfds + * and tmp_fds is NULL or too small for new pollfds array. + * Needed size is equal to n as minimum. + * + * Here we have to drop the lock in order to call + * kmalloc, which might sleep. + * If something else came in and changed the pollfds array + * so we will not be able to put new pollfd struct to pollfds + * then we free the buffer tmp_fds and try again. + */ + irq_unlock(flags); + if (tmp_pfd != NULL) { kfree(tmp_pfd); + tmp_pfd = NULL; } - if(pollfds != NULL){ - memcpy(tmp_pfd, pollfds, - sizeof(pollfds[0]) * pollfds_size); - kfree(pollfds); - } - pollfds = tmp_pfd; - pollfds_size++; - } - if(type == IRQ_WRITE) - fd = -1; + tmp_pfd = um_kmalloc(n); + if (tmp_pfd == NULL) + goto out_kfree; - pollfds[pollfds_num] = ((struct pollfd) { .fd = fd, - .events = events, - .revents = 0 }); - pollfds_num++; + flags = irq_lock(); + } + /*-------------*/ *last_irq_ptr = new_fd; last_irq_ptr = &new_fd->next; @@ -196,6 +166,7 @@ int activate_fd(int irq, int fd, int type, void *dev_id) out_unlock: irq_unlock(flags); + out_kfree: kfree(new_fd); out: return(err); @@ -203,43 +174,10 @@ int activate_fd(int irq, int fd, int type, void *dev_id) static void free_irq_by_cb(int (*test)(struct irq_fd *, void *), void *arg) { - struct irq_fd **prev; unsigned long flags; - int i = 0; flags = irq_lock(); - prev = &active_fds; - while(*prev != NULL){ - if((*test)(*prev, arg)){ - struct irq_fd *old_fd = *prev; - if((pollfds[i].fd != -1) && - (pollfds[i].fd != (*prev)->fd)){ - printk("free_irq_by_cb - mismatch between " - "active_fds and pollfds, fd %d vs %d\n", - (*prev)->fd, pollfds[i].fd); - goto out; - } - - pollfds_num--; - - /* This moves the *whole* array after pollfds[i] (though - * it doesn't spot as such)! */ - - memmove(&pollfds[i], &pollfds[i + 1], - (pollfds_num - i) * sizeof(pollfds[0])); - - if(last_irq_ptr == &old_fd->next) - last_irq_ptr = prev; - *prev = (*prev)->next; - if(old_fd->type == IRQ_WRITE) - ignore_sigio_fd(old_fd->fd); - kfree(old_fd); - continue; - } - prev = &(*prev)->next; - i++; - } - out: + os_free_irq_by_cb(test, arg, active_fds, &last_irq_ptr); irq_unlock(flags); } @@ -277,6 +215,7 @@ static struct irq_fd *find_irq_by_fd(int fd, int irqnum, int *index_out) { struct irq_fd *irq; int i = 0; + int fdi; for(irq=active_fds; irq != NULL; irq = irq->next){ if((irq->fd == fd) && (irq->irq == irqnum)) break; @@ -286,10 +225,11 @@ static struct irq_fd *find_irq_by_fd(int fd, int irqnum, int *index_out) printk("find_irq_by_fd doesn't have descriptor %d\n", fd); goto out; } - if((pollfds[i].fd != -1) && (pollfds[i].fd != fd)){ + fdi = os_get_pollfd(i); + if((fdi != -1) && (fdi != fd)){ printk("find_irq_by_fd - mismatch between active_fds and " - "pollfds, fd %d vs %d, need %d\n", irq->fd, - pollfds[i].fd, fd); + "pollfds, fd %d vs %d, need %d\n", irq->fd, + fdi, fd); irq = NULL; goto out; } @@ -310,9 +250,7 @@ void reactivate_fd(int fd, int irqnum) irq_unlock(flags); return; } - - pollfds[i].fd = irq->fd; - + os_set_pollfd(i, irq->fd); irq_unlock(flags); /* This calls activate_fd, so it has to be outside the critical @@ -331,7 +269,7 @@ void deactivate_fd(int fd, int irqnum) irq = find_irq_by_fd(fd, irqnum, &i); if(irq == NULL) goto out; - pollfds[i].fd = -1; + os_set_pollfd(i, -1); out: irq_unlock(flags); } @@ -347,21 +285,11 @@ int deactivate_all_fds(void) return(err); } /* If there is a signal already queued, after unblocking ignore it */ - set_handler(SIGIO, SIG_IGN, 0, -1); + os_set_ioignore(); return(0); } -void forward_ipi(int fd, int pid) -{ - int err; - - err = os_set_owner(fd, pid); - if(err < 0) - printk("forward_ipi: set_owner failed, fd = %d, me = %d, " - "target = %d, err = %d\n", fd, os_getpid(), pid, -err); -} - void forward_interrupts(int pid) { struct irq_fd *irq; @@ -384,22 +312,6 @@ void forward_interrupts(int pid) irq_unlock(flags); } -void init_irq_signals(int on_sigstack) -{ - __sighandler_t h; - int flags; - - flags = on_sigstack ? SA_ONSTACK : 0; - if(timer_irq_inited) h = (__sighandler_t) alarm_handler; - else h = boot_timer_handler; - - set_handler(SIGVTALRM, h, flags | SA_RESTART, - SIGUSR1, SIGIO, SIGWINCH, SIGALRM, -1); - set_handler(SIGIO, (__sighandler_t) sig_handler, flags | SA_RESTART, - SIGUSR1, SIGIO, SIGWINCH, SIGALRM, SIGVTALRM, -1); - signal(SIGWINCH, SIG_IGN); -} - /* * Overrides for Emacs so that we follow Linus's tabbing style. * Emacs will notice this stuff at the end of the file and automatically diff --git a/arch/um/kernel/smp.c b/arch/um/kernel/smp.c index 72113b0a96e7..c8d8d0ac1a7f 100644 --- a/arch/um/kernel/smp.c +++ b/arch/um/kernel/smp.c @@ -1,4 +1,4 @@ -/* +/* * Copyright (C) 2000 - 2003 Jeff Dike (jdike@addtoit.com) * Licensed under the GPL */ @@ -77,9 +77,9 @@ static int idle_proc(void *cpup) if(err < 0) panic("CPU#%d failed to create IPI pipe, err = %d", cpu, -err); - activate_ipi(cpu_data[cpu].ipi_pipe[0], + os_set_fd_async(cpu_data[cpu].ipi_pipe[0], current->thread.mode.tt.extern_pid); - + wmb(); if (cpu_test_and_set(cpu, cpu_callin_map)) { printk("huh, CPU#%d already present??\n", cpu); @@ -106,7 +106,7 @@ static struct task_struct *idle_thread(int cpu) panic("copy_process failed in idle_thread, error = %ld", PTR_ERR(new_task)); - cpu_tasks[cpu] = ((struct cpu_task) + cpu_tasks[cpu] = ((struct cpu_task) { .pid = new_task->thread.mode.tt.extern_pid, .task = new_task } ); idle_threads[cpu] = new_task; @@ -134,12 +134,12 @@ void smp_prepare_cpus(unsigned int maxcpus) if(err < 0) panic("CPU#0 failed to create IPI pipe, errno = %d", -err); - activate_ipi(cpu_data[me].ipi_pipe[0], + os_set_fd_async(cpu_data[me].ipi_pipe[0], current->thread.mode.tt.extern_pid); for(cpu = 1; cpu < ncpus; cpu++){ printk("Booting processor %d...\n", cpu); - + idle = idle_thread(cpu); init_idle(idle, cpu); @@ -223,7 +223,7 @@ void smp_call_function_slave(int cpu) atomic_inc(&scf_finished); } -int smp_call_function(void (*_func)(void *info), void *_info, int nonatomic, +int smp_call_function(void (*_func)(void *info), void *_info, int nonatomic, int wait) { int cpus = num_online_cpus() - 1; diff --git a/arch/um/os-Linux/Makefile b/arch/um/os-Linux/Makefile index 08a4e628b24c..73d3d837ed6b 100644 --- a/arch/um/os-Linux/Makefile +++ b/arch/um/os-Linux/Makefile @@ -3,14 +3,14 @@ # Licensed under the GPL # -obj-y = aio.o elf_aux.o file.o helper.o main.o mem.o process.o signal.o \ +obj-y = aio.o elf_aux.o file.o helper.o irq.o main.o mem.o process.o signal.o \ start_up.o time.o trap.o tt.o tty.o uaccess.o umid.o user_syms.o \ util.o drivers/ sys-$(SUBARCH)/ obj-$(CONFIG_MODE_SKAS) += skas/ -USER_OBJS := aio.o elf_aux.o file.o helper.o main.o mem.o process.o signal.o \ - start_up.o time.o trap.o tt.o tty.o uaccess.o umid.o util.o +USER_OBJS := aio.o elf_aux.o file.o helper.o irq.o main.o mem.o process.o \ + signal.o start_up.o time.o trap.o tt.o tty.o uaccess.o umid.o util.o elf_aux.o: $(ARCH_DIR)/kernel-offsets.h CFLAGS_elf_aux.o += -I$(objtree)/arch/um diff --git a/arch/um/os-Linux/irq.c b/arch/um/os-Linux/irq.c new file mode 100644 index 000000000000..e599be423da1 --- /dev/null +++ b/arch/um/os-Linux/irq.c @@ -0,0 +1,162 @@ +/* + * Copyright (C) 2000, 2001, 2002 Jeff Dike (jdike@karaya.com) + * Licensed under the GPL + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "user_util.h" +#include "kern_util.h" +#include "user.h" +#include "process.h" +#include "sigio.h" +#include "irq_user.h" +#include "os.h" + +static struct pollfd *pollfds = NULL; +static int pollfds_num = 0; +static int pollfds_size = 0; + +int os_waiting_for_events(struct irq_fd *active_fds) +{ + struct irq_fd *irq_fd; + int i, n, err; + + n = poll(pollfds, pollfds_num, 0); + if(n < 0){ + err = -errno; + if(errno != EINTR) + printk("sigio_handler: os_waiting_for_events:" + " poll returned %d, errno = %d\n", n, errno); + return err; + } + + if(n == 0) + return 0; + + irq_fd = active_fds; + + for(i = 0; i < pollfds_num; i++){ + if(pollfds[i].revents != 0){ + irq_fd->current_events = pollfds[i].revents; + pollfds[i].fd = -1; + } + irq_fd = irq_fd->next; + } + return n; +} + +int os_isatty(int fd) +{ + return(isatty(fd)); +} + +int os_create_pollfd(int fd, int events, void *tmp_pfd, int size_tmpfds) +{ + if (pollfds_num == pollfds_size) { + if (size_tmpfds <= pollfds_size * sizeof(pollfds[0])) { + /* return min size needed for new pollfds area */ + return((pollfds_size + 1) * sizeof(pollfds[0])); + } + + if(pollfds != NULL){ + memcpy(tmp_pfd, pollfds, + sizeof(pollfds[0]) * pollfds_size); + /* remove old pollfds */ + kfree(pollfds); + } + pollfds = tmp_pfd; + pollfds_size++; + } else { + /* remove not used tmp_pfd */ + if (tmp_pfd != NULL) + kfree(tmp_pfd); + } + + pollfds[pollfds_num] = ((struct pollfd) { .fd = fd, + .events = events, + .revents = 0 }); + pollfds_num++; + + return(0); +} + +void os_free_irq_by_cb(int (*test)(struct irq_fd *, void *), void *arg, + struct irq_fd *active_fds, struct irq_fd ***last_irq_ptr2) +{ + struct irq_fd **prev; + int i = 0; + + prev = &active_fds; + while(*prev != NULL){ + if((*test)(*prev, arg)){ + struct irq_fd *old_fd = *prev; + if((pollfds[i].fd != -1) && + (pollfds[i].fd != (*prev)->fd)){ + printk("os_free_irq_by_cb - mismatch between " + "active_fds and pollfds, fd %d vs %d\n", + (*prev)->fd, pollfds[i].fd); + goto out; + } + + pollfds_num--; + + /* This moves the *whole* array after pollfds[i] + * (though it doesn't spot as such)! + */ + + memmove(&pollfds[i], &pollfds[i + 1], + (pollfds_num - i) * sizeof(pollfds[0])); + if(*last_irq_ptr2 == &old_fd->next) + *last_irq_ptr2 = prev; + + *prev = (*prev)->next; + if(old_fd->type == IRQ_WRITE) + ignore_sigio_fd(old_fd->fd); + kfree(old_fd); + continue; + } + prev = &(*prev)->next; + i++; + } + out: + return; +} + + +int os_get_pollfd(int i) +{ + return(pollfds[i].fd); +} + +void os_set_pollfd(int i, int fd) +{ + pollfds[i].fd = fd; +} + +void os_set_ioignore(void) +{ + set_handler(SIGIO, SIG_IGN, 0, -1); +} + +void init_irq_signals(int on_sigstack) +{ + __sighandler_t h; + int flags; + + flags = on_sigstack ? SA_ONSTACK : 0; + if(timer_irq_inited) h = (__sighandler_t) alarm_handler; + else h = boot_timer_handler; + + set_handler(SIGVTALRM, h, flags | SA_RESTART, + SIGUSR1, SIGIO, SIGWINCH, SIGALRM, -1); + set_handler(SIGIO, (__sighandler_t) sig_handler, flags | SA_RESTART, + SIGUSR1, SIGIO, SIGWINCH, SIGALRM, SIGVTALRM, -1); + signal(SIGWINCH, SIG_IGN); +} diff --git a/arch/um/os-Linux/tt.c b/arch/um/os-Linux/tt.c index 919d19f11537..5461a065bbb9 100644 --- a/arch/um/os-Linux/tt.c +++ b/arch/um/os-Linux/tt.c @@ -110,6 +110,16 @@ int wait_for_stop(int pid, int sig, int cont_type, void *relay) } } +void forward_ipi(int fd, int pid) +{ + int err; + + err = os_set_owner(fd, pid); + if(err < 0) + printk("forward_ipi: set_owner failed, fd = %d, me = %d, " + "target = %d, err = %d\n", fd, os_getpid(), pid, -err); +} + /* *------------------------- * only for tt mode (will be deleted in future...) diff --git a/arch/um/sys-i386/user-offsets.c b/arch/um/sys-i386/user-offsets.c index 26b68675053d..6f4ef2b7fa4a 100644 --- a/arch/um/sys-i386/user-offsets.c +++ b/arch/um/sys-i386/user-offsets.c @@ -3,12 +3,13 @@ #include #include #include +#include #define DEFINE(sym, val) \ - asm volatile("\n->" #sym " %0 " #val : : "i" (val)) + asm volatile("\n->" #sym " %0 " #val : : "i" (val)) #define DEFINE_LONGS(sym, val) \ - asm volatile("\n->" #sym " %0 " #val : : "i" (val/sizeof(unsigned long))) + asm volatile("\n->" #sym " %0 " #val : : "i" (val/sizeof(unsigned long))) #define OFFSET(sym, str, mem) \ DEFINE(sym, offsetof(struct str, mem)); @@ -67,4 +68,9 @@ void foo(void) DEFINE(HOST_ES, ES); DEFINE(HOST_GS, GS); DEFINE(UM_FRAME_SIZE, sizeof(struct user_regs_struct)); + + /* XXX Duplicated between i386 and x86_64 */ + DEFINE(UM_POLLIN, POLLIN); + DEFINE(UM_POLLPRI, POLLPRI); + DEFINE(UM_POLLOUT, POLLOUT); } diff --git a/arch/um/sys-x86_64/user-offsets.c b/arch/um/sys-x86_64/user-offsets.c index 7bd54a921cf7..899cebb57c3f 100644 --- a/arch/um/sys-x86_64/user-offsets.c +++ b/arch/um/sys-x86_64/user-offsets.c @@ -1,6 +1,7 @@ #include #include #include +#include #define __FRAME_OFFSETS #include #include @@ -88,4 +89,9 @@ void foo(void) DEFINE_LONGS(HOST_IP, RIP); DEFINE_LONGS(HOST_SP, RSP); DEFINE(UM_FRAME_SIZE, sizeof(struct user_regs_struct)); + + /* XXX Duplicated between i386 and x86_64 */ + DEFINE(UM_POLLIN, POLLIN); + DEFINE(UM_POLLPRI, POLLPRI); + DEFINE(UM_POLLOUT, POLLOUT); } -- cgit v1.2.3 From 9b4f018d92dbeff9305b4cf4aa80874c3974cfcc Mon Sep 17 00:00:00 2001 From: Jeff Dike Date: Mon, 27 Mar 2006 01:14:31 -0800 Subject: [PATCH] uml: merge irq_user.c and irq.c The serial UML OS-abstraction layer patch (um/kernel dir). This joins irq_user.c and irq.c files. Signed-off-by: Gennady Sharapov Signed-off-by: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/kernel/Makefile | 2 +- arch/um/kernel/irq.c | 294 +++++++++++++++++++++++++++++++++++++++++ arch/um/kernel/irq_user.c | 324 ---------------------------------------------- 3 files changed, 295 insertions(+), 325 deletions(-) delete mode 100644 arch/um/kernel/irq_user.c (limited to 'arch/um') diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile index 693018ba80f1..8458c30a6265 100644 --- a/arch/um/kernel/Makefile +++ b/arch/um/kernel/Makefile @@ -7,7 +7,7 @@ extra-y := vmlinux.lds clean-files := obj-y = config.o exec_kern.o exitcode.o \ - init_task.o irq.o irq_user.o ksyms.o mem.o physmem.o \ + init_task.o irq.o ksyms.o mem.o physmem.o \ process_kern.o ptrace.o reboot.o resource.o sigio_user.o sigio_kern.o \ signal_kern.o smp.o syscall_kern.o sysrq.o \ time_kern.o tlb.o trap_kern.o uaccess.o um_arch.o umid.o diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c index bbf94bf2921e..c39ea3abeda4 100644 --- a/arch/um/kernel/irq.c +++ b/arch/um/kernel/irq.c @@ -31,6 +31,8 @@ #include "irq_user.h" #include "irq_kern.h" #include "os.h" +#include "sigio.h" +#include "misc_constants.h" /* * Generic, controller-independent functions: @@ -77,6 +79,298 @@ skip: return 0; } +struct irq_fd *active_fds = NULL; +static struct irq_fd **last_irq_ptr = &active_fds; + +extern void free_irqs(void); + +void sigio_handler(int sig, union uml_pt_regs *regs) +{ + struct irq_fd *irq_fd; + int n; + + if(smp_sigio_handler()) return; + while(1){ + n = os_waiting_for_events(active_fds); + if (n <= 0) { + if(n == -EINTR) continue; + else break; + } + + for(irq_fd = active_fds; irq_fd != NULL; irq_fd = irq_fd->next){ + if(irq_fd->current_events != 0){ + irq_fd->current_events = 0; + do_IRQ(irq_fd->irq, regs); + } + } + } + + free_irqs(); +} + +static void maybe_sigio_broken(int fd, int type) +{ + if(os_isatty(fd)){ + if((type == IRQ_WRITE) && !pty_output_sigio){ + write_sigio_workaround(); + add_sigio_fd(fd, 0); + } + else if((type == IRQ_READ) && !pty_close_sigio){ + write_sigio_workaround(); + add_sigio_fd(fd, 1); + } + } +} + + +int activate_fd(int irq, int fd, int type, void *dev_id) +{ + struct pollfd *tmp_pfd; + struct irq_fd *new_fd, *irq_fd; + unsigned long flags; + int pid, events, err, n; + + pid = os_getpid(); + err = os_set_fd_async(fd, pid); + if(err < 0) + goto out; + + new_fd = um_kmalloc(sizeof(*new_fd)); + err = -ENOMEM; + if(new_fd == NULL) + goto out; + + if(type == IRQ_READ) events = UM_POLLIN | UM_POLLPRI; + else events = UM_POLLOUT; + *new_fd = ((struct irq_fd) { .next = NULL, + .id = dev_id, + .fd = fd, + .type = type, + .irq = irq, + .pid = pid, + .events = events, + .current_events = 0 } ); + + /* Critical section - locked by a spinlock because this stuff can + * be changed from interrupt handlers. The stuff above is done + * outside the lock because it allocates memory. + */ + + /* Actually, it only looks like it can be called from interrupt + * context. The culprit is reactivate_fd, which calls + * maybe_sigio_broken, which calls write_sigio_workaround, + * which calls activate_fd. However, write_sigio_workaround should + * only be called once, at boot time. That would make it clear that + * this is called only from process context, and can be locked with + * a semaphore. + */ + flags = irq_lock(); + for(irq_fd = active_fds; irq_fd != NULL; irq_fd = irq_fd->next){ + if((irq_fd->fd == fd) && (irq_fd->type == type)){ + printk("Registering fd %d twice\n", fd); + printk("Irqs : %d, %d\n", irq_fd->irq, irq); + printk("Ids : 0x%p, 0x%p\n", irq_fd->id, dev_id); + goto out_unlock; + } + } + + /*-------------*/ + if(type == IRQ_WRITE) + fd = -1; + + tmp_pfd = NULL; + n = 0; + + while(1){ + n = os_create_pollfd(fd, events, tmp_pfd, n); + if (n == 0) + break; + + /* n > 0 + * It means we couldn't put new pollfd to current pollfds + * and tmp_fds is NULL or too small for new pollfds array. + * Needed size is equal to n as minimum. + * + * Here we have to drop the lock in order to call + * kmalloc, which might sleep. + * If something else came in and changed the pollfds array + * so we will not be able to put new pollfd struct to pollfds + * then we free the buffer tmp_fds and try again. + */ + irq_unlock(flags); + if (tmp_pfd != NULL) { + kfree(tmp_pfd); + tmp_pfd = NULL; + } + + tmp_pfd = um_kmalloc(n); + if (tmp_pfd == NULL) + goto out_kfree; + + flags = irq_lock(); + } + /*-------------*/ + + *last_irq_ptr = new_fd; + last_irq_ptr = &new_fd->next; + + irq_unlock(flags); + + /* This calls activate_fd, so it has to be outside the critical + * section. + */ + maybe_sigio_broken(fd, type); + + return(0); + + out_unlock: + irq_unlock(flags); + out_kfree: + kfree(new_fd); + out: + return(err); +} + +static void free_irq_by_cb(int (*test)(struct irq_fd *, void *), void *arg) +{ + unsigned long flags; + + flags = irq_lock(); + os_free_irq_by_cb(test, arg, active_fds, &last_irq_ptr); + irq_unlock(flags); +} + +struct irq_and_dev { + int irq; + void *dev; +}; + +static int same_irq_and_dev(struct irq_fd *irq, void *d) +{ + struct irq_and_dev *data = d; + + return((irq->irq == data->irq) && (irq->id == data->dev)); +} + +void free_irq_by_irq_and_dev(unsigned int irq, void *dev) +{ + struct irq_and_dev data = ((struct irq_and_dev) { .irq = irq, + .dev = dev }); + + free_irq_by_cb(same_irq_and_dev, &data); +} + +static int same_fd(struct irq_fd *irq, void *fd) +{ + return(irq->fd == *((int *) fd)); +} + +void free_irq_by_fd(int fd) +{ + free_irq_by_cb(same_fd, &fd); +} + +static struct irq_fd *find_irq_by_fd(int fd, int irqnum, int *index_out) +{ + struct irq_fd *irq; + int i = 0; + int fdi; + + for(irq=active_fds; irq != NULL; irq = irq->next){ + if((irq->fd == fd) && (irq->irq == irqnum)) break; + i++; + } + if(irq == NULL){ + printk("find_irq_by_fd doesn't have descriptor %d\n", fd); + goto out; + } + fdi = os_get_pollfd(i); + if((fdi != -1) && (fdi != fd)){ + printk("find_irq_by_fd - mismatch between active_fds and " + "pollfds, fd %d vs %d, need %d\n", irq->fd, + fdi, fd); + irq = NULL; + goto out; + } + *index_out = i; + out: + return(irq); +} + +void reactivate_fd(int fd, int irqnum) +{ + struct irq_fd *irq; + unsigned long flags; + int i; + + flags = irq_lock(); + irq = find_irq_by_fd(fd, irqnum, &i); + if(irq == NULL){ + irq_unlock(flags); + return; + } + os_set_pollfd(i, irq->fd); + irq_unlock(flags); + + /* This calls activate_fd, so it has to be outside the critical + * section. + */ + maybe_sigio_broken(fd, irq->type); +} + +void deactivate_fd(int fd, int irqnum) +{ + struct irq_fd *irq; + unsigned long flags; + int i; + + flags = irq_lock(); + irq = find_irq_by_fd(fd, irqnum, &i); + if(irq == NULL) + goto out; + os_set_pollfd(i, -1); + out: + irq_unlock(flags); +} + +int deactivate_all_fds(void) +{ + struct irq_fd *irq; + int err; + + for(irq=active_fds;irq != NULL;irq = irq->next){ + err = os_clear_fd_async(irq->fd); + if(err) + return(err); + } + /* If there is a signal already queued, after unblocking ignore it */ + os_set_ioignore(); + + return(0); +} + +void forward_interrupts(int pid) +{ + struct irq_fd *irq; + unsigned long flags; + int err; + + flags = irq_lock(); + for(irq=active_fds;irq != NULL;irq = irq->next){ + err = os_set_owner(irq->fd, pid); + if(err < 0){ + /* XXX Just remove the irq rather than + * print out an infinite stream of these + */ + printk("Failed to forward %d to pid %d, err = %d\n", + irq->fd, pid, -err); + } + + irq->pid = pid; + } + irq_unlock(flags); +} + /* * do_IRQ handles all normal device IRQ's (the special * SMP cross-CPU interrupts have their own specific diff --git a/arch/um/kernel/irq_user.c b/arch/um/kernel/irq_user.c deleted file mode 100644 index 483e79c5ab98..000000000000 --- a/arch/um/kernel/irq_user.c +++ /dev/null @@ -1,324 +0,0 @@ -/* - * Copyright (C) 2000 Jeff Dike (jdike@karaya.com) - * Licensed under the GPL - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include "user_util.h" -#include "kern_util.h" -#include "user.h" -#include "process.h" -#include "sigio.h" -#include "irq_user.h" -#include "os.h" -#include "misc_constants.h" - -struct irq_fd *active_fds = NULL; -static struct irq_fd **last_irq_ptr = &active_fds; - -extern void free_irqs(void); - -void sigio_handler(int sig, union uml_pt_regs *regs) -{ - struct irq_fd *irq_fd; - int n; - - if(smp_sigio_handler()) return; - while(1){ - n = os_waiting_for_events(active_fds); - if (n <= 0) { - if(n == -EINTR) continue; - else break; - } - - for(irq_fd = active_fds; irq_fd != NULL; irq_fd = irq_fd->next){ - if(irq_fd->current_events != 0){ - irq_fd->current_events = 0; - do_IRQ(irq_fd->irq, regs); - } - } - } - - free_irqs(); -} - -static void maybe_sigio_broken(int fd, int type) -{ - if(os_isatty(fd)){ - if((type == IRQ_WRITE) && !pty_output_sigio){ - write_sigio_workaround(); - add_sigio_fd(fd, 0); - } - else if((type == IRQ_READ) && !pty_close_sigio){ - write_sigio_workaround(); - add_sigio_fd(fd, 1); - } - } -} - - -int activate_fd(int irq, int fd, int type, void *dev_id) -{ - struct pollfd *tmp_pfd; - struct irq_fd *new_fd, *irq_fd; - unsigned long flags; - int pid, events, err, n; - - pid = os_getpid(); - err = os_set_fd_async(fd, pid); - if(err < 0) - goto out; - - new_fd = um_kmalloc(sizeof(*new_fd)); - err = -ENOMEM; - if(new_fd == NULL) - goto out; - - if(type == IRQ_READ) events = UM_POLLIN | UM_POLLPRI; - else events = UM_POLLOUT; - *new_fd = ((struct irq_fd) { .next = NULL, - .id = dev_id, - .fd = fd, - .type = type, - .irq = irq, - .pid = pid, - .events = events, - .current_events = 0 } ); - - /* Critical section - locked by a spinlock because this stuff can - * be changed from interrupt handlers. The stuff above is done - * outside the lock because it allocates memory. - */ - - /* Actually, it only looks like it can be called from interrupt - * context. The culprit is reactivate_fd, which calls - * maybe_sigio_broken, which calls write_sigio_workaround, - * which calls activate_fd. However, write_sigio_workaround should - * only be called once, at boot time. That would make it clear that - * this is called only from process context, and can be locked with - * a semaphore. - */ - flags = irq_lock(); - for(irq_fd = active_fds; irq_fd != NULL; irq_fd = irq_fd->next){ - if((irq_fd->fd == fd) && (irq_fd->type == type)){ - printk("Registering fd %d twice\n", fd); - printk("Irqs : %d, %d\n", irq_fd->irq, irq); - printk("Ids : 0x%x, 0x%x\n", irq_fd->id, dev_id); - goto out_unlock; - } - } - - /*-------------*/ - if(type == IRQ_WRITE) - fd = -1; - - tmp_pfd = NULL; - n = 0; - - while(1){ - n = os_create_pollfd(fd, events, tmp_pfd, n); - if (n == 0) - break; - - /* n > 0 - * It means we couldn't put new pollfd to current pollfds - * and tmp_fds is NULL or too small for new pollfds array. - * Needed size is equal to n as minimum. - * - * Here we have to drop the lock in order to call - * kmalloc, which might sleep. - * If something else came in and changed the pollfds array - * so we will not be able to put new pollfd struct to pollfds - * then we free the buffer tmp_fds and try again. - */ - irq_unlock(flags); - if (tmp_pfd != NULL) { - kfree(tmp_pfd); - tmp_pfd = NULL; - } - - tmp_pfd = um_kmalloc(n); - if (tmp_pfd == NULL) - goto out_kfree; - - flags = irq_lock(); - } - /*-------------*/ - - *last_irq_ptr = new_fd; - last_irq_ptr = &new_fd->next; - - irq_unlock(flags); - - /* This calls activate_fd, so it has to be outside the critical - * section. - */ - maybe_sigio_broken(fd, type); - - return(0); - - out_unlock: - irq_unlock(flags); - out_kfree: - kfree(new_fd); - out: - return(err); -} - -static void free_irq_by_cb(int (*test)(struct irq_fd *, void *), void *arg) -{ - unsigned long flags; - - flags = irq_lock(); - os_free_irq_by_cb(test, arg, active_fds, &last_irq_ptr); - irq_unlock(flags); -} - -struct irq_and_dev { - int irq; - void *dev; -}; - -static int same_irq_and_dev(struct irq_fd *irq, void *d) -{ - struct irq_and_dev *data = d; - - return((irq->irq == data->irq) && (irq->id == data->dev)); -} - -void free_irq_by_irq_and_dev(unsigned int irq, void *dev) -{ - struct irq_and_dev data = ((struct irq_and_dev) { .irq = irq, - .dev = dev }); - - free_irq_by_cb(same_irq_and_dev, &data); -} - -static int same_fd(struct irq_fd *irq, void *fd) -{ - return(irq->fd == *((int *) fd)); -} - -void free_irq_by_fd(int fd) -{ - free_irq_by_cb(same_fd, &fd); -} - -static struct irq_fd *find_irq_by_fd(int fd, int irqnum, int *index_out) -{ - struct irq_fd *irq; - int i = 0; - int fdi; - - for(irq=active_fds; irq != NULL; irq = irq->next){ - if((irq->fd == fd) && (irq->irq == irqnum)) break; - i++; - } - if(irq == NULL){ - printk("find_irq_by_fd doesn't have descriptor %d\n", fd); - goto out; - } - fdi = os_get_pollfd(i); - if((fdi != -1) && (fdi != fd)){ - printk("find_irq_by_fd - mismatch between active_fds and " - "pollfds, fd %d vs %d, need %d\n", irq->fd, - fdi, fd); - irq = NULL; - goto out; - } - *index_out = i; - out: - return(irq); -} - -void reactivate_fd(int fd, int irqnum) -{ - struct irq_fd *irq; - unsigned long flags; - int i; - - flags = irq_lock(); - irq = find_irq_by_fd(fd, irqnum, &i); - if(irq == NULL){ - irq_unlock(flags); - return; - } - os_set_pollfd(i, irq->fd); - irq_unlock(flags); - - /* This calls activate_fd, so it has to be outside the critical - * section. - */ - maybe_sigio_broken(fd, irq->type); -} - -void deactivate_fd(int fd, int irqnum) -{ - struct irq_fd *irq; - unsigned long flags; - int i; - - flags = irq_lock(); - irq = find_irq_by_fd(fd, irqnum, &i); - if(irq == NULL) - goto out; - os_set_pollfd(i, -1); - out: - irq_unlock(flags); -} - -int deactivate_all_fds(void) -{ - struct irq_fd *irq; - int err; - - for(irq=active_fds;irq != NULL;irq = irq->next){ - err = os_clear_fd_async(irq->fd); - if(err) - return(err); - } - /* If there is a signal already queued, after unblocking ignore it */ - os_set_ioignore(); - - return(0); -} - -void forward_interrupts(int pid) -{ - struct irq_fd *irq; - unsigned long flags; - int err; - - flags = irq_lock(); - for(irq=active_fds;irq != NULL;irq = irq->next){ - err = os_set_owner(irq->fd, pid); - if(err < 0){ - /* XXX Just remove the irq rather than - * print out an infinite stream of these - */ - printk("Failed to forward %d to pid %d, err = %d\n", - irq->fd, pid, -err); - } - - irq->pid = pid; - } - irq_unlock(flags); -} - -/* - * Overrides for Emacs so that we follow Linus's tabbing style. - * Emacs will notice this stuff at the end of the file and automatically - * adjust the settings for this buffer only. This must remain at the end - * of the file. - * --------------------------------------------------------------------------- - * Local variables: - * c-file-style: "linux" - * End: - */ -- cgit v1.2.3 From 8e367065eea04a6fde5cb8f3854164af99c45693 Mon Sep 17 00:00:00 2001 From: Jeff Dike Date: Mon, 27 Mar 2006 01:14:32 -0800 Subject: [PATCH] uml: move SIGIO startup code to os-Linux/start_up.c The serial UML OS-abstraction layer patch (um/kernel dir). This moves all startup code from sigio_user.c file under os-Linux dir Signed-off-by: Gennady Sharapov Signed-off-by: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/include/os.h | 1 + arch/um/include/sigio.h | 1 - arch/um/kernel/sigio_kern.c | 10 ++- arch/um/kernel/sigio_user.c | 162 +++----------------------------------------- arch/um/kernel/um_arch.c | 3 +- arch/um/os-Linux/start_up.c | 128 ++++++++++++++++++++++++++++++++++ 6 files changed, 148 insertions(+), 157 deletions(-) (limited to 'arch/um') diff --git a/arch/um/include/os.h b/arch/um/include/os.h index efae3e6acb5b..6d865d4eade0 100644 --- a/arch/um/include/os.h +++ b/arch/um/include/os.h @@ -161,6 +161,7 @@ extern int os_lock_file(int fd, int excl); /* start_up.c */ extern void os_early_checks(void); extern int can_do_skas(void); +extern void os_check_bugs(void); /* Make sure they are clear when running in TT mode. Required by * SEGV_MAYBE_FIXABLE */ diff --git a/arch/um/include/sigio.h b/arch/um/include/sigio.h index 37d76e29a147..1432fcfb3212 100644 --- a/arch/um/include/sigio.h +++ b/arch/um/include/sigio.h @@ -8,7 +8,6 @@ extern int write_sigio_irq(int fd); extern int register_sigio_fd(int fd); -extern int read_sigio_fd(int fd); extern int add_sigio_fd(int fd, int read); extern int ignore_sigio_fd(int fd); extern void sigio_lock(void); diff --git a/arch/um/kernel/sigio_kern.c b/arch/um/kernel/sigio_kern.c index 229988463c4c..1c1300fb1e95 100644 --- a/arch/um/kernel/sigio_kern.c +++ b/arch/um/kernel/sigio_kern.c @@ -1,4 +1,4 @@ -/* +/* * Copyright (C) 2002 - 2003 Jeff Dike (jdike@addtoit.com) * Licensed under the GPL */ @@ -12,13 +12,16 @@ #include "sigio.h" #include "irq_user.h" #include "irq_kern.h" +#include "os.h" /* Protected by sigio_lock() called from write_sigio_workaround */ static int sigio_irq_fd = -1; static irqreturn_t sigio_interrupt(int irq, void *data, struct pt_regs *unused) { - read_sigio_fd(sigio_irq_fd); + char c; + + os_read_file(sigio_irq_fd, &c, sizeof(c)); reactivate_fd(sigio_irq_fd, SIGIO_WRITE_IRQ); return(IRQ_HANDLED); } @@ -51,6 +54,9 @@ void sigio_unlock(void) spin_unlock(&sigio_spinlock); } +extern void sigio_cleanup(void); +__uml_exitcall(sigio_cleanup); + /* * Overrides for Emacs so that we follow Linus's tabbing style. * Emacs will notice this stuff at the end of the file and automatically diff --git a/arch/um/kernel/sigio_user.c b/arch/um/kernel/sigio_user.c index f7b18e157d35..9bef9413cb5d 100644 --- a/arch/um/kernel/sigio_user.c +++ b/arch/um/kernel/sigio_user.c @@ -1,4 +1,4 @@ -/* +/* * Copyright (C) 2002 Jeff Dike (jdike@karaya.com) * Licensed under the GPL */ @@ -20,127 +20,6 @@ #include "sigio.h" #include "os.h" -/* Changed during early boot */ -int pty_output_sigio = 0; -int pty_close_sigio = 0; - -/* Used as a flag during SIGIO testing early in boot */ -static volatile int got_sigio = 0; - -void __init handler(int sig) -{ - got_sigio = 1; -} - -struct openpty_arg { - int master; - int slave; - int err; -}; - -static void openpty_cb(void *arg) -{ - struct openpty_arg *info = arg; - - info->err = 0; - if(openpty(&info->master, &info->slave, NULL, NULL, NULL)) - info->err = -errno; -} - -void __init check_one_sigio(void (*proc)(int, int)) -{ - struct sigaction old, new; - struct openpty_arg pty = { .master = -1, .slave = -1 }; - int master, slave, err; - - initial_thread_cb(openpty_cb, &pty); - if(pty.err){ - printk("openpty failed, errno = %d\n", -pty.err); - return; - } - - master = pty.master; - slave = pty.slave; - - if((master == -1) || (slave == -1)){ - printk("openpty failed to allocate a pty\n"); - return; - } - - /* Not now, but complain so we now where we failed. */ - err = raw(master); - if (err < 0) - panic("check_sigio : __raw failed, errno = %d\n", -err); - - err = os_sigio_async(master, slave); - if(err < 0) - panic("tty_fds : sigio_async failed, err = %d\n", -err); - - if(sigaction(SIGIO, NULL, &old) < 0) - panic("check_sigio : sigaction 1 failed, errno = %d\n", errno); - new = old; - new.sa_handler = handler; - if(sigaction(SIGIO, &new, NULL) < 0) - panic("check_sigio : sigaction 2 failed, errno = %d\n", errno); - - got_sigio = 0; - (*proc)(master, slave); - - os_close_file(master); - os_close_file(slave); - - if(sigaction(SIGIO, &old, NULL) < 0) - panic("check_sigio : sigaction 3 failed, errno = %d\n", errno); -} - -static void tty_output(int master, int slave) -{ - int n; - char buf[512]; - - printk("Checking that host ptys support output SIGIO..."); - - memset(buf, 0, sizeof(buf)); - - while(os_write_file(master, buf, sizeof(buf)) > 0) ; - if(errno != EAGAIN) - panic("check_sigio : write failed, errno = %d\n", errno); - while(((n = os_read_file(slave, buf, sizeof(buf))) > 0) && !got_sigio) ; - - if (got_sigio) { - printk("Yes\n"); - pty_output_sigio = 1; - } else if (n == -EAGAIN) { - printk("No, enabling workaround\n"); - } else { - panic("check_sigio : read failed, err = %d\n", n); - } -} - -static void tty_close(int master, int slave) -{ - printk("Checking that host ptys support SIGIO on close..."); - - os_close_file(slave); - if(got_sigio){ - printk("Yes\n"); - pty_close_sigio = 1; - } - else printk("No, enabling workaround\n"); -} - -void __init check_sigio(void) -{ - if((os_access("/dev/ptmx", OS_ACC_R_OK) < 0) && - (os_access("/dev/ptyp0", OS_ACC_R_OK) < 0)){ - printk("No pseudo-terminals available - skipping pty SIGIO " - "check\n"); - return; - } - check_one_sigio(tty_output); - check_one_sigio(tty_close); -} - /* Protected by sigio_lock(), also used by sigio_cleanup, which is an * exitcall. */ @@ -267,10 +146,10 @@ static void update_thread(void) if(write_sigio_pid != -1) os_kill_process(write_sigio_pid, 1); write_sigio_pid = -1; - os_close_file(sigio_private[0]); - os_close_file(sigio_private[1]); - os_close_file(write_sigio_fds[0]); - os_close_file(write_sigio_fds[1]); + close(sigio_private[0]); + close(sigio_private[1]); + close(write_sigio_fds[0]); + close(write_sigio_fds[1]); /* Critical section end */ set_signals(flags); } @@ -428,39 +307,18 @@ void write_sigio_workaround(void) out_free: kfree(p); out_close2: - os_close_file(l_sigio_private[0]); - os_close_file(l_sigio_private[1]); + close(l_sigio_private[0]); + close(l_sigio_private[1]); out_close1: - os_close_file(l_write_sigio_fds[0]); - os_close_file(l_write_sigio_fds[1]); + close(l_write_sigio_fds[0]); + close(l_write_sigio_fds[1]); return; } -int read_sigio_fd(int fd) -{ - int n; - char c; - - n = os_read_file(fd, &c, sizeof(c)); - if(n != sizeof(c)){ - if(n < 0) { - printk("read_sigio_fd - read failed, err = %d\n", -n); - return(n); - } - else { - printk("read_sigio_fd - short read, bytes = %d\n", n); - return(-EIO); - } - } - return(n); -} - -static void sigio_cleanup(void) +void sigio_cleanup(void) { if (write_sigio_pid != -1) { os_kill_process(write_sigio_pid, 1); write_sigio_pid = -1; } } - -__uml_exitcall(sigio_cleanup); diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 0c5b9dcfbe2e..bb1c87211ac1 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -487,8 +487,7 @@ void __init setup_arch(char **cmdline_p) void __init check_bugs(void) { arch_check_bugs(); - check_sigio(); - check_devanon(); + os_check_bugs(); } void apply_alternatives(struct alt_instr *start, struct alt_instr *end) diff --git a/arch/um/os-Linux/start_up.c b/arch/um/os-Linux/start_up.c index 829d6b0d8b02..32753131f8d8 100644 --- a/arch/um/os-Linux/start_up.c +++ b/arch/um/os-Linux/start_up.c @@ -3,6 +3,7 @@ * Licensed under the GPL */ +#include #include #include #include @@ -539,3 +540,130 @@ int __init parse_iomem(char *str, int *add) return(1); } + +/* Changed during early boot */ +int pty_output_sigio = 0; +int pty_close_sigio = 0; + +/* Used as a flag during SIGIO testing early in boot */ +static volatile int got_sigio = 0; + +static void __init handler(int sig) +{ + got_sigio = 1; +} + +struct openpty_arg { + int master; + int slave; + int err; +}; + +static void openpty_cb(void *arg) +{ + struct openpty_arg *info = arg; + + info->err = 0; + if(openpty(&info->master, &info->slave, NULL, NULL, NULL)) + info->err = -errno; +} + +static void __init check_one_sigio(void (*proc)(int, int)) +{ + struct sigaction old, new; + struct openpty_arg pty = { .master = -1, .slave = -1 }; + int master, slave, err; + + initial_thread_cb(openpty_cb, &pty); + if(pty.err){ + printk("openpty failed, errno = %d\n", -pty.err); + return; + } + + master = pty.master; + slave = pty.slave; + + if((master == -1) || (slave == -1)){ + printk("openpty failed to allocate a pty\n"); + return; + } + + /* Not now, but complain so we now where we failed. */ + err = raw(master); + if (err < 0) + panic("check_sigio : __raw failed, errno = %d\n", -err); + + err = os_sigio_async(master, slave); + if(err < 0) + panic("tty_fds : sigio_async failed, err = %d\n", -err); + + if(sigaction(SIGIO, NULL, &old) < 0) + panic("check_sigio : sigaction 1 failed, errno = %d\n", errno); + new = old; + new.sa_handler = handler; + if(sigaction(SIGIO, &new, NULL) < 0) + panic("check_sigio : sigaction 2 failed, errno = %d\n", errno); + + got_sigio = 0; + (*proc)(master, slave); + + close(master); + close(slave); + + if(sigaction(SIGIO, &old, NULL) < 0) + panic("check_sigio : sigaction 3 failed, errno = %d\n", errno); +} + +static void tty_output(int master, int slave) +{ + int n; + char buf[512]; + + printk("Checking that host ptys support output SIGIO..."); + + memset(buf, 0, sizeof(buf)); + + while(os_write_file(master, buf, sizeof(buf)) > 0) ; + if(errno != EAGAIN) + panic("check_sigio : write failed, errno = %d\n", errno); + while(((n = os_read_file(slave, buf, sizeof(buf))) > 0) && !got_sigio) ; + + if(got_sigio){ + printk("Yes\n"); + pty_output_sigio = 1; + } + else if(n == -EAGAIN) printk("No, enabling workaround\n"); + else panic("check_sigio : read failed, err = %d\n", n); +} + +static void tty_close(int master, int slave) +{ + printk("Checking that host ptys support SIGIO on close..."); + + close(slave); + if(got_sigio){ + printk("Yes\n"); + pty_close_sigio = 1; + } + else printk("No, enabling workaround\n"); +} + +void __init check_sigio(void) +{ + if((os_access("/dev/ptmx", OS_ACC_R_OK) < 0) && + (os_access("/dev/ptyp0", OS_ACC_R_OK) < 0)){ + printk("No pseudo-terminals available - skipping pty SIGIO " + "check\n"); + return; + } + check_one_sigio(tty_output); + check_one_sigio(tty_close); +} + +void os_check_bugs(void) +{ + check_ptrace(); + check_sigio(); + check_devanon(); +} + -- cgit v1.2.3 From f206aabb035318ac4bafbf0b87798335de3634df Mon Sep 17 00:00:00 2001 From: Jeff Dike Date: Mon, 27 Mar 2006 01:14:33 -0800 Subject: [PATCH] uml: move sigio_user.c to os-Linux/sigio.c The serial UML OS-abstraction layer patch (um/kernel dir). This moves sigio_user.c to os-Linux dir Signed-off-by: Gennady Sharapov Signed-off-by: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/include/os.h | 5 + arch/um/include/sigio.h | 2 - arch/um/include/user_util.h | 1 - arch/um/kernel/Makefile | 2 +- arch/um/kernel/sigio_user.c | 324 -------------------------------------------- arch/um/os-Linux/Makefile | 9 +- arch/um/os-Linux/sigio.c | 324 ++++++++++++++++++++++++++++++++++++++++++++ 7 files changed, 335 insertions(+), 332 deletions(-) delete mode 100644 arch/um/kernel/sigio_user.c create mode 100644 arch/um/os-Linux/sigio.c (limited to 'arch/um') diff --git a/arch/um/include/os.h b/arch/um/include/os.h index 6d865d4eade0..53dee8d3cdcc 100644 --- a/arch/um/include/os.h +++ b/arch/um/include/os.h @@ -311,4 +311,9 @@ extern void os_set_pollfd(int i, int fd); extern void os_set_ioignore(void); extern void init_irq_signals(int on_sigstack); +/* sigio.c */ +extern void write_sigio_workaround(void); +extern int add_sigio_fd(int fd, int read); +extern int ignore_sigio_fd(int fd); + #endif diff --git a/arch/um/include/sigio.h b/arch/um/include/sigio.h index 1432fcfb3212..fe99ea163c2e 100644 --- a/arch/um/include/sigio.h +++ b/arch/um/include/sigio.h @@ -8,8 +8,6 @@ extern int write_sigio_irq(int fd); extern int register_sigio_fd(int fd); -extern int add_sigio_fd(int fd, int read); -extern int ignore_sigio_fd(int fd); extern void sigio_lock(void); extern void sigio_unlock(void); diff --git a/arch/um/include/user_util.h b/arch/um/include/user_util.h index a6f1f176cf84..992a7e1e0fca 100644 --- a/arch/um/include/user_util.h +++ b/arch/um/include/user_util.h @@ -58,7 +58,6 @@ extern int attach(int pid); extern void kill_child_dead(int pid); extern int cont(int pid); extern void check_sigio(void); -extern void write_sigio_workaround(void); extern void arch_check_bugs(void); extern int cpu_feature(char *what, char *buf, int len); extern int arch_handle_signal(int sig, union uml_pt_regs *regs); diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile index 8458c30a6265..ac5afaa0306f 100644 --- a/arch/um/kernel/Makefile +++ b/arch/um/kernel/Makefile @@ -8,7 +8,7 @@ clean-files := obj-y = config.o exec_kern.o exitcode.o \ init_task.o irq.o ksyms.o mem.o physmem.o \ - process_kern.o ptrace.o reboot.o resource.o sigio_user.o sigio_kern.o \ + process_kern.o ptrace.o reboot.o resource.o sigio_kern.o \ signal_kern.o smp.o syscall_kern.o sysrq.o \ time_kern.o tlb.o trap_kern.o uaccess.o um_arch.o umid.o diff --git a/arch/um/kernel/sigio_user.c b/arch/um/kernel/sigio_user.c deleted file mode 100644 index 9bef9413cb5d..000000000000 --- a/arch/um/kernel/sigio_user.c +++ /dev/null @@ -1,324 +0,0 @@ -/* - * Copyright (C) 2002 Jeff Dike (jdike@karaya.com) - * Licensed under the GPL - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include "init.h" -#include "user.h" -#include "kern_util.h" -#include "user_util.h" -#include "sigio.h" -#include "os.h" - -/* Protected by sigio_lock(), also used by sigio_cleanup, which is an - * exitcall. - */ -static int write_sigio_pid = -1; - -/* These arrays are initialized before the sigio thread is started, and - * the descriptors closed after it is killed. So, it can't see them change. - * On the UML side, they are changed under the sigio_lock. - */ -static int write_sigio_fds[2] = { -1, -1 }; -static int sigio_private[2] = { -1, -1 }; - -struct pollfds { - struct pollfd *poll; - int size; - int used; -}; - -/* Protected by sigio_lock(). Used by the sigio thread, but the UML thread - * synchronizes with it. - */ -struct pollfds current_poll = { - .poll = NULL, - .size = 0, - .used = 0 -}; - -struct pollfds next_poll = { - .poll = NULL, - .size = 0, - .used = 0 -}; - -static int write_sigio_thread(void *unused) -{ - struct pollfds *fds, tmp; - struct pollfd *p; - int i, n, respond_fd; - char c; - - signal(SIGWINCH, SIG_IGN); - fds = ¤t_poll; - while(1){ - n = poll(fds->poll, fds->used, -1); - if(n < 0){ - if(errno == EINTR) continue; - printk("write_sigio_thread : poll returned %d, " - "errno = %d\n", n, errno); - } - for(i = 0; i < fds->used; i++){ - p = &fds->poll[i]; - if(p->revents == 0) continue; - if(p->fd == sigio_private[1]){ - n = os_read_file(sigio_private[1], &c, sizeof(c)); - if(n != sizeof(c)) - printk("write_sigio_thread : " - "read failed, err = %d\n", -n); - tmp = current_poll; - current_poll = next_poll; - next_poll = tmp; - respond_fd = sigio_private[1]; - } - else { - respond_fd = write_sigio_fds[1]; - fds->used--; - memmove(&fds->poll[i], &fds->poll[i + 1], - (fds->used - i) * sizeof(*fds->poll)); - } - - n = os_write_file(respond_fd, &c, sizeof(c)); - if(n != sizeof(c)) - printk("write_sigio_thread : write failed, " - "err = %d\n", -n); - } - } - - return 0; -} - -static int need_poll(int n) -{ - if(n <= next_poll.size){ - next_poll.used = n; - return(0); - } - kfree(next_poll.poll); - next_poll.poll = um_kmalloc_atomic(n * sizeof(struct pollfd)); - if(next_poll.poll == NULL){ - printk("need_poll : failed to allocate new pollfds\n"); - next_poll.size = 0; - next_poll.used = 0; - return(-1); - } - next_poll.size = n; - next_poll.used = n; - return(0); -} - -/* Must be called with sigio_lock held, because it's needed by the marked - * critical section. */ -static void update_thread(void) -{ - unsigned long flags; - int n; - char c; - - flags = set_signals(0); - n = os_write_file(sigio_private[0], &c, sizeof(c)); - if(n != sizeof(c)){ - printk("update_thread : write failed, err = %d\n", -n); - goto fail; - } - - n = os_read_file(sigio_private[0], &c, sizeof(c)); - if(n != sizeof(c)){ - printk("update_thread : read failed, err = %d\n", -n); - goto fail; - } - - set_signals(flags); - return; - fail: - /* Critical section start */ - if(write_sigio_pid != -1) - os_kill_process(write_sigio_pid, 1); - write_sigio_pid = -1; - close(sigio_private[0]); - close(sigio_private[1]); - close(write_sigio_fds[0]); - close(write_sigio_fds[1]); - /* Critical section end */ - set_signals(flags); -} - -int add_sigio_fd(int fd, int read) -{ - int err = 0, i, n, events; - - sigio_lock(); - for(i = 0; i < current_poll.used; i++){ - if(current_poll.poll[i].fd == fd) - goto out; - } - - n = current_poll.used + 1; - err = need_poll(n); - if(err) - goto out; - - for(i = 0; i < current_poll.used; i++) - next_poll.poll[i] = current_poll.poll[i]; - - if(read) events = POLLIN; - else events = POLLOUT; - - next_poll.poll[n - 1] = ((struct pollfd) { .fd = fd, - .events = events, - .revents = 0 }); - update_thread(); - out: - sigio_unlock(); - return(err); -} - -int ignore_sigio_fd(int fd) -{ - struct pollfd *p; - int err = 0, i, n = 0; - - sigio_lock(); - for(i = 0; i < current_poll.used; i++){ - if(current_poll.poll[i].fd == fd) break; - } - if(i == current_poll.used) - goto out; - - err = need_poll(current_poll.used - 1); - if(err) - goto out; - - for(i = 0; i < current_poll.used; i++){ - p = ¤t_poll.poll[i]; - if(p->fd != fd) next_poll.poll[n++] = current_poll.poll[i]; - } - if(n == i){ - printk("ignore_sigio_fd : fd %d not found\n", fd); - err = -1; - goto out; - } - - update_thread(); - out: - sigio_unlock(); - return(err); -} - -static struct pollfd* setup_initial_poll(int fd) -{ - struct pollfd *p; - - p = um_kmalloc(sizeof(struct pollfd)); - if (p == NULL) { - printk("setup_initial_poll : failed to allocate poll\n"); - return NULL; - } - *p = ((struct pollfd) { .fd = fd, - .events = POLLIN, - .revents = 0 }); - return p; -} - -void write_sigio_workaround(void) -{ - unsigned long stack; - struct pollfd *p; - int err; - int l_write_sigio_fds[2]; - int l_sigio_private[2]; - int l_write_sigio_pid; - - /* We call this *tons* of times - and most ones we must just fail. */ - sigio_lock(); - l_write_sigio_pid = write_sigio_pid; - sigio_unlock(); - - if (l_write_sigio_pid != -1) - return; - - err = os_pipe(l_write_sigio_fds, 1, 1); - if(err < 0){ - printk("write_sigio_workaround - os_pipe 1 failed, " - "err = %d\n", -err); - return; - } - err = os_pipe(l_sigio_private, 1, 1); - if(err < 0){ - printk("write_sigio_workaround - os_pipe 1 failed, " - "err = %d\n", -err); - goto out_close1; - } - - p = setup_initial_poll(l_sigio_private[1]); - if(!p) - goto out_close2; - - sigio_lock(); - - /* Did we race? Don't try to optimize this, please, it's not so likely - * to happen, and no more than once at the boot. */ - if(write_sigio_pid != -1) - goto out_unlock; - - write_sigio_pid = run_helper_thread(write_sigio_thread, NULL, - CLONE_FILES | CLONE_VM, &stack, 0); - - if (write_sigio_pid < 0) - goto out_clear; - - if (write_sigio_irq(l_write_sigio_fds[0])) - goto out_kill; - - /* Success, finally. */ - memcpy(write_sigio_fds, l_write_sigio_fds, sizeof(l_write_sigio_fds)); - memcpy(sigio_private, l_sigio_private, sizeof(l_sigio_private)); - - current_poll = ((struct pollfds) { .poll = p, - .used = 1, - .size = 1 }); - - sigio_unlock(); - return; - - out_kill: - l_write_sigio_pid = write_sigio_pid; - write_sigio_pid = -1; - sigio_unlock(); - /* Going to call waitpid, avoid holding the lock. */ - os_kill_process(l_write_sigio_pid, 1); - goto out_free; - - out_clear: - write_sigio_pid = -1; - out_unlock: - sigio_unlock(); - out_free: - kfree(p); - out_close2: - close(l_sigio_private[0]); - close(l_sigio_private[1]); - out_close1: - close(l_write_sigio_fds[0]); - close(l_write_sigio_fds[1]); - return; -} - -void sigio_cleanup(void) -{ - if (write_sigio_pid != -1) { - os_kill_process(write_sigio_pid, 1); - write_sigio_pid = -1; - } -} diff --git a/arch/um/os-Linux/Makefile b/arch/um/os-Linux/Makefile index 73d3d837ed6b..c3d56c2935c2 100644 --- a/arch/um/os-Linux/Makefile +++ b/arch/um/os-Linux/Makefile @@ -3,14 +3,15 @@ # Licensed under the GPL # -obj-y = aio.o elf_aux.o file.o helper.o irq.o main.o mem.o process.o signal.o \ - start_up.o time.o trap.o tt.o tty.o uaccess.o umid.o user_syms.o \ - util.o drivers/ sys-$(SUBARCH)/ +obj-y = aio.o elf_aux.o file.o helper.o irq.o main.o mem.o process.o sigio.o \ + signal.o start_up.o time.o trap.o tt.o tty.o uaccess.o umid.o \ + user_syms.o util.o drivers/ sys-$(SUBARCH)/ obj-$(CONFIG_MODE_SKAS) += skas/ USER_OBJS := aio.o elf_aux.o file.o helper.o irq.o main.o mem.o process.o \ - signal.o start_up.o time.o trap.o tt.o tty.o uaccess.o umid.o util.o + sigio.o signal.o start_up.o time.o trap.o tt.o tty.o uaccess.o umid.o \ + util.o elf_aux.o: $(ARCH_DIR)/kernel-offsets.h CFLAGS_elf_aux.o += -I$(objtree)/arch/um diff --git a/arch/um/os-Linux/sigio.c b/arch/um/os-Linux/sigio.c new file mode 100644 index 000000000000..7604c404c4c2 --- /dev/null +++ b/arch/um/os-Linux/sigio.c @@ -0,0 +1,324 @@ +/* + * Copyright (C) 2002 Jeff Dike (jdike@karaya.com) + * Licensed under the GPL + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "init.h" +#include "user.h" +#include "kern_util.h" +#include "user_util.h" +#include "sigio.h" +#include "os.h" + +/* Protected by sigio_lock(), also used by sigio_cleanup, which is an + * exitcall. + */ +static int write_sigio_pid = -1; + +/* These arrays are initialized before the sigio thread is started, and + * the descriptors closed after it is killed. So, it can't see them change. + * On the UML side, they are changed under the sigio_lock. + */ +static int write_sigio_fds[2] = { -1, -1 }; +static int sigio_private[2] = { -1, -1 }; + +struct pollfds { + struct pollfd *poll; + int size; + int used; +}; + +/* Protected by sigio_lock(). Used by the sigio thread, but the UML thread + * synchronizes with it. + */ +struct pollfds current_poll = { + .poll = NULL, + .size = 0, + .used = 0 +}; + +struct pollfds next_poll = { + .poll = NULL, + .size = 0, + .used = 0 +}; + +static int write_sigio_thread(void *unused) +{ + struct pollfds *fds, tmp; + struct pollfd *p; + int i, n, respond_fd; + char c; + + signal(SIGWINCH, SIG_IGN); + fds = ¤t_poll; + while(1){ + n = poll(fds->poll, fds->used, -1); + if(n < 0){ + if(errno == EINTR) continue; + printk("write_sigio_thread : poll returned %d, " + "errno = %d\n", n, errno); + } + for(i = 0; i < fds->used; i++){ + p = &fds->poll[i]; + if(p->revents == 0) continue; + if(p->fd == sigio_private[1]){ + n = os_read_file(sigio_private[1], &c, sizeof(c)); + if(n != sizeof(c)) + printk("write_sigio_thread : " + "read failed, err = %d\n", -n); + tmp = current_poll; + current_poll = next_poll; + next_poll = tmp; + respond_fd = sigio_private[1]; + } + else { + respond_fd = write_sigio_fds[1]; + fds->used--; + memmove(&fds->poll[i], &fds->poll[i + 1], + (fds->used - i) * sizeof(*fds->poll)); + } + + n = os_write_file(respond_fd, &c, sizeof(c)); + if(n != sizeof(c)) + printk("write_sigio_thread : write failed, " + "err = %d\n", -n); + } + } + + return 0; +} + +static int need_poll(int n) +{ + if(n <= next_poll.size){ + next_poll.used = n; + return(0); + } + kfree(next_poll.poll); + next_poll.poll = um_kmalloc_atomic(n * sizeof(struct pollfd)); + if(next_poll.poll == NULL){ + printk("need_poll : failed to allocate new pollfds\n"); + next_poll.size = 0; + next_poll.used = 0; + return(-1); + } + next_poll.size = n; + next_poll.used = n; + return(0); +} + +/* Must be called with sigio_lock held, because it's needed by the marked + * critical section. */ +static void update_thread(void) +{ + unsigned long flags; + int n; + char c; + + flags = set_signals(0); + n = os_write_file(sigio_private[0], &c, sizeof(c)); + if(n != sizeof(c)){ + printk("update_thread : write failed, err = %d\n", -n); + goto fail; + } + + n = os_read_file(sigio_private[0], &c, sizeof(c)); + if(n != sizeof(c)){ + printk("update_thread : read failed, err = %d\n", -n); + goto fail; + } + + set_signals(flags); + return; + fail: + /* Critical section start */ + if(write_sigio_pid != -1) + os_kill_process(write_sigio_pid, 1); + write_sigio_pid = -1; + close(sigio_private[0]); + close(sigio_private[1]); + close(write_sigio_fds[0]); + close(write_sigio_fds[1]); + /* Critical section end */ + set_signals(flags); +} + +int add_sigio_fd(int fd, int read) +{ + int err = 0, i, n, events; + + sigio_lock(); + for(i = 0; i < current_poll.used; i++){ + if(current_poll.poll[i].fd == fd) + goto out; + } + + n = current_poll.used + 1; + err = need_poll(n); + if(err) + goto out; + + for(i = 0; i < current_poll.used; i++) + next_poll.poll[i] = current_poll.poll[i]; + + if(read) events = POLLIN; + else events = POLLOUT; + + next_poll.poll[n - 1] = ((struct pollfd) { .fd = fd, + .events = events, + .revents = 0 }); + update_thread(); + out: + sigio_unlock(); + return(err); +} + +int ignore_sigio_fd(int fd) +{ + struct pollfd *p; + int err = 0, i, n = 0; + + sigio_lock(); + for(i = 0; i < current_poll.used; i++){ + if(current_poll.poll[i].fd == fd) break; + } + if(i == current_poll.used) + goto out; + + err = need_poll(current_poll.used - 1); + if(err) + goto out; + + for(i = 0; i < current_poll.used; i++){ + p = ¤t_poll.poll[i]; + if(p->fd != fd) next_poll.poll[n++] = current_poll.poll[i]; + } + if(n == i){ + printk("ignore_sigio_fd : fd %d not found\n", fd); + err = -1; + goto out; + } + + update_thread(); + out: + sigio_unlock(); + return(err); +} + +static struct pollfd *setup_initial_poll(int fd) +{ + struct pollfd *p; + + p = um_kmalloc(sizeof(struct pollfd)); + if (p == NULL) { + printk("setup_initial_poll : failed to allocate poll\n"); + return NULL; + } + *p = ((struct pollfd) { .fd = fd, + .events = POLLIN, + .revents = 0 }); + return p; +} + +void write_sigio_workaround(void) +{ + unsigned long stack; + struct pollfd *p; + int err; + int l_write_sigio_fds[2]; + int l_sigio_private[2]; + int l_write_sigio_pid; + + /* We call this *tons* of times - and most ones we must just fail. */ + sigio_lock(); + l_write_sigio_pid = write_sigio_pid; + sigio_unlock(); + + if (l_write_sigio_pid != -1) + return; + + err = os_pipe(l_write_sigio_fds, 1, 1); + if(err < 0){ + printk("write_sigio_workaround - os_pipe 1 failed, " + "err = %d\n", -err); + return; + } + err = os_pipe(l_sigio_private, 1, 1); + if(err < 0){ + printk("write_sigio_workaround - os_pipe 2 failed, " + "err = %d\n", -err); + goto out_close1; + } + + p = setup_initial_poll(l_sigio_private[1]); + if(!p) + goto out_close2; + + sigio_lock(); + + /* Did we race? Don't try to optimize this, please, it's not so likely + * to happen, and no more than once at the boot. */ + if(write_sigio_pid != -1) + goto out_unlock; + + write_sigio_pid = run_helper_thread(write_sigio_thread, NULL, + CLONE_FILES | CLONE_VM, &stack, 0); + + if (write_sigio_pid < 0) + goto out_clear; + + if (write_sigio_irq(l_write_sigio_fds[0])) + goto out_kill; + + /* Success, finally. */ + memcpy(write_sigio_fds, l_write_sigio_fds, sizeof(l_write_sigio_fds)); + memcpy(sigio_private, l_sigio_private, sizeof(l_sigio_private)); + + current_poll = ((struct pollfds) { .poll = p, + .used = 1, + .size = 1 }); + + sigio_unlock(); + return; + + out_kill: + l_write_sigio_pid = write_sigio_pid; + write_sigio_pid = -1; + sigio_unlock(); + /* Going to call waitpid, avoid holding the lock. */ + os_kill_process(l_write_sigio_pid, 1); + goto out_free; + + out_clear: + write_sigio_pid = -1; + out_unlock: + sigio_unlock(); + out_free: + kfree(p); + out_close2: + close(l_sigio_private[0]); + close(l_sigio_private[1]); + out_close1: + close(l_write_sigio_fds[0]); + close(l_write_sigio_fds[1]); + return; +} + +void sigio_cleanup(void) +{ + if(write_sigio_pid != -1){ + os_kill_process(write_sigio_pid, 1); + write_sigio_pid = -1; + } +} -- cgit v1.2.3 From 81efcd3300754462537ffac60336158b2f773b4e Mon Sep 17 00:00:00 2001 From: Bodo Stroesser Date: Mon, 27 Mar 2006 01:14:34 -0800 Subject: [PATCH] uml: more carefully test whether we are in a system call For security reasons, UML in is_syscall() needs to have access to code in vsyscall-page. The current implementation grants this access by explicitly allowing access to vsyscall in access_ok_skas(). With this change, copy_from_user() may be used to read the code. Ptrace access to vsyscall-page for debugging already was implemented in get_user_pages() by mainline. In i386, copy_from_user can't access vsyscall-page, but returns EFAULT. To make UML behave as i386 does, I changed is_syscall to use access_process_vm(current) to read the code from vsyscall-page. This doesn't hurt security, but simplifies the code and prepares implementation of stub-vmas. Signed-off-by: Bodo Stroesser Signed-off-by: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/sys-i386/ptrace.c | 15 ++++++++++++--- arch/um/sys-x86_64/ptrace.c | 22 +++++++++++++++++++++- 2 files changed, 33 insertions(+), 4 deletions(-) (limited to 'arch/um') diff --git a/arch/um/sys-i386/ptrace.c b/arch/um/sys-i386/ptrace.c index e839ce65ad28..8032a105949a 100644 --- a/arch/um/sys-i386/ptrace.c +++ b/arch/um/sys-i386/ptrace.c @@ -6,6 +6,7 @@ #include #include #include "linux/sched.h" +#include "linux/mm.h" #include "asm/elf.h" #include "asm/ptrace.h" #include "asm/uaccess.h" @@ -26,9 +27,17 @@ int is_syscall(unsigned long addr) n = copy_from_user(&instr, (void __user *) addr, sizeof(instr)); if(n){ - printk("is_syscall : failed to read instruction from 0x%lx\n", - addr); - return(0); + /* access_process_vm() grants access to vsyscall and stub, + * while copy_from_user doesn't. Maybe access_process_vm is + * slow, but that doesn't matter, since it will be called only + * in case of singlestepping, if copy_from_user failed. + */ + n = access_process_vm(current, addr, &instr, sizeof(instr), 0); + if(n != sizeof(instr)) { + printk("is_syscall : failed to read instruction from " + "0x%lx\n", addr); + return(1); + } } /* int 0x80 or sysenter */ return((instr == 0x80cd) || (instr == 0x340f)); diff --git a/arch/um/sys-x86_64/ptrace.c b/arch/um/sys-x86_64/ptrace.c index 74eee5c7c6dd..147bbf05cbc2 100644 --- a/arch/um/sys-x86_64/ptrace.c +++ b/arch/um/sys-x86_64/ptrace.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -136,9 +137,28 @@ void arch_switch(void) */ } +/* XXX Mostly copied from sys-i386 */ int is_syscall(unsigned long addr) { - panic("is_syscall"); + unsigned short instr; + int n; + + n = copy_from_user(&instr, (void __user *) addr, sizeof(instr)); + if(n){ + /* access_process_vm() grants access to vsyscall and stub, + * while copy_from_user doesn't. Maybe access_process_vm is + * slow, but that doesn't matter, since it will be called only + * in case of singlestepping, if copy_from_user failed. + */ + n = access_process_vm(current, addr, &instr, sizeof(instr), 0); + if(n != sizeof(instr)) { + printk("is_syscall : failed to read instruction from " + "0x%lx\n", addr); + return(1); + } + } + /* sysenter */ + return(instr == 0x050f); } int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu ) -- cgit v1.2.3 From c554f899b6747c9d8035bf91864d89b337ceb411 Mon Sep 17 00:00:00 2001 From: Jeff Dike Date: Mon, 27 Mar 2006 01:14:36 -0800 Subject: [PATCH] uml: move tty logging to os-Linux The serial UML OS-abstraction layer patch (um/kernel dir). This moves all systemcalls from tty_log.c file under os-Linux dir Signed-off-by: Gennady Sharapov Cc: Paolo 'Blaisorblade' Giarrusso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/kernel/Makefile | 5 +- arch/um/kernel/exec_kern.c | 2 - arch/um/kernel/tty_log.c | 230 --------------------------------------------- arch/um/os-Linux/Makefile | 8 +- arch/um/os-Linux/tty_log.c | 218 ++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 224 insertions(+), 239 deletions(-) delete mode 100644 arch/um/kernel/tty_log.c create mode 100644 arch/um/os-Linux/tty_log.c (limited to 'arch/um') diff --git a/arch/um/kernel/Makefile b/arch/um/kernel/Makefile index ac5afaa0306f..fe08971b64cf 100644 --- a/arch/um/kernel/Makefile +++ b/arch/um/kernel/Makefile @@ -15,15 +15,12 @@ obj-y = config.o exec_kern.o exitcode.o \ obj-$(CONFIG_BLK_DEV_INITRD) += initrd.o obj-$(CONFIG_GPROF) += gprof_syms.o obj-$(CONFIG_GCOV) += gmon_syms.o -obj-$(CONFIG_TTY_LOG) += tty_log.o obj-$(CONFIG_SYSCALL_DEBUG) += syscall.o obj-$(CONFIG_MODE_TT) += tt/ obj-$(CONFIG_MODE_SKAS) += skas/ -user-objs-$(CONFIG_TTY_LOG) += tty_log.o - -USER_OBJS := $(user-objs-y) config.o tty_log.o +USER_OBJS := config.o include arch/um/scripts/Makefile.rules diff --git a/arch/um/kernel/exec_kern.c b/arch/um/kernel/exec_kern.c index c264e1c05ab3..1ca84319317d 100644 --- a/arch/um/kernel/exec_kern.c +++ b/arch/um/kernel/exec_kern.c @@ -30,8 +30,6 @@ void start_thread(struct pt_regs *regs, unsigned long eip, unsigned long esp) CHOOSE_MODE_PROC(start_thread_tt, start_thread_skas, regs, eip, esp); } -extern void log_exec(char **argv, void *tty); - static long execve1(char *file, char __user * __user *argv, char __user *__user *env) { diff --git a/arch/um/kernel/tty_log.c b/arch/um/kernel/tty_log.c deleted file mode 100644 index 9ada656f68ce..000000000000 --- a/arch/um/kernel/tty_log.c +++ /dev/null @@ -1,230 +0,0 @@ -/* - * Copyright (C) 2002 Jeff Dike (jdike@karaya.com) and - * geoffrey hing - * Licensed under the GPL - */ - -#include -#include -#include -#include -#include -#include -#include "init.h" -#include "user.h" -#include "kern_util.h" -#include "os.h" - -#define TTY_LOG_DIR "./" - -/* Set early in boot and then unchanged */ -static char *tty_log_dir = TTY_LOG_DIR; -static int tty_log_fd = -1; - -#define TTY_LOG_OPEN 1 -#define TTY_LOG_CLOSE 2 -#define TTY_LOG_WRITE 3 -#define TTY_LOG_EXEC 4 - -#define TTY_READ 1 -#define TTY_WRITE 2 - -struct tty_log_buf { - int what; - unsigned long tty; - int len; - int direction; - unsigned long sec; - unsigned long usec; -}; - -int open_tty_log(void *tty, void *current_tty) -{ - struct timeval tv; - struct tty_log_buf data; - char buf[strlen(tty_log_dir) + sizeof("01234567890-01234567\0")]; - int fd; - - gettimeofday(&tv, NULL); - if(tty_log_fd != -1){ - data = ((struct tty_log_buf) { .what = TTY_LOG_OPEN, - .tty = (unsigned long) tty, - .len = sizeof(current_tty), - .direction = 0, - .sec = tv.tv_sec, - .usec = tv.tv_usec } ); - os_write_file(tty_log_fd, &data, sizeof(data)); - os_write_file(tty_log_fd, ¤t_tty, data.len); - return(tty_log_fd); - } - - sprintf(buf, "%s/%0u-%0u", tty_log_dir, (unsigned int) tv.tv_sec, - (unsigned int) tv.tv_usec); - - fd = os_open_file(buf, of_append(of_create(of_rdwr(OPENFLAGS()))), - 0644); - if(fd < 0){ - printk("open_tty_log : couldn't open '%s', errno = %d\n", - buf, -fd); - } - return(fd); -} - -void close_tty_log(int fd, void *tty) -{ - struct tty_log_buf data; - struct timeval tv; - - if(tty_log_fd != -1){ - gettimeofday(&tv, NULL); - data = ((struct tty_log_buf) { .what = TTY_LOG_CLOSE, - .tty = (unsigned long) tty, - .len = 0, - .direction = 0, - .sec = tv.tv_sec, - .usec = tv.tv_usec } ); - os_write_file(tty_log_fd, &data, sizeof(data)); - return; - } - os_close_file(fd); -} - -static int log_chunk(int fd, const char *buf, int len) -{ - int total = 0, try, missed, n; - char chunk[64]; - - while(len > 0){ - try = (len > sizeof(chunk)) ? sizeof(chunk) : len; - missed = copy_from_user_proc(chunk, (char *) buf, try); - try -= missed; - n = os_write_file(fd, chunk, try); - if(n != try) { - if(n < 0) - return(n); - return(-EIO); - } - if(missed != 0) - return(-EFAULT); - - len -= try; - total += try; - buf += try; - } - - return(total); -} - -int write_tty_log(int fd, const char *buf, int len, void *tty, int is_read) -{ - struct timeval tv; - struct tty_log_buf data; - int direction; - - if(fd == tty_log_fd){ - gettimeofday(&tv, NULL); - direction = is_read ? TTY_READ : TTY_WRITE; - data = ((struct tty_log_buf) { .what = TTY_LOG_WRITE, - .tty = (unsigned long) tty, - .len = len, - .direction = direction, - .sec = tv.tv_sec, - .usec = tv.tv_usec } ); - os_write_file(tty_log_fd, &data, sizeof(data)); - } - - return(log_chunk(fd, buf, len)); -} - -void log_exec(char **argv, void *tty) -{ - struct timeval tv; - struct tty_log_buf data; - char **ptr,*arg; - int len; - - if(tty_log_fd == -1) return; - - gettimeofday(&tv, NULL); - - len = 0; - for(ptr = argv; ; ptr++){ - if(copy_from_user_proc(&arg, ptr, sizeof(arg))) - return; - if(arg == NULL) break; - len += strlen_user_proc(arg); - } - - data = ((struct tty_log_buf) { .what = TTY_LOG_EXEC, - .tty = (unsigned long) tty, - .len = len, - .direction = 0, - .sec = tv.tv_sec, - .usec = tv.tv_usec } ); - os_write_file(tty_log_fd, &data, sizeof(data)); - - for(ptr = argv; ; ptr++){ - if(copy_from_user_proc(&arg, ptr, sizeof(arg))) - return; - if(arg == NULL) break; - log_chunk(tty_log_fd, arg, strlen_user_proc(arg)); - } -} - -extern void register_tty_logger(int (*opener)(void *, void *), - int (*writer)(int, const char *, int, - void *, int), - void (*closer)(int, void *)); - -static int register_logger(void) -{ - register_tty_logger(open_tty_log, write_tty_log, close_tty_log); - return(0); -} - -__uml_initcall(register_logger); - -static int __init set_tty_log_dir(char *name, int *add) -{ - tty_log_dir = name; - return 0; -} - -__uml_setup("tty_log_dir=", set_tty_log_dir, -"tty_log_dir=\n" -" This is used to specify the directory where the logs of all pty\n" -" data from this UML machine will be written.\n\n" -); - -static int __init set_tty_log_fd(char *name, int *add) -{ - char *end; - - tty_log_fd = strtoul(name, &end, 0); - if((*end != '\0') || (end == name)){ - printf("set_tty_log_fd - strtoul failed on '%s'\n", name); - tty_log_fd = -1; - } - - *add = 0; - return 0; -} - -__uml_setup("tty_log_fd=", set_tty_log_fd, -"tty_log_fd=\n" -" This is used to specify a preconfigured file descriptor to which all\n" -" tty data will be written. Preconfigure the descriptor with something\n" -" like '10>tty_log tty_log_fd=10'.\n\n" -); - - -/* - * Overrides for Emacs so that we follow Linus's tabbing style. - * Emacs will notice this stuff at the end of the file and automatically - * adjust the settings for this buffer only. This must remain at the end - * of the file. - * --------------------------------------------------------------------------- - * Local variables: - * c-file-style: "linux" - * End: - */ diff --git a/arch/um/os-Linux/Makefile b/arch/um/os-Linux/Makefile index c3d56c2935c2..1659386b42bb 100644 --- a/arch/um/os-Linux/Makefile +++ b/arch/um/os-Linux/Makefile @@ -8,10 +8,12 @@ obj-y = aio.o elf_aux.o file.o helper.o irq.o main.o mem.o process.o sigio.o \ user_syms.o util.o drivers/ sys-$(SUBARCH)/ obj-$(CONFIG_MODE_SKAS) += skas/ +obj-$(CONFIG_TTY_LOG) += tty_log.o +user-objs-$(CONFIG_TTY_LOG) += tty_log.o -USER_OBJS := aio.o elf_aux.o file.o helper.o irq.o main.o mem.o process.o \ - sigio.o signal.o start_up.o time.o trap.o tt.o tty.o uaccess.o umid.o \ - util.o +USER_OBJS := $(user-objs-y) aio.o elf_aux.o file.o helper.o irq.o main.o mem.o \ + process.o sigio.o signal.o start_up.o time.o trap.o tt.o tty.o \ + uaccess.o umid.o util.o elf_aux.o: $(ARCH_DIR)/kernel-offsets.h CFLAGS_elf_aux.o += -I$(objtree)/arch/um diff --git a/arch/um/os-Linux/tty_log.c b/arch/um/os-Linux/tty_log.c new file mode 100644 index 000000000000..c6ba56c1560f --- /dev/null +++ b/arch/um/os-Linux/tty_log.c @@ -0,0 +1,218 @@ +/* + * Copyright (C) 2002 Jeff Dike (jdike@karaya.com) and + * geoffrey hing + * Licensed under the GPL + */ + +#include +#include +#include +#include +#include +#include +#include "init.h" +#include "user.h" +#include "kern_util.h" +#include "os.h" + +#define TTY_LOG_DIR "./" + +/* Set early in boot and then unchanged */ +static char *tty_log_dir = TTY_LOG_DIR; +static int tty_log_fd = -1; + +#define TTY_LOG_OPEN 1 +#define TTY_LOG_CLOSE 2 +#define TTY_LOG_WRITE 3 +#define TTY_LOG_EXEC 4 + +#define TTY_READ 1 +#define TTY_WRITE 2 + +struct tty_log_buf { + int what; + unsigned long tty; + int len; + int direction; + unsigned long sec; + unsigned long usec; +}; + +int open_tty_log(void *tty, void *current_tty) +{ + struct timeval tv; + struct tty_log_buf data; + char buf[strlen(tty_log_dir) + sizeof("01234567890-01234567\0")]; + int fd; + + gettimeofday(&tv, NULL); + if(tty_log_fd != -1){ + data = ((struct tty_log_buf) { .what = TTY_LOG_OPEN, + .tty = (unsigned long) tty, + .len = sizeof(current_tty), + .direction = 0, + .sec = tv.tv_sec, + .usec = tv.tv_usec } ); + os_write_file(tty_log_fd, &data, sizeof(data)); + os_write_file(tty_log_fd, ¤t_tty, data.len); + return(tty_log_fd); + } + + sprintf(buf, "%s/%0u-%0u", tty_log_dir, (unsigned int) tv.tv_sec, + (unsigned int) tv.tv_usec); + + fd = os_open_file(buf, of_append(of_create(of_rdwr(OPENFLAGS()))), + 0644); + if(fd < 0){ + printk("open_tty_log : couldn't open '%s', errno = %d\n", + buf, -fd); + } + return(fd); +} + +void close_tty_log(int fd, void *tty) +{ + struct tty_log_buf data; + struct timeval tv; + + if(tty_log_fd != -1){ + gettimeofday(&tv, NULL); + data = ((struct tty_log_buf) { .what = TTY_LOG_CLOSE, + .tty = (unsigned long) tty, + .len = 0, + .direction = 0, + .sec = tv.tv_sec, + .usec = tv.tv_usec } ); + os_write_file(tty_log_fd, &data, sizeof(data)); + return; + } + os_close_file(fd); +} + +static int log_chunk(int fd, const char *buf, int len) +{ + int total = 0, try, missed, n; + char chunk[64]; + + while(len > 0){ + try = (len > sizeof(chunk)) ? sizeof(chunk) : len; + missed = copy_from_user_proc(chunk, (char *) buf, try); + try -= missed; + n = os_write_file(fd, chunk, try); + if(n != try) { + if(n < 0) + return(n); + return(-EIO); + } + if(missed != 0) + return(-EFAULT); + + len -= try; + total += try; + buf += try; + } + + return(total); +} + +int write_tty_log(int fd, const char *buf, int len, void *tty, int is_read) +{ + struct timeval tv; + struct tty_log_buf data; + int direction; + + if(fd == tty_log_fd){ + gettimeofday(&tv, NULL); + direction = is_read ? TTY_READ : TTY_WRITE; + data = ((struct tty_log_buf) { .what = TTY_LOG_WRITE, + .tty = (unsigned long) tty, + .len = len, + .direction = direction, + .sec = tv.tv_sec, + .usec = tv.tv_usec } ); + os_write_file(tty_log_fd, &data, sizeof(data)); + } + + return(log_chunk(fd, buf, len)); +} + +void log_exec(char **argv, void *tty) +{ + struct timeval tv; + struct tty_log_buf data; + char **ptr,*arg; + int len; + + if(tty_log_fd == -1) return; + + gettimeofday(&tv, NULL); + + len = 0; + for(ptr = argv; ; ptr++){ + if(copy_from_user_proc(&arg, ptr, sizeof(arg))) + return; + if(arg == NULL) break; + len += strlen_user_proc(arg); + } + + data = ((struct tty_log_buf) { .what = TTY_LOG_EXEC, + .tty = (unsigned long) tty, + .len = len, + .direction = 0, + .sec = tv.tv_sec, + .usec = tv.tv_usec } ); + os_write_file(tty_log_fd, &data, sizeof(data)); + + for(ptr = argv; ; ptr++){ + if(copy_from_user_proc(&arg, ptr, sizeof(arg))) + return; + if(arg == NULL) break; + log_chunk(tty_log_fd, arg, strlen_user_proc(arg)); + } +} + +extern void register_tty_logger(int (*opener)(void *, void *), + int (*writer)(int, const char *, int, + void *, int), + void (*closer)(int, void *)); + +static int register_logger(void) +{ + register_tty_logger(open_tty_log, write_tty_log, close_tty_log); + return(0); +} + +__uml_initcall(register_logger); + +static int __init set_tty_log_dir(char *name, int *add) +{ + tty_log_dir = name; + return 0; +} + +__uml_setup("tty_log_dir=", set_tty_log_dir, +"tty_log_dir=\n" +" This is used to specify the directory where the logs of all pty\n" +" data from this UML machine will be written.\n\n" +); + +static int __init set_tty_log_fd(char *name, int *add) +{ + char *end; + + tty_log_fd = strtoul(name, &end, 0); + if((*end != '\0') || (end == name)){ + printf("set_tty_log_fd - strtoul failed on '%s'\n", name); + tty_log_fd = -1; + } + + *add = 0; + return 0; +} + +__uml_setup("tty_log_fd=", set_tty_log_fd, +"tty_log_fd=\n" +" This is used to specify a preconfigured file descriptor to which all\n" +" tty data will be written. Preconfigure the descriptor with something\n" +" like '10>tty_log tty_log_fd=10'.\n\n" +); -- cgit v1.2.3 From cf9165a50aa21027d2f0eefc90476ec59ae6d2b8 Mon Sep 17 00:00:00 2001 From: Jeff Dike Date: Mon, 27 Mar 2006 01:14:36 -0800 Subject: [PATCH] uml: oS header cleanups This rearranges the OS declarations by moving some declarations into os.h. Signed-off-by: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/include/os.h | 14 ++++++++++++++ arch/um/include/skas/mode-skas.h | 1 - arch/um/include/skas/skas.h | 1 - 3 files changed, 14 insertions(+), 2 deletions(-) (limited to 'arch/um') diff --git a/arch/um/include/os.h b/arch/um/include/os.h index 53dee8d3cdcc..d3d1bc6074ef 100644 --- a/arch/um/include/os.h +++ b/arch/um/include/os.h @@ -122,6 +122,7 @@ static inline struct openflags of_cloexec(struct openflags flags) return(flags); } +/* file.c */ extern int os_stat_file(const char *file_name, struct uml_stat *buf); extern int os_stat_fd(const int fd, struct uml_stat *buf); extern int os_access(const char *file, int mode); @@ -157,6 +158,15 @@ extern int os_connect_socket(char *name); extern int os_file_type(char *file); extern int os_file_mode(char *file, struct openflags *mode_out); extern int os_lock_file(int fd, int excl); +extern void os_flush_stdout(void); +extern int os_stat_filesystem(char *path, long *bsize_out, + long long *blocks_out, long long *bfree_out, + long long *bavail_out, long long *files_out, + long long *ffree_out, void *fsid_out, + int fsid_size, long *namelen_out, + long *spare_out); +extern int os_change_dir(char *dir); +extern int os_fchange_dir(int fd); /* start_up.c */ extern void os_early_checks(void); @@ -316,4 +326,8 @@ extern void write_sigio_workaround(void); extern int add_sigio_fd(int fd, int read); extern int ignore_sigio_fd(int fd); +/* skas/trap */ +extern void sig_handler_common_skas(int sig, void *sc_ptr); +extern void user_signal(int sig, union uml_pt_regs *regs, int pid); + #endif diff --git a/arch/um/include/skas/mode-skas.h b/arch/um/include/skas/mode-skas.h index 260065cfeef1..8bc6916bbbb1 100644 --- a/arch/um/include/skas/mode-skas.h +++ b/arch/um/include/skas/mode-skas.h @@ -13,7 +13,6 @@ extern unsigned long exec_fp_regs[]; extern unsigned long exec_fpx_regs[]; extern int have_fpx_regs; -extern void sig_handler_common_skas(int sig, void *sc_ptr); extern void kill_off_processes_skas(void); #endif diff --git a/arch/um/include/skas/skas.h b/arch/um/include/skas/skas.h index 86357282d681..853b26f148c5 100644 --- a/arch/um/include/skas/skas.h +++ b/arch/um/include/skas/skas.h @@ -17,7 +17,6 @@ extern int user_thread(unsigned long stack, int flags); extern void new_thread_proc(void *stack, void (*handler)(int sig)); extern void new_thread_handler(int sig); extern void handle_syscall(union uml_pt_regs *regs); -extern void user_signal(int sig, union uml_pt_regs *regs, int pid); extern int new_mm(unsigned long stack); extern void get_skas_faultinfo(int pid, struct faultinfo * fi); extern long execute_syscall_skas(void *r); -- cgit v1.2.3 From 6c29256c5703ad7c3cf62276dbc38d802a05669e Mon Sep 17 00:00:00 2001 From: Jeff Dike Date: Mon, 27 Mar 2006 01:14:37 -0800 Subject: [PATCH] uml: allow ubd devices to be shared in a cluster This adds a 'c' option to the ubd switch which turns off host file locking so that the device can be shared, as with a cluster. There's also some whitespace cleanup while I was in this file. Signed-off-by: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/drivers/ubd_kern.c | 76 ++++++++++++++++++++++++++-------------------- 1 file changed, 43 insertions(+), 33 deletions(-) (limited to 'arch/um') diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index fa617e0719ab..0336575d2448 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -1,4 +1,4 @@ -/* +/* * Copyright (C) 2000 Jeff Dike (jdike@karaya.com) * Licensed under the GPL */ @@ -71,7 +71,7 @@ struct io_thread_req { int error; }; -extern int open_ubd_file(char *file, struct openflags *openflags, +extern int open_ubd_file(char *file, struct openflags *openflags, int shared, char **backing_file_out, int *bitmap_offset_out, unsigned long *bitmap_len_out, int *data_offset_out, int *create_cow_out); @@ -137,7 +137,7 @@ static int fake_major = MAJOR_NR; static struct gendisk *ubd_gendisk[MAX_DEV]; static struct gendisk *fake_gendisk[MAX_DEV]; - + #ifdef CONFIG_BLK_DEV_UBD_SYNC #define OPEN_FLAGS ((struct openflags) { .r = 1, .w = 1, .s = 1, .c = 0, \ .cl = 1 }) @@ -168,6 +168,7 @@ struct ubd { __u64 size; struct openflags boot_openflags; struct openflags openflags; + int shared; int no_cow; struct cow cow; struct platform_device pdev; @@ -189,6 +190,7 @@ struct ubd { .boot_openflags = OPEN_FLAGS, \ .openflags = OPEN_FLAGS, \ .no_cow = 0, \ + .shared = 0, \ .cow = DEFAULT_COW, \ } @@ -305,7 +307,7 @@ static int ubd_setup_common(char *str, int *index_out) } major = simple_strtoul(str, &end, 0); if((*end != '\0') || (end == str)){ - printk(KERN_ERR + printk(KERN_ERR "ubd_setup : didn't parse major number\n"); return(1); } @@ -316,7 +318,7 @@ static int ubd_setup_common(char *str, int *index_out) printk(KERN_ERR "Can't assign a fake major twice\n"); goto out1; } - + fake_major = major; printk(KERN_INFO "Setting extra ubd major number to %d\n", @@ -351,7 +353,7 @@ static int ubd_setup_common(char *str, int *index_out) if (index_out) *index_out = n; - for (i = 0; i < 4; i++) { + for (i = 0; i < sizeof("rscd="); i++) { switch (*str) { case 'r': flags.w = 0; @@ -362,11 +364,14 @@ static int ubd_setup_common(char *str, int *index_out) case 'd': dev->no_cow = 1; break; + case 'c': + dev->shared = 1; + break; case '=': str++; goto break_loop; default: - printk(KERN_ERR "ubd_setup : Expected '=' or flag letter (r,s or d)\n"); + printk(KERN_ERR "ubd_setup : Expected '=' or flag letter (r, s, c, or d)\n"); goto out; } str++; @@ -515,7 +520,7 @@ static void ubd_handler(void) spin_unlock(&ubd_io_lock); return; } - + ubd_finish(rq, req.error); reactivate_fd(thread_fd, UBD_IRQ); do_ubd_request(ubd_queue); @@ -532,7 +537,7 @@ static int io_pid = -1; void kill_io_thread(void) { - if(io_pid != -1) + if(io_pid != -1) os_kill_process(io_pid, 1); } @@ -567,14 +572,15 @@ static int ubd_open_dev(struct ubd *dev) create_cow = 0; create_ptr = (dev->cow.file != NULL) ? &create_cow : NULL; back_ptr = dev->no_cow ? NULL : &dev->cow.file; - dev->fd = open_ubd_file(dev->file, &dev->openflags, back_ptr, - &dev->cow.bitmap_offset, &dev->cow.bitmap_len, - &dev->cow.data_offset, create_ptr); + dev->fd = open_ubd_file(dev->file, &dev->openflags, dev->shared, + back_ptr, &dev->cow.bitmap_offset, + &dev->cow.bitmap_len, &dev->cow.data_offset, + create_ptr); if((dev->fd == -ENOENT) && create_cow){ - dev->fd = create_cow_file(dev->file, dev->cow.file, + dev->fd = create_cow_file(dev->file, dev->cow.file, dev->openflags, 1 << 9, PAGE_SIZE, - &dev->cow.bitmap_offset, + &dev->cow.bitmap_offset, &dev->cow.bitmap_len, &dev->cow.data_offset); if(dev->fd >= 0){ @@ -598,16 +604,16 @@ static int ubd_open_dev(struct ubd *dev) } flush_tlb_kernel_vm(); - err = read_cow_bitmap(dev->fd, dev->cow.bitmap, - dev->cow.bitmap_offset, + err = read_cow_bitmap(dev->fd, dev->cow.bitmap, + dev->cow.bitmap_offset, dev->cow.bitmap_len); if(err < 0) goto error; flags = dev->openflags; flags.w = 0; - err = open_ubd_file(dev->cow.file, &flags, NULL, NULL, NULL, - NULL, NULL); + err = open_ubd_file(dev->cow.file, &flags, dev->shared, NULL, + NULL, NULL, NULL, NULL); if(err < 0) goto error; dev->cow.fd = err; } @@ -685,11 +691,11 @@ static int ubd_add(int n) dev->size = ROUND_BLOCK(dev->size); err = ubd_new_disk(MAJOR_NR, dev->size, n, &ubd_gendisk[n]); - if(err) + if(err) goto out_close; - + if(fake_major != MAJOR_NR) - ubd_new_disk(fake_major, dev->size, n, + ubd_new_disk(fake_major, dev->size, n, &fake_gendisk[n]); /* perhaps this should also be under the "if (fake_major)" above */ @@ -854,7 +860,7 @@ int ubd_init(void) return -1; } platform_driver_register(&ubd_driver); - for (i = 0; i < MAX_DEV; i++) + for (i = 0; i < MAX_DEV; i++) ubd_add(i); return 0; } @@ -872,16 +878,16 @@ int ubd_driver_init(void){ * enough. So use anyway the io thread. */ } stack = alloc_stack(0, 0); - io_pid = start_io_thread(stack + PAGE_SIZE - sizeof(void *), + io_pid = start_io_thread(stack + PAGE_SIZE - sizeof(void *), &thread_fd); if(io_pid < 0){ - printk(KERN_ERR + printk(KERN_ERR "ubd : Failed to start I/O thread (errno = %d) - " "falling back to synchronous I/O\n", -io_pid); io_pid = -1; return(0); } - err = um_request_irq(UBD_IRQ, thread_fd, IRQ_READ, ubd_intr, + err = um_request_irq(UBD_IRQ, thread_fd, IRQ_READ, ubd_intr, SA_INTERRUPT, "ubd", ubd_dev); if(err != 0) printk(KERN_ERR "um_request_irq failed - errno = %d\n", -err); @@ -978,7 +984,7 @@ static void cowify_req(struct io_thread_req *req, unsigned long *bitmap, if(req->op == UBD_READ) { for(i = 0; i < req->length >> 9; i++){ if(ubd_test_bit(sector + i, (unsigned char *) bitmap)) - ubd_set_bit(i, (unsigned char *) + ubd_set_bit(i, (unsigned char *) &req->sector_mask); } } @@ -999,7 +1005,7 @@ static int prepare_request(struct request *req, struct io_thread_req *io_req) /* This should be impossible now */ if((rq_data_dir(req) == WRITE) && !dev->openflags.w){ - printk("Write attempted on readonly ubd device %s\n", + printk("Write attempted on readonly ubd device %s\n", disk->disk_name); end_request(req, 0); return(1); @@ -1182,7 +1188,7 @@ int read_cow_bitmap(int fd, void *buf, int offset, int len) return(0); } -int open_ubd_file(char *file, struct openflags *openflags, +int open_ubd_file(char *file, struct openflags *openflags, int shared, char **backing_file_out, int *bitmap_offset_out, unsigned long *bitmap_len_out, int *data_offset_out, int *create_cow_out) @@ -1206,10 +1212,14 @@ int open_ubd_file(char *file, struct openflags *openflags, return fd; } - err = os_lock_file(fd, openflags->w); - if(err < 0){ - printk("Failed to lock '%s', err = %d\n", file, -err); - goto out_close; + if(shared) + printk("Not locking \"%s\" on the host\n", file); + else { + err = os_lock_file(fd, openflags->w); + if(err < 0){ + printk("Failed to lock '%s', err = %d\n", file, -err); + goto out_close; + } } /* Succesful return case! */ @@ -1260,7 +1270,7 @@ int create_cow_file(char *cow_file, char *backing_file, struct openflags flags, int err, fd; flags.c = 1; - fd = open_ubd_file(cow_file, &flags, NULL, NULL, NULL, NULL, NULL); + fd = open_ubd_file(cow_file, &flags, 0, NULL, NULL, NULL, NULL, NULL); if(fd < 0){ err = fd; printk("Open of COW file '%s' failed, errno = %d\n", cow_file, -- cgit v1.2.3 From 98c18238f146a9038098244d60a7d2b1f67ee790 Mon Sep 17 00:00:00 2001 From: Jeff Dike Date: Mon, 27 Mar 2006 01:14:38 -0800 Subject: [PATCH] uml: fix segfault on signal delivery This fixes a process segfault where a signal was being delivered such that a new stack page needed to be allocated to hold the signal frame. This was tripping some logic in the page fault handler which wouldn't allocate the page if the faulting address was more that 32 bytes lower than the current stack pointer. Since a signal frame is greater than 32 bytes, this exercised that case. It's fixed by updating the SP in the pt_regs before starting to copy the signal frame. Since those are the registers that will be copied on to the stack, we have to be careful to put the original SP, not the new one which points to the signal frame, on the stack. Signed-off-by: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/sys-i386/signal.c | 59 +++++++++++++++++++++++++++++++++------------ arch/um/sys-x86_64/signal.c | 56 ++++++++++++++++++++++++++++++------------ 2 files changed, 85 insertions(+), 30 deletions(-) (limited to 'arch/um') diff --git a/arch/um/sys-i386/signal.c b/arch/um/sys-i386/signal.c index 7cd1a82dc8c2..33a40f5ef0d2 100644 --- a/arch/um/sys-i386/signal.c +++ b/arch/um/sys-i386/signal.c @@ -58,7 +58,7 @@ static int copy_sc_from_user_skas(struct pt_regs *regs, } int copy_sc_to_user_skas(struct sigcontext *to, struct _fpstate *to_fp, - struct pt_regs *regs) + struct pt_regs *regs, unsigned long sp) { struct sigcontext sc; unsigned long fpregs[HOST_FP_SIZE]; @@ -72,7 +72,7 @@ int copy_sc_to_user_skas(struct sigcontext *to, struct _fpstate *to_fp, sc.edi = REGS_EDI(regs->regs.skas.regs); sc.esi = REGS_ESI(regs->regs.skas.regs); sc.ebp = REGS_EBP(regs->regs.skas.regs); - sc.esp = REGS_SP(regs->regs.skas.regs); + sc.esp = sp; sc.ebx = REGS_EBX(regs->regs.skas.regs); sc.edx = REGS_EDX(regs->regs.skas.regs); sc.ecx = REGS_ECX(regs->regs.skas.regs); @@ -132,7 +132,7 @@ int copy_sc_from_user_tt(struct sigcontext *to, struct sigcontext *from, } int copy_sc_to_user_tt(struct sigcontext *to, struct _fpstate *fp, - struct sigcontext *from, int fpsize) + struct sigcontext *from, int fpsize, unsigned long sp) { struct _fpstate *to_fp, *from_fp; int err; @@ -140,11 +140,18 @@ int copy_sc_to_user_tt(struct sigcontext *to, struct _fpstate *fp, to_fp = (fp ? fp : (struct _fpstate *) (to + 1)); from_fp = from->fpstate; err = copy_to_user(to, from, sizeof(*to)); + + /* The SP in the sigcontext is the updated one for the signal + * delivery. The sp passed in is the original, and this needs + * to be restored, so we stick it in separately. + */ + err |= copy_to_user(&SC_SP(to), sp, sizeof(sp)); + if(from_fp != NULL){ err |= copy_to_user(&to->fpstate, &to_fp, sizeof(to->fpstate)); err |= copy_to_user(to_fp, from_fp, fpsize); } - return(err); + return err; } #endif @@ -159,11 +166,11 @@ static int copy_sc_from_user(struct pt_regs *to, void __user *from) } static int copy_sc_to_user(struct sigcontext *to, struct _fpstate *fp, - struct pt_regs *from) + struct pt_regs *from, unsigned long sp) { return(CHOOSE_MODE(copy_sc_to_user_tt(to, fp, UPT_SC(&from->regs), - sizeof(*fp)), - copy_sc_to_user_skas(to, fp, from))); + sizeof(*fp), sp), + copy_sc_to_user_skas(to, fp, from, sp))); } static int copy_ucontext_to_user(struct ucontext *uc, struct _fpstate *fp, @@ -174,7 +181,7 @@ static int copy_ucontext_to_user(struct ucontext *uc, struct _fpstate *fp, err |= put_user(current->sas_ss_sp, &uc->uc_stack.ss_sp); err |= put_user(sas_ss_flags(sp), &uc->uc_stack.ss_flags); err |= put_user(current->sas_ss_size, &uc->uc_stack.ss_size); - err |= copy_sc_to_user(&uc->uc_mcontext, fp, ¤t->thread.regs); + err |= copy_sc_to_user(&uc->uc_mcontext, fp, ¤t->thread.regs, sp); err |= copy_to_user(&uc->uc_sigmask, set, sizeof(*set)); return(err); } @@ -207,6 +214,7 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig, { struct sigframe __user *frame; void *restorer; + unsigned long save_sp = PT_REGS_SP(regs); int err = 0; stack_top &= -8UL; @@ -218,9 +226,19 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig, if(ka->sa.sa_flags & SA_RESTORER) restorer = ka->sa.sa_restorer; + /* Update SP now because the page fault handler refuses to extend + * the stack if the faulting address is too far below the current + * SP, which frame now certainly is. If there's an error, the original + * value is restored on the way out. + * When writing the sigcontext to the stack, we have to write the + * original value, so that's passed to copy_sc_to_user, which does + * the right thing with it. + */ + PT_REGS_SP(regs) = (unsigned long) frame; + err |= __put_user(restorer, &frame->pretcode); err |= __put_user(sig, &frame->sig); - err |= copy_sc_to_user(&frame->sc, NULL, regs); + err |= copy_sc_to_user(&frame->sc, NULL, regs, save_sp); err |= __put_user(mask->sig[0], &frame->sc.oldmask); if (_NSIG_WORDS > 1) err |= __copy_to_user(&frame->extramask, &mask->sig[1], @@ -238,7 +256,7 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig, err |= __put_user(0x80cd, (short __user *)(frame->retcode+6)); if(err) - return(err); + goto err; PT_REGS_SP(regs) = (unsigned long) frame; PT_REGS_IP(regs) = (unsigned long) ka->sa.sa_handler; @@ -248,7 +266,11 @@ int setup_signal_stack_sc(unsigned long stack_top, int sig, if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED)) ptrace_notify(SIGTRAP); - return(0); + return 0; + +err: + PT_REGS_SP(regs) = save_sp; + return err; } int setup_signal_stack_si(unsigned long stack_top, int sig, @@ -257,6 +279,7 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, { struct rt_sigframe __user *frame; void *restorer; + unsigned long save_sp = PT_REGS_SP(regs); int err = 0; stack_top &= -8UL; @@ -268,13 +291,16 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, if(ka->sa.sa_flags & SA_RESTORER) restorer = ka->sa.sa_restorer; + /* See comment above about why this is here */ + PT_REGS_SP(regs) = (unsigned long) frame; + err |= __put_user(restorer, &frame->pretcode); err |= __put_user(sig, &frame->sig); err |= __put_user(&frame->info, &frame->pinfo); err |= __put_user(&frame->uc, &frame->puc); err |= copy_siginfo_to_user(&frame->info, info); err |= copy_ucontext_to_user(&frame->uc, &frame->fpstate, mask, - PT_REGS_SP(regs)); + save_sp); /* * This is movl $,%eax ; int $0x80 @@ -288,9 +314,8 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, err |= __put_user(0x80cd, (short __user *)(frame->retcode+5)); if(err) - return(err); + goto err; - PT_REGS_SP(regs) = (unsigned long) frame; PT_REGS_IP(regs) = (unsigned long) ka->sa.sa_handler; PT_REGS_EAX(regs) = (unsigned long) sig; PT_REGS_EDX(regs) = (unsigned long) &frame->info; @@ -298,7 +323,11 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, if ((current->ptrace & PT_DTRACE) && (current->ptrace & PT_PTRACED)) ptrace_notify(SIGTRAP); - return(0); + return 0; + +err: + PT_REGS_SP(regs) = save_sp; + return err; } long sys_sigreturn(struct pt_regs regs) diff --git a/arch/um/sys-x86_64/signal.c b/arch/um/sys-x86_64/signal.c index fe1d065332b1..e75c4e1838b0 100644 --- a/arch/um/sys-x86_64/signal.c +++ b/arch/um/sys-x86_64/signal.c @@ -55,7 +55,8 @@ static int copy_sc_from_user_skas(struct pt_regs *regs, } int copy_sc_to_user_skas(struct sigcontext *to, struct _fpstate *to_fp, - struct pt_regs *regs, unsigned long mask) + struct pt_regs *regs, unsigned long mask, + unsigned long sp) { struct faultinfo * fi = ¤t->thread.arch.faultinfo; int err = 0; @@ -70,7 +71,11 @@ int copy_sc_to_user_skas(struct sigcontext *to, struct _fpstate *to_fp, err |= PUTREG(regs, RDI, to, rdi); err |= PUTREG(regs, RSI, to, rsi); err |= PUTREG(regs, RBP, to, rbp); - err |= PUTREG(regs, RSP, to, rsp); + /* Must use orignal RSP, which is passed in, rather than what's in + * the pt_regs, because that's already been updated to point at the + * signal frame. + */ + err |= __put_user(sp, &to->rsp); err |= PUTREG(regs, RBX, to, rbx); err |= PUTREG(regs, RDX, to, rdx); err |= PUTREG(regs, RCX, to, rcx); @@ -102,7 +107,7 @@ int copy_sc_to_user_skas(struct sigcontext *to, struct _fpstate *to_fp, #ifdef CONFIG_MODE_TT int copy_sc_from_user_tt(struct sigcontext *to, struct sigcontext *from, - int fpsize) + int fpsize) { struct _fpstate *to_fp, *from_fp; unsigned long sigs; @@ -120,7 +125,7 @@ int copy_sc_from_user_tt(struct sigcontext *to, struct sigcontext *from, } int copy_sc_to_user_tt(struct sigcontext *to, struct _fpstate *fp, - struct sigcontext *from, int fpsize) + struct sigcontext *from, int fpsize, unsigned long sp) { struct _fpstate *to_fp, *from_fp; int err; @@ -128,11 +133,17 @@ int copy_sc_to_user_tt(struct sigcontext *to, struct _fpstate *fp, to_fp = (fp ? fp : (struct _fpstate *) (to + 1)); from_fp = from->fpstate; err = copy_to_user(to, from, sizeof(*to)); + /* The SP in the sigcontext is the updated one for the signal + * delivery. The sp passed in is the original, and this needs + * to be restored, so we stick it in separately. + */ + err |= copy_to_user(&SC_SP(to), sp, sizeof(sp)); + if(from_fp != NULL){ err |= copy_to_user(&to->fpstate, &to_fp, sizeof(to->fpstate)); err |= copy_to_user(to_fp, from_fp, fpsize); } - return(err); + return err; } #endif @@ -148,11 +159,12 @@ static int copy_sc_from_user(struct pt_regs *to, void __user *from) } static int copy_sc_to_user(struct sigcontext *to, struct _fpstate *fp, - struct pt_regs *from, unsigned long mask) + struct pt_regs *from, unsigned long mask, + unsigned long sp) { return(CHOOSE_MODE(copy_sc_to_user_tt(to, fp, UPT_SC(&from->regs), - sizeof(*fp)), - copy_sc_to_user_skas(to, fp, from, mask))); + sizeof(*fp), sp), + copy_sc_to_user_skas(to, fp, from, mask, sp))); } struct rt_sigframe @@ -170,6 +182,7 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, { struct rt_sigframe __user *frame; struct _fpstate __user *fp = NULL; + unsigned long save_sp = PT_REGS_RSP(regs); int err = 0; struct task_struct *me = current; @@ -193,14 +206,25 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, goto out; } + /* Update SP now because the page fault handler refuses to extend + * the stack if the faulting address is too far below the current + * SP, which frame now certainly is. If there's an error, the original + * value is restored on the way out. + * When writing the sigcontext to the stack, we have to write the + * original value, so that's passed to copy_sc_to_user, which does + * the right thing with it. + */ + PT_REGS_RSP(regs) = (unsigned long) frame; + /* Create the ucontext. */ err |= __put_user(0, &frame->uc.uc_flags); err |= __put_user(0, &frame->uc.uc_link); err |= __put_user(me->sas_ss_sp, &frame->uc.uc_stack.ss_sp); - err |= __put_user(sas_ss_flags(PT_REGS_SP(regs)), + err |= __put_user(sas_ss_flags(save_sp), &frame->uc.uc_stack.ss_flags); err |= __put_user(me->sas_ss_size, &frame->uc.uc_stack.ss_size); - err |= copy_sc_to_user(&frame->uc.uc_mcontext, fp, regs, set->sig[0]); + err |= copy_sc_to_user(&frame->uc.uc_mcontext, fp, regs, set->sig[0], + save_sp); err |= __put_user(fp, &frame->uc.uc_mcontext.fpstate); if (sizeof(*set) == 16) { __put_user(set->sig[0], &frame->uc.uc_sigmask.sig[0]); @@ -217,10 +241,10 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, err |= __put_user(ka->sa.sa_restorer, &frame->pretcode); else /* could use a vstub here */ - goto out; + goto restore_sp; if (err) - goto out; + goto restore_sp; /* Set up registers for signal handler */ { @@ -238,10 +262,12 @@ int setup_signal_stack_si(unsigned long stack_top, int sig, PT_REGS_RSI(regs) = (unsigned long) &frame->info; PT_REGS_RDX(regs) = (unsigned long) &frame->uc; PT_REGS_RIP(regs) = (unsigned long) ka->sa.sa_handler; - - PT_REGS_RSP(regs) = (unsigned long) frame; out: - return(err); + return err; + +restore_sp: + PT_REGS_RSP(regs) = save_sp; + return err; } long sys_rt_sigreturn(struct pt_regs *regs) -- cgit v1.2.3 From 1fbbd6844e6a84e5d166ab475dc298d3b89fa4bf Mon Sep 17 00:00:00 2001 From: Jeff Dike Date: Mon, 27 Mar 2006 01:14:39 -0800 Subject: [PATCH] uml: prevent umid theft Behavior when booting two UMLs with the same umid was broken. The second one would steal the umid. This fixes that, making the second UML take a random umid instead. Signed-off-by: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/os-Linux/umid.c | 33 +++++++++++++++++++++++---------- 1 file changed, 23 insertions(+), 10 deletions(-) (limited to 'arch/um') diff --git a/arch/um/os-Linux/umid.c b/arch/um/os-Linux/umid.c index ecf107ae5ac8..198e59163288 100644 --- a/arch/um/os-Linux/umid.c +++ b/arch/um/os-Linux/umid.c @@ -143,8 +143,10 @@ static int not_dead_yet(char *dir) goto out_close; } - if((kill(p, 0) == 0) || (errno != ESRCH)) + if((kill(p, 0) == 0) || (errno != ESRCH)){ + printk("umid \"%s\" is already in use by pid %d\n", umid, p); return 1; + } err = actually_do_remove(dir); if(err) @@ -234,33 +236,44 @@ int __init make_umid(void) err = mkdir(tmp, 0777); if(err < 0){ err = -errno; - if(errno != EEXIST) + if(err != -EEXIST) goto err; - if(not_dead_yet(tmp) < 0) + /* 1 -> this umid is already in use + * < 0 -> we couldn't remove the umid directory + * In either case, we can't use this umid, so return -EEXIST. + */ + if(not_dead_yet(tmp) != 0) goto err; err = mkdir(tmp, 0777); } - if(err < 0){ - printk("Failed to create '%s' - err = %d\n", umid, err); - goto err_rmdir; + if(err){ + err = -errno; + printk("Failed to create '%s' - err = %d\n", umid, -errno); + goto err; } umid_setup = 1; create_pid_file(); - return 0; - - err_rmdir: - rmdir(tmp); + err = 0; err: return err; } static int __init make_umid_init(void) { + if(!make_umid()) + return 0; + + /* If initializing with the given umid failed, then try again with + * a random one. + */ + printk("Failed to initialize umid \"%s\", trying with a random umid\n", + umid); + *umid = '\0'; make_umid(); return 0; -- cgit v1.2.3 From 5f4e8fd08f3993bc31a7dd91767fdb4da4fe6278 Mon Sep 17 00:00:00 2001 From: Jeff Dike Date: Mon, 27 Mar 2006 01:14:40 -0800 Subject: [PATCH] uml: fix thread startup race This fixes a race in the starting of write_sigio_thread. Previously, some of the data needed by the thread was initialized after the clone. If the thread ran immediately, it would see the uninitialized data, including an empty pollfds, which would cause it to hang. We move the data initialization to before the clone, and adjust the error paths and cleanup accordingly. Signed-off-by: Jeff Dike Cc: Paolo 'Blaisorblade' Giarrusso Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/os-Linux/sigio.c | 55 ++++++++++++++++++++++++------------------------ 1 file changed, 27 insertions(+), 28 deletions(-) (limited to 'arch/um') diff --git a/arch/um/os-Linux/sigio.c b/arch/um/os-Linux/sigio.c index 7604c404c4c2..9ba942947146 100644 --- a/arch/um/os-Linux/sigio.c +++ b/arch/um/os-Linux/sigio.c @@ -29,8 +29,10 @@ static int write_sigio_pid = -1; * the descriptors closed after it is killed. So, it can't see them change. * On the UML side, they are changed under the sigio_lock. */ -static int write_sigio_fds[2] = { -1, -1 }; -static int sigio_private[2] = { -1, -1 }; +#define SIGIO_FDS_INIT {-1, -1} + +static int write_sigio_fds[2] = SIGIO_FDS_INIT; +static int sigio_private[2] = SIGIO_FDS_INIT; struct pollfds { struct pollfd *poll; @@ -270,49 +272,46 @@ void write_sigio_workaround(void) /* Did we race? Don't try to optimize this, please, it's not so likely * to happen, and no more than once at the boot. */ if(write_sigio_pid != -1) - goto out_unlock; - - write_sigio_pid = run_helper_thread(write_sigio_thread, NULL, - CLONE_FILES | CLONE_VM, &stack, 0); + goto out_free; - if (write_sigio_pid < 0) - goto out_clear; + current_poll = ((struct pollfds) { .poll = p, + .used = 1, + .size = 1 }); if (write_sigio_irq(l_write_sigio_fds[0])) - goto out_kill; + goto out_clear_poll; - /* Success, finally. */ memcpy(write_sigio_fds, l_write_sigio_fds, sizeof(l_write_sigio_fds)); memcpy(sigio_private, l_sigio_private, sizeof(l_sigio_private)); - current_poll = ((struct pollfds) { .poll = p, - .used = 1, - .size = 1 }); + write_sigio_pid = run_helper_thread(write_sigio_thread, NULL, + CLONE_FILES | CLONE_VM, &stack, 0); - sigio_unlock(); - return; + if (write_sigio_pid < 0) + goto out_clear; - out_kill: - l_write_sigio_pid = write_sigio_pid; - write_sigio_pid = -1; sigio_unlock(); - /* Going to call waitpid, avoid holding the lock. */ - os_kill_process(l_write_sigio_pid, 1); - goto out_free; + return; - out_clear: +out_clear: write_sigio_pid = -1; - out_unlock: - sigio_unlock(); - out_free: + write_sigio_fds[0] = -1; + write_sigio_fds[1] = -1; + sigio_private[0] = -1; + sigio_private[1] = -1; +out_clear_poll: + current_poll = ((struct pollfds) { .poll = NULL, + .size = 0, + .used = 0 }); +out_free: kfree(p); - out_close2: + sigio_unlock(); +out_close2: close(l_sigio_private[0]); close(l_sigio_private[1]); - out_close1: +out_close1: close(l_write_sigio_fds[0]); close(l_write_sigio_fds[1]); - return; } void sigio_cleanup(void) -- cgit v1.2.3 From 22a9835c350782a5c3257343713932af3ac92ee0 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Mon, 27 Mar 2006 01:16:04 -0800 Subject: [PATCH] unify PFN_* macros Just about every architecture defines some macros to do operations on pfns. They're all virtually identical. This patch consolidates all of them. One minor glitch is that at least i386 uses them in a very skeletal header file. To keep away from #include dependency hell, I stuck the new definitions in a new, isolated header. Of all of the implementations, sh64 is the only one that varied by a bit. It used some masks to ensure that any sign-extension got ripped away before the arithmetic is done. This has been posted to that sh64 maintainers and the development list. Compiles on x86, x86_64, ia64 and ppc64. Signed-off-by: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/kernel/physmem.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch/um') diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c index 0e65340eee33..0500800df1c1 100644 --- a/arch/um/kernel/physmem.c +++ b/arch/um/kernel/physmem.c @@ -9,6 +9,7 @@ #include "linux/vmalloc.h" #include "linux/bootmem.h" #include "linux/module.h" +#include "linux/pfn.h" #include "asm/types.h" #include "asm/pgtable.h" #include "kern_util.h" @@ -316,8 +317,6 @@ void map_memory(unsigned long virt, unsigned long phys, unsigned long len, } } -#define PFN_UP(x) (((x) + PAGE_SIZE-1) >> PAGE_SHIFT) - extern int __syscall_stub_start, __binary_start; void setup_physmem(unsigned long start, unsigned long reserve_end, -- cgit v1.2.3 From e041c683412d5bf44dc2b109053e3b837b71742d Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 27 Mar 2006 01:16:30 -0800 Subject: [PATCH] Notifier chain update: API changes The kernel's implementation of notifier chains is unsafe. There is no protection against entries being added to or removed from a chain while the chain is in use. The issues were discussed in this thread: http://marc.theaimsgroup.com/?l=linux-kernel&m=113018709002036&w=2 We noticed that notifier chains in the kernel fall into two basic usage classes: "Blocking" chains are always called from a process context and the callout routines are allowed to sleep; "Atomic" chains can be called from an atomic context and the callout routines are not allowed to sleep. We decided to codify this distinction and make it part of the API. Therefore this set of patches introduces three new, parallel APIs: one for blocking notifiers, one for atomic notifiers, and one for "raw" notifiers (which is really just the old API under a new name). New kinds of data structures are used for the heads of the chains, and new routines are defined for registration, unregistration, and calling a chain. The three APIs are explained in include/linux/notifier.h and their implementation is in kernel/sys.c. With atomic and blocking chains, the implementation guarantees that the chain links will not be corrupted and that chain callers will not get messed up by entries being added or removed. For raw chains the implementation provides no guarantees at all; users of this API must provide their own protections. (The idea was that situations may come up where the assumptions of the atomic and blocking APIs are not appropriate, so it should be possible for users to handle these things in their own way.) There are some limitations, which should not be too hard to live with. For atomic/blocking chains, registration and unregistration must always be done in a process context since the chain is protected by a mutex/rwsem. Also, a callout routine for a non-raw chain must not try to register or unregister entries on its own chain. (This did happen in a couple of places and the code had to be changed to avoid it.) Since atomic chains may be called from within an NMI handler, they cannot use spinlocks for synchronization. Instead we use RCU. The overhead falls almost entirely in the unregister routine, which is okay since unregistration is much less frequent that calling a chain. Here is the list of chains that we adjusted and their classifications. None of them use the raw API, so for the moment it is only a placeholder. ATOMIC CHAINS ------------- arch/i386/kernel/traps.c: i386die_chain arch/ia64/kernel/traps.c: ia64die_chain arch/powerpc/kernel/traps.c: powerpc_die_chain arch/sparc64/kernel/traps.c: sparc64die_chain arch/x86_64/kernel/traps.c: die_chain drivers/char/ipmi/ipmi_si_intf.c: xaction_notifier_list kernel/panic.c: panic_notifier_list kernel/profile.c: task_free_notifier net/bluetooth/hci_core.c: hci_notifier net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_chain net/ipv4/netfilter/ip_conntrack_core.c: ip_conntrack_expect_chain net/ipv6/addrconf.c: inet6addr_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_chain net/netfilter/nf_conntrack_core.c: nf_conntrack_expect_chain net/netlink/af_netlink.c: netlink_chain BLOCKING CHAINS --------------- arch/powerpc/platforms/pseries/reconfig.c: pSeries_reconfig_chain arch/s390/kernel/process.c: idle_chain arch/x86_64/kernel/process.c idle_notifier drivers/base/memory.c: memory_chain drivers/cpufreq/cpufreq.c cpufreq_policy_notifier_list drivers/cpufreq/cpufreq.c cpufreq_transition_notifier_list drivers/macintosh/adb.c: adb_client_list drivers/macintosh/via-pmu.c sleep_notifier_list drivers/macintosh/via-pmu68k.c sleep_notifier_list drivers/macintosh/windfarm_core.c wf_client_list drivers/usb/core/notify.c usb_notifier_list drivers/video/fbmem.c fb_notifier_list kernel/cpu.c cpu_chain kernel/module.c module_notify_list kernel/profile.c munmap_notifier kernel/profile.c task_exit_notifier kernel/sys.c reboot_notifier_list net/core/dev.c netdev_chain net/decnet/dn_dev.c: dnaddr_chain net/ipv4/devinet.c: inetaddr_chain It's possible that some of these classifications are wrong. If they are, please let us know or submit a patch to fix them. Note that any chain that gets called very frequently should be atomic, because the rwsem read-locking used for blocking chains is very likely to incur cache misses on SMP systems. (However, if the chain's callout routines may sleep then the chain cannot be atomic.) The patch set was written by Alan Stern and Chandra Seetharaman, incorporating material written by Keith Owens and suggestions from Paul McKenney and Andrew Morton. [jes@sgi.com: restructure the notifier chain initialization macros] Signed-off-by: Alan Stern Signed-off-by: Chandra Seetharaman Signed-off-by: Jes Sorensen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/drivers/mconsole_kern.c | 3 ++- arch/um/kernel/um_arch.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'arch/um') diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 54388d10bcf9..1488816588ea 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -762,7 +762,8 @@ static struct notifier_block panic_exit_notifier = { static int add_notifier(void) { - notifier_chain_register(&panic_notifier_list, &panic_exit_notifier); + atomic_notifier_chain_register(&panic_notifier_list, + &panic_exit_notifier); return(0); } diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index bb1c87211ac1..7d51dd7201c3 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -477,7 +477,8 @@ static struct notifier_block panic_exit_notifier = { void __init setup_arch(char **cmdline_p) { - notifier_chain_register(&panic_notifier_list, &panic_exit_notifier); + atomic_notifier_chain_register(&panic_notifier_list, + &panic_exit_notifier); paging_init(); strlcpy(saved_command_line, command_line, COMMAND_LINE_SIZE); *cmdline_p = command_line; -- cgit v1.2.3 From 73b9ebfe126a4a886ee46cbab637374d7024668a Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 28 Mar 2006 16:11:07 -0800 Subject: [PATCH] pidhash: don't count idle threads fork_idle() does unhash_process() just after copy_process(). Contrary, boot_cpu's idle thread explicitely registers itself for each pid_type with nr = 0. copy_process() already checks p->pid != 0 before process_counts++, I think we can just skip attach_pid() calls and job control inits for idle threads and kill unhash_process(). We don't need to cleanup ->proc_dentry in fork_idle() because with this patch idle threads are never hashed in kernel/pid.c:pid_hash[]. We don't need to hash pid == 0 in pidmap_init(). free_pidmap() is never called with pid == 0 arg, so it will never be reused. So it is still possible to use pid == 0 in any PIDTYPE_xxx namespace from kernel/pid.c's POV. However with this patch we don't hash pid == 0 for PIDTYPE_PID case. We still have have PIDTYPE_PGID/PIDTYPE_SID entries with pid == 0: /sbin/init and kernel threads which don't call daemonize(). Signed-off-by: Oleg Nesterov Cc: "Eric W. Biederman" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/um/kernel/smp.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/um') diff --git a/arch/um/kernel/smp.c b/arch/um/kernel/smp.c index c8d8d0ac1a7f..511116aebaf7 100644 --- a/arch/um/kernel/smp.c +++ b/arch/um/kernel/smp.c @@ -143,7 +143,6 @@ void smp_prepare_cpus(unsigned int maxcpus) idle = idle_thread(cpu); init_idle(idle, cpu); - unhash_process(idle); waittime = 200000000; while (waittime-- && !cpu_isset(cpu, cpu_callin_map)) -- cgit v1.2.3