From 63fe08177f92ce21929df8af6361491b98ad12cd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 14 Apr 2009 12:01:53 +1000 Subject: md: tiny md.h cleanups - update inclusion guard and make sure it covers the whole file - remove superflous #ifdef CONFIG_BLOCK - make sure all required headers are included so that new users aren't required to include others before Signed-off-by: Christoph Hellwig Signed-off-by: NeilBrown --- drivers/md/md.h | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) (limited to 'drivers') diff --git a/drivers/md/md.h b/drivers/md/md.h index e9b7f54c24d6..8227ab909d44 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -12,10 +12,17 @@ Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ -#ifndef _MD_K_H -#define _MD_K_H - -#ifdef CONFIG_BLOCK +#ifndef _MD_MD_H +#define _MD_MD_H + +#include +#include +#include +#include +#include +#include +#include +#include #define MaxSector (~(sector_t)0) @@ -408,10 +415,6 @@ static inline void safe_put_page(struct page *p) if (p) put_page(p); } -#endif /* CONFIG_BLOCK */ -#endif - - extern int register_md_personality(struct mdk_personality *p); extern int unregister_md_personality(struct mdk_personality *p); extern mdk_thread_t * md_register_thread(void (*run) (mddev_t *mddev), @@ -434,3 +437,5 @@ extern void md_new_event(mddev_t *mddev); extern int md_allow_write(mddev_t *mddev); extern void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev); extern void md_set_array_sectors(mddev_t *mddev, sector_t array_sectors); + +#endif /* _MD_MD_H */ -- cgit v1.3-14-g43fede From 6d56e278444bc8323b1bcfcada126b8e4dbba0f4 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 14 Apr 2009 12:01:57 +1000 Subject: md: allow setting newly added device to 'in_sync' via sysfs. When adding devices to an active array via sysfs, there is currently no way to mark a device as 'in-sync' which is useful when incrementally assembling an array. So add that option. Signed-off-by: NeilBrown --- drivers/md/md.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/md/md.c b/drivers/md/md.c index ed5727c089a9..298731b8e951 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2086,6 +2086,7 @@ state_store(mdk_rdev_t *rdev, const char *buf, size_t len) * -writemostly - clears write_mostly * blocked - sets the Blocked flag * -blocked - clears the Blocked flag + * insync - sets Insync providing device isn't active */ int err = -EINVAL; if (cmd_match(buf, "faulty") && rdev->mddev->pers) { @@ -2117,6 +2118,9 @@ state_store(mdk_rdev_t *rdev, const char *buf, size_t len) set_bit(MD_RECOVERY_NEEDED, &rdev->mddev->recovery); md_wakeup_thread(rdev->mddev->thread); + err = 0; + } else if (cmd_match(buf, "insync") && rdev->raid_disk == -1) { + set_bit(In_sync, &rdev->flags); err = 0; } if (!err && rdev->sysfs_state) @@ -2190,7 +2194,7 @@ slot_store(mdk_rdev_t *rdev, const char *buf, size_t len) } else if (rdev->mddev->pers) { mdk_rdev_t *rdev2; /* Activating a spare .. or possibly reactivating - * if we every get bitmaps working here. + * if we ever get bitmaps working here. */ if (rdev->raid_disk != -1) -- cgit v1.3-14-g43fede From acb180b0e335ad88acfed6c8a33e39c05b95dc49 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Tue, 14 Apr 2009 16:28:34 +1000 Subject: md: improve usefulness and accuracy of sysfs file md/sync_completed. The sync_completed file reports how much of a resync (or recovery or reshape) has been completed. However due to the possibility of out-of-order completion of writes, it is not certain to be accurate. We have an internal value - mddev->curr_resync_completed - which is an accurate value (though it might not always be quite so uptodate). So: - make curr_resync_completed be uptodate a little more often, particularly when raid5 reshape updates status in the metadata - report curr_resync_completed in the sysfs file - allow poll/select to report all updates to md/sync_completed. This makes sync_completed completed usable by any external metadata handler that wants to record this status information in its metadata. Signed-off-by: NeilBrown --- drivers/md/bitmap.c | 1 + drivers/md/md.c | 34 ++++++++++++++++++++++------------ drivers/md/raid5.c | 4 ++++ 3 files changed, 27 insertions(+), 12 deletions(-) (limited to 'drivers') diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index f8a9f7ab2cb8..e4510c976b34 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -1479,6 +1479,7 @@ void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector) s += blocks; } bitmap->last_end_sync = jiffies; + sysfs_notify(&bitmap->mddev->kobj, NULL, "sync_completed"); } static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed) diff --git a/drivers/md/md.c b/drivers/md/md.c index 298731b8e951..7af64f3846a6 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2017,6 +2017,8 @@ repeat: clear_bit(MD_CHANGE_PENDING, &mddev->flags); spin_unlock_irq(&mddev->write_lock); wake_up(&mddev->sb_wait); + if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + sysfs_notify(&mddev->kobj, NULL, "sync_completed"); } @@ -3486,12 +3488,15 @@ sync_completed_show(mddev_t *mddev, char *page) { unsigned long max_sectors, resync; + if (!test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) + return sprintf(page, "none\n"); + if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) max_sectors = mddev->resync_max_sectors; else max_sectors = mddev->dev_sectors; - resync = (mddev->curr_resync - atomic_read(&mddev->recovery_active)); + resync = mddev->curr_resync_completed; return sprintf(page, "%lu / %lu\n", resync, max_sectors); } @@ -6338,18 +6343,12 @@ void md_do_sync(mddev_t *mddev) sector_t sectors; skipped = 0; - if (j >= mddev->resync_max) { - sysfs_notify(&mddev->kobj, NULL, "sync_completed"); - wait_event(mddev->recovery_wait, - mddev->resync_max > j - || kthread_should_stop()); - } - if (kthread_should_stop()) - goto interrupted; - if (mddev->curr_resync > mddev->curr_resync_completed && - (mddev->curr_resync - mddev->curr_resync_completed) - > (max_sectors >> 4)) { + if ((mddev->curr_resync > mddev->curr_resync_completed && + (mddev->curr_resync - mddev->curr_resync_completed) + > (max_sectors >> 4)) || + j >= mddev->resync_max + ) { /* time to update curr_resync_completed */ blk_unplug(mddev->queue); wait_event(mddev->recovery_wait, @@ -6357,7 +6356,17 @@ void md_do_sync(mddev_t *mddev) mddev->curr_resync_completed = mddev->curr_resync; set_bit(MD_CHANGE_CLEAN, &mddev->flags); + sysfs_notify(&mddev->kobj, NULL, "sync_completed"); } + + if (j >= mddev->resync_max) + wait_event(mddev->recovery_wait, + mddev->resync_max > j + || kthread_should_stop()); + + if (kthread_should_stop()) + goto interrupted; + sectors = mddev->pers->sync_request(mddev, j, &skipped, currspeed < speed_min(mddev)); if (sectors == 0) { @@ -6465,6 +6474,7 @@ void md_do_sync(mddev_t *mddev) skip: mddev->curr_resync = 0; + mddev->curr_resync_completed = 0; mddev->resync_min = 0; mddev->resync_max = MaxSector; sysfs_notify(&mddev->kobj, NULL, "sync_completed"); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 3bbc6d647044..76892ac72544 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3845,6 +3845,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped wait_event(conf->wait_for_overlap, atomic_read(&conf->reshape_stripes)==0); mddev->reshape_position = conf->reshape_progress; + mddev->curr_resync_completed = mddev->curr_resync; conf->reshape_checkpoint = jiffies; set_bit(MD_CHANGE_DEVS, &mddev->flags); md_wakeup_thread(mddev->thread); @@ -3854,6 +3855,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped conf->reshape_safe = mddev->reshape_position; spin_unlock_irq(&conf->device_lock); wake_up(&conf->wait_for_overlap); + sysfs_notify(&mddev->kobj, NULL, "sync_completed"); } if (mddev->delta_disks < 0) { @@ -3943,6 +3945,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped wait_event(conf->wait_for_overlap, atomic_read(&conf->reshape_stripes) == 0); mddev->reshape_position = conf->reshape_progress; + mddev->curr_resync_completed = mddev->curr_resync; conf->reshape_checkpoint = jiffies; set_bit(MD_CHANGE_DEVS, &mddev->flags); md_wakeup_thread(mddev->thread); @@ -3953,6 +3956,7 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped conf->reshape_safe = mddev->reshape_position; spin_unlock_irq(&conf->device_lock); wake_up(&conf->wait_for_overlap); + sysfs_notify(&mddev->kobj, NULL, "sync_completed"); } return reshape_sectors; } -- cgit v1.3-14-g43fede From c03f6a19699fce4389888a45db8245969311d868 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Fri, 17 Apr 2009 11:06:30 +1000 Subject: md: update sync_completed and reshape_position even more often. There are circumstances when a user-space process might need to "oversee" a resync/reshape process. For example when doing an in-place reshape of a raid5, it is prudent to take a backup of each section before reshaping it as this is the only way to provide safety against an unplanned shutdown (i.e. crash/power failure). The sync_max sysfs value can be used to stop the resync from advancing beyond a particular point. So user-space can: suspend IO to the first section and back it up set 'sync_max' to the end of the section wait for 'sync_completed' to reach that point resume IO on the first section and move on to the next section. However this process requires the kernel and user-space to run in lock-step which could introduce unnecessary delays. It would be better if a 'double buffered' approach could be used with userspace and kernel space working on different sections with the 'next' section always ready when the 'current' section is finished. One problem with implementing this is that sync_completed is only guaranteed to be updated when the sync process reaches sync_max. (it is updated on a time basis at other times, but it is hard to rely on that). This defeats some of the double buffering. With this patch, sync_completed (and reshape_position) get updated as the current position approaches sync_max, so there is room for userspace to advance sync_max early without losing updates. To be precise, sync_completed is updated when the current sync position reaches half way between the current value of sync_completed and the value of sync_max. This will usually be a good time for user space to update sync_max. If sync_max does not get updated, the updates to sync_completed (together with associated metadata updates) will occur at an exponentially increasing frequency which will get unreasonably fast (one update every page) immediately before the process hits sync_max and stops. So the update rate will be unreasonably fast only for an insignificant period of time. Signed-off-by: NeilBrown --- drivers/md/md.c | 3 ++- drivers/md/raid5.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/md/md.c b/drivers/md/md.c index 7af64f3846a6..612343fdde94 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6347,7 +6347,8 @@ void md_do_sync(mddev_t *mddev) if ((mddev->curr_resync > mddev->curr_resync_completed && (mddev->curr_resync - mddev->curr_resync_completed) > (max_sectors >> 4)) || - j >= mddev->resync_max + (j - mddev->curr_resync_completed)*2 + >= mddev->resync_max - mddev->curr_resync_completed ) { /* time to update curr_resync_completed */ blk_unplug(mddev->queue); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 76892ac72544..4616bc3a6e71 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3940,7 +3940,8 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped * then we need to write out the superblock. */ sector_nr += reshape_sectors; - if (sector_nr >= mddev->resync_max) { + if ((sector_nr - mddev->curr_resync_completed) * 2 + >= mddev->resync_max - mddev->curr_resync_completed) { /* Cannot proceed until we've updated the superblock... */ wait_event(conf->wait_for_overlap, atomic_read(&conf->reshape_stripes) == 0); -- cgit v1.3-14-g43fede From 88df781afb788fa588dbf2e77f205214022a8893 Mon Sep 17 00:00:00 2001 From: Matias Zabaljauregui Date: Wed, 8 Apr 2009 17:58:39 -0300 Subject: lguest: fix crash on vmlinux images Typical message: 'lguest: unhandled trap 6 at 0x418726 (0x0)' vmlinux guests were broken by 4cd8b5e2a159f18a1507f1187b44a1acbfa6341b 'lguest: use KVM hypercalls', which rewrites guest text from kvm hypercalls to trap 31. The Launcher mmaps the kernel image. The Guest executes and immediately faults in the first text page (read-only). Then it hits a hypercall, and we rewrite that hypercall, causing a copy-on-write. But the Guest pagetables still refer to the old page: we fault again, but as Host we see the hypercall already rewritten, and pass the fault back to the Guest. The Guest hasn't set up an IDT yet, so we kill it. This doesn't happen with bzImages: they unpack themselves and so the text pages are already read-write. Signed-off-by: Rusty Russell Tested-by: Patrick McHardy --- drivers/lguest/x86/core.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'drivers') diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c index a6b717644be0..d6d7ac0982ab 100644 --- a/drivers/lguest/x86/core.c +++ b/drivers/lguest/x86/core.c @@ -324,6 +324,11 @@ static void rewrite_hypercall(struct lg_cpu *cpu) u8 insn[3] = {0xcd, 0x1f, 0x90}; __lgwrite(cpu, guest_pa(cpu, cpu->regs->eip), insn, sizeof(insn)); + /* The above write might have caused a copy of that page to be made + * (if it was read-only). We need to make sure the Guest has + * up-to-date pagetables. As this doesn't happen often, we can just + * drop them all. */ + guest_pagetable_clear_all(cpu); } static bool is_hypercall(struct lg_cpu *cpu) -- cgit v1.3-14-g43fede From a489f0b555b753f9df8ddc24c7e74f657ef7ee7b Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Sun, 19 Apr 2009 23:14:00 -0600 Subject: lguest: fix guest crash on non-linear addresses in gdt pvops Fixes guest crash 'lguest: bad read address 0x4800000 len 256' The new per-cpu allocator ends up handing a non-linear address to write_gdt_entry. We do __pa() on it, and hand it to the host, which kills us. I've long wanted to make the hypercall "LOAD_GDT_ENTRY" to match the IDT code, but had no pressing reason until now. Signed-off-by: Rusty Russell Cc: lguest@ozlabs.org --- arch/x86/include/asm/lguest_hcall.h | 2 +- arch/x86/lguest/boot.c | 16 +++++++++------- drivers/lguest/lg.h | 3 ++- drivers/lguest/segments.c | 13 +++++++------ drivers/lguest/x86/core.c | 4 ++-- 5 files changed, 21 insertions(+), 17 deletions(-) (limited to 'drivers') diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h index 0f4ee7148afe..faae1996487b 100644 --- a/arch/x86/include/asm/lguest_hcall.h +++ b/arch/x86/include/asm/lguest_hcall.h @@ -5,7 +5,6 @@ #define LHCALL_FLUSH_ASYNC 0 #define LHCALL_LGUEST_INIT 1 #define LHCALL_SHUTDOWN 2 -#define LHCALL_LOAD_GDT 3 #define LHCALL_NEW_PGTABLE 4 #define LHCALL_FLUSH_TLB 5 #define LHCALL_LOAD_IDT_ENTRY 6 @@ -17,6 +16,7 @@ #define LHCALL_SET_PMD 15 #define LHCALL_LOAD_TLS 16 #define LHCALL_NOTIFY 17 +#define LHCALL_LOAD_GDT_ENTRY 18 #define LGUEST_TRAP_ENTRY 0x1F diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index e94a11e42f98..a2085368a3dc 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -273,15 +273,15 @@ static void lguest_load_idt(const struct desc_ptr *desc) * controls the entire thing and the Guest asks it to make changes using the * LOAD_GDT hypercall. * - * This is the opposite of the IDT code where we have a LOAD_IDT_ENTRY - * hypercall and use that repeatedly to load a new IDT. I don't think it - * really matters, but wouldn't it be nice if they were the same? Wouldn't - * it be even better if you were the one to send the patch to fix it? + * This is the exactly like the IDT code. */ static void lguest_load_gdt(const struct desc_ptr *desc) { - BUG_ON((desc->size + 1) / 8 != GDT_ENTRIES); - kvm_hypercall2(LHCALL_LOAD_GDT, __pa(desc->address), GDT_ENTRIES); + unsigned int i; + struct desc_struct *gdt = (void *)desc->address; + + for (i = 0; i < (desc->size+1)/8; i++) + kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, i, gdt[i].a, gdt[i].b); } /* For a single GDT entry which changes, we do the lazy thing: alter our GDT, @@ -291,7 +291,9 @@ static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum, const void *desc, int type) { native_write_gdt_entry(dt, entrynum, desc, type); - kvm_hypercall2(LHCALL_LOAD_GDT, __pa(dt), GDT_ENTRIES); + /* Tell Host about this new entry. */ + kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, entrynum, + dt[entrynum].a, dt[entrynum].b); } /* OK, I lied. There are three "thread local storage" GDT entries which change diff --git a/drivers/lguest/lg.h b/drivers/lguest/lg.h index ac8a4a3741b8..af92a176697f 100644 --- a/drivers/lguest/lg.h +++ b/drivers/lguest/lg.h @@ -158,7 +158,8 @@ void free_interrupts(void); /* segments.c: */ void setup_default_gdt_entries(struct lguest_ro_state *state); void setup_guest_gdt(struct lg_cpu *cpu); -void load_guest_gdt(struct lg_cpu *cpu, unsigned long table, u32 num); +void load_guest_gdt_entry(struct lg_cpu *cpu, unsigned int i, + u32 low, u32 hi); void guest_load_tls(struct lg_cpu *cpu, unsigned long tls_array); void copy_gdt(const struct lg_cpu *cpu, struct desc_struct *gdt); void copy_gdt_tls(const struct lg_cpu *cpu, struct desc_struct *gdt); diff --git a/drivers/lguest/segments.c b/drivers/lguest/segments.c index 4f15439b7f12..7ede64ffeef9 100644 --- a/drivers/lguest/segments.c +++ b/drivers/lguest/segments.c @@ -144,18 +144,19 @@ void copy_gdt(const struct lg_cpu *cpu, struct desc_struct *gdt) gdt[i] = cpu->arch.gdt[i]; } -/*H:620 This is where the Guest asks us to load a new GDT (LHCALL_LOAD_GDT). - * We copy it from the Guest and tweak the entries. */ -void load_guest_gdt(struct lg_cpu *cpu, unsigned long table, u32 num) +/*H:620 This is where the Guest asks us to load a new GDT entry + * (LHCALL_LOAD_GDT_ENTRY). We tweak the entry and copy it in. */ +void load_guest_gdt_entry(struct lg_cpu *cpu, u32 num, u32 lo, u32 hi) { /* We assume the Guest has the same number of GDT entries as the * Host, otherwise we'd have to dynamically allocate the Guest GDT. */ if (num > ARRAY_SIZE(cpu->arch.gdt)) kill_guest(cpu, "too many gdt entries %i", num); - /* We read the whole thing in, then fix it up. */ - __lgread(cpu, cpu->arch.gdt, table, num * sizeof(cpu->arch.gdt[0])); - fixup_gdt_table(cpu, 0, ARRAY_SIZE(cpu->arch.gdt)); + /* Set it up, then fix it. */ + cpu->arch.gdt[num].a = lo; + cpu->arch.gdt[num].b = hi; + fixup_gdt_table(cpu, num, num+1); /* Mark that the GDT changed so the core knows it has to copy it again, * even if the Guest is run on the same CPU. */ cpu->changed |= CHANGED_GDT; diff --git a/drivers/lguest/x86/core.c b/drivers/lguest/x86/core.c index d6d7ac0982ab..1a83910f674f 100644 --- a/drivers/lguest/x86/core.c +++ b/drivers/lguest/x86/core.c @@ -568,8 +568,8 @@ void __exit lguest_arch_host_fini(void) int lguest_arch_do_hcall(struct lg_cpu *cpu, struct hcall_args *args) { switch (args->arg0) { - case LHCALL_LOAD_GDT: - load_guest_gdt(cpu, args->arg1, args->arg2); + case LHCALL_LOAD_GDT_ENTRY: + load_guest_gdt_entry(cpu, args->arg1, args->arg2, args->arg3); break; case LHCALL_LOAD_IDT_ENTRY: load_guest_idt_entry(cpu, args->arg1, args->arg2, args->arg3); -- cgit v1.3-14-g43fede From 84a139a985300901dfad99bd93c7345d180af860 Mon Sep 17 00:00:00 2001 From: Marcelo Tosatti Date: Thu, 16 Apr 2009 21:14:04 -0300 Subject: virtio: fix suspend when using virtio_balloon Break out of wait_event_interruptible() if freezing has been requested, in the vballoon thread. Without this change vballoon refuses to stop and the system can't suspend. Signed-off-by: Marcelo Tosatti Signed-off-by: Rusty Russell Cc: stable@kernel.org --- drivers/virtio/virtio_balloon.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 59268266b79a..9c76a061a04d 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -190,7 +190,8 @@ static int balloon(void *_vballoon) try_to_freeze(); wait_event_interruptible(vb->config_change, (diff = towards_target(vb)) != 0 - || kthread_should_stop()); + || kthread_should_stop() + || freezing(current)); if (diff > 0) fill_balloon(vb, diff); else if (diff < 0) -- cgit v1.3-14-g43fede From c0b7988200a82290287c6f4cd49585007f73175a Mon Sep 17 00:00:00 2001 From: Samuel Thibault Date: Sat, 18 Apr 2009 22:17:17 +0200 Subject: Revert "console ASCII glyph 1:1 mapping" This reverts commit 1c55f18717304100a5f624c923f7cb6511b4116d. Ingo Brueckl was assuming that reverting to 1:1 mapping for chars >= 128 was not useful, but it happens to be: due to the limitations of the Linux console, when a blind user wants to read BIG5 on it, he has no other way than loading a font without SFM and let the 1:1 mapping permit the screen reader to get the BIG5 encoding. Signed-off-by: Samuel Thibault Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- drivers/char/vt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/char/vt.c b/drivers/char/vt.c index 2c1d133819b5..08151d4de489 100644 --- a/drivers/char/vt.c +++ b/drivers/char/vt.c @@ -2274,7 +2274,7 @@ rescan_last_byte: continue; /* nothing to display */ } /* Glyph not found */ - if ((!(vc->vc_utf && !vc->vc_disp_ctrl) && c < 128) && !(c & ~charmask)) { + if ((!(vc->vc_utf && !vc->vc_disp_ctrl) || c < 128) && !(c & ~charmask)) { /* In legacy mode use the glyph we get by a 1:1 mapping. This would make absolutely no sense with Unicode in mind, but do this for ASCII characters since a font may lack -- cgit v1.3-14-g43fede From 6a7c7eaf71b636f197d73b381a2ab729ebdcfb2e Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 19 Apr 2009 20:08:42 +0200 Subject: PM/Suspend: Introduce two new platform callbacks to avoid breakage Commit 900af0d973856d6feb6fc088c2d0d3fde57707d3 (PM: Change suspend code ordering) changed the ordering of suspend code in such a way that the platform .prepare() callback is now executed after the device drivers' late suspend callbacks have run. Unfortunately, this turns out to break ARM platforms that need to talk via I2C to power control devices during the .prepare() callback. For this reason introduce two new platform suspend callbacks, .prepare_late() and .wake(), that will be called just prior to disabling non-boot CPUs and right after bringing them back on line, respectively, and use them instead of .prepare() and .finish() for ACPI suspend. Make the PM core execute the .prepare() and .finish() platform suspend callbacks where they were executed previously (that is, right after calling the regular suspend methods provided by device drivers and right before executing their regular resume methods, respectively). It is not necessary to make analogous changes to the hibernation code and data structures at the moment, because they are only used by ACPI platforms. Signed-off-by: Rafael J. Wysocki Reported-by: Russell King Acked-by: Len Brown --- drivers/acpi/sleep.c | 8 ++++---- include/linux/suspend.h | 36 ++++++++++++++++++++++++++---------- kernel/power/main.c | 24 +++++++++++++++++------- 3 files changed, 47 insertions(+), 21 deletions(-) (limited to 'drivers') diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 779e4e500df4..d060e6fd7fd5 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -300,9 +300,9 @@ static int acpi_suspend_state_valid(suspend_state_t pm_state) static struct platform_suspend_ops acpi_suspend_ops = { .valid = acpi_suspend_state_valid, .begin = acpi_suspend_begin, - .prepare = acpi_pm_prepare, + .prepare_late = acpi_pm_prepare, .enter = acpi_suspend_enter, - .finish = acpi_pm_finish, + .wake = acpi_pm_finish, .end = acpi_pm_end, }; @@ -328,9 +328,9 @@ static int acpi_suspend_begin_old(suspend_state_t pm_state) static struct platform_suspend_ops acpi_suspend_ops_old = { .valid = acpi_suspend_state_valid, .begin = acpi_suspend_begin_old, - .prepare = acpi_pm_disable_gpes, + .prepare_late = acpi_pm_disable_gpes, .enter = acpi_suspend_enter, - .finish = acpi_pm_finish, + .wake = acpi_pm_finish, .end = acpi_pm_end, .recover = acpi_pm_finish, }; diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 3e3a4364cbff..795032edfc46 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -58,10 +58,17 @@ typedef int __bitwise suspend_state_t; * by @begin(). * @prepare() is called right after devices have been suspended (ie. the * appropriate .suspend() method has been executed for each device) and - * before the nonboot CPUs are disabled (it is executed with IRQs enabled). - * This callback is optional. It returns 0 on success or a negative - * error code otherwise, in which case the system cannot enter the desired - * sleep state (@enter() and @finish() will not be called in that case). + * before device drivers' late suspend callbacks are executed. It returns + * 0 on success or a negative error code otherwise, in which case the + * system cannot enter the desired sleep state (@prepare_late(), @enter(), + * @wake(), and @finish() will not be called in that case). + * + * @prepare_late: Finish preparing the platform for entering the system sleep + * state indicated by @begin(). + * @prepare_late is called before disabling nonboot CPUs and after + * device drivers' late suspend callbacks have been executed. It returns + * 0 on success or a negative error code otherwise, in which case the + * system cannot enter the desired sleep state (@enter() and @wake()). * * @enter: Enter the system sleep state indicated by @begin() or represented by * the argument if @begin() is not implemented. @@ -69,19 +76,26 @@ typedef int __bitwise suspend_state_t; * error code otherwise, in which case the system cannot enter the desired * sleep state. * - * @finish: Called when the system has just left a sleep state, right after - * the nonboot CPUs have been enabled and before devices are resumed (it is - * executed with IRQs enabled). + * @wake: Called when the system has just left a sleep state, right after + * the nonboot CPUs have been enabled and before device drivers' early + * resume callbacks are executed. + * This callback is optional, but should be implemented by the platforms + * that implement @prepare_late(). If implemented, it is always called + * after @enter(), even if @enter() fails. + * + * @finish: Finish wake-up of the platform. + * @finish is called right prior to calling device drivers' regular suspend + * callbacks. * This callback is optional, but should be implemented by the platforms * that implement @prepare(). If implemented, it is always called after - * @enter() (even if @enter() fails). + * @enter() and @wake(), if implemented, even if any of them fails. * * @end: Called by the PM core right after resuming devices, to indicate to * the platform that the system has returned to the working state or * the transition to the sleep state has been aborted. * This callback is optional, but should be implemented by the platforms - * that implement @begin(), but platforms implementing @begin() should - * also provide a @end() which cleans up transitions aborted before + * that implement @begin(). Accordingly, platforms implementing @begin() + * should also provide a @end() which cleans up transitions aborted before * @enter(). * * @recover: Recover the platform from a suspend failure. @@ -93,7 +107,9 @@ struct platform_suspend_ops { int (*valid)(suspend_state_t state); int (*begin)(suspend_state_t state); int (*prepare)(void); + int (*prepare_late)(void); int (*enter)(suspend_state_t state); + void (*wake)(void); void (*finish)(void); void (*end)(void); void (*recover)(void); diff --git a/kernel/power/main.c b/kernel/power/main.c index f172f41858bb..f99ed6a75eac 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -291,20 +291,26 @@ static int suspend_enter(suspend_state_t state) device_pm_lock(); + if (suspend_ops->prepare) { + error = suspend_ops->prepare(); + if (error) + goto Done; + } + error = device_power_down(PMSG_SUSPEND); if (error) { printk(KERN_ERR "PM: Some devices failed to power down\n"); - goto Done; + goto Platfrom_finish; } - if (suspend_ops->prepare) { - error = suspend_ops->prepare(); + if (suspend_ops->prepare_late) { + error = suspend_ops->prepare_late(); if (error) goto Power_up_devices; } if (suspend_test(TEST_PLATFORM)) - goto Platfrom_finish; + goto Platform_wake; error = disable_nonboot_cpus(); if (error || suspend_test(TEST_CPUS)) @@ -326,13 +332,17 @@ static int suspend_enter(suspend_state_t state) Enable_cpus: enable_nonboot_cpus(); - Platfrom_finish: - if (suspend_ops->finish) - suspend_ops->finish(); + Platform_wake: + if (suspend_ops->wake) + suspend_ops->wake(); Power_up_devices: device_power_up(PMSG_RESUME); + Platfrom_finish: + if (suspend_ops->finish) + suspend_ops->finish(); + Done: device_pm_unlock(); -- cgit v1.3-14-g43fede From d9c6f546469f33f9aa48ae5991c33da8cd535b37 Mon Sep 17 00:00:00 2001 From: Roel Kluin Date: Thu, 16 Apr 2009 22:57:46 +0200 Subject: drm: count reaches -1 With a postfix decrement in the test count will reach -1 rather than 0, subsequent tests fail. Signed-off-by: Roel Kluin Signed-off-by: Dave Airlie --- drivers/gpu/drm/via/via_dma.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) (limited to 'drivers') diff --git a/drivers/gpu/drm/via/via_dma.c b/drivers/gpu/drm/via/via_dma.c index 7a339dba6a69..bfb92d283260 100644 --- a/drivers/gpu/drm/via/via_dma.c +++ b/drivers/gpu/drm/via/via_dma.c @@ -481,11 +481,13 @@ static int via_wait_idle(drm_via_private_t * dev_priv) { int count = 10000000; - while (!(VIA_READ(VIA_REG_STATUS) & VIA_VR_QUEUE_BUSY) && count--); + while (!(VIA_READ(VIA_REG_STATUS) & VIA_VR_QUEUE_BUSY) && --count) + ; - while (count-- && (VIA_READ(VIA_REG_STATUS) & + while (count && (VIA_READ(VIA_REG_STATUS) & (VIA_CMD_RGTR_BUSY | VIA_2D_ENG_BUSY | - VIA_3D_ENG_BUSY))) ; + VIA_3D_ENG_BUSY))) + --count; return count; } @@ -705,7 +707,7 @@ static int via_cmdbuf_size(struct drm_device *dev, void *data, struct drm_file * switch (d_siz->func) { case VIA_CMDBUF_SPACE: while (((tmp_size = via_cmdbuf_space(dev_priv)) < d_siz->size) - && count--) { + && --count) { if (!d_siz->wait) { break; } @@ -717,7 +719,7 @@ static int via_cmdbuf_size(struct drm_device *dev, void *data, struct drm_file * break; case VIA_CMDBUF_LAG: while (((tmp_size = via_cmdbuf_lag(dev_priv)) > d_siz->size) - && count--) { + && --count) { if (!d_siz->wait) { break; } -- cgit v1.3-14-g43fede From 77d26dc9b9805f322f5a1f6e559b18ad66205bd9 Mon Sep 17 00:00:00 2001 From: Ma Ling Date: Thu, 16 Apr 2009 17:51:25 +0800 Subject: drm: clean dirty memory after device release In current code we register/unregister connector object by drm_sysfs_connector_add/remove function. However under some cases, we need to dynamically register or unregister device multiple times, so we have to go through register -> unregister ->register routine. Because after device_unregister function our memory is dirty, we need to do clean operation in order to re-register the device, otherwise the system will crash. The patch intends to clean device after device release. Signed-off-by: Ma Ling Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_sysfs.c | 1 + 1 file changed, 1 insertion(+) (limited to 'drivers') diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c index bc0c6849360c..022876ae34f0 100644 --- a/drivers/gpu/drm/drm_sysfs.c +++ b/drivers/gpu/drm/drm_sysfs.c @@ -132,6 +132,7 @@ void drm_sysfs_destroy(void) */ static void drm_sysfs_device_release(struct device *dev) { + memset(dev, 0, sizeof(struct device)); return; } -- cgit v1.3-14-g43fede From 6b0084266c1d4917ad9259759a1e7bd623cb3888 Mon Sep 17 00:00:00 2001 From: Jonas Bonn Date: Thu, 16 Apr 2009 09:00:02 +0200 Subject: drm: set/clear is_master when master changed The variable is_master is being used to track the drm_file that is currently master, so its value needs to be updated accordingly when the master is changed. Signed-off-by: Jonas Bonn Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_stub.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c index d009661781bc..1b3e0ff57b45 100644 --- a/drivers/gpu/drm/drm_stub.c +++ b/drivers/gpu/drm/drm_stub.c @@ -159,6 +159,9 @@ void drm_master_put(struct drm_master **master) int drm_setmaster_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { + if (file_priv->is_master) + return 0; + if (file_priv->minor->master && file_priv->minor->master != file_priv->master) return -EINVAL; @@ -169,6 +172,7 @@ int drm_setmaster_ioctl(struct drm_device *dev, void *data, file_priv->minor->master != file_priv->master) { mutex_lock(&dev->struct_mutex); file_priv->minor->master = drm_master_get(file_priv->master); + file_priv->is_master = 1; mutex_unlock(&dev->struct_mutex); } @@ -178,10 +182,12 @@ int drm_setmaster_ioctl(struct drm_device *dev, void *data, int drm_dropmaster_ioctl(struct drm_device *dev, void *data, struct drm_file *file_priv) { - if (!file_priv->master) + if (!file_priv->is_master) return -EINVAL; + mutex_lock(&dev->struct_mutex); drm_master_put(&file_priv->minor->master); + file_priv->is_master = 0; mutex_unlock(&dev->struct_mutex); return 0; } -- cgit v1.3-14-g43fede From 07f1c7a7f6736d9ec2eba57d209c5f48888d841e Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Mon, 20 Apr 2009 09:32:50 +1000 Subject: drm: check for minor master before allowing drop master. When fast user switching a lot eventually we get to the point, where we were checking for the wrong thing in this function. Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_stub.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'drivers') diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c index 1b3e0ff57b45..ef878615c49f 100644 --- a/drivers/gpu/drm/drm_stub.c +++ b/drivers/gpu/drm/drm_stub.c @@ -185,6 +185,9 @@ int drm_dropmaster_ioctl(struct drm_device *dev, void *data, if (!file_priv->is_master) return -EINVAL; + if (!file_priv->minor->master) + return -EINVAL; + mutex_lock(&dev->struct_mutex); drm_master_put(&file_priv->minor->master); file_priv->is_master = 0; -- cgit v1.3-14-g43fede From 59de2bebabc5027f93df999d59cc65df591c3e6e Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Mon, 20 Apr 2009 10:08:35 +1000 Subject: agp: zero pages before sending to userspace AGP pages might be mapped into userspace finally, so the pages should be set to zero before userspace can use it. Otherwise there is potential information leakage. Signed-off-by: Shaohua Li Signed-off-by: Dave Airlie --- drivers/char/agp/generic.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/char/agp/generic.c b/drivers/char/agp/generic.c index 10d6cbd7c05e..2224b762b7fb 100644 --- a/drivers/char/agp/generic.c +++ b/drivers/char/agp/generic.c @@ -1226,7 +1226,7 @@ int agp_generic_alloc_pages(struct agp_bridge_data *bridge, struct agp_memory *m int i, ret = -ENOMEM; for (i = 0; i < num_pages; i++) { - page = alloc_page(GFP_KERNEL | GFP_DMA32); + page = alloc_page(GFP_KERNEL | GFP_DMA32 | __GFP_ZERO); /* agp_free_memory() needs gart address */ if (page == NULL) goto out; @@ -1257,7 +1257,7 @@ void *agp_generic_alloc_page(struct agp_bridge_data *bridge) { struct page * page; - page = alloc_page(GFP_KERNEL | GFP_DMA32); + page = alloc_page(GFP_KERNEL | GFP_DMA32 | __GFP_ZERO); if (page == NULL) return NULL; -- cgit v1.3-14-g43fede From 1f59390339f263c0fe7908fbe54466dbf3a64b58 Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Mon, 20 Apr 2009 11:50:24 +1000 Subject: md: support bitmaps on RAID10 arrays larger then 2 terabytes .. and other arrays with components larger than 2 terabytes. We use a "long" rather than a "sector_t" in part of the bitmap size calculations, which is sad. Reported-by: "Mario 'BitKoenig' Holbe" Signed-off-by: NeilBrown --- drivers/md/bitmap.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'drivers') diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index e4510c976b34..1fb91edc7de2 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -1590,7 +1590,7 @@ void bitmap_destroy(mddev_t *mddev) int bitmap_create(mddev_t *mddev) { struct bitmap *bitmap; - unsigned long blocks = mddev->resync_max_sectors; + sector_t blocks = mddev->resync_max_sectors; unsigned long chunks; unsigned long pages; struct file *file = mddev->bitmap_file; @@ -1632,8 +1632,8 @@ int bitmap_create(mddev_t *mddev) bitmap->chunkshift = ffz(~bitmap->chunksize); /* now that chunksize and chunkshift are set, we can use these macros */ - chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) / - CHUNK_BLOCK_RATIO(bitmap); + chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) >> + CHUNK_BLOCK_SHIFT(bitmap); pages = (chunks + PAGE_COUNTER_RATIO - 1) / PAGE_COUNTER_RATIO; BUG_ON(!pages); -- cgit v1.3-14-g43fede From 8a577ffc75d9194fe8cdb7479236f2081c26ca1f Mon Sep 17 00:00:00 2001 From: Kay Sievers Date: Sat, 18 Apr 2009 15:05:45 -0700 Subject: driver: dont update dev_name via device_add path notice one system /proc/iomem some entries missed the name for pci_devices it turns that dev->dev.kobj name is changed after device_add. for pci code: via acpi_pci_root_driver.ops.add (aka acpi_pci_root_add) ==> pci_acpi_scan_root is used to scan pci bus/device, and at the same time we read the resource for pci_dev in the pci_read_bases, we have res->name = pci_name(pci_dev); pci_name is calling dev_name. later via acpi_pci_root_driver.ops.start (aka acpi_pci_root_start) ==> pci_bus_add_device to add all pci_dev in kobj tree. pci_bus_add_device will call device_add. actually in device_add /* first, register with generic layer. */ error = kobject_add(&dev->kobj, dev->kobj.parent, "%s", dev_name(dev)); if (error) goto Error; will get one new name for that kobj, old name is freed. [Impact: fix corrupted names in /proc/iomem ] Signed-off-by: Yinghai Lu Signed-off-by: Linus Torvalds --- drivers/base/core.c | 3 ++- lib/kobject.c | 3 +++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/base/core.c b/drivers/base/core.c index d230ff4b3eec..4aa527b8a913 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -891,7 +891,8 @@ int device_add(struct device *dev) set_dev_node(dev, dev_to_node(parent)); /* first, register with generic layer. */ - error = kobject_add(&dev->kobj, dev->kobj.parent, "%s", dev_name(dev)); + /* we require the name to be set before, and pass NULL */ + error = kobject_add(&dev->kobj, dev->kobj.parent, NULL); if (error) goto Error; diff --git a/lib/kobject.c b/lib/kobject.c index a6dec32f2ddd..bacf6fe4f7a0 100644 --- a/lib/kobject.c +++ b/lib/kobject.c @@ -218,6 +218,9 @@ int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, const char *old_name = kobj->name; char *s; + if (kobj->name && !fmt) + return 0; + kobj->name = kvasprintf(GFP_KERNEL, fmt, vargs); if (!kobj->name) return -ENOMEM; -- cgit v1.3-14-g43fede