From 33b6c7765f0c20da9d61246a095acad0f98a1da5 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 25 Feb 2014 15:01:39 -0800 Subject: mm, hwpoison: release page on PageHWPoison() in __do_fault() It seems we forget to release page after detecting HW error. Signed-off-by: Kirill A. Shutemov Cc: Mel Gorman Cc: Rik van Riel Cc: Andi Kleen Cc: Matthew Wilcox Cc: Dave Hansen Cc: Naoya Horiguchi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 1 + 1 file changed, 1 insertion(+) diff --git a/mm/memory.c b/mm/memory.c index be6a0c0d4ae..5f2001a7ab3 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3348,6 +3348,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (ret & VM_FAULT_LOCKED) unlock_page(vmf.page); ret = VM_FAULT_HWPOISON; + page_cache_release(vmf.page); goto uncharge_out; } -- cgit v1.2.3-70-g09d2 From ff3a2b73b7d6d79038512d60690de18cd7aa4e21 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 25 Feb 2014 15:01:40 -0800 Subject: drivers/iommu/omap-iommu-debug.c: fix decimal permissions These should have been octal. Signed-off-by: Joe Perches Cc: Joerg Roedel Cc: Hiroshi DOYU Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/iommu/omap-iommu-debug.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/iommu/omap-iommu-debug.c b/drivers/iommu/omap-iommu-debug.c index d97fbe4fb9b..80fffba7f12 100644 --- a/drivers/iommu/omap-iommu-debug.c +++ b/drivers/iommu/omap-iommu-debug.c @@ -354,8 +354,8 @@ DEBUG_FOPS(mem); return -ENOMEM; \ } -#define DEBUG_ADD_FILE(name) __DEBUG_ADD_FILE(name, 600) -#define DEBUG_ADD_FILE_RO(name) __DEBUG_ADD_FILE(name, 400) +#define DEBUG_ADD_FILE(name) __DEBUG_ADD_FILE(name, 0600) +#define DEBUG_ADD_FILE_RO(name) __DEBUG_ADD_FILE(name, 0400) static int iommu_debug_register(struct device *dev, void *data) { -- cgit v1.2.3-70-g09d2 From 01412886b735ef241f9a41adf9f707ce1522eb61 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 25 Feb 2014 15:01:41 -0800 Subject: drivers/fmc/fmc-write-eeprom.c: fix decimal permissions This 444 should have been octal. Signed-off-by: Joe Perches Cc: Alessandro Rubini Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/fmc/fmc-write-eeprom.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/fmc/fmc-write-eeprom.c b/drivers/fmc/fmc-write-eeprom.c index ee5b4790413..9bb2cbd5c9f 100644 --- a/drivers/fmc/fmc-write-eeprom.c +++ b/drivers/fmc/fmc-write-eeprom.c @@ -27,7 +27,7 @@ FMC_PARAM_BUSID(fwe_drv); /* The "file=" is like the generic "gateware=" used elsewhere */ static char *fwe_file[FMC_MAX_CARDS]; static int fwe_file_n; -module_param_array_named(file, fwe_file, charp, &fwe_file_n, 444); +module_param_array_named(file, fwe_file, charp, &fwe_file_n, 0444); static int fwe_run_tlv(struct fmc_device *fmc, const struct firmware *fw, int write) -- cgit v1.2.3-70-g09d2 From 9845cbbd113fbb5b769a45d8e88dc47bc12df4e0 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Tue, 25 Feb 2014 15:01:42 -0800 Subject: mm, thp: fix infinite loop on memcg OOM Masayoshi Mizuma reported a bug with the hang of an application under the memcg limit. It happens on write-protection fault to huge zero page If we successfully allocate a huge page to replace zero page but hit the memcg limit we need to split the zero page with split_huge_page_pmd() and fallback to small pages. The other part of the problem is that VM_FAULT_OOM has special meaning in do_huge_pmd_wp_page() context. __handle_mm_fault() expects the page to be split if it sees VM_FAULT_OOM and it will will retry page fault handling. This causes an infinite loop if the page was not split. do_huge_pmd_wp_zero_page_fallback() can return VM_FAULT_OOM if it failed to allocate one small page, so fallback to small pages will not help. The solution for this part is to replace VM_FAULT_OOM with VM_FAULT_FALLBACK is fallback required. Signed-off-by: Kirill A. Shutemov Reported-by: Masayoshi Mizuma Reviewed-by: Michal Hocko Cc: Johannes Weiner Cc: Andrea Arcangeli Cc: David Rientjes Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 9 ++++++--- mm/memory.c | 14 +++----------- 2 files changed, 9 insertions(+), 14 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index da23eb96779..4df39b1bde9 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1166,8 +1166,10 @@ alloc: } else { ret = do_huge_pmd_wp_page_fallback(mm, vma, address, pmd, orig_pmd, page, haddr); - if (ret & VM_FAULT_OOM) + if (ret & VM_FAULT_OOM) { split_huge_page(page); + ret |= VM_FAULT_FALLBACK; + } put_page(page); } count_vm_event(THP_FAULT_FALLBACK); @@ -1179,9 +1181,10 @@ alloc: if (page) { split_huge_page(page); put_page(page); - } + } else + split_huge_page_pmd(vma, address, pmd); + ret |= VM_FAULT_FALLBACK; count_vm_event(THP_FAULT_FALLBACK); - ret |= VM_FAULT_OOM; goto out; } diff --git a/mm/memory.c b/mm/memory.c index 5f2001a7ab3..22dfa617bdd 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3704,7 +3704,6 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(is_vm_hugetlb_page(vma))) return hugetlb_fault(mm, vma, address, flags); -retry: pgd = pgd_offset(mm, address); pud = pud_alloc(mm, pgd, address); if (!pud) @@ -3742,20 +3741,13 @@ retry: if (dirty && !pmd_write(orig_pmd)) { ret = do_huge_pmd_wp_page(mm, vma, address, pmd, orig_pmd); - /* - * If COW results in an oom, the huge pmd will - * have been split, so retry the fault on the - * pte for a smaller charge. - */ - if (unlikely(ret & VM_FAULT_OOM)) - goto retry; - return ret; + if (!(ret & VM_FAULT_FALLBACK)) + return ret; } else { huge_pmd_set_accessed(mm, vma, address, pmd, orig_pmd, dirty); + return 0; } - - return 0; } } -- cgit v1.2.3-70-g09d2 From 08088cb9ac0a9c28d4cf3efa4f6848a9b053ccfd Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 25 Feb 2014 15:01:44 -0800 Subject: memcg: change oom_info_lock to mutex Kirill has reported the following: Task in /test killed as a result of limit of /test memory: usage 10240kB, limit 10240kB, failcnt 51 memory+swap: usage 10240kB, limit 10240kB, failcnt 0 kmem: usage 0kB, limit 18014398509481983kB, failcnt 0 Memory cgroup stats for /test: BUG: sleeping function called from invalid context at kernel/cpu.c:68 in_atomic(): 1, irqs_disabled(): 0, pid: 66, name: memcg_test 2 locks held by memcg_test/66: #0: (memcg_oom_lock#2){+.+...}, at: [] pagefault_out_of_memory+0x14/0x90 #1: (oom_info_lock){+.+...}, at: [] mem_cgroup_print_oom_info+0x2a/0x390 CPU: 2 PID: 66 Comm: memcg_test Not tainted 3.14.0-rc1-dirty #745 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS Bochs 01/01/2011 Call Trace: __might_sleep+0x16a/0x210 get_online_cpus+0x1c/0x60 mem_cgroup_read_stat+0x27/0xb0 mem_cgroup_print_oom_info+0x260/0x390 dump_header+0x88/0x251 ? trace_hardirqs_on+0xd/0x10 oom_kill_process+0x258/0x3d0 mem_cgroup_oom_synchronize+0x656/0x6c0 ? mem_cgroup_charge_common+0xd0/0xd0 pagefault_out_of_memory+0x14/0x90 mm_fault_error+0x91/0x189 __do_page_fault+0x48e/0x580 do_page_fault+0xe/0x10 page_fault+0x22/0x30 which complains that mem_cgroup_read_stat cannot be called from an atomic context but mem_cgroup_print_oom_info takes a spinlock. Change oom_info_lock to a mutex. This was introduced by 947b3dd1a84b ("memcg, oom: lock mem_cgroup_print_oom_info"). Signed-off-by: Michal Hocko Reported-by: "Kirill A. Shutemov" Cc: Johannes Weiner Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 53385cd4e6f..ce7a8cc7b40 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1687,7 +1687,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) * protects memcg_name and makes sure that parallel ooms do not * interleave */ - static DEFINE_SPINLOCK(oom_info_lock); + static DEFINE_MUTEX(oom_info_lock); struct cgroup *task_cgrp; struct cgroup *mem_cgrp; static char memcg_name[PATH_MAX]; @@ -1698,7 +1698,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) if (!p) return; - spin_lock(&oom_info_lock); + mutex_lock(&oom_info_lock); rcu_read_lock(); mem_cgrp = memcg->css.cgroup; @@ -1767,7 +1767,7 @@ done: pr_cont("\n"); } - spin_unlock(&oom_info_lock); + mutex_unlock(&oom_info_lock); } /* -- cgit v1.2.3-70-g09d2 From f3713fd9cff733d9df83116422d8e4af6e86b2bb Mon Sep 17 00:00:00 2001 From: Davidlohr Bueso Date: Tue, 25 Feb 2014 15:01:45 -0800 Subject: ipc,mqueue: remove limits for the amount of system-wide queues Commit 93e6f119c0ce ("ipc/mqueue: cleanup definition names and locations") added global hardcoded limits to the amount of message queues that can be created. While these limits are per-namespace, reality is that it ends up breaking userspace applications. Historically users have, at least in theory, been able to create up to INT_MAX queues, and limiting it to just 1024 is way too low and dramatic for some workloads and use cases. For instance, Madars reports: "This update imposes bad limits on our multi-process application. As our app uses approaches that each process opens its own set of queues (usually something about 3-5 queues per process). In some scenarios we might run up to 3000 processes or more (which of-course for linux is not a problem). Thus we might need up to 9000 queues or more. All processes run under one user." Other affected users can be found in launchpad bug #1155695: https://bugs.launchpad.net/ubuntu/+source/manpages/+bug/1155695 Instead of increasing this limit, revert it entirely and fallback to the original way of dealing queue limits -- where once a user's resource limit is reached, and all memory is used, new queues cannot be created. Signed-off-by: Davidlohr Bueso Reported-by: Madars Vitolins Acked-by: Doug Ledford Cc: Manfred Spraul Cc: [3.5+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/ipc_namespace.h | 2 -- ipc/mq_sysctl.c | 18 ++++++++++++------ ipc/mqueue.c | 6 +++--- 3 files changed, 15 insertions(+), 11 deletions(-) diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index e7831d20373..35e7eca4e33 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -118,9 +118,7 @@ extern int mq_init_ns(struct ipc_namespace *ns); * the new maximum will handle anyone else. I may have to revisit this * in the future. */ -#define MIN_QUEUESMAX 1 #define DFLT_QUEUESMAX 256 -#define HARD_QUEUESMAX 1024 #define MIN_MSGMAX 1 #define DFLT_MSG 10U #define DFLT_MSGMAX 10 diff --git a/ipc/mq_sysctl.c b/ipc/mq_sysctl.c index 383d638340b..5bb8bfe6714 100644 --- a/ipc/mq_sysctl.c +++ b/ipc/mq_sysctl.c @@ -22,6 +22,16 @@ static void *get_mq(ctl_table *table) return which; } +static int proc_mq_dointvec(ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table mq_table; + memcpy(&mq_table, table, sizeof(mq_table)); + mq_table.data = get_mq(table); + + return proc_dointvec(&mq_table, write, buffer, lenp, ppos); +} + static int proc_mq_dointvec_minmax(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -33,12 +43,10 @@ static int proc_mq_dointvec_minmax(ctl_table *table, int write, lenp, ppos); } #else +#define proc_mq_dointvec NULL #define proc_mq_dointvec_minmax NULL #endif -static int msg_queues_limit_min = MIN_QUEUESMAX; -static int msg_queues_limit_max = HARD_QUEUESMAX; - static int msg_max_limit_min = MIN_MSGMAX; static int msg_max_limit_max = HARD_MSGMAX; @@ -51,9 +59,7 @@ static ctl_table mq_sysctls[] = { .data = &init_ipc_ns.mq_queues_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_mq_dointvec_minmax, - .extra1 = &msg_queues_limit_min, - .extra2 = &msg_queues_limit_max, + .proc_handler = proc_mq_dointvec, }, { .procname = "msg_max", diff --git a/ipc/mqueue.c b/ipc/mqueue.c index ccf1f9fd263..c3b31179122 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -433,9 +433,9 @@ static int mqueue_create(struct inode *dir, struct dentry *dentry, error = -EACCES; goto out_unlock; } - if (ipc_ns->mq_queues_count >= HARD_QUEUESMAX || - (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max && - !capable(CAP_SYS_RESOURCE))) { + + if (ipc_ns->mq_queues_count >= ipc_ns->mq_queues_max && + !capable(CAP_SYS_RESOURCE)) { error = -ENOSPC; goto out_unlock; } -- cgit v1.2.3-70-g09d2 From 27b2a49a1493f5199a4c2f84abc6aebf81184e2b Mon Sep 17 00:00:00 2001 From: Fathi Boudra Date: Tue, 25 Feb 2014 15:01:46 -0800 Subject: Makefile: fix extra parenthesis typo when CC_STACKPROTECTOR_REGULAR is enabled An extra parenthesis typo introduced in 19952a92037e ("stackprotector: Unify the HAVE_CC_STACKPROTECTOR logic between architectures") is causing the following error when CONFIG_CC_STACKPROTECTOR_REGULAR is enabled: Makefile:608: Cannot use CONFIG_CC_STACKPROTECTOR: -fstack-protector not supported by compiler Makefile:608: *** missing separator. Stop. Signed-off-by: Fathi Boudra Acked-by: Kees Cook Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 831b36a6b0a..15e90be5c02 100644 --- a/Makefile +++ b/Makefile @@ -606,7 +606,7 @@ ifdef CONFIG_CC_STACKPROTECTOR_REGULAR stackp-flag := -fstack-protector ifeq ($(call cc-option, $(stackp-flag)),) $(warning Cannot use CONFIG_CC_STACKPROTECTOR: \ - -fstack-protector not supported by compiler)) + -fstack-protector not supported by compiler) endif else ifdef CONFIG_CC_STACKPROTECTOR_STRONG stackp-flag := -fstack-protector-strong -- cgit v1.2.3-70-g09d2 From cf015e9f279f100e3c2a826217a4ab5dba3eb5ed Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Tue, 25 Feb 2014 15:01:47 -0800 Subject: MAINTAINERS: update L: misuses L: lines are for the email addresses of traditional mailing lists. W: lines are for URLs. Convert two L: misuses to W: links. Signed-off-by: Joe Perches Reported-by: Paul Bolle Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 85b3dd8008b..eab00889f9d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2611,9 +2611,9 @@ DC395x SCSI driver M: Oliver Neukum M: Ali Akcaagac M: Jamie Lenehan -W: http://twibble.org/dist/dc395x/ L: dc395x@twibble.org -L: http://lists.twibble.org/mailman/listinfo/dc395x/ +W: http://twibble.org/dist/dc395x/ +W: http://lists.twibble.org/mailman/listinfo/dc395x/ S: Maintained F: Documentation/scsi/dc395x.txt F: drivers/scsi/dc395x.* @@ -8443,8 +8443,8 @@ TARGET SUBSYSTEM M: Nicholas A. Bellinger L: linux-scsi@vger.kernel.org L: target-devel@vger.kernel.org -L: http://groups.google.com/group/linux-iscsi-target-dev W: http://www.linux-iscsi.org +W: http://groups.google.com/group/linux-iscsi-target-dev T: git git://git.kernel.org/pub/scm/linux/kernel/git/nab/target-pending.git master S: Supported F: drivers/target/ -- cgit v1.2.3-70-g09d2 From 6c15b327ccbdce45878d4689f4d938f29dd309db Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Tue, 25 Feb 2014 15:01:48 -0800 Subject: Makefile: fix build with make 3.80 again According to Documentation/Changes, make 3.80 is still being supported for building the kernel, hence make files must not make (unconditional) use of features introduced only in newer versions. Commit 8779657d29c0 ("stackprotector: Introduce CONFIG_CC_STACKPROTECTOR_STRONG") however introduced an "else ifdef" construct which make 3.80 doesn't understand. Also correct a warning message still referencing the old config option name. Apart from that I question the use of "ifdef" here (but it was used that way already prior to said commit): ifeq (,y) would seem more to the point. Signed-off-by: Jan Beulich Acked-by: Kees Cook Cc: Ingo Molnar Cc: Michal Marek Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Makefile | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/Makefile b/Makefile index 15e90be5c02..81f1bf39031 100644 --- a/Makefile +++ b/Makefile @@ -605,10 +605,11 @@ endif ifdef CONFIG_CC_STACKPROTECTOR_REGULAR stackp-flag := -fstack-protector ifeq ($(call cc-option, $(stackp-flag)),) - $(warning Cannot use CONFIG_CC_STACKPROTECTOR: \ + $(warning Cannot use CONFIG_CC_STACKPROTECTOR_REGULAR: \ -fstack-protector not supported by compiler) endif -else ifdef CONFIG_CC_STACKPROTECTOR_STRONG +else +ifdef CONFIG_CC_STACKPROTECTOR_STRONG stackp-flag := -fstack-protector-strong ifeq ($(call cc-option, $(stackp-flag)),) $(warning Cannot use CONFIG_CC_STACKPROTECTOR_STRONG: \ @@ -618,6 +619,7 @@ else # Force off for distro compilers that enable stack protector by default. stackp-flag := $(call cc-option, -fno-stack-protector) endif +endif KBUILD_CFLAGS += $(stackp-flag) # This warning generated too much noise in a regular build. -- cgit v1.2.3-70-g09d2 From 61bd0943bc410c9f0daf0965535cb92ce76e1e8a Mon Sep 17 00:00:00 2001 From: Tobias Klauser Date: Tue, 25 Feb 2014 15:01:49 -0800 Subject: MAINTAINERS: change mailing list address for Altera UART drivers The nios2-dev list has been moved to the RocketBoards infrastructure, so adjust the address accordingly. Signed-off-by: Tobias Klauser Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index eab00889f9d..df8869d49c3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -538,7 +538,7 @@ F: arch/alpha/ ALTERA UART/JTAG UART SERIAL DRIVERS M: Tobias Klauser L: linux-serial@vger.kernel.org -L: nios2-dev@sopc.et.ntust.edu.tw (moderated for non-subscribers) +L: nios2-dev@lists.rocketboards.org (moderated for non-subscribers) S: Maintained F: drivers/tty/serial/altera_uart.c F: drivers/tty/serial/altera_jtaguart.c -- cgit v1.2.3-70-g09d2