| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20160816200627.GB9336@kroah.com>
Date: Tue, 16 Aug 2016 22:06:27 +0200
From: Greg KH <gregkh@...uxfoundation.org>
To: linux-kernel@...r.kernel.org,
Andrew Morton <akpm@...ux-foundation.org>,
torvalds@...ux-foundation.org, stable@...r.kernel.org
Cc: lwn@....net, Jiri Slaby <jslaby@...e.cz>
Subject: Re: Linux 4.4.18
diff --git a/Documentation/x86/pat.txt b/Documentation/x86/pat.txt
index 54944c71b819..2a4ee6302122 100644
--- a/Documentation/x86/pat.txt
+++ b/Documentation/x86/pat.txt
@@ -196,3 +196,35 @@ Another, more verbose way of getting PAT related debug messages is with
"debugpat" boot parameter. With this parameter, various debug messages are
printed to dmesg log.
+PAT Initialization
+------------------
+
+The following table describes how PAT is initialized under various
+configurations. The PAT MSR must be updated by Linux in order to support WC
+and WT attributes. Otherwise, the PAT MSR has the value programmed in it
+by the firmware. Note, Xen enables WC attribute in the PAT MSR for guests.
+
+ MTRR PAT Call Sequence PAT State PAT MSR
+ =========================================================
+ E E MTRR -> PAT init Enabled OS
+ E D MTRR -> PAT init Disabled -
+ D E MTRR -> PAT disable Disabled BIOS
+ D D MTRR -> PAT disable Disabled -
+ - np/E PAT -> PAT disable Disabled BIOS
+ - np/D PAT -> PAT disable Disabled -
+ E !P/E MTRR -> PAT init Disabled BIOS
+ D !P/E MTRR -> PAT disable Disabled BIOS
+ !M !P/E MTRR stub -> PAT disable Disabled BIOS
+
+ Legend
+ ------------------------------------------------
+ E Feature enabled in CPU
+ D Feature disabled/unsupported in CPU
+ np "nopat" boot option specified
+ !P CONFIG_X86_PAT option unset
+ !M CONFIG_MTRR option unset
+ Enabled PAT state set to enabled
+ Disabled PAT state set to disabled
+ OS PAT initializes PAT MSR with OS setting
+ BIOS PAT keeps PAT MSR with BIOS setting
+
diff --git a/Makefile b/Makefile
index 76d34f763a41..eaedea88a8a7 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
VERSION = 4
PATCHLEVEL = 4
-SUBLEVEL = 17
+SUBLEVEL = 18
EXTRAVERSION =
NAME = Blurry Fish Butt
diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c
index 087acb569b63..5f221acd21ae 100644
--- a/arch/arm/kernel/sys_oabi-compat.c
+++ b/arch/arm/kernel/sys_oabi-compat.c
@@ -279,8 +279,12 @@ asmlinkage long sys_oabi_epoll_wait(int epfd,
mm_segment_t fs;
long ret, err, i;
- if (maxevents <= 0 || maxevents > (INT_MAX/sizeof(struct epoll_event)))
+ if (maxevents <= 0 ||
+ maxevents > (INT_MAX/sizeof(*kbuf)) ||
+ maxevents > (INT_MAX/sizeof(*events)))
return -EINVAL;
+ if (!access_ok(VERIFY_WRITE, events, sizeof(*events) * maxevents))
+ return -EFAULT;
kbuf = kmalloc(sizeof(*kbuf) * maxevents, GFP_KERNEL);
if (!kbuf)
return -ENOMEM;
@@ -317,6 +321,8 @@ asmlinkage long sys_oabi_semtimedop(int semid,
if (nsops < 1 || nsops > SEMOPM)
return -EINVAL;
+ if (!access_ok(VERIFY_READ, tsops, sizeof(*tsops) * nsops))
+ return -EFAULT;
sops = kmalloc(sizeof(*sops) * nsops, GFP_KERNEL);
if (!sops)
return -ENOMEM;
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 5a69eb48d0a8..ee93d5fe61d7 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -344,7 +344,7 @@ EXPORT(sysn32_call_table)
PTR sys_ni_syscall /* available, was setaltroot */
PTR sys_add_key
PTR sys_request_key
- PTR sys_keyctl /* 6245 */
+ PTR compat_sys_keyctl /* 6245 */
PTR sys_set_thread_area
PTR sys_inotify_init
PTR sys_inotify_add_watch
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index e4b6d7c97822..b77052ec6fb2 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -500,7 +500,7 @@ EXPORT(sys32_call_table)
PTR sys_ni_syscall /* available, was setaltroot */
PTR sys_add_key /* 4280 */
PTR sys_request_key
- PTR sys_keyctl
+ PTR compat_sys_keyctl
PTR sys_set_thread_area
PTR sys_inotify_init
PTR sys_inotify_add_watch /* 4285 */
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index b1f0a90f933b..42570d8fb265 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -2070,13 +2070,6 @@ void s390_reset_system(void (*fn_pre)(void),
S390_lowcore.program_new_psw.addr =
PSW_ADDR_AMODE | (unsigned long) s390_base_pgm_handler;
- /*
- * Clear subchannel ID and number to signal new kernel that no CCW or
- * SCSI IPL has been done (for kexec and kdump)
- */
- S390_lowcore.subchannel_id = 0;
- S390_lowcore.subchannel_nr = 0;
-
/* Store status at absolute zero */
store_status();
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index f17705e1332c..e62f4401e792 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -294,7 +294,7 @@
# 285 sys_setaltroot
286 i386 add_key sys_add_key
287 i386 request_key sys_request_key
-288 i386 keyctl sys_keyctl
+288 i386 keyctl sys_keyctl compat_sys_keyctl
289 i386 ioprio_set sys_ioprio_set
290 i386 ioprio_get sys_ioprio_get
291 i386 inotify_init sys_inotify_init
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index b94f6f64e23d..dbff1456d215 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -24,6 +24,7 @@
#define _ASM_X86_MTRR_H
#include <uapi/asm/mtrr.h>
+#include <asm/pat.h>
/*
@@ -83,9 +84,12 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn)
static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
{
}
+static inline void mtrr_bp_init(void)
+{
+ pat_disable("MTRRs disabled, skipping PAT initialization too.");
+}
#define mtrr_ap_init() do {} while (0)
-#define mtrr_bp_init() do {} while (0)
#define set_mtrr_aps_delayed_init() do {} while (0)
#define mtrr_aps_init() do {} while (0)
#define mtrr_bp_restore() do {} while (0)
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index ca6c228d5e62..0b1ff4c1c14e 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -5,8 +5,8 @@
#include <asm/pgtable_types.h>
bool pat_enabled(void);
+void pat_disable(const char *reason);
extern void pat_init(void);
-void pat_init_cache_modes(u64);
extern int reserve_memtype(u64 start, u64 end,
enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 3b533cf37c74..b5624fafa44a 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -444,11 +444,24 @@ static void __init print_mtrr_state(void)
pr_debug("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20);
}
+/* PAT setup for BP. We need to go through sync steps here */
+void __init mtrr_bp_pat_init(void)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ prepare_set();
+
+ pat_init();
+
+ post_set();
+ local_irq_restore(flags);
+}
+
/* Grab all of the MTRR state for this CPU into *state */
bool __init get_mtrr_state(void)
{
struct mtrr_var_range *vrs;
- unsigned long flags;
unsigned lo, dummy;
unsigned int i;
@@ -481,15 +494,6 @@ bool __init get_mtrr_state(void)
mtrr_state_set = 1;
- /* PAT setup for BP. We need to go through sync steps here */
- local_irq_save(flags);
- prepare_set();
-
- pat_init();
-
- post_set();
- local_irq_restore(flags);
-
return !!(mtrr_state.enabled & MTRR_STATE_MTRR_ENABLED);
}
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index f891b4750f04..fa77ac8291f0 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -752,6 +752,9 @@ void __init mtrr_bp_init(void)
/* BIOS may override */
__mtrr_enabled = get_mtrr_state();
+ if (mtrr_enabled())
+ mtrr_bp_pat_init();
+
if (mtrr_cleanup(phys_addr)) {
changed_by_mtrr_cleanup = 1;
mtrr_if->set_all();
@@ -759,8 +762,16 @@ void __init mtrr_bp_init(void)
}
}
- if (!mtrr_enabled())
+ if (!mtrr_enabled()) {
pr_info("MTRR: Disabled\n");
+
+ /*
+ * PAT initialization relies on MTRR's rendezvous handler.
+ * Skip PAT init until the handler can initialize both
+ * features independently.
+ */
+ pat_disable("MTRRs disabled, skipping PAT initialization too.");
+ }
}
void mtrr_ap_init(void)
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h
index 951884dcc433..6c7ced07d16d 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.h
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.h
@@ -52,6 +52,7 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt);
void fill_mtrr_var_range(unsigned int index,
u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi);
bool get_mtrr_state(void);
+void mtrr_bp_pat_init(void);
extern void set_mtrr_ops(const struct mtrr_ops *ops);
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 844b06d67df4..307f60ecfc6d 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -94,18 +94,6 @@ static unsigned long mmap_base(unsigned long rnd)
}
/*
- * Bottom-up (legacy) layout on X86_32 did not support randomization, X86_64
- * does, but not when emulating X86_32
- */
-static unsigned long mmap_legacy_base(unsigned long rnd)
-{
- if (mmap_is_ia32())
- return TASK_UNMAPPED_BASE;
- else
- return TASK_UNMAPPED_BASE + rnd;
-}
-
-/*
* This function, called very early during the creation of a new
* process VM image, sets up which VM layout function to use:
*/
@@ -116,7 +104,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
if (current->flags & PF_RANDOMIZE)
random_factor = arch_mmap_rnd();
- mm->mmap_legacy_base = mmap_legacy_base(random_factor);
+ mm->mmap_legacy_base = TASK_UNMAPPED_BASE + random_factor;
if (mmap_is_legacy()) {
mm->mmap_base = mm->mmap_legacy_base;
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 188e3e07eeeb..6ad687d104ca 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -39,11 +39,22 @@
static bool boot_cpu_done;
static int __read_mostly __pat_enabled = IS_ENABLED(CONFIG_X86_PAT);
+static void init_cache_modes(void);
-static inline void pat_disable(const char *reason)
+void pat_disable(const char *reason)
{
+ if (!__pat_enabled)
+ return;
+
+ if (boot_cpu_done) {
+ WARN_ONCE(1, "x86/PAT: PAT cannot be disabled after initialization\n");
+ return;
+ }
+
__pat_enabled = 0;
pr_info("x86/PAT: %s\n", reason);
+
+ init_cache_modes();
}
static int __init nopat(char *str)
@@ -180,7 +191,7 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg)
* configuration.
* Using lower indices is preferred, so we start with highest index.
*/
-void pat_init_cache_modes(u64 pat)
+static void __init_cache_modes(u64 pat)
{
enum page_cache_mode cache;
char pat_msg[33];
@@ -201,14 +212,11 @@ static void pat_bsp_init(u64 pat)
{
u64 tmp_pat;
- if (!cpu_has_pat) {
+ if (!boot_cpu_has(X86_FEATURE_PAT)) {
pat_disable("PAT not supported by CPU.");
return;
}
- if (!pat_enabled())
- goto done;
-
rdmsrl(MSR_IA32_CR_PAT, tmp_pat);
if (!tmp_pat) {
pat_disable("PAT MSR is 0, disabled.");
@@ -217,16 +225,12 @@ static void pat_bsp_init(u64 pat)
wrmsrl(MSR_IA32_CR_PAT, pat);
-done:
- pat_init_cache_modes(pat);
+ __init_cache_modes(pat);
}
static void pat_ap_init(u64 pat)
{
- if (!pat_enabled())
- return;
-
- if (!cpu_has_pat) {
+ if (!boot_cpu_has(X86_FEATURE_PAT)) {
/*
* If this happens we are on a secondary CPU, but switched to
* PAT on the boot CPU. We have no way to undo PAT.
@@ -237,18 +241,32 @@ static void pat_ap_init(u64 pat)
wrmsrl(MSR_IA32_CR_PAT, pat);
}
-void pat_init(void)
+static void init_cache_modes(void)
{
- u64 pat;
- struct cpuinfo_x86 *c = &boot_cpu_data;
+ u64 pat = 0;
+ static int init_cm_done;
- if (!pat_enabled()) {
+ if (init_cm_done)
+ return;
+
+ if (boot_cpu_has(X86_FEATURE_PAT)) {
+ /*
+ * CPU supports PAT. Set PAT table to be consistent with
+ * PAT MSR. This case supports "nopat" boot option, and
+ * virtual machine environments which support PAT without
+ * MTRRs. In specific, Xen has unique setup to PAT MSR.
+ *
+ * If PAT MSR returns 0, it is considered invalid and emulates
+ * as No PAT.
+ */
+ rdmsrl(MSR_IA32_CR_PAT, pat);
+ }
+
+ if (!pat) {
/*
* No PAT. Emulate the PAT table that corresponds to the two
- * cache bits, PWT (Write Through) and PCD (Cache Disable). This
- * setup is the same as the BIOS default setup when the system
- * has PAT but the "nopat" boot option has been specified. This
- * emulated PAT table is used when MSR_IA32_CR_PAT returns 0.
+ * cache bits, PWT (Write Through) and PCD (Cache Disable).
+ * This setup is also the same as the BIOS default setup.
*
* PTE encoding:
*
@@ -265,10 +283,36 @@ void pat_init(void)
*/
pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) |
PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC);
+ }
+
+ __init_cache_modes(pat);
+
+ init_cm_done = 1;
+}
+
+/**
+ * pat_init - Initialize PAT MSR and PAT table
+ *
+ * This function initializes PAT MSR and PAT table with an OS-defined value
+ * to enable additional cache attributes, WC and WT.
+ *
+ * This function must be called on all CPUs using the specific sequence of
+ * operations defined in Intel SDM. mtrr_rendezvous_handler() provides this
+ * procedure for PAT.
+ */
+void pat_init(void)
+{
+ u64 pat;
+ struct cpuinfo_x86 *c = &boot_cpu_data;
+
+ if (!pat_enabled()) {
+ init_cache_modes();
+ return;
+ }
- } else if ((c->x86_vendor == X86_VENDOR_INTEL) &&
- (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
- ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
+ if ((c->x86_vendor == X86_VENDOR_INTEL) &&
+ (((c->x86 == 0x6) && (c->x86_model <= 0xd)) ||
+ ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) {
/*
* PAT support with the lower four entries. Intel Pentium 2,
* 3, M, and 4 are affected by PAT errata, which makes the
@@ -733,25 +777,6 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
if (file->f_flags & O_DSYNC)
pcm = _PAGE_CACHE_MODE_UC_MINUS;
-#ifdef CONFIG_X86_32
- /*
- * On the PPro and successors, the MTRRs are used to set
- * memory types for physical addresses outside main memory,
- * so blindly setting UC or PWT on those pages is wrong.
- * For Pentiums and earlier, the surround logic should disable
- * caching for the high addresses through the KEN pin, but
- * we maintain the tradition of paranoia in this code.
- */
- if (!pat_enabled() &&
- !(boot_cpu_has(X86_FEATURE_MTRR) ||
- boot_cpu_has(X86_FEATURE_K6_MTRR) ||
- boot_cpu_has(X86_FEATURE_CYRIX_ARR) ||
- boot_cpu_has(X86_FEATURE_CENTAUR_MCR)) &&
- (pfn << PAGE_SHIFT) >= __pa(high_memory)) {
- pcm = _PAGE_CACHE_MODE_UC;
- }
-#endif
-
*vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
cachemode2protval(pcm));
return 1;
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index beab8c706ac9..ffa41591bff9 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -74,7 +74,6 @@
#include <asm/mach_traps.h>
#include <asm/mwait.h>
#include <asm/pci_x86.h>
-#include <asm/pat.h>
#include <asm/cpu.h>
#ifdef CONFIG_ACPI
@@ -1519,7 +1518,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
{
struct physdev_set_iopl set_iopl;
unsigned long initrd_start = 0;
- u64 pat;
int rc;
if (!xen_start_info)
@@ -1627,13 +1625,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
xen_start_info->nr_pages);
xen_reserve_special_pages();
- /*
- * Modify the cache mode translation tables to match Xen's PAT
- * configuration.
- */
- rdmsrl(MSR_IA32_CR_PAT, pat);
- pat_init_cache_modes(pat);
-
/* keep using Xen gdt for now; no urgent need to change it */
#ifdef CONFIG_X86_32
diff --git a/block/genhd.c b/block/genhd.c
index e5cafa51567c..d2a1d43bf9fa 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -831,6 +831,7 @@ static void disk_seqf_stop(struct seq_file *seqf, void *v)
if (iter) {
class_dev_iter_exit(iter);
kfree(iter);
+ seqf->private = NULL;
}
}
diff --git a/crypto/gcm.c b/crypto/gcm.c
index bec329b3de8d..d9ea5f9c0574 100644
--- a/crypto/gcm.c
+++ b/crypto/gcm.c
@@ -639,7 +639,9 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl,
ghash_alg = crypto_find_alg(ghash_name, &crypto_ahash_type,
CRYPTO_ALG_TYPE_HASH,
- CRYPTO_ALG_TYPE_AHASH_MASK);
+ CRYPTO_ALG_TYPE_AHASH_MASK |
+ crypto_requires_sync(algt->type,
+ algt->mask));
if (IS_ERR(ghash_alg))
return PTR_ERR(ghash_alg);
diff --git a/crypto/scatterwalk.c b/crypto/scatterwalk.c
index ea5815c5e128..bc769c448d4a 100644
--- a/crypto/scatterwalk.c
+++ b/crypto/scatterwalk.c
@@ -72,7 +72,8 @@ static void scatterwalk_pagedone(struct scatter_walk *walk, int out,
void scatterwalk_done(struct scatter_walk *walk, int out, int more)
{
- if (!(scatterwalk_pagelen(walk) & (PAGE_SIZE - 1)) || !more)
+ if (!more || walk->offset >= walk->sg->offset + walk->sg->length ||
+ !(walk->offset & (PAGE_SIZE - 1)))
scatterwalk_pagedone(walk, out, more);
}
EXPORT_SYMBOL_GPL(scatterwalk_done);
diff --git a/drivers/char/random.c b/drivers/char/random.c
index d0da5d852d41..0227b0465b40 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -722,15 +722,18 @@ retry:
}
}
-static void credit_entropy_bits_safe(struct entropy_store *r, int nbits)
+static int credit_entropy_bits_safe(struct entropy_store *r, int nbits)
{
const int nbits_max = (int)(~0U >> (ENTROPY_SHIFT + 1));
+ if (nbits < 0)
+ return -EINVAL;
+
/* Cap the value to avoid overflows */
nbits = min(nbits, nbits_max);
- nbits = max(nbits, -nbits_max);
credit_entropy_bits(r, nbits);
+ return 0;
}
/*********************************************************************
@@ -1542,8 +1545,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
return -EPERM;
if (get_user(ent_count, p))
return -EFAULT;
- credit_entropy_bits_safe(&input_pool, ent_count);
- return 0;
+ return credit_entropy_bits_safe(&input_pool, ent_count);
case RNDADDENTROPY:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
@@ -1557,8 +1559,7 @@ static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
size);
if (retval < 0)
return retval;
- credit_entropy_bits_safe(&input_pool, ent_count);
- return 0;
+ return credit_entropy_bits_safe(&input_pool, ent_count);
case RNDZAPENTCNT:
case RNDCLEARPOOL:
/*
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 62284e45d531..eb434881ddbc 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -1789,16 +1789,20 @@ static uint32_t ilk_compute_cur_wm(const struct intel_crtc_state *cstate,
const struct intel_plane_state *pstate,
uint32_t mem_value)
{
- int bpp = pstate->base.fb ? pstate->base.fb->bits_per_pixel / 8 : 0;
+ /*
+ * We treat the cursor plane as always-on for the purposes of watermark
+ * calculation. Until we have two-stage watermark programming merged,
+ * this is necessary to avoid flickering.
+ */
+ int cpp = 4;
+ int width = pstate->visible ? pstate->base.crtc_w : 64;
- if (!cstate->base.active || !pstate->visible)
+ if (!cstate->base.active)
return 0;
return ilk_wm_method2(ilk_pipe_pixel_rate(cstate),
cstate->base.adjusted_mode.crtc_htotal,
- drm_rect_width(&pstate->dst),
- bpp,
- mem_value);
+ width, cpp, mem_value);
}
/* Only for WM_LP. */
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index 774cd2210566..21febbb0d84e 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -1418,8 +1418,10 @@ static int sixaxis_set_operational_usb(struct hid_device *hdev)
}
ret = hid_hw_output_report(hdev, buf, 1);
- if (ret < 0)
- hid_err(hdev, "can't set operational mode: step 3\n");
+ if (ret < 0) {
+ hid_info(hdev, "can't set operational mode: step 3, ignoring\n");
+ ret = 0;
+ }
out:
kfree(buf);
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index 27fa0cb09538..85f39cc3e276 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -244,6 +244,13 @@ struct i801_priv {
struct platform_device *mux_pdev;
#endif
struct platform_device *tco_pdev;
+
+ /*
+ * If set to true the host controller registers are reserved for
+ * ACPI AML use. Protected by acpi_lock.
+ */
+ bool acpi_reserved;
+ struct mutex acpi_lock;
};
#define FEATURE_SMBUS_PEC (1 << 0)
@@ -714,9 +721,15 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,
{
int hwpec;
int block = 0;
- int ret, xact = 0;
+ int ret = 0, xact = 0;
struct i801_priv *priv = i2c_get_adapdata(adap);
+ mutex_lock(&priv->acpi_lock);
+ if (priv->acpi_reserved) {
+ mutex_unlock(&priv->acpi_lock);
+ return -EBUSY;
+ }
+
hwpec = (priv->features & FEATURE_SMBUS_PEC) && (flags & I2C_CLIENT_PEC)
&& size != I2C_SMBUS_QUICK
&& size != I2C_SMBUS_I2C_BLOCK_DATA;
@@ -773,7 +786,8 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,
default:
dev_err(&priv->pci_dev->dev, "Unsupported transaction %d\n",
size);
- return -EOPNOTSUPP;
+ ret = -EOPNOTSUPP;
+ goto out;
}
if (hwpec) /* enable/disable hardware PEC */
@@ -796,11 +810,11 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,
~(SMBAUXCTL_CRC | SMBAUXCTL_E32B), SMBAUXCTL(priv));
if (block)
- return ret;
+ goto out;
if (ret)
- return ret;
+ goto out;
if ((read_write == I2C_SMBUS_WRITE) || (xact == I801_QUICK))
- return 0;
+ goto out;
switch (xact & 0x7f) {
case I801_BYTE: /* Result put in SMBHSTDAT0 */
@@ -812,7 +826,10 @@ static s32 i801_access(struct i2c_adapter *adap, u16 addr,
(inb_p(SMBHSTDAT1(priv)) << 8);
break;
}
- return 0;
+
+out:
+ mutex_unlock(&priv->acpi_lock);
+ return ret;
}
@@ -1249,6 +1266,72 @@ static void i801_add_tco(struct i801_priv *priv)
priv->tco_pdev = pdev;
}
+#ifdef CONFIG_ACPI
+static acpi_status
+i801_acpi_io_handler(u32 function, acpi_physical_address address, u32 bits,
+ u64 *value, void *handler_context, void *region_context)
+{
+ struct i801_priv *priv = handler_context;
+ struct pci_dev *pdev = priv->pci_dev;
+ acpi_status status;
+
+ /*
+ * Once BIOS AML code touches the OpRegion we warn and inhibit any
+ * further access from the driver itself. This device is now owned
+ * by the system firmware.
+ */
+ mutex_lock(&priv->acpi_lock);
+
+ if (!priv->acpi_reserved) {
+ priv->acpi_reserved = true;
+
+ dev_warn(&pdev->dev, "BIOS is accessing SMBus registers\n");
+ dev_warn(&pdev->dev, "Driver SMBus register access inhibited\n");
+ }
+
+ if ((function & ACPI_IO_MASK) == ACPI_READ)
+ status = acpi_os_read_port(address, (u32 *)value, bits);
+ else
+ status = acpi_os_write_port(address, (u32)*value, bits);
+
+ mutex_unlock(&priv->acpi_lock);
+
+ return status;
+}
+
+static int i801_acpi_probe(struct i801_priv *priv)
+{
+ struct acpi_device *adev;
+ acpi_status status;
+
+ adev = ACPI_COMPANION(&priv->pci_dev->dev);
+ if (adev) {
+ status = acpi_install_address_space_handler(adev->handle,
+ ACPI_ADR_SPACE_SYSTEM_IO, i801_acpi_io_handler,
+ NULL, priv);
+ if (ACPI_SUCCESS(status))
+ return 0;
+ }
+
+ return acpi_check_resource_conflict(&priv->pci_dev->resource[SMBBAR]);
+}
+
+static void i801_acpi_remove(struct i801_priv *priv)
+{
+ struct acpi_device *adev;
+
+ adev = ACPI_COMPANION(&priv->pci_dev->dev);
+ if (!adev)
+ return;
+
+ acpi_remove_address_space_handler(adev->handle,
+ ACPI_ADR_SPACE_SYSTEM_IO, i801_acpi_io_handler);
+}
+#else
+static inline int i801_acpi_probe(struct i801_priv *priv) { return 0; }
+static inline void i801_acpi_remove(struct i801_priv *priv) { }
+#endif
+
static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
{
unsigned char temp;
@@ -1266,6 +1349,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
priv->adapter.dev.parent = &dev->dev;
ACPI_COMPANION_SET(&priv->adapter.dev, ACPI_COMPANION(&dev->dev));
priv->adapter.retries = 3;
+ mutex_init(&priv->acpi_lock);
priv->pci_dev = dev;
switch (dev->device) {
@@ -1328,10 +1412,8 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
return -ENODEV;
}
- err = acpi_check_resource_conflict(&dev->resource[SMBBAR]);
- if (err) {
+ if (i801_acpi_probe(priv))
return -ENODEV;
- }
err = pcim_iomap_regions(dev, 1 << SMBBAR,
dev_driver_string(&dev->dev));
@@ -1340,6 +1422,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
"Failed to request SMBus region 0x%lx-0x%Lx\n",
priv->smba,
(unsigned long long)pci_resource_end(dev, SMBBAR));
+ i801_acpi_remove(priv);
return err;
}
@@ -1404,6 +1487,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
err = i2c_add_adapter(&priv->adapter);
if (err) {
dev_err(&dev->dev, "Failed to add SMBus adapter\n");
+ i801_acpi_remove(priv);
return err;
}
@@ -1422,6 +1506,7 @@ static void i801_remove(struct pci_dev *dev)
i801_del_mux(priv);
i2c_del_adapter(&priv->adapter);
+ i801_acpi_remove(priv);
pci_write_config_byte(dev, SMBHSTCFG, priv->original_hstcfg);
platform_device_unregister(priv->tco_pdev);
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index db760e84119f..b8df0f5e8c25 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -446,7 +446,11 @@ static int bond_newlink(struct net *src_net, struct net_device *bond_dev,
if (err < 0)
return err;
- return register_netdevice(bond_dev);
+ err = register_netdevice(bond_dev);
+
+ netif_carrier_off(bond_dev);
+
+ return err;
}
static size_t bond_get_size(const struct net_device *bond_dev)
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index 28f7610b03fe..c32f5d32f811 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -219,7 +219,7 @@ err_dma:
dma_unmap_single(dma_dev, slot->dma_addr, skb_headlen(skb),
DMA_TO_DEVICE);
- while (i > 0) {
+ while (i-- > 0) {
int index = (ring->end + i) % BGMAC_TX_RING_SLOTS;
struct bgmac_slot_info *slot = &ring->slots[index];
u32 ctl1 = le32_to_cpu(ring->cpu_base[index].ctl1);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 3dd548ab8df1..40365cb1abe6 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -794,13 +794,12 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn,
* in a bitmap and increasing the chain consumer only
* for the first successive completed entries.
*/
- bitmap_set(p_spq->p_comp_bitmap, pos, SPQ_RING_SIZE);
+ __set_bit(pos, p_spq->p_comp_bitmap);
while (test_bit(p_spq->comp_bitmap_idx,
p_spq->p_comp_bitmap)) {
- bitmap_clear(p_spq->p_comp_bitmap,
- p_spq->comp_bitmap_idx,
- SPQ_RING_SIZE);
+ __clear_bit(p_spq->comp_bitmap_idx,
+ p_spq->p_comp_bitmap);
p_spq->comp_bitmap_idx++;
qed_chain_return_produced(&p_spq->chain);
}
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index a790d5f90b83..e0e94b855bbe 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -952,8 +952,6 @@ EXPORT_SYMBOL_GPL(cdc_ncm_select_altsetting);
static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf)
{
- int ret;
-
/* MBIM backwards compatible function? */
if (cdc_ncm_select_altsetting(intf) != CDC_NCM_COMM_ALTSETTING_NCM)
return -ENODEV;
@@ -962,16 +960,7 @@ static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf)
* Additionally, generic NCM devices are assumed to accept arbitrarily
* placed NDP.
*/
- ret = cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0);
-
- /*
- * We should get an event when network connection is "connected" or
- * "disconnected". Set network connection in "disconnected" state
- * (carrier is OFF) during attach, so the IP network stack does not
- * start IPv6 negotiation and more.
- */
- usbnet_link_change(dev, 0, 0);
- return ret;
+ return cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0);
}
static void cdc_ncm_align_tail(struct sk_buff *skb, size_t modulus, size_t remainder, size_t max)
@@ -1554,7 +1543,8 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb)
static const struct driver_info cdc_ncm_info = {
.description = "CDC NCM",
- .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET,
+ .flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
+ | FLAG_LINK_INTR,
.bind = cdc_ncm_bind,
.unbind = cdc_ncm_unbind,
.manage_power = usbnet_manage_power,
@@ -1567,7 +1557,7 @@ static const struct driver_info cdc_ncm_info = {
static const struct driver_info wwan_info = {
.description = "Mobile Broadband Network Device",
.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
- | FLAG_WWAN,
+ | FLAG_LINK_INTR | FLAG_WWAN,
.bind = cdc_ncm_bind,
.unbind = cdc_ncm_unbind,
.manage_power = usbnet_manage_power,
@@ -1580,7 +1570,7 @@ static const struct driver_info wwan_info = {
static const struct driver_info wwan_noarp_info = {
.description = "Mobile Broadband Network Device (NO ARP)",
.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
- | FLAG_WWAN | FLAG_NOARP,
+ | FLAG_LINK_INTR | FLAG_WWAN | FLAG_NOARP,
.bind = cdc_ncm_bind,
.unbind = cdc_ncm_unbind,
.manage_power = usbnet_manage_power,
diff --git a/drivers/pnp/quirks.c b/drivers/pnp/quirks.c
index 943c1cb9566c..d28e3ab9479c 100644
--- a/drivers/pnp/quirks.c
+++ b/drivers/pnp/quirks.c
@@ -342,7 +342,9 @@ static void quirk_amd_mmconfig_area(struct pnp_dev *dev)
/* Device IDs of parts that have 32KB MCH space */
static const unsigned int mch_quirk_devices[] = {
0x0154, /* Ivy Bridge */
+ 0x0a04, /* Haswell-ULT */
0x0c00, /* Haswell */
+ 0x1604, /* Broadwell */
};
static struct pci_dev *get_intel_host(void)
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index f7ae898833dd..7232d43e2207 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -1058,11 +1058,12 @@ int scsi_sysfs_add_sdev(struct scsi_device *sdev)
}
error = scsi_dh_add_device(sdev);
- if (error) {
+ if (error)
+ /*
+ * device_handler is optional, so any error can be ignored
+ */
sdev_printk(KERN_INFO, sdev,
"failed to add device handler: %d\n", error);
- return error;
- }
device_enable_async_suspend(&sdev->sdev_dev);
error = device_add(&sdev->sdev_dev);
diff --git a/drivers/staging/rdma/ipath/ipath_file_ops.c b/drivers/staging/rdma/ipath/ipath_file_ops.c
index 13c3cd11ab92..05d30f433b19 100644
--- a/drivers/staging/rdma/ipath/ipath_file_ops.c
+++ b/drivers/staging/rdma/ipath/ipath_file_ops.c
@@ -45,6 +45,8 @@
#include <linux/uio.h>
#include <asm/pgtable.h>
+#include <rdma/ib.h>
+
#include "ipath_kernel.h"
#include "ipath_common.h"
#include "ipath_user_sdma.h"
@@ -2243,6 +2245,9 @@ static ssize_t ipath_write(struct file *fp, const char __user *data,
ssize_t ret = 0;
void *dest;
+ if (WARN_ON_ONCE(!ib_safe_file_access(fp)))
+ return -EACCES;
+
if (count < sizeof(cmd.type)) {
ret = -EINVAL;
goto bail;
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index 7865228f664f..807d80145686 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -679,14 +679,14 @@ static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty)
/* this is called once with whichever end is closed last */
static void pty_unix98_shutdown(struct tty_struct *tty)
{
- struct inode *ptmx_inode;
+ struct pts_fs_info *fsi;
if (tty->driver->subtype == PTY_TYPE_MASTER)
- ptmx_inode = tty->driver_data;
+ fsi = tty->driver_data;
else
- ptmx_inode = tty->link->driver_data;
- devpts_kill_index(ptmx_inode, tty->index);
- devpts_del_ref(ptmx_inode);
+ fsi = tty->link->driver_data;
+ devpts_kill_index(fsi, tty->index);
+ devpts_put_ref(fsi);
}
static const struct tty_operations ptm_unix98_ops = {
@@ -738,6 +738,7 @@ static const struct tty_operations pty_unix98_ops = {
static int ptmx_open(struct inode *inode, struct file *filp)
{
+ struct pts_fs_info *fsi;
struct tty_struct *tty;
struct inode *slave_inode;
int retval;
@@ -752,47 +753,41 @@ static int ptmx_open(struct inode *inode, struct file *filp)
if (retval)
return retval;
+ fsi = devpts_get_ref(inode, filp);
+ retval = -ENODEV;
+ if (!fsi)
+ goto out_free_file;
+
/* find a device that is not in use. */
mutex_lock(&devpts_mutex);
- index = devpts_new_index(inode);
- if (index < 0) {
- retval = index;
- mutex_unlock(&devpts_mutex);
- goto err_file;
- }
-
+ index = devpts_new_index(fsi);
mutex_unlock(&devpts_mutex);
- mutex_lock(&tty_mutex);
- tty = tty_init_dev(ptm_driver, index);
+ retval = index;
+ if (index < 0)
+ goto out_put_ref;
- if (IS_ERR(tty)) {
- retval = PTR_ERR(tty);
- goto out;
- }
+ mutex_lock(&tty_mutex);
+ tty = tty_init_dev(ptm_driver, index);
/* The tty returned here is locked so we can safely
drop the mutex */
mutex_unlock(&tty_mutex);
- set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */
- tty->driver_data = inode;
+ retval = PTR_ERR(tty);
+ if (IS_ERR(tty))
+ goto out;
/*
- * In the case where all references to ptmx inode are dropped and we
- * still have /dev/tty opened pointing to the master/slave pair (ptmx
- * is closed/released before /dev/tty), we must make sure that the inode
- * is still valid when we call the final pty_unix98_shutdown, thus we
- * hold an additional reference to the ptmx inode. For the same /dev/tty
- * last close case, we also need to make sure the super_block isn't
- * destroyed (devpts instance unmounted), before /dev/tty is closed and
- * on its release devpts_kill_index is called.
+ * From here on out, the tty is "live", and the index and
+ * fsi will be killed/put by the tty_release()
*/
- devpts_add_ref(inode);
+ set_bit(TTY_PTY_LOCK, &tty->flags); /* LOCK THE SLAVE */
+ tty->driver_data = fsi;
tty_add_file(tty, filp);
- slave_inode = devpts_pty_new(inode,
+ slave_inode = devpts_pty_new(fsi,
MKDEV(UNIX98_PTY_SLAVE_MAJOR, index), index,
tty->link);
if (IS_ERR(slave_inode)) {
@@ -811,12 +806,14 @@ static int ptmx_open(struct inode *inode, struct file *filp)
return 0;
err_release:
tty_unlock(tty);
+ // This will also put-ref the fsi
tty_release(inode, filp);
return retval;
out:
- mutex_unlock(&tty_mutex);
- devpts_kill_index(inode, index);
-err_file:
+ devpts_kill_index(fsi, index);
+out_put_ref:
+ devpts_put_ref(fsi);
+out_free_file:
tty_free_file(filp);
return retval;
}
diff --git a/fs/dcache.c b/fs/dcache.c
index 108d7d810be3..71b6056ad35d 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -578,7 +578,6 @@ static struct dentry *dentry_kill(struct dentry *dentry)
failed:
spin_unlock(&dentry->d_lock);
- cpu_relax();
return dentry; /* try again with same dentry */
}
@@ -752,6 +751,8 @@ void dput(struct dentry *dentry)
return;
repeat:
+ might_sleep();
+
rcu_read_lock();
if (likely(fast_dput(dentry))) {
rcu_read_unlock();
@@ -783,8 +784,10 @@ repeat:
kill_it:
dentry = dentry_kill(dentry);
- if (dentry)
+ if (dentry) {
+ cond_resched();
goto repeat;
+ }
}
EXPORT_SYMBOL(dput);
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 706de324f2a6..c82edb049117 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -128,6 +128,7 @@ static const match_table_t tokens = {
struct pts_fs_info {
struct ida allocated_ptys;
struct pts_mount_opts mount_opts;
+ struct super_block *sb;
struct dentry *ptmx_dentry;
};
@@ -358,7 +359,7 @@ static const struct super_operations devpts_sops = {
.show_options = devpts_show_options,
};
-static void *new_pts_fs_info(void)
+static void *new_pts_fs_info(struct super_block *sb)
{
struct pts_fs_info *fsi;
@@ -369,6 +370,7 @@ static void *new_pts_fs_info(void)
ida_init(&fsi->allocated_ptys);
fsi->mount_opts.mode = DEVPTS_DEFAULT_MODE;
fsi->mount_opts.ptmxmode = DEVPTS_DEFAULT_PTMX_MODE;
+ fsi->sb = sb;
return fsi;
}
@@ -384,7 +386,7 @@ devpts_fill_super(struct super_block *s, void *data, int silent)
s->s_op = &devpts_sops;
s->s_time_gran = 1;
- s->s_fs_info = new_pts_fs_info();
+ s->s_fs_info = new_pts_fs_info(s);
if (!s->s_fs_info)
goto fail;
@@ -524,17 +526,14 @@ static struct file_system_type devpts_fs_type = {
* to the System V naming convention
*/
-int devpts_new_index(struct inode *ptmx_inode)
+int devpts_new_index(struct pts_fs_info *fsi)
{
- struct super_block *sb = pts_sb_from_inode(ptmx_inode);
- struct pts_fs_info *fsi;
int index;
int ida_ret;
- if (!sb)
+ if (!fsi)
return -ENODEV;
- fsi = DEVPTS_SB(sb);
retry:
if (!ida_pre_get(&fsi->allocated_ptys, GFP_KERNEL))
return -ENOMEM;
@@ -564,11 +563,8 @@ retry:
return index;
}
-void devpts_kill_index(struct inode *ptmx_inode, int idx)
+void devpts_kill_index(struct pts_fs_info *fsi, int idx)
{
- struct super_block *sb = pts_sb_from_inode(ptmx_inode);
- struct pts_fs_info *fsi = DEVPTS_SB(sb);
-
mutex_lock(&allocated_ptys_lock);
ida_remove(&fsi->allocated_ptys, idx);
pty_count--;
@@ -578,21 +574,25 @@ void devpts_kill_index(struct inode *ptmx_inode, int idx)
/*
* pty code needs to hold extra references in case of last /dev/tty close
*/
-
-void devpts_add_ref(struct inode *ptmx_inode)
+struct pts_fs_info *devpts_get_ref(struct inode *ptmx_inode, struct file *file)
{
- struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+ struct super_block *sb;
+ struct pts_fs_info *fsi;
+
+ sb = pts_sb_from_inode(ptmx_inode);
+ if (!sb)
+ return NULL;
+ fsi = DEVPTS_SB(sb);
+ if (!fsi)
+ return NULL;
atomic_inc(&sb->s_active);
- ihold(ptmx_inode);
+ return fsi;
}
-void devpts_del_ref(struct inode *ptmx_inode)
+void devpts_put_ref(struct pts_fs_info *fsi)
{
- struct super_block *sb = pts_sb_from_inode(ptmx_inode);
-
- iput(ptmx_inode);
- deactivate_super(sb);
+ deactivate_super(fsi->sb);
}
/**
@@ -604,22 +604,21 @@ void devpts_del_ref(struct inode *ptmx_inode)
*
* The created inode is returned. Remove it from /dev/pts/ by devpts_pty_kill.
*/
-struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
+struct inode *devpts_pty_new(struct pts_fs_info *fsi, dev_t device, int index,
void *priv)
{
struct dentry *dentry;
- struct super_block *sb = pts_sb_from_inode(ptmx_inode);
+ struct super_block *sb;
struct inode *inode;
struct dentry *root;
- struct pts_fs_info *fsi;
struct pts_mount_opts *opts;
char s[12];
- if (!sb)
+ if (!fsi)
return ERR_PTR(-ENODEV);
+ sb = fsi->sb;
root = sb->s_root;
- fsi = DEVPTS_SB(sb);
opts = &fsi->mount_opts;
inode = new_inode(sb);
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index fe1f50fe764f..f97110461c19 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -208,6 +208,9 @@ static int ext4_init_block_bitmap(struct super_block *sb,
memset(bh->b_data, 0, sb->s_blocksize);
bit_max = ext4_num_base_meta_clusters(sb, block_group);
+ if ((bit_max >> 3) >= bh->b_size)
+ return -EFSCORRUPTED;
+
for (bit = 0; bit < bit_max; bit++)
ext4_set_bit(bit, bh->b_data);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 62880586ed85..8eac7d586997 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -376,9 +376,13 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
ext4_fsblk_t block = ext4_ext_pblock(ext);
int len = ext4_ext_get_actual_len(ext);
ext4_lblk_t lblock = le32_to_cpu(ext->ee_block);
- ext4_lblk_t last = lblock + len - 1;
- if (len == 0 || lblock > last)
+ /*
+ * We allow neither:
+ * - zero length
+ * - overflow/wrap-around
+ */
+ if (lblock + len <= lblock)
return 0;
return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index e31d762eedce..9a5ad0f0d3ed 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -205,9 +205,9 @@ void ext4_evict_inode(struct inode *inode)
* Note that directories do not have this problem because they
* don't use page cache.
*/
- if (ext4_should_journal_data(inode) &&
- (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
- inode->i_ino != EXT4_JOURNAL_INO) {
+ if (inode->i_ino != EXT4_JOURNAL_INO &&
+ ext4_should_journal_data(inode) &&
+ (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
@@ -2589,13 +2589,36 @@ retry:
done = true;
}
}
- ext4_journal_stop(handle);
+ /*
+ * Caution: If the handle is synchronous,
+ * ext4_journal_stop() can wait for transaction commit
+ * to finish which may depend on writeback of pages to
+ * complete or on page lock to be released. In that
+ * case, we have to wait until after after we have
+ * submitted all the IO, released page locks we hold,
+ * and dropped io_end reference (for extent conversion
+ * to be able to complete) before stopping the handle.
+ */
+ if (!ext4_handle_valid(handle) || handle->h_sync == 0) {
+ ext4_journal_stop(handle);
+ handle = NULL;
+ }
/* Submit prepared bio */
ext4_io_submit(&mpd.io_submit);
/* Unlock pages we didn't use */
mpage_release_unused_pages(&mpd, give_up_on_write);
- /* Drop our io_end reference we got from init */
- ext4_put_io_end(mpd.io_submit.io_end);
+ /*
+ * Drop our io_end reference we got from init. We have
+ * to be careful and use deferred io_end finishing if
+ * we are still holding the transaction as we can
+ * release the last reference to io_end which may end
+ * up doing unwritten extent conversion.
+ */
+ if (handle) {
+ ext4_put_io_end_defer(mpd.io_submit.io_end);
+ ext4_journal_stop(handle);
+ } else
+ ext4_put_io_end(mpd.io_submit.io_end);
if (ret == -ENOSPC && sbi->s_journal) {
/*
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index cf734170daa9..c4dcac8a018d 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2932,7 +2932,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
ext4_error(sb, "Allocating blocks %llu-%llu which overlap "
"fs metadata", block, block+len);
/* File system mounted not to panic on error
- * Fix the bitmap and repeat the block allocation
+ * Fix the bitmap and return EFSCORRUPTED
* We leak some of the blocks here.
*/
ext4_lock_group(sb, ac->ac_b_ex.fe_group);
@@ -2941,7 +2941,7 @@ ext4_mb_mark_diskspace_used(struct ext4_allocation_context *ac,
ext4_unlock_group(sb, ac->ac_b_ex.fe_group);
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
if (!err)
- err = -EAGAIN;
+ err = -EFSCORRUPTED;
goto out_err;
}
@@ -4506,18 +4506,7 @@ repeat:
}
if (likely(ac->ac_status == AC_STATUS_FOUND)) {
*errp = ext4_mb_mark_diskspace_used(ac, handle, reserv_clstrs);
- if (*errp == -EAGAIN) {
- /*
- * drop the reference that we took
- * in ext4_mb_use_best_found
- */
- ext4_mb_release_context(ac);
- ac->ac_b_ex.fe_group = 0;
- ac->ac_b_ex.fe_start = 0;
- ac->ac_b_ex.fe_len = 0;
- ac->ac_status = AC_STATUS_CONTINUE;
- goto repeat;
- } else if (*errp) {
+ if (*errp) {
ext4_discard_allocated_blocks(ac);
goto errout;
} else {
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 852c26806af2..c542ebcf7a92 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2240,6 +2240,16 @@ static void ext4_orphan_cleanup(struct super_block *sb,
while (es->s_last_orphan) {
struct inode *inode;
+ /*
+ * We may have encountered an error during cleanup; if
+ * so, skip the rest.
+ */
+ if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
+ jbd_debug(1, "Skipping orphan recovery on fs with errors.\n");
+ es->s_last_orphan = 0;
+ break;
+ }
+
inode = ext4_orphan_get(sb, le32_to_cpu(es->s_last_orphan));
if (IS_ERR(inode)) {
es->s_last_orphan = 0;
@@ -3372,6 +3382,13 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
goto failed_mount;
}
+ if (le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) > (blocksize / 4)) {
+ ext4_msg(sb, KERN_ERR,
+ "Number of reserved GDT blocks insanely large: %d",
+ le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks));
+ goto failed_mount;
+ }
+
if (sbi->s_mount_opt & EXT4_MOUNT_DAX) {
if (blocksize != PAGE_SIZE) {
ext4_msg(sb, KERN_ERR,
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index c2e340d6ec6e..d58d4c0af0ce 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -417,6 +417,15 @@ static int fuse_flush(struct file *file, fl_owner_t id)
fuse_sync_writes(inode);
mutex_unlock(&inode->i_mutex);
+ if (test_bit(AS_ENOSPC, &file->f_mapping->flags) &&
+ test_and_clear_bit(AS_ENOSPC, &file->f_mapping->flags))
+ err = -ENOSPC;
+ if (test_bit(AS_EIO, &file->f_mapping->flags) &&
+ test_and_clear_bit(AS_EIO, &file->f_mapping->flags))
+ err = -EIO;
+ if (err)
+ return err;
+
req = fuse_get_req_nofail_nopages(fc, file);
memset(&inarg, 0, sizeof(inarg));
inarg.fh = ff->fh;
@@ -462,6 +471,21 @@ int fuse_fsync_common(struct file *file, loff_t start, loff_t end,
goto out;
fuse_sync_writes(inode);
+
+ /*
+ * Due to implementation of fuse writeback
+ * filemap_write_and_wait_range() does not catch errors.
+ * We have to do this directly after fuse_sync_writes()
+ */
+ if (test_bit(AS_ENOSPC, &file->f_mapping->flags) &&
+ test_and_clear_bit(AS_ENOSPC, &file->f_mapping->flags))
+ err = -ENOSPC;
+ if (test_bit(AS_EIO, &file->f_mapping->flags) &&
+ test_and_clear_bit(AS_EIO, &file->f_mapping->flags))
+ err = -EIO;
+ if (err)
+ goto out;
+
err = sync_inode_metadata(inode, 1);
if (err)
goto out;
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 2913db2a5b99..0d5e8e59b390 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -926,7 +926,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC |
FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK |
FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ |
- FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA |
+ FUSE_FLOCK_LOCKS | FUSE_HAS_IOCTL_DIR | FUSE_AUTO_INVAL_DATA |
FUSE_DO_READDIRPLUS | FUSE_READDIRPLUS_AUTO | FUSE_ASYNC_DIO |
FUSE_WRITEBACK_CACHE | FUSE_NO_OPEN_SUPPORT;
req->in.h.opcode = FUSE_INIT;
diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h
index e0ee0b3000b2..358a4db72a27 100644
--- a/include/linux/devpts_fs.h
+++ b/include/linux/devpts_fs.h
@@ -15,38 +15,24 @@
#include <linux/errno.h>
+struct pts_fs_info;
+
#ifdef CONFIG_UNIX98_PTYS
-int devpts_new_index(struct inode *ptmx_inode);
-void devpts_kill_index(struct inode *ptmx_inode, int idx);
-void devpts_add_ref(struct inode *ptmx_inode);
-void devpts_del_ref(struct inode *ptmx_inode);
+/* Look up a pts fs info and get a ref to it */
+struct pts_fs_info *devpts_get_ref(struct inode *, struct file *);
+void devpts_put_ref(struct pts_fs_info *);
+
+int devpts_new_index(struct pts_fs_info *);
+void devpts_kill_index(struct pts_fs_info *, int);
+
/* mknod in devpts */
-struct inode *devpts_pty_new(struct inode *ptmx_inode, dev_t device, int index,
- void *priv);
+struct inode *devpts_pty_new(struct pts_fs_info *, dev_t, int, void *);
/* get private structure */
void *devpts_get_priv(struct inode *pts_inode);
/* unlink */
void devpts_pty_kill(struct inode *inode);
-#else
-
-/* Dummy stubs in the no-pty case */
-static inline int devpts_new_index(struct inode *ptmx_inode) { return -EINVAL; }
-static inline void devpts_kill_index(struct inode *ptmx_inode, int idx) { }
-static inline void devpts_add_ref(struct inode *ptmx_inode) { }
-static inline void devpts_del_ref(struct inode *ptmx_inode) { }
-static inline struct inode *devpts_pty_new(struct inode *ptmx_inode,
- dev_t device, int index, void *priv)
-{
- return ERR_PTR(-EINVAL);
-}
-static inline void *devpts_get_priv(struct inode *pts_inode)
-{
- return NULL;
-}
-static inline void devpts_pty_kill(struct inode *inode) { }
-
#endif
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index cd0e2413c358..435fd8426b8a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -174,6 +174,11 @@ struct mem_cgroup_thresholds {
struct mem_cgroup_threshold_ary *spare;
};
+struct mem_cgroup_id {
+ int id;
+ atomic_t ref;
+};
+
/*
* The memory controller data structure. The memory controller controls both
* page cache and RSS per cgroup. We would eventually like to provide
@@ -183,6 +188,9 @@ struct mem_cgroup_thresholds {
struct mem_cgroup {
struct cgroup_subsys_state css;
+ /* Private memcg ID. Used to ID objects that outlive the cgroup */
+ struct mem_cgroup_id id;
+
/* Accounted resources */
struct page_counter memory;
struct page_counter memsw;
diff --git a/ipc/msg.c b/ipc/msg.c
index 1471db9a7e61..c6521c205cb4 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -680,7 +680,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
rcu_read_lock();
ipc_lock_object(&msq->q_perm);
- ipc_rcu_putref(msq, ipc_rcu_free);
+ ipc_rcu_putref(msq, msg_rcu_free);
/* raced with RMID? */
if (!ipc_valid_object(&msq->q_perm)) {
err = -EIDRM;
diff --git a/ipc/sem.c b/ipc/sem.c
index b471e5a3863d..20d07008ad5e 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -442,7 +442,7 @@ static inline struct sem_array *sem_obtain_object_check(struct ipc_namespace *ns
static inline void sem_lock_and_putref(struct sem_array *sma)
{
sem_lock(sma, NULL, -1);
- ipc_rcu_putref(sma, ipc_rcu_free);
+ ipc_rcu_putref(sma, sem_rcu_free);
}
static inline void sem_rmid(struct ipc_namespace *ns, struct sem_array *s)
@@ -1385,7 +1385,7 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
rcu_read_unlock();
sem_io = ipc_alloc(sizeof(ushort)*nsems);
if (sem_io == NULL) {
- ipc_rcu_putref(sma, ipc_rcu_free);
+ ipc_rcu_putref(sma, sem_rcu_free);
return -ENOMEM;
}
@@ -1419,20 +1419,20 @@ static int semctl_main(struct ipc_namespace *ns, int semid, int semnum,
if (nsems > SEMMSL_FAST) {
sem_io = ipc_alloc(sizeof(ushort)*nsems);
if (sem_io == NULL) {
- ipc_rcu_putref(sma, ipc_rcu_free);
+ ipc_rcu_putref(sma, sem_rcu_free);
return -ENOMEM;
}
}
if (copy_from_user(sem_io, p, nsems*sizeof(ushort))) {
- ipc_rcu_putref(sma, ipc_rcu_free);
+ ipc_rcu_putref(sma, sem_rcu_free);
err = -EFAULT;
goto out_free;
}
for (i = 0; i < nsems; i++) {
if (sem_io[i] > SEMVMX) {
- ipc_rcu_putref(sma, ipc_rcu_free);
+ ipc_rcu_putref(sma, sem_rcu_free);
err = -ERANGE;
goto out_free;
}
@@ -1722,7 +1722,7 @@ static struct sem_undo *find_alloc_undo(struct ipc_namespace *ns, int semid)
/* step 2: allocate new undo structure */
new = kzalloc(sizeof(struct sem_undo) + sizeof(short)*nsems, GFP_KERNEL);
if (!new) {
- ipc_rcu_putref(sma, ipc_rcu_free);
+ ipc_rcu_putref(sma, sem_rcu_free);
return ERR_PTR(-ENOMEM);
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 67648e6b2ac8..6b90d184e9c0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -272,21 +272,7 @@ static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg)
static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
{
- return memcg->css.id;
-}
-
-/*
- * A helper function to get mem_cgroup from ID. must be called under
- * rcu_read_lock(). The caller is responsible for calling
- * css_tryget_online() if the mem_cgroup is used for charging. (dropping
- * refcnt from swap can be called against removed memcg.)
- */
-static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
-{
- struct cgroup_subsys_state *css;
-
- css = css_from_id(id, &memory_cgrp_subsys);
- return mem_cgroup_from_css(css);
+ return memcg->id.id;
}
/* Writing them here to avoid exposing memcg's inner layout */
@@ -4124,6 +4110,88 @@ static struct cftype mem_cgroup_legacy_files[] = {
{ }, /* terminate */
};
+/*
+ * Private memory cgroup IDR
+ *
+ * Swap-out records and page cache shadow entries need to store memcg
+ * references in constrained space, so we maintain an ID space that is
+ * limited to 16 bit (MEM_CGROUP_ID_MAX), limiting the total number of
+ * memory-controlled cgroups to 64k.
+ *
+ * However, there usually are many references to the oflline CSS after
+ * the cgroup has been destroyed, such as page cache or reclaimable
+ * slab objects, that don't need to hang on to the ID. We want to keep
+ * those dead CSS from occupying IDs, or we might quickly exhaust the
+ * relatively small ID space and prevent the creation of new cgroups
+ * even when there are much fewer than 64k cgroups - possibly none.
+ *
+ * Maintain a private 16-bit ID space for memcg, and allow the ID to
+ * be freed and recycled when it's no longer needed, which is usually
+ * when the CSS is offlined.
+ *
+ * The only exception to that are records of swapped out tmpfs/shmem
+ * pages that need to be attributed to live ancestors on swapin. But
+ * those references are manageable from userspace.
+ */
+
+static DEFINE_IDR(mem_cgroup_idr);
+
+static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n)
+{
+ atomic_add(n, &memcg->id.ref);
+}
+
+static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
+{
+ while (!atomic_inc_not_zero(&memcg->id.ref)) {
+ /*
+ * The root cgroup cannot be destroyed, so it's refcount must
+ * always be >= 1.
+ */
+ if (WARN_ON_ONCE(memcg == root_mem_cgroup)) {
+ VM_BUG_ON(1);
+ break;
+ }
+ memcg = parent_mem_cgroup(memcg);
+ if (!memcg)
+ memcg = root_mem_cgroup;
+ }
+ return memcg;
+}
+
+static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n)
+{
+ if (atomic_sub_and_test(n, &memcg->id.ref)) {
+ idr_remove(&mem_cgroup_idr, memcg->id.id);
+ memcg->id.id = 0;
+
+ /* Memcg ID pins CSS */
+ css_put(&memcg->css);
+ }
+}
+
+static inline void mem_cgroup_id_get(struct mem_cgroup *memcg)
+{
+ mem_cgroup_id_get_many(memcg, 1);
+}
+
+static inline void mem_cgroup_id_put(struct mem_cgroup *memcg)
+{
+ mem_cgroup_id_put_many(memcg, 1);
+}
+
+/**
+ * mem_cgroup_from_id - look up a memcg from a memcg id
+ * @id: the memcg id to look up
+ *
+ * Caller must hold rcu_read_lock().
+ */
+struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
+{
+ WARN_ON_ONCE(!rcu_read_lock_held());
+ return idr_find(&mem_cgroup_idr, id);
+}
+
static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
{
struct mem_cgroup_per_node *pn;
@@ -4178,6 +4246,12 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
if (memcg_wb_domain_init(memcg, GFP_KERNEL))
goto out_free_stat;
+ memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL,
+ 1, MEM_CGROUP_ID_MAX,
+ GFP_KERNEL);
+ if (memcg->id.id < 0)
+ goto out_free_stat;
+
return memcg;
out_free_stat:
@@ -4263,9 +4337,11 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
#ifdef CONFIG_CGROUP_WRITEBACK
INIT_LIST_HEAD(&memcg->cgwb_list);
#endif
+ idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
return &memcg->css;
free_out:
+ idr_remove(&mem_cgroup_idr, memcg->id.id);
__mem_cgroup_free(memcg);
return ERR_PTR(error);
}
@@ -4277,8 +4353,9 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
struct mem_cgroup *parent = mem_cgroup_from_css(css->parent);
int ret;
- if (css->id > MEM_CGROUP_ID_MAX)
- return -ENOSPC;
+ /* Online state pins memcg ID, memcg ID pins CSS */
+ mem_cgroup_id_get(mem_cgroup_from_css(css));
+ css_get(css);
if (!parent)
return 0;
@@ -4352,6 +4429,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
memcg_deactivate_kmem(memcg);
wb_memcg_offline(memcg);
+
+ mem_cgroup_id_put(memcg);
}
static void mem_cgroup_css_released(struct cgroup_subsys_state *css)
@@ -4785,6 +4864,8 @@ static void __mem_cgroup_clear_mc(void)
if (!mem_cgroup_is_root(mc.from))
page_counter_uncharge(&mc.from->memsw, mc.moved_swap);
+ mem_cgroup_id_put_many(mc.from, mc.moved_swap);
+
/*
* we charged both to->memory and to->memsw, so we
* should uncharge to->memory.
@@ -4792,9 +4873,9 @@ static void __mem_cgroup_clear_mc(void)
if (!mem_cgroup_is_root(mc.to))
page_counter_uncharge(&mc.to->memory, mc.moved_swap);
- css_put_many(&mc.from->css, mc.moved_swap);
+ mem_cgroup_id_get_many(mc.to, mc.moved_swap);
+ css_put_many(&mc.to->css, mc.moved_swap);
- /* we've already done css_get(mc.to) */
mc.moved_swap = 0;
}
memcg_oom_recover(from);
@@ -5670,7 +5751,7 @@ subsys_initcall(mem_cgroup_init);
*/
void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
{
- struct mem_cgroup *memcg;
+ struct mem_cgroup *memcg, *swap_memcg;
unsigned short oldid;
VM_BUG_ON_PAGE(PageLRU(page), page);
@@ -5685,15 +5766,27 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
if (!memcg)
return;
- oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
+ /*
+ * In case the memcg owning these pages has been offlined and doesn't
+ * have an ID allocated to it anymore, charge the closest online
+ * ancestor for the swap instead and transfer the memory+swap charge.
+ */
+ swap_memcg = mem_cgroup_id_get_online(memcg);
+ oldid = swap_cgroup_record(entry, mem_cgroup_id(swap_memcg));
VM_BUG_ON_PAGE(oldid, page);
- mem_cgroup_swap_statistics(memcg, true);
+ mem_cgroup_swap_statistics(swap_memcg, true);
page->mem_cgroup = NULL;
if (!mem_cgroup_is_root(memcg))
page_counter_uncharge(&memcg->memory, 1);
+ if (memcg != swap_memcg) {
+ if (!mem_cgroup_is_root(swap_memcg))
+ page_counter_charge(&swap_memcg->memsw, 1);
+ page_counter_uncharge(&memcg->memsw, 1);
+ }
+
/*
* Interrupts should be disabled here because the caller holds the
* mapping->tree_lock lock which is taken with interrupts-off. It is
@@ -5703,6 +5796,9 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
VM_BUG_ON(!irqs_disabled());
mem_cgroup_charge_statistics(memcg, page, -1);
memcg_check_events(memcg, page);
+
+ if (!mem_cgroup_is_root(memcg))
+ css_put(&memcg->css);
}
/**
@@ -5726,7 +5822,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry)
if (!mem_cgroup_is_root(memcg))
page_counter_uncharge(&memcg->memsw, 1);
mem_cgroup_swap_statistics(memcg, false);
- css_put(&memcg->css);
+ mem_cgroup_id_put(memcg);
}
rcu_read_unlock();
}
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 3c6a86b4ec25..bec2fce9fafc 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -521,8 +521,8 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
goto out_unlock;
cgroup_name(css->cgroup, memcg_name_buf, sizeof(memcg_name_buf));
- cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name,
- css->id, memcg_name_buf);
+ cache_name = kasprintf(GFP_KERNEL, "%s(%llu:%s)", root_cache->name,
+ css->serial_nr, memcg_name_buf);
if (!cache_name)
goto out_unlock;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 2b68418c7198..ffe95d954007 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -479,6 +479,9 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
if (!rtnh_ok(rtnh, remaining))
return -EINVAL;
+ if (rtnh->rtnh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
+ return -EINVAL;
+
nexthop_nh->nh_flags =
(cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags;
nexthop_nh->nh_oif = rtnh->rtnh_ifindex;
@@ -1003,6 +1006,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
if (fib_props[cfg->fc_type].scope > cfg->fc_scope)
goto err_inval;
+ if (cfg->fc_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
+ goto err_inval;
+
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (cfg->fc_mp) {
nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d4c51158470f..12b98e257c5f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -89,7 +89,7 @@ int sysctl_tcp_adv_win_scale __read_mostly = 1;
EXPORT_SYMBOL(sysctl_tcp_adv_win_scale);
/* rfc5961 challenge ack rate limiting */
-int sysctl_tcp_challenge_ack_limit = 100;
+int sysctl_tcp_challenge_ack_limit = 1000;
int sysctl_tcp_stdurg __read_mostly;
int sysctl_tcp_rfc1337 __read_mostly;
@@ -3390,6 +3390,23 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32
return flag;
}
+static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,
+ u32 *last_oow_ack_time)
+{
+ if (*last_oow_ack_time) {
+ s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time);
+
+ if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {
+ NET_INC_STATS_BH(net, mib_idx);
+ return true; /* rate-limited: don't send yet! */
+ }
+ }
+
+ *last_oow_ack_time = tcp_time_stamp;
+
+ return false; /* not rate-limited: go ahead, send dupack now! */
+}
+
/* Return true if we're currently rate-limiting out-of-window ACKs and
* thus shouldn't send a dupack right now. We rate-limit dupacks in
* response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS
@@ -3403,21 +3420,9 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb,
/* Data packets without SYNs are not likely part of an ACK loop. */
if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) &&
!tcp_hdr(skb)->syn)
- goto not_rate_limited;
-
- if (*last_oow_ack_time) {
- s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time);
-
- if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {
- NET_INC_STATS_BH(net, mib_idx);
- return true; /* rate-limited: don't send yet! */
- }
- }
-
- *last_oow_ack_time = tcp_time_stamp;
+ return false;
-not_rate_limited:
- return false; /* not rate-limited: go ahead, send dupack now! */
+ return __tcp_oow_rate_limited(net, mib_idx, last_oow_ack_time);
}
/* RFC 5961 7 [ACK Throttling] */
@@ -3427,21 +3432,26 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
static u32 challenge_timestamp;
static unsigned int challenge_count;
struct tcp_sock *tp = tcp_sk(sk);
- u32 now;
+ u32 count, now;
/* First check our per-socket dupack rate limit. */
- if (tcp_oow_rate_limited(sock_net(sk), skb,
- LINUX_MIB_TCPACKSKIPPEDCHALLENGE,
- &tp->last_oow_ack_time))
+ if (__tcp_oow_rate_limited(sock_net(sk),
+ LINUX_MIB_TCPACKSKIPPEDCHALLENGE,
+ &tp->last_oow_ack_time))
return;
- /* Then check the check host-wide RFC 5961 rate limit. */
+ /* Then check host-wide RFC 5961 rate limit. */
now = jiffies / HZ;
if (now != challenge_timestamp) {
+ u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1;
+
challenge_timestamp = now;
- challenge_count = 0;
+ WRITE_ONCE(challenge_count, half +
+ prandom_u32_max(sysctl_tcp_challenge_ack_limit));
}
- if (++challenge_count <= sysctl_tcp_challenge_ack_limit) {
+ count = READ_ONCE(challenge_count);
+ if (count > 0) {
+ WRITE_ONCE(challenge_count, count - 1);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK);
tcp_send_ack(sk);
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 7c9883ab56e5..660c967ba84a 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -239,7 +239,8 @@ void tcp_select_initial_window(int __space, __u32 mss,
/* Set window scaling on max possible window
* See RFC1323 for an explanation of the limit to 14
*/
- space = max_t(u32, sysctl_tcp_rmem[2], sysctl_rmem_max);
+ space = max_t(u32, space, sysctl_tcp_rmem[2]);
+ space = max_t(u32, space, sysctl_rmem_max);
space = min_t(u32, space, *window_clamp);
while (space > 65535 && (*rcv_wscale) < 14) {
space >>= 1;
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 923abd6b3064..8d2f7c9b491d 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -1024,8 +1024,11 @@ static int irda_connect(struct socket *sock, struct sockaddr *uaddr,
}
/* Check if we have opened a local TSAP */
- if (!self->tsap)
- irda_open_tsap(self, LSAP_ANY, addr->sir_name);
+ if (!self->tsap) {
+ err = irda_open_tsap(self, LSAP_ANY, addr->sir_name);
+ if (err)
+ goto out;
+ }
/* Move to connecting socket, start sending Connect Requests */
sock->state = SS_CONNECTING;
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index ad4fa49ad1db..9068369f8a1b 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -331,6 +331,7 @@ static int aa_fs_seq_hash_show(struct seq_file *seq, void *v)
seq_printf(seq, "%.2x", profile->hash[i]);
seq_puts(seq, "\n");
}
+ aa_put_profile(profile);
return 0;
}
Powered by blists - more mailing lists