diff options
Diffstat (limited to '3.2.70/1062_linux-3.2.63.patch')
-rw-r--r-- | 3.2.70/1062_linux-3.2.63.patch | 5394 |
1 files changed, 5394 insertions, 0 deletions
diff --git a/3.2.70/1062_linux-3.2.63.patch b/3.2.70/1062_linux-3.2.63.patch new file mode 100644 index 0000000..f7c7415 --- /dev/null +++ b/3.2.70/1062_linux-3.2.63.patch @@ -0,0 +1,5394 @@ +diff --git a/Documentation/sound/alsa/ALSA-Configuration.txt b/Documentation/sound/alsa/ALSA-Configuration.txt +index 936699e..15806ef 100644 +--- a/Documentation/sound/alsa/ALSA-Configuration.txt ++++ b/Documentation/sound/alsa/ALSA-Configuration.txt +@@ -2018,8 +2018,8 @@ Prior to version 0.9.0rc4 options had a 'snd_' prefix. This was removed. + ------------------- + + Module for sound cards based on the Asus AV66/AV100/AV200 chips, +- i.e., Xonar D1, DX, D2, D2X, DS, Essence ST (Deluxe), Essence STX, +- HDAV1.3 (Deluxe), and HDAV1.3 Slim. ++ i.e., Xonar D1, DX, D2, D2X, DS, DSX, Essence ST (Deluxe), ++ Essence STX (II), HDAV1.3 (Deluxe), and HDAV1.3 Slim. + + This module supports autoprobe and multiple cards. + +diff --git a/Documentation/stable_kernel_rules.txt b/Documentation/stable_kernel_rules.txt +index 22bf11b..53feeac 100644 +--- a/Documentation/stable_kernel_rules.txt ++++ b/Documentation/stable_kernel_rules.txt +@@ -29,6 +29,9 @@ Rules on what kind of patches are accepted, and which ones are not, into the + + Procedure for submitting patches to the -stable tree: + ++ - If the patch covers files in net/ or drivers/net please follow netdev stable ++ submission guidelines as described in ++ Documentation/networking/netdev-FAQ.txt + - Send the patch, after verifying that it follows the above rules, to + stable@vger.kernel.org. You must note the upstream commit ID in the + changelog of your submission. +diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt +index d6498e3..f33a936 100644 +--- a/Documentation/x86/x86_64/mm.txt ++++ b/Documentation/x86/x86_64/mm.txt +@@ -12,6 +12,8 @@ ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space + ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole + ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB) + ... unused hole ... ++ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks ++... unused hole ... + ffffffff80000000 - ffffffffa0000000 (=512 MB) kernel text mapping, from phys 0 + ffffffffa0000000 - fffffffffff00000 (=1536 MB) module mapping space + +diff --git a/Makefile b/Makefile +index 30a5c65..6d3f2d4 100644 +--- a/Makefile ++++ b/Makefile +@@ -1,6 +1,6 @@ + VERSION = 3 + PATCHLEVEL = 2 +-SUBLEVEL = 62 ++SUBLEVEL = 63 + EXTRAVERSION = + NAME = Saber-toothed Squirrel + +@@ -592,6 +592,8 @@ KBUILD_CFLAGS += -fomit-frame-pointer + endif + endif + ++KBUILD_CFLAGS += $(call cc-option, -fno-var-tracking-assignments) ++ + ifdef CONFIG_DEBUG_INFO + KBUILD_CFLAGS += -g + KBUILD_AFLAGS += -gdwarf-2 +diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S +index 9a8531e..9d95a46 100644 +--- a/arch/arm/kernel/entry-header.S ++++ b/arch/arm/kernel/entry-header.S +@@ -76,26 +76,21 @@ + #ifndef CONFIG_THUMB2_KERNEL + .macro svc_exit, rpsr + msr spsr_cxsf, \rpsr +-#if defined(CONFIG_CPU_V6) +- ldr r0, [sp] +- strex r1, r2, [sp] @ clear the exclusive monitor +- ldmib sp, {r1 - pc}^ @ load r1 - pc, cpsr +-#elif defined(CONFIG_CPU_32v6K) +- clrex @ clear the exclusive monitor +- ldmia sp, {r0 - pc}^ @ load r0 - pc, cpsr +-#else +- ldmia sp, {r0 - pc}^ @ load r0 - pc, cpsr ++#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K) ++ @ We must avoid clrex due to Cortex-A15 erratum #830321 ++ sub r0, sp, #4 @ uninhabited address ++ strex r1, r2, [r0] @ clear the exclusive monitor + #endif ++ ldmia sp, {r0 - pc}^ @ load r0 - pc, cpsr + .endm + + .macro restore_user_regs, fast = 0, offset = 0 + ldr r1, [sp, #\offset + S_PSR] @ get calling cpsr + ldr lr, [sp, #\offset + S_PC]! @ get pc + msr spsr_cxsf, r1 @ save in spsr_svc +-#if defined(CONFIG_CPU_V6) ++#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K) ++ @ We must avoid clrex due to Cortex-A15 erratum #830321 + strex r1, r2, [sp] @ clear the exclusive monitor +-#elif defined(CONFIG_CPU_32v6K) +- clrex @ clear the exclusive monitor + #endif + .if \fast + ldmdb sp, {r1 - lr}^ @ get calling r1 - lr +@@ -123,7 +118,10 @@ + .macro svc_exit, rpsr + ldr lr, [sp, #S_SP] @ top of the stack + ldrd r0, r1, [sp, #S_LR] @ calling lr and pc +- clrex @ clear the exclusive monitor ++ ++ @ We must avoid clrex due to Cortex-A15 erratum #830321 ++ strex r2, r1, [sp, #S_LR] @ clear the exclusive monitor ++ + stmdb lr!, {r0, r1, \rpsr} @ calling lr and rfe context + ldmia sp, {r0 - r12} + mov sp, lr +@@ -132,13 +130,16 @@ + .endm + + .macro restore_user_regs, fast = 0, offset = 0 +- clrex @ clear the exclusive monitor + mov r2, sp + load_user_sp_lr r2, r3, \offset + S_SP @ calling sp, lr + ldr r1, [sp, #\offset + S_PSR] @ get calling cpsr + ldr lr, [sp, #\offset + S_PC] @ get pc + add sp, sp, #\offset + S_SP + msr spsr_cxsf, r1 @ save in spsr_svc ++ ++ @ We must avoid clrex due to Cortex-A15 erratum #830321 ++ strex r1, r2, [sp] @ clear the exclusive monitor ++ + .if \fast + ldmdb sp, {r1 - r12} @ get calling r1 - r12 + .else +diff --git a/arch/arm/mach-omap2/control.c b/arch/arm/mach-omap2/control.c +index e34d27f..724f823 100644 +--- a/arch/arm/mach-omap2/control.c ++++ b/arch/arm/mach-omap2/control.c +@@ -282,7 +282,8 @@ void omap3_save_scratchpad_contents(void) + scratchpad_contents.public_restore_ptr = + virt_to_phys(omap3_restore_3630); + else if (omap_rev() != OMAP3430_REV_ES3_0 && +- omap_rev() != OMAP3430_REV_ES3_1) ++ omap_rev() != OMAP3430_REV_ES3_1 && ++ omap_rev() != OMAP3430_REV_ES3_1_2) + scratchpad_contents.public_restore_ptr = + virt_to_phys(omap3_restore); + else +diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S +index 8074199..5d777a5 100644 +--- a/arch/arm/mm/abort-ev6.S ++++ b/arch/arm/mm/abort-ev6.S +@@ -17,12 +17,6 @@ + */ + .align 5 + ENTRY(v6_early_abort) +-#ifdef CONFIG_CPU_V6 +- sub r1, sp, #4 @ Get unused stack location +- strex r0, r1, [r1] @ Clear the exclusive monitor +-#elif defined(CONFIG_CPU_32v6K) +- clrex +-#endif + mrc p15, 0, r1, c5, c0, 0 @ get FSR + mrc p15, 0, r0, c6, c0, 0 @ get FAR + /* +diff --git a/arch/arm/mm/abort-ev7.S b/arch/arm/mm/abort-ev7.S +index 7033752..4812ad0 100644 +--- a/arch/arm/mm/abort-ev7.S ++++ b/arch/arm/mm/abort-ev7.S +@@ -13,12 +13,6 @@ + */ + .align 5 + ENTRY(v7_early_abort) +- /* +- * The effect of data aborts on on the exclusive access monitor are +- * UNPREDICTABLE. Do a CLREX to clear the state +- */ +- clrex +- + mrc p15, 0, r1, c5, c0, 0 @ get FSR + mrc p15, 0, r0, c6, c0, 0 @ get FAR + +diff --git a/arch/microblaze/boot/Makefile b/arch/microblaze/boot/Makefile +index 4c4e58e..5365519 100644 +--- a/arch/microblaze/boot/Makefile ++++ b/arch/microblaze/boot/Makefile +@@ -8,7 +8,7 @@ obj-y += linked_dtb.o + + targets := linux.bin linux.bin.gz simpleImage.% + +-OBJCOPYFLAGS := -O binary ++OBJCOPYFLAGS := -R .note -R .comment -R .note.gnu.build-id -O binary + + # Ensure system.dtb exists + $(obj)/linked_dtb.o: $(obj)/system.dtb +diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c +index 2d9028f..3c5f61c 100644 +--- a/arch/mips/cavium-octeon/setup.c ++++ b/arch/mips/cavium-octeon/setup.c +@@ -266,6 +266,18 @@ static irqreturn_t octeon_rlm_interrupt(int cpl, void *dev_id) + } + #endif + ++static char __read_mostly octeon_system_type[80]; ++ ++static int __init init_octeon_system_type(void) ++{ ++ snprintf(octeon_system_type, sizeof(octeon_system_type), "%s (%s)", ++ cvmx_board_type_to_string(octeon_bootinfo->board_type), ++ octeon_model_get_string(read_c0_prid())); ++ ++ return 0; ++} ++early_initcall(init_octeon_system_type); ++ + /** + * Return a string representing the system type + * +@@ -273,11 +285,7 @@ static irqreturn_t octeon_rlm_interrupt(int cpl, void *dev_id) + */ + const char *octeon_board_type_string(void) + { +- static char name[80]; +- sprintf(name, "%s (%s)", +- cvmx_board_type_to_string(octeon_bootinfo->board_type), +- octeon_model_get_string(read_c0_prid())); +- return name; ++ return octeon_system_type; + } + + const char *get_system_type(void) +diff --git a/arch/mips/kernel/irq-gic.c b/arch/mips/kernel/irq-gic.c +index 0c527f6..e132bfd 100644 +--- a/arch/mips/kernel/irq-gic.c ++++ b/arch/mips/kernel/irq-gic.c +@@ -166,11 +166,13 @@ static void __init gic_setup_intr(unsigned int intr, unsigned int cpu, + { + /* Setup Intr to Pin mapping */ + if (pin & GIC_MAP_TO_NMI_MSK) { ++ int i; ++ + GICWRITE(GIC_REG_ADDR(SHARED, GIC_SH_MAP_TO_PIN(intr)), pin); + /* FIXME: hack to route NMI to all cpu's */ +- for (cpu = 0; cpu < NR_CPUS; cpu += 32) { ++ for (i = 0; i < NR_CPUS; i += 32) { + GICWRITE(GIC_REG_ADDR(SHARED, +- GIC_SH_MAP_TO_VPE_REG_OFF(intr, cpu)), ++ GIC_SH_MAP_TO_VPE_REG_OFF(intr, i)), + 0xffffffff); + } + } else { +diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c +index 315fc0b..dc6ffe0 100644 +--- a/arch/mips/kernel/perf_event_mipsxx.c ++++ b/arch/mips/kernel/perf_event_mipsxx.c +@@ -162,11 +162,6 @@ static unsigned int counters_total_to_per_cpu(unsigned int counters) + return counters >> vpe_shift(); + } + +-static unsigned int counters_per_cpu_to_total(unsigned int counters) +-{ +- return counters << vpe_shift(); +-} +- + #else /* !CONFIG_MIPS_MT_SMP */ + #define vpe_id() 0 + +diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c +index 4e6ea1f..e56c692 100644 +--- a/arch/mips/kernel/ptrace.c ++++ b/arch/mips/kernel/ptrace.c +@@ -162,6 +162,7 @@ int ptrace_setfpregs(struct task_struct *child, __u32 __user *data) + __get_user(fregs[i], i + (__u64 __user *) data); + + __get_user(child->thread.fpu.fcr31, data + 64); ++ child->thread.fpu.fcr31 &= ~FPU_CSR_ALL_X; + + /* FIR may not be written. */ + +@@ -452,7 +453,7 @@ long arch_ptrace(struct task_struct *child, long request, + break; + #endif + case FPC_CSR: +- child->thread.fpu.fcr31 = data; ++ child->thread.fpu.fcr31 = data & ~FPU_CSR_ALL_X; + break; + case DSP_BASE ... DSP_BASE + 5: { + dspreg_t *dregs; +diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c +index 7d5ac0b..fe425bb 100644 +--- a/arch/mips/mm/c-r4k.c ++++ b/arch/mips/mm/c-r4k.c +@@ -12,6 +12,7 @@ + #include <linux/highmem.h> + #include <linux/kernel.h> + #include <linux/linkage.h> ++#include <linux/preempt.h> + #include <linux/sched.h> + #include <linux/smp.h> + #include <linux/mm.h> +@@ -599,6 +600,7 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size) + /* Catch bad driver code */ + BUG_ON(size == 0); + ++ preempt_disable(); + if (cpu_has_inclusive_pcaches) { + if (size >= scache_size) + r4k_blast_scache(); +@@ -619,6 +621,7 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size) + R4600_HIT_CACHEOP_WAR_IMPL; + blast_dcache_range(addr, addr + size); + } ++ preempt_enable(); + + bc_wback_inv(addr, size); + __sync(); +@@ -629,6 +632,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size) + /* Catch bad driver code */ + BUG_ON(size == 0); + ++ preempt_disable(); + if (cpu_has_inclusive_pcaches) { + if (size >= scache_size) + r4k_blast_scache(); +@@ -653,6 +657,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size) + R4600_HIT_CACHEOP_WAR_IMPL; + blast_inv_dcache_range(addr, addr + size); + } ++ preempt_enable(); + + bc_inv(addr, size); + __sync(); +diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c +index e06370f..3ee768e 100644 +--- a/arch/mips/mm/tlbex.c ++++ b/arch/mips/mm/tlbex.c +@@ -1282,6 +1282,7 @@ static void __cpuinit build_r4000_tlb_refill_handler(void) + } + #ifdef CONFIG_HUGETLB_PAGE + uasm_l_tlb_huge_update(&l, p); ++ UASM_i_LW(&p, K0, 0, K1); + build_huge_update_entries(&p, htlb_info.huge_pte, K1); + build_huge_tlb_write_entry(&p, &l, &r, K0, tlb_random, + htlb_info.restore_scratch); +diff --git a/arch/openrisc/kernel/head.S b/arch/openrisc/kernel/head.S +index c75018d..23a3019 100644 +--- a/arch/openrisc/kernel/head.S ++++ b/arch/openrisc/kernel/head.S +@@ -19,6 +19,7 @@ + #include <linux/threads.h> + #include <linux/errno.h> + #include <linux/init.h> ++#include <linux/serial_reg.h> + #include <asm/processor.h> + #include <asm/page.h> + #include <asm/mmu.h> +diff --git a/arch/openrisc/kernel/init_task.c b/arch/openrisc/kernel/init_task.c +index 45744a38..ca53408 100644 +--- a/arch/openrisc/kernel/init_task.c ++++ b/arch/openrisc/kernel/init_task.c +@@ -17,6 +17,7 @@ + + #include <linux/init_task.h> + #include <linux/mqueue.h> ++#include <linux/export.h> + + static struct signal_struct init_signals = INIT_SIGNALS(init_signals); + static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand); +diff --git a/arch/openrisc/kernel/irq.c b/arch/openrisc/kernel/irq.c +index 59b3023..4bfead2 100644 +--- a/arch/openrisc/kernel/irq.c ++++ b/arch/openrisc/kernel/irq.c +@@ -23,6 +23,7 @@ + #include <linux/irq.h> + #include <linux/seq_file.h> + #include <linux/kernel_stat.h> ++#include <linux/export.h> + + #include <linux/irqflags.h> + +diff --git a/arch/powerpc/include/asm/pte-hash64-64k.h b/arch/powerpc/include/asm/pte-hash64-64k.h +index 59247e8..4ac50bb 100644 +--- a/arch/powerpc/include/asm/pte-hash64-64k.h ++++ b/arch/powerpc/include/asm/pte-hash64-64k.h +@@ -40,17 +40,39 @@ + + #ifndef __ASSEMBLY__ + ++#include <asm/system.h> /* for smp_rmb() */ ++ + /* + * With 64K pages on hash table, we have a special PTE format that + * uses a second "half" of the page table to encode sub-page information + * in order to deal with 64K made of 4K HW pages. Thus we override the + * generic accessors and iterators here + */ +-#define __real_pte(e,p) ((real_pte_t) { \ +- (e), ((e) & _PAGE_COMBO) ? \ +- (pte_val(*((p) + PTRS_PER_PTE))) : 0 }) +-#define __rpte_to_hidx(r,index) ((pte_val((r).pte) & _PAGE_COMBO) ? \ +- (((r).hidx >> ((index)<<2)) & 0xf) : ((pte_val((r).pte) >> 12) & 0xf)) ++#define __real_pte __real_pte ++static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep) ++{ ++ real_pte_t rpte; ++ ++ rpte.pte = pte; ++ rpte.hidx = 0; ++ if (pte_val(pte) & _PAGE_COMBO) { ++ /* ++ * Make sure we order the hidx load against the _PAGE_COMBO ++ * check. The store side ordering is done in __hash_page_4K ++ */ ++ smp_rmb(); ++ rpte.hidx = pte_val(*((ptep) + PTRS_PER_PTE)); ++ } ++ return rpte; ++} ++ ++static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index) ++{ ++ if ((pte_val(rpte.pte) & _PAGE_COMBO)) ++ return (rpte.hidx >> (index<<2)) & 0xf; ++ return (pte_val(rpte.pte) >> 12) & 0xf; ++} ++ + #define __rpte_to_pte(r) ((r).pte) + #define __rpte_sub_valid(rpte, index) \ + (pte_val(rpte.pte) & (_PAGE_HPTE_SUB0 >> (index))) +diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c +index 458ed3b..12659ab 100644 +--- a/arch/powerpc/kernel/pci-common.c ++++ b/arch/powerpc/kernel/pci-common.c +@@ -363,7 +363,6 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, + enum pci_mmap_state mmap_state, + int write_combine) + { +- unsigned long prot = pgprot_val(protection); + + /* Write combine is always 0 on non-memory space mappings. On + * memory space, if the user didn't pass 1, we check for a +@@ -380,9 +379,9 @@ static pgprot_t __pci_mmap_set_pgprot(struct pci_dev *dev, struct resource *rp, + + /* XXX would be nice to have a way to ask for write-through */ + if (write_combine) +- return pgprot_noncached_wc(prot); ++ return pgprot_noncached_wc(protection); + else +- return pgprot_noncached(prot); ++ return pgprot_noncached(protection); + } + + /* +diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c +index e94b57f..75dd32e 100644 +--- a/arch/powerpc/mm/init_64.c ++++ b/arch/powerpc/mm/init_64.c +@@ -218,7 +218,8 @@ static void __meminit vmemmap_create_mapping(unsigned long start, + unsigned long phys) + { + int mapped = htab_bolt_mapping(start, start + page_size, phys, +- PAGE_KERNEL, mmu_vmemmap_psize, ++ pgprot_val(PAGE_KERNEL), ++ mmu_vmemmap_psize, + mmu_kernel_ssize); + BUG_ON(mapped < 0); + } +diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c +index 24523dc..f4b78a3 100644 +--- a/arch/powerpc/mm/numa.c ++++ b/arch/powerpc/mm/numa.c +@@ -600,8 +600,8 @@ static int __cpuinit cpu_numa_callback(struct notifier_block *nfb, + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + unmap_cpu_from_node(lcpu); +- break; + ret = NOTIFY_OK; ++ break; + #endif + } + return ret; +diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig +index a3c40e8..aed3d91 100644 +--- a/arch/s390/Kconfig ++++ b/arch/s390/Kconfig +@@ -119,6 +119,7 @@ config S390 + select ARCH_INLINE_WRITE_UNLOCK_BH + select ARCH_INLINE_WRITE_UNLOCK_IRQ + select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE ++ select ARCH_SUPPORTS_ATOMIC_RMW + + config SCHED_OMIT_FRAME_POINTER + def_bool y +diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild +index 2c2e388..39a0b4f 100644 +--- a/arch/sparc/include/asm/Kbuild ++++ b/arch/sparc/include/asm/Kbuild +@@ -21,3 +21,4 @@ generic-y += div64.h + generic-y += local64.h + generic-y += irq_regs.h + generic-y += local.h ++generic-y += types.h +diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h +index ddbbea3..7ee5a1c 100644 +--- a/arch/sparc/include/asm/pgtable_64.h ++++ b/arch/sparc/include/asm/pgtable_64.h +@@ -25,7 +25,8 @@ + + /* The kernel image occupies 0x4000000 to 0x6000000 (4MB --> 96MB). + * The page copy blockops can use 0x6000000 to 0x8000000. +- * The TSB is mapped in the 0x8000000 to 0xa000000 range. ++ * The 8K TSB is mapped in the 0x8000000 to 0x8400000 range. ++ * The 4M TSB is mapped in the 0x8400000 to 0x8800000 range. + * The PROM resides in an area spanning 0xf0000000 to 0x100000000. + * The vmalloc area spans 0x100000000 to 0x200000000. + * Since modules need to be in the lowest 32-bits of the address space, +@@ -34,7 +35,8 @@ + * 0x400000000. + */ + #define TLBTEMP_BASE _AC(0x0000000006000000,UL) +-#define TSBMAP_BASE _AC(0x0000000008000000,UL) ++#define TSBMAP_8K_BASE _AC(0x0000000008000000,UL) ++#define TSBMAP_4M_BASE _AC(0x0000000008400000,UL) + #define MODULES_VADDR _AC(0x0000000010000000,UL) + #define MODULES_LEN _AC(0x00000000e0000000,UL) + #define MODULES_END _AC(0x00000000f0000000,UL) +diff --git a/arch/sparc/include/asm/tlbflush_64.h b/arch/sparc/include/asm/tlbflush_64.h +index f0d6a97..1a4bb97 100644 +--- a/arch/sparc/include/asm/tlbflush_64.h ++++ b/arch/sparc/include/asm/tlbflush_64.h +@@ -35,6 +35,8 @@ static inline void flush_tlb_range(struct vm_area_struct *vma, + { + } + ++void flush_tlb_kernel_range(unsigned long start, unsigned long end); ++ + #define __HAVE_ARCH_ENTER_LAZY_MMU_MODE + + extern void flush_tlb_pending(void); +@@ -49,11 +51,6 @@ extern void __flush_tlb_kernel_range(unsigned long start, unsigned long end); + + #ifndef CONFIG_SMP + +-#define flush_tlb_kernel_range(start,end) \ +-do { flush_tsb_kernel_range(start,end); \ +- __flush_tlb_kernel_range(start,end); \ +-} while (0) +- + static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) + { + __flush_tlb_page(CTX_HWBITS(mm->context), vaddr); +@@ -64,11 +61,6 @@ static inline void global_flush_tlb_page(struct mm_struct *mm, unsigned long vad + extern void smp_flush_tlb_kernel_range(unsigned long start, unsigned long end); + extern void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr); + +-#define flush_tlb_kernel_range(start, end) \ +-do { flush_tsb_kernel_range(start,end); \ +- smp_flush_tlb_kernel_range(start, end); \ +-} while (0) +- + #define global_flush_tlb_page(mm, vaddr) \ + smp_flush_tlb_page(mm, vaddr) + +diff --git a/arch/sparc/include/asm/types.h b/arch/sparc/include/asm/types.h +deleted file mode 100644 +index 91e5a03..0000000 +--- a/arch/sparc/include/asm/types.h ++++ /dev/null +@@ -1,23 +0,0 @@ +-#ifndef _SPARC_TYPES_H +-#define _SPARC_TYPES_H +-/* +- * This file is never included by application software unless +- * explicitly requested (e.g., via linux/types.h) in which case the +- * application is Linux specific so (user-) name space pollution is +- * not a major issue. However, for interoperability, libraries still +- * need to be careful to avoid a name clashes. +- */ +- +-#if defined(__sparc__) +- +-#include <asm-generic/int-ll64.h> +- +-#ifndef __ASSEMBLY__ +- +-typedef unsigned short umode_t; +- +-#endif /* __ASSEMBLY__ */ +- +-#endif /* defined(__sparc__) */ +- +-#endif /* defined(_SPARC_TYPES_H) */ +diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c +index 435e406..1beaf60 100644 +--- a/arch/sparc/kernel/ldc.c ++++ b/arch/sparc/kernel/ldc.c +@@ -1339,7 +1339,7 @@ int ldc_connect(struct ldc_channel *lp) + if (!(lp->flags & LDC_FLAG_ALLOCED_QUEUES) || + !(lp->flags & LDC_FLAG_REGISTERED_QUEUES) || + lp->hs_state != LDC_HS_OPEN) +- err = -EINVAL; ++ err = ((lp->hs_state > LDC_HS_OPEN) ? 0 : -EINVAL); + else + err = start_handshake(lp); + +diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c +index e21d3c0d..ffd1245 100644 +--- a/arch/sparc/kernel/smp_64.c ++++ b/arch/sparc/kernel/smp_64.c +@@ -151,7 +151,7 @@ void cpu_panic(void) + #define NUM_ROUNDS 64 /* magic value */ + #define NUM_ITERS 5 /* likewise */ + +-static DEFINE_SPINLOCK(itc_sync_lock); ++static DEFINE_RAW_SPINLOCK(itc_sync_lock); + static unsigned long go[SLAVE + 1]; + + #define DEBUG_TICK_SYNC 0 +@@ -259,7 +259,7 @@ static void smp_synchronize_one_tick(int cpu) + go[MASTER] = 0; + membar_safe("#StoreLoad"); + +- spin_lock_irqsave(&itc_sync_lock, flags); ++ raw_spin_lock_irqsave(&itc_sync_lock, flags); + { + for (i = 0; i < NUM_ROUNDS*NUM_ITERS; i++) { + while (!go[MASTER]) +@@ -270,7 +270,7 @@ static void smp_synchronize_one_tick(int cpu) + membar_safe("#StoreLoad"); + } + } +- spin_unlock_irqrestore(&itc_sync_lock, flags); ++ raw_spin_unlock_irqrestore(&itc_sync_lock, flags); + } + + #if defined(CONFIG_SUN_LDOMS) && defined(CONFIG_HOTPLUG_CPU) +diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S +index d97f3eb..085c60f 100644 +--- a/arch/sparc/kernel/sys32.S ++++ b/arch/sparc/kernel/sys32.S +@@ -87,7 +87,7 @@ SIGN1(sys32_io_submit, compat_sys_io_submit, %o1) + SIGN1(sys32_mq_open, compat_sys_mq_open, %o1) + SIGN1(sys32_select, compat_sys_select, %o0) + SIGN1(sys32_mkdir, sys_mkdir, %o1) +-SIGN3(sys32_futex, compat_sys_futex, %o1, %o2, %o5) ++SIGN1(sys32_futex, compat_sys_futex, %o1) + SIGN1(sys32_sysfs, compat_sys_sysfs, %o0) + SIGN2(sys32_sendfile, compat_sys_sendfile, %o0, %o1) + SIGN2(sys32_sendfile64, compat_sys_sendfile64, %o0, %o1) +diff --git a/arch/sparc/kernel/unaligned_64.c b/arch/sparc/kernel/unaligned_64.c +index 76e4ac1..1c90812 100644 +--- a/arch/sparc/kernel/unaligned_64.c ++++ b/arch/sparc/kernel/unaligned_64.c +@@ -156,17 +156,23 @@ static unsigned long *fetch_reg_addr(unsigned int reg, struct pt_regs *regs) + unsigned long compute_effective_address(struct pt_regs *regs, + unsigned int insn, unsigned int rd) + { ++ int from_kernel = (regs->tstate & TSTATE_PRIV) != 0; + unsigned int rs1 = (insn >> 14) & 0x1f; + unsigned int rs2 = insn & 0x1f; +- int from_kernel = (regs->tstate & TSTATE_PRIV) != 0; ++ unsigned long addr; + + if (insn & 0x2000) { + maybe_flush_windows(rs1, 0, rd, from_kernel); +- return (fetch_reg(rs1, regs) + sign_extend_imm13(insn)); ++ addr = (fetch_reg(rs1, regs) + sign_extend_imm13(insn)); + } else { + maybe_flush_windows(rs1, rs2, rd, from_kernel); +- return (fetch_reg(rs1, regs) + fetch_reg(rs2, regs)); ++ addr = (fetch_reg(rs1, regs) + fetch_reg(rs2, regs)); + } ++ ++ if (!from_kernel && test_thread_flag(TIF_32BIT)) ++ addr &= 0xffffffff; ++ ++ return addr; + } + + /* This is just to make gcc think die_if_kernel does return... */ +diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S +index 0aed756..e993fc8 100644 +--- a/arch/sparc/lib/NG2memcpy.S ++++ b/arch/sparc/lib/NG2memcpy.S +@@ -236,6 +236,7 @@ FUNC_NAME: /* %o0=dst, %o1=src, %o2=len */ + */ + VISEntryHalf + ++ membar #Sync + alignaddr %o1, %g0, %g0 + + add %o1, (64 - 1), %o4 +diff --git a/arch/sparc/math-emu/math_32.c b/arch/sparc/math-emu/math_32.c +index aa4d55b..5ce8f2f 100644 +--- a/arch/sparc/math-emu/math_32.c ++++ b/arch/sparc/math-emu/math_32.c +@@ -499,7 +499,7 @@ static int do_one_mathemu(u32 insn, unsigned long *pfsr, unsigned long *fregs) + case 0: fsr = *pfsr; + if (IR == -1) IR = 2; + /* fcc is always fcc0 */ +- fsr &= ~0xc00; fsr |= (IR << 10); break; ++ fsr &= ~0xc00; fsr |= (IR << 10); + *pfsr = fsr; + break; + case 1: rd->s = IR; break; +diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c +index 504c062..2c0b966 100644 +--- a/arch/sparc/mm/fault_64.c ++++ b/arch/sparc/mm/fault_64.c +@@ -95,38 +95,51 @@ static unsigned int get_user_insn(unsigned long tpc) + pte_t *ptep, pte; + unsigned long pa; + u32 insn = 0; +- unsigned long pstate; + +- if (pgd_none(*pgdp)) +- goto outret; ++ if (pgd_none(*pgdp) || unlikely(pgd_bad(*pgdp))) ++ goto out; + pudp = pud_offset(pgdp, tpc); +- if (pud_none(*pudp)) +- goto outret; +- pmdp = pmd_offset(pudp, tpc); +- if (pmd_none(*pmdp)) +- goto outret; +- +- /* This disables preemption for us as well. */ +- __asm__ __volatile__("rdpr %%pstate, %0" : "=r" (pstate)); +- __asm__ __volatile__("wrpr %0, %1, %%pstate" +- : : "r" (pstate), "i" (PSTATE_IE)); +- ptep = pte_offset_map(pmdp, tpc); +- pte = *ptep; +- if (!pte_present(pte)) ++ if (pud_none(*pudp) || unlikely(pud_bad(*pudp))) + goto out; + +- pa = (pte_pfn(pte) << PAGE_SHIFT); +- pa += (tpc & ~PAGE_MASK); +- +- /* Use phys bypass so we don't pollute dtlb/dcache. */ +- __asm__ __volatile__("lduwa [%1] %2, %0" +- : "=r" (insn) +- : "r" (pa), "i" (ASI_PHYS_USE_EC)); ++ /* This disables preemption for us as well. */ ++ local_irq_disable(); + ++ pmdp = pmd_offset(pudp, tpc); ++ if (pmd_none(*pmdp) || unlikely(pmd_bad(*pmdp))) ++ goto out_irq_enable; ++ ++#ifdef CONFIG_TRANSPARENT_HUGEPAGE ++ if (pmd_trans_huge(*pmdp)) { ++ if (pmd_trans_splitting(*pmdp)) ++ goto out_irq_enable; ++ ++ pa = pmd_pfn(*pmdp) << PAGE_SHIFT; ++ pa += tpc & ~HPAGE_MASK; ++ ++ /* Use phys bypass so we don't pollute dtlb/dcache. */ ++ __asm__ __volatile__("lduwa [%1] %2, %0" ++ : "=r" (insn) ++ : "r" (pa), "i" (ASI_PHYS_USE_EC)); ++ } else ++#endif ++ { ++ ptep = pte_offset_map(pmdp, tpc); ++ pte = *ptep; ++ if (pte_present(pte)) { ++ pa = (pte_pfn(pte) << PAGE_SHIFT); ++ pa += (tpc & ~PAGE_MASK); ++ ++ /* Use phys bypass so we don't pollute dtlb/dcache. */ ++ __asm__ __volatile__("lduwa [%1] %2, %0" ++ : "=r" (insn) ++ : "r" (pa), "i" (ASI_PHYS_USE_EC)); ++ } ++ pte_unmap(ptep); ++ } ++out_irq_enable: ++ local_irq_enable(); + out: +- pte_unmap(ptep); +- __asm__ __volatile__("wrpr %0, 0x0, %%pstate" : : "r" (pstate)); +-outret: + return insn; + } + +@@ -154,7 +167,8 @@ show_signal_msg(struct pt_regs *regs, int sig, int code, + extern unsigned long compute_effective_address(struct pt_regs *, unsigned int, unsigned int); + + static void do_fault_siginfo(int code, int sig, struct pt_regs *regs, +- unsigned int insn, int fault_code) ++ unsigned long fault_addr, unsigned int insn, ++ int fault_code) + { + unsigned long addr; + siginfo_t info; +@@ -162,10 +176,18 @@ static void do_fault_siginfo(int code, int sig, struct pt_regs *regs, + info.si_code = code; + info.si_signo = sig; + info.si_errno = 0; +- if (fault_code & FAULT_CODE_ITLB) ++ if (fault_code & FAULT_CODE_ITLB) { + addr = regs->tpc; +- else +- addr = compute_effective_address(regs, insn, 0); ++ } else { ++ /* If we were able to probe the faulting instruction, use it ++ * to compute a precise fault address. Otherwise use the fault ++ * time provided address which may only have page granularity. ++ */ ++ if (insn) ++ addr = compute_effective_address(regs, insn, 0); ++ else ++ addr = fault_addr; ++ } + info.si_addr = (void __user *) addr; + info.si_trapno = 0; + +@@ -240,7 +262,7 @@ static void __kprobes do_kernel_fault(struct pt_regs *regs, int si_code, + /* The si_code was set to make clear whether + * this was a SEGV_MAPERR or SEGV_ACCERR fault. + */ +- do_fault_siginfo(si_code, SIGSEGV, regs, insn, fault_code); ++ do_fault_siginfo(si_code, SIGSEGV, regs, address, insn, fault_code); + return; + } + +@@ -260,18 +282,6 @@ static void noinline __kprobes bogus_32bit_fault_tpc(struct pt_regs *regs) + show_regs(regs); + } + +-static void noinline __kprobes bogus_32bit_fault_address(struct pt_regs *regs, +- unsigned long addr) +-{ +- static int times; +- +- if (times++ < 10) +- printk(KERN_ERR "FAULT[%s:%d]: 32-bit process " +- "reports 64-bit fault address [%lx]\n", +- current->comm, current->pid, addr); +- show_regs(regs); +-} +- + asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) + { + struct mm_struct *mm = current->mm; +@@ -299,10 +309,8 @@ asmlinkage void __kprobes do_sparc64_fault(struct pt_regs *regs) + goto intr_or_no_mm; + } + } +- if (unlikely((address >> 32) != 0)) { +- bogus_32bit_fault_address(regs, address); ++ if (unlikely((address >> 32) != 0)) + goto intr_or_no_mm; +- } + } + + if (regs->tstate & TSTATE_PRIV) { +@@ -492,7 +500,7 @@ do_sigbus: + * Send a sigbus, regardless of whether we were in kernel + * or user mode. + */ +- do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, insn, fault_code); ++ do_fault_siginfo(BUS_ADRERR, SIGBUS, regs, address, insn, fault_code); + + /* Kernel mode? Handle exceptions or die */ + if (regs->tstate & TSTATE_PRIV) +diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c +index b4989f9..d2c5737 100644 +--- a/arch/sparc/mm/init_64.c ++++ b/arch/sparc/mm/init_64.c +@@ -309,6 +309,10 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t * + tsb_index = MM_TSB_BASE; + tsb_hash_shift = PAGE_SHIFT; + ++ /* Don't insert a non-valid PTE into the TSB, we'll deadlock. */ ++ if (!(pte_val(pte) & _PAGE_VALID)) ++ return; ++ + spin_lock_irqsave(&mm->context.lock, flags); + + #ifdef CONFIG_HUGETLB_PAGE +@@ -2436,3 +2440,26 @@ void __flush_tlb_all(void) + __asm__ __volatile__("wrpr %0, 0, %%pstate" + : : "r" (pstate)); + } ++ ++#ifdef CONFIG_SMP ++#define do_flush_tlb_kernel_range smp_flush_tlb_kernel_range ++#else ++#define do_flush_tlb_kernel_range __flush_tlb_kernel_range ++#endif ++ ++void flush_tlb_kernel_range(unsigned long start, unsigned long end) ++{ ++ if (start < HI_OBP_ADDRESS && end > LOW_OBP_ADDRESS) { ++ if (start < LOW_OBP_ADDRESS) { ++ flush_tsb_kernel_range(start, LOW_OBP_ADDRESS); ++ do_flush_tlb_kernel_range(start, LOW_OBP_ADDRESS); ++ } ++ if (end > HI_OBP_ADDRESS) { ++ flush_tsb_kernel_range(end, HI_OBP_ADDRESS); ++ do_flush_tlb_kernel_range(end, HI_OBP_ADDRESS); ++ } ++ } else { ++ flush_tsb_kernel_range(start, end); ++ do_flush_tlb_kernel_range(start, end); ++ } ++} +diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c +index 3ebcac7..6ddf60b 100644 +--- a/arch/sparc/mm/tsb.c ++++ b/arch/sparc/mm/tsb.c +@@ -151,7 +151,19 @@ static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsign + mm->context.tsb_block[tsb_idx].tsb_nentries = + tsb_bytes / sizeof(struct tsb); + +- base = TSBMAP_BASE; ++ switch (tsb_idx) { ++ case MM_TSB_BASE: ++ base = TSBMAP_8K_BASE; ++ break; ++#if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE) ++ case MM_TSB_HUGE: ++ base = TSBMAP_4M_BASE; ++ break; ++#endif ++ default: ++ BUG(); ++ } ++ + tte = pgprot_val(PAGE_KERNEL_LOCKED); + tsb_paddr = __pa(mm->context.tsb_block[tsb_idx].tsb); + BUG_ON(tsb_paddr & (tsb_bytes - 1UL)); +diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig +index 901447e..28a1bca 100644 +--- a/arch/x86/Kconfig ++++ b/arch/x86/Kconfig +@@ -896,10 +896,27 @@ config VM86 + default y + depends on X86_32 + ---help--- +- This option is required by programs like DOSEMU to run 16-bit legacy +- code on X86 processors. It also may be needed by software like +- XFree86 to initialize some video cards via BIOS. Disabling this +- option saves about 6k. ++ This option is required by programs like DOSEMU to run ++ 16-bit real mode legacy code on x86 processors. It also may ++ be needed by software like XFree86 to initialize some video ++ cards via BIOS. Disabling this option saves about 6K. ++ ++config X86_16BIT ++ bool "Enable support for 16-bit segments" if EXPERT ++ default y ++ ---help--- ++ This option is required by programs like Wine to run 16-bit ++ protected mode legacy code on x86 processors. Disabling ++ this option saves about 300 bytes on i386, or around 6K text ++ plus 16K runtime memory on x86-64, ++ ++config X86_ESPFIX32 ++ def_bool y ++ depends on X86_16BIT && X86_32 ++ ++config X86_ESPFIX64 ++ def_bool y ++ depends on X86_16BIT && X86_64 + + config TOSHIBA + tristate "Toshiba Laptop support" +diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h +new file mode 100644 +index 0000000..99efebb +--- /dev/null ++++ b/arch/x86/include/asm/espfix.h +@@ -0,0 +1,16 @@ ++#ifndef _ASM_X86_ESPFIX_H ++#define _ASM_X86_ESPFIX_H ++ ++#ifdef CONFIG_X86_64 ++ ++#include <asm/percpu.h> ++ ++DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); ++DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); ++ ++extern void init_espfix_bsp(void); ++extern void init_espfix_ap(void); ++ ++#endif /* CONFIG_X86_64 */ ++ ++#endif /* _ASM_X86_ESPFIX_H */ +diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h +index bba3cf8..0a8b519 100644 +--- a/arch/x86/include/asm/irqflags.h ++++ b/arch/x86/include/asm/irqflags.h +@@ -129,7 +129,7 @@ static inline notrace unsigned long arch_local_irq_save(void) + + #define PARAVIRT_ADJUST_EXCEPTION_FRAME /* */ + +-#define INTERRUPT_RETURN iretq ++#define INTERRUPT_RETURN jmp native_iret + #define USERGS_SYSRET64 \ + swapgs; \ + sysretq; +diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h +index 766ea16..51817fa 100644 +--- a/arch/x86/include/asm/pgtable_64_types.h ++++ b/arch/x86/include/asm/pgtable_64_types.h +@@ -59,5 +59,7 @@ typedef struct { pteval_t pte; } pte_t; + #define MODULES_VADDR _AC(0xffffffffa0000000, UL) + #define MODULES_END _AC(0xffffffffff000000, UL) + #define MODULES_LEN (MODULES_END - MODULES_VADDR) ++#define ESPFIX_PGD_ENTRY _AC(-2, UL) ++#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT) + + #endif /* _ASM_X86_PGTABLE_64_DEFS_H */ +diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h +index 9756551..8a87336 100644 +--- a/arch/x86/include/asm/setup.h ++++ b/arch/x86/include/asm/setup.h +@@ -61,6 +61,8 @@ static inline void x86_ce4100_early_setup(void) { } + + #ifndef _SETUP + ++#include <asm/espfix.h> ++ + /* + * This is set up by the setup-routine at boot-time + */ +diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile +index 8baca3c..96efa3e 100644 +--- a/arch/x86/kernel/Makefile ++++ b/arch/x86/kernel/Makefile +@@ -27,6 +27,7 @@ obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o + obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o + obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o + obj-$(CONFIG_X86_64) += vsyscall_emu_64.o ++obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o + obj-y += bootflag.o e820.o + obj-y += pci-dma.o quirks.o topology.o kdebugfs.o + obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o +diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S +index dd52355..0fa4f89 100644 +--- a/arch/x86/kernel/entry_32.S ++++ b/arch/x86/kernel/entry_32.S +@@ -527,6 +527,7 @@ syscall_exit: + restore_all: + TRACE_IRQS_IRET + restore_all_notrace: ++#ifdef CONFIG_X86_ESPFIX32 + movl PT_EFLAGS(%esp), %eax # mix EFLAGS, SS and CS + # Warning: PT_OLDSS(%esp) contains the wrong/random values if we + # are returning to the kernel. +@@ -537,6 +538,7 @@ restore_all_notrace: + cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax + CFI_REMEMBER_STATE + je ldt_ss # returning to user-space with LDT SS ++#endif + restore_nocheck: + RESTORE_REGS 4 # skip orig_eax/error_code + irq_return: +@@ -552,6 +554,7 @@ ENTRY(iret_exc) + .long irq_return,iret_exc + .previous + ++#ifdef CONFIG_X86_ESPFIX32 + CFI_RESTORE_STATE + ldt_ss: + #ifdef CONFIG_PARAVIRT +@@ -595,6 +598,7 @@ ldt_ss: + lss (%esp), %esp /* switch to espfix segment */ + CFI_ADJUST_CFA_OFFSET -8 + jmp restore_nocheck ++#endif + CFI_ENDPROC + ENDPROC(system_call) + +@@ -766,6 +770,7 @@ ENDPROC(ptregs_clone) + * the high word of the segment base from the GDT and swiches to the + * normal stack and adjusts ESP with the matching offset. + */ ++#ifdef CONFIG_X86_ESPFIX32 + /* fixup the stack */ + mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */ + mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */ +@@ -775,8 +780,10 @@ ENDPROC(ptregs_clone) + pushl_cfi %eax + lss (%esp), %esp /* switch to the normal stack segment */ + CFI_ADJUST_CFA_OFFSET -8 ++#endif + .endm + .macro UNWIND_ESPFIX_STACK ++#ifdef CONFIG_X86_ESPFIX32 + movl %ss, %eax + /* see if on espfix stack */ + cmpw $__ESPFIX_SS, %ax +@@ -787,6 +794,7 @@ ENDPROC(ptregs_clone) + /* switch to normal stack */ + FIXUP_ESPFIX_STACK + 27: ++#endif + .endm + + /* +@@ -1323,11 +1331,13 @@ END(debug) + */ + ENTRY(nmi) + RING0_INT_FRAME ++#ifdef CONFIG_X86_ESPFIX32 + pushl_cfi %eax + movl %ss, %eax + cmpw $__ESPFIX_SS, %ax + popl_cfi %eax + je nmi_espfix_stack ++#endif + cmpl $ia32_sysenter_target,(%esp) + je nmi_stack_fixup + pushl_cfi %eax +@@ -1367,6 +1377,7 @@ nmi_debug_stack_check: + FIX_STACK 24, nmi_stack_correct, 1 + jmp nmi_stack_correct + ++#ifdef CONFIG_X86_ESPFIX32 + nmi_espfix_stack: + /* We have a RING0_INT_FRAME here. + * +@@ -1388,6 +1399,7 @@ nmi_espfix_stack: + lss 12+4(%esp), %esp # back to espfix stack + CFI_ADJUST_CFA_OFFSET -24 + jmp irq_return ++#endif + CFI_ENDPROC + END(nmi) + +diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S +index 6274f5f..4b511ef 100644 +--- a/arch/x86/kernel/entry_64.S ++++ b/arch/x86/kernel/entry_64.S +@@ -55,6 +55,7 @@ + #include <asm/paravirt.h> + #include <asm/ftrace.h> + #include <asm/percpu.h> ++#include <asm/pgtable_types.h> + + /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this. */ + #include <linux/elf-em.h> +@@ -862,17 +863,47 @@ restore_args: + irq_return: + INTERRUPT_RETURN + +- .section __ex_table, "a" +- .quad irq_return, bad_iret +- .previous +- +-#ifdef CONFIG_PARAVIRT + ENTRY(native_iret) ++ /* ++ * Are we returning to a stack segment from the LDT? Note: in ++ * 64-bit mode SS:RSP on the exception stack is always valid. ++ */ ++#ifdef CONFIG_X86_ESPFIX64 ++ testb $4,(SS-RIP)(%rsp) ++ jnz native_irq_return_ldt ++#endif ++ ++native_irq_return_iret: + iretq + + .section __ex_table,"a" +- .quad native_iret, bad_iret ++ .quad native_irq_return_iret, bad_iret + .previous ++ ++#ifdef CONFIG_X86_ESPFIX64 ++native_irq_return_ldt: ++ pushq_cfi %rax ++ pushq_cfi %rdi ++ SWAPGS ++ movq PER_CPU_VAR(espfix_waddr),%rdi ++ movq %rax,(0*8)(%rdi) /* RAX */ ++ movq (2*8)(%rsp),%rax /* RIP */ ++ movq %rax,(1*8)(%rdi) ++ movq (3*8)(%rsp),%rax /* CS */ ++ movq %rax,(2*8)(%rdi) ++ movq (4*8)(%rsp),%rax /* RFLAGS */ ++ movq %rax,(3*8)(%rdi) ++ movq (6*8)(%rsp),%rax /* SS */ ++ movq %rax,(5*8)(%rdi) ++ movq (5*8)(%rsp),%rax /* RSP */ ++ movq %rax,(4*8)(%rdi) ++ andl $0xffff0000,%eax ++ popq_cfi %rdi ++ orq PER_CPU_VAR(espfix_stack),%rax ++ SWAPGS ++ movq %rax,%rsp ++ popq_cfi %rax ++ jmp native_irq_return_iret + #endif + + .section .fixup,"ax" +@@ -938,9 +969,40 @@ ENTRY(retint_kernel) + call preempt_schedule_irq + jmp exit_intr + #endif +- + CFI_ENDPROC + END(common_interrupt) ++ ++ /* ++ * If IRET takes a fault on the espfix stack, then we ++ * end up promoting it to a doublefault. In that case, ++ * modify the stack to make it look like we just entered ++ * the #GP handler from user space, similar to bad_iret. ++ */ ++#ifdef CONFIG_X86_ESPFIX64 ++ ALIGN ++__do_double_fault: ++ XCPT_FRAME 1 RDI+8 ++ movq RSP(%rdi),%rax /* Trap on the espfix stack? */ ++ sarq $PGDIR_SHIFT,%rax ++ cmpl $ESPFIX_PGD_ENTRY,%eax ++ jne do_double_fault /* No, just deliver the fault */ ++ cmpl $__KERNEL_CS,CS(%rdi) ++ jne do_double_fault ++ movq RIP(%rdi),%rax ++ cmpq $native_irq_return_iret,%rax ++ jne do_double_fault /* This shouldn't happen... */ ++ movq PER_CPU_VAR(kernel_stack),%rax ++ subq $(6*8-KERNEL_STACK_OFFSET),%rax /* Reset to original stack */ ++ movq %rax,RSP(%rdi) ++ movq $0,(%rax) /* Missing (lost) #GP error code */ ++ movq $general_protection,RIP(%rdi) ++ retq ++ CFI_ENDPROC ++END(__do_double_fault) ++#else ++# define __do_double_fault do_double_fault ++#endif ++ + /* + * End of kprobes section + */ +@@ -1107,7 +1169,7 @@ zeroentry overflow do_overflow + zeroentry bounds do_bounds + zeroentry invalid_op do_invalid_op + zeroentry device_not_available do_device_not_available +-paranoiderrorentry double_fault do_double_fault ++paranoiderrorentry double_fault __do_double_fault + zeroentry coprocessor_segment_overrun do_coprocessor_segment_overrun + errorentry invalid_TSS do_invalid_TSS + errorentry segment_not_present do_segment_not_present +@@ -1438,7 +1500,7 @@ error_sti: + */ + error_kernelspace: + incl %ebx +- leaq irq_return(%rip),%rcx ++ leaq native_irq_return_iret(%rip),%rcx + cmpq %rcx,RIP+8(%rsp) + je error_swapgs + movl %ecx,%eax /* zero extend */ +diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c +new file mode 100644 +index 0000000..94d857f +--- /dev/null ++++ b/arch/x86/kernel/espfix_64.c +@@ -0,0 +1,208 @@ ++/* ----------------------------------------------------------------------- * ++ * ++ * Copyright 2014 Intel Corporation; author: H. Peter Anvin ++ * ++ * This program is free software; you can redistribute it and/or modify it ++ * under the terms and conditions of the GNU General Public License, ++ * version 2, as published by the Free Software Foundation. ++ * ++ * This program is distributed in the hope it will be useful, but WITHOUT ++ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or ++ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for ++ * more details. ++ * ++ * ----------------------------------------------------------------------- */ ++ ++/* ++ * The IRET instruction, when returning to a 16-bit segment, only ++ * restores the bottom 16 bits of the user space stack pointer. This ++ * causes some 16-bit software to break, but it also leaks kernel state ++ * to user space. ++ * ++ * This works around this by creating percpu "ministacks", each of which ++ * is mapped 2^16 times 64K apart. When we detect that the return SS is ++ * on the LDT, we copy the IRET frame to the ministack and use the ++ * relevant alias to return to userspace. The ministacks are mapped ++ * readonly, so if the IRET fault we promote #GP to #DF which is an IST ++ * vector and thus has its own stack; we then do the fixup in the #DF ++ * handler. ++ * ++ * This file sets up the ministacks and the related page tables. The ++ * actual ministack invocation is in entry_64.S. ++ */ ++ ++#include <linux/init.h> ++#include <linux/init_task.h> ++#include <linux/kernel.h> ++#include <linux/percpu.h> ++#include <linux/gfp.h> ++#include <linux/random.h> ++#include <asm/pgtable.h> ++#include <asm/pgalloc.h> ++#include <asm/setup.h> ++#include <asm/espfix.h> ++ ++/* ++ * Note: we only need 6*8 = 48 bytes for the espfix stack, but round ++ * it up to a cache line to avoid unnecessary sharing. ++ */ ++#define ESPFIX_STACK_SIZE (8*8UL) ++#define ESPFIX_STACKS_PER_PAGE (PAGE_SIZE/ESPFIX_STACK_SIZE) ++ ++/* There is address space for how many espfix pages? */ ++#define ESPFIX_PAGE_SPACE (1UL << (PGDIR_SHIFT-PAGE_SHIFT-16)) ++ ++#define ESPFIX_MAX_CPUS (ESPFIX_STACKS_PER_PAGE * ESPFIX_PAGE_SPACE) ++#if CONFIG_NR_CPUS > ESPFIX_MAX_CPUS ++# error "Need more than one PGD for the ESPFIX hack" ++#endif ++ ++#define PGALLOC_GFP (GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO) ++ ++/* This contains the *bottom* address of the espfix stack */ ++DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); ++DEFINE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); ++ ++/* Initialization mutex - should this be a spinlock? */ ++static DEFINE_MUTEX(espfix_init_mutex); ++ ++/* Page allocation bitmap - each page serves ESPFIX_STACKS_PER_PAGE CPUs */ ++#define ESPFIX_MAX_PAGES DIV_ROUND_UP(CONFIG_NR_CPUS, ESPFIX_STACKS_PER_PAGE) ++static void *espfix_pages[ESPFIX_MAX_PAGES]; ++ ++static __page_aligned_bss pud_t espfix_pud_page[PTRS_PER_PUD] ++ __aligned(PAGE_SIZE); ++ ++static unsigned int page_random, slot_random; ++ ++/* ++ * This returns the bottom address of the espfix stack for a specific CPU. ++ * The math allows for a non-power-of-two ESPFIX_STACK_SIZE, in which case ++ * we have to account for some amount of padding at the end of each page. ++ */ ++static inline unsigned long espfix_base_addr(unsigned int cpu) ++{ ++ unsigned long page, slot; ++ unsigned long addr; ++ ++ page = (cpu / ESPFIX_STACKS_PER_PAGE) ^ page_random; ++ slot = (cpu + slot_random) % ESPFIX_STACKS_PER_PAGE; ++ addr = (page << PAGE_SHIFT) + (slot * ESPFIX_STACK_SIZE); ++ addr = (addr & 0xffffUL) | ((addr & ~0xffffUL) << 16); ++ addr += ESPFIX_BASE_ADDR; ++ return addr; ++} ++ ++#define PTE_STRIDE (65536/PAGE_SIZE) ++#define ESPFIX_PTE_CLONES (PTRS_PER_PTE/PTE_STRIDE) ++#define ESPFIX_PMD_CLONES PTRS_PER_PMD ++#define ESPFIX_PUD_CLONES (65536/(ESPFIX_PTE_CLONES*ESPFIX_PMD_CLONES)) ++ ++#define PGTABLE_PROT ((_KERNPG_TABLE & ~_PAGE_RW) | _PAGE_NX) ++ ++static void init_espfix_random(void) ++{ ++ unsigned long rand; ++ ++ /* ++ * This is run before the entropy pools are initialized, ++ * but this is hopefully better than nothing. ++ */ ++ if (!arch_get_random_long(&rand)) { ++ /* The constant is an arbitrary large prime */ ++ rdtscll(rand); ++ rand *= 0xc345c6b72fd16123UL; ++ } ++ ++ slot_random = rand % ESPFIX_STACKS_PER_PAGE; ++ page_random = (rand / ESPFIX_STACKS_PER_PAGE) ++ & (ESPFIX_PAGE_SPACE - 1); ++} ++ ++void __init init_espfix_bsp(void) ++{ ++ pgd_t *pgd_p; ++ pteval_t ptemask; ++ ++ ptemask = __supported_pte_mask; ++ ++ /* Install the espfix pud into the kernel page directory */ ++ pgd_p = &init_level4_pgt[pgd_index(ESPFIX_BASE_ADDR)]; ++ pgd_populate(&init_mm, pgd_p, (pud_t *)espfix_pud_page); ++ ++ /* Randomize the locations */ ++ init_espfix_random(); ++ ++ /* The rest is the same as for any other processor */ ++ init_espfix_ap(); ++} ++ ++void init_espfix_ap(void) ++{ ++ unsigned int cpu, page; ++ unsigned long addr; ++ pud_t pud, *pud_p; ++ pmd_t pmd, *pmd_p; ++ pte_t pte, *pte_p; ++ int n; ++ void *stack_page; ++ pteval_t ptemask; ++ ++ /* We only have to do this once... */ ++ if (likely(this_cpu_read(espfix_stack))) ++ return; /* Already initialized */ ++ ++ cpu = smp_processor_id(); ++ addr = espfix_base_addr(cpu); ++ page = cpu/ESPFIX_STACKS_PER_PAGE; ++ ++ /* Did another CPU already set this up? */ ++ stack_page = ACCESS_ONCE(espfix_pages[page]); ++ if (likely(stack_page)) ++ goto done; ++ ++ mutex_lock(&espfix_init_mutex); ++ ++ /* Did we race on the lock? */ ++ stack_page = ACCESS_ONCE(espfix_pages[page]); ++ if (stack_page) ++ goto unlock_done; ++ ++ ptemask = __supported_pte_mask; ++ ++ pud_p = &espfix_pud_page[pud_index(addr)]; ++ pud = *pud_p; ++ if (!pud_present(pud)) { ++ pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP); ++ pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask)); ++ paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT); ++ for (n = 0; n < ESPFIX_PUD_CLONES; n++) ++ set_pud(&pud_p[n], pud); ++ } ++ ++ pmd_p = pmd_offset(&pud, addr); ++ pmd = *pmd_p; ++ if (!pmd_present(pmd)) { ++ pte_p = (pte_t *)__get_free_page(PGALLOC_GFP); ++ pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask)); ++ paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT); ++ for (n = 0; n < ESPFIX_PMD_CLONES; n++) ++ set_pmd(&pmd_p[n], pmd); ++ } ++ ++ pte_p = pte_offset_kernel(&pmd, addr); ++ stack_page = (void *)__get_free_page(GFP_KERNEL); ++ pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask)); ++ for (n = 0; n < ESPFIX_PTE_CLONES; n++) ++ set_pte(&pte_p[n*PTE_STRIDE], pte); ++ ++ /* Job is done for this CPU and any CPU which shares this page */ ++ ACCESS_ONCE(espfix_pages[page]) = stack_page; ++ ++unlock_done: ++ mutex_unlock(&espfix_init_mutex); ++done: ++ this_cpu_write(espfix_stack, addr); ++ this_cpu_write(espfix_waddr, (unsigned long)stack_page ++ + (addr & ~PAGE_MASK)); ++} +diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c +index 3e0ccbf..0a8e65e 100644 +--- a/arch/x86/kernel/ldt.c ++++ b/arch/x86/kernel/ldt.c +@@ -21,8 +21,6 @@ + #include <asm/mmu_context.h> + #include <asm/syscalls.h> + +-int sysctl_ldt16 = 0; +- + #ifdef CONFIG_SMP + static void flush_ldt(void *current_mm) + { +@@ -232,16 +230,10 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode) + } + } + +- /* +- * On x86-64 we do not support 16-bit segments due to +- * IRET leaking the high bits of the kernel stack address. +- */ +-#ifdef CONFIG_X86_64 +- if (!ldt_info.seg_32bit && !sysctl_ldt16) { ++ if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) { + error = -EINVAL; + goto out_unlock; + } +-#endif + + fill_ldt(&ldt, &ldt_info); + if (oldmode) +diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c +index 3f08f34..a1da673 100644 +--- a/arch/x86/kernel/paravirt_patch_64.c ++++ b/arch/x86/kernel/paravirt_patch_64.c +@@ -6,7 +6,6 @@ DEF_NATIVE(pv_irq_ops, irq_disable, "cli"); + DEF_NATIVE(pv_irq_ops, irq_enable, "sti"); + DEF_NATIVE(pv_irq_ops, restore_fl, "pushq %rdi; popfq"); + DEF_NATIVE(pv_irq_ops, save_fl, "pushfq; popq %rax"); +-DEF_NATIVE(pv_cpu_ops, iret, "iretq"); + DEF_NATIVE(pv_mmu_ops, read_cr2, "movq %cr2, %rax"); + DEF_NATIVE(pv_mmu_ops, read_cr3, "movq %cr3, %rax"); + DEF_NATIVE(pv_mmu_ops, write_cr3, "movq %rdi, %cr3"); +@@ -50,7 +49,6 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf, + PATCH_SITE(pv_irq_ops, save_fl); + PATCH_SITE(pv_irq_ops, irq_enable); + PATCH_SITE(pv_irq_ops, irq_disable); +- PATCH_SITE(pv_cpu_ops, iret); + PATCH_SITE(pv_cpu_ops, irq_enable_sysexit); + PATCH_SITE(pv_cpu_ops, usergs_sysret32); + PATCH_SITE(pv_cpu_ops, usergs_sysret64); +diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c +index 2a26819..80eab01 100644 +--- a/arch/x86/kernel/resource.c ++++ b/arch/x86/kernel/resource.c +@@ -37,10 +37,12 @@ static void remove_e820_regions(struct resource *avail) + + void arch_remove_reservations(struct resource *avail) + { +- /* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */ ++ /* ++ * Trim out BIOS area (high 2MB) and E820 regions. We do not remove ++ * the low 1MB unconditionally, as this area is needed for some ISA ++ * cards requiring a memory range, e.g. the i82365 PCMCIA controller. ++ */ + if (avail->flags & IORESOURCE_MEM) { +- if (avail->start < BIOS_END) +- avail->start = BIOS_END; + resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END); + + remove_e820_regions(avail); +diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c +index b88eadb..6e68bd9 100644 +--- a/arch/x86/kernel/smpboot.c ++++ b/arch/x86/kernel/smpboot.c +@@ -266,6 +266,13 @@ notrace static void __cpuinit start_secondary(void *unused) + check_tsc_sync_target(); + + /* ++ * Enable the espfix hack for this CPU ++ */ ++#ifdef CONFIG_X86_ESPFIX64 ++ init_espfix_ap(); ++#endif ++ ++ /* + * We need to hold call_lock, so there is no inconsistency + * between the time smp_call_function() determines number of + * IPI recipients, and the time when the determination is made +diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c +index f5302da..638cab5 100644 +--- a/arch/x86/kvm/emulate.c ++++ b/arch/x86/kvm/emulate.c +@@ -1818,6 +1818,7 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) + { + int rc; + unsigned long cs; ++ int cpl = ctxt->ops->cpl(ctxt); + + rc = emulate_pop(ctxt, &ctxt->_eip, ctxt->op_bytes); + if (rc != X86EMUL_CONTINUE) +@@ -1827,6 +1828,9 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) + rc = emulate_pop(ctxt, &cs, ctxt->op_bytes); + if (rc != X86EMUL_CONTINUE) + return rc; ++ /* Outer-privilege level return is not implemented */ ++ if (ctxt->mode >= X86EMUL_MODE_PROT16 && (cs & 3) > cpl) ++ return X86EMUL_UNHANDLEABLE; + rc = load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS); + return rc; + } +diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c +index 0002a3a..e04e677 100644 +--- a/arch/x86/mm/dump_pagetables.c ++++ b/arch/x86/mm/dump_pagetables.c +@@ -30,11 +30,13 @@ struct pg_state { + unsigned long start_address; + unsigned long current_address; + const struct addr_marker *marker; ++ unsigned long lines; + }; + + struct addr_marker { + unsigned long start_address; + const char *name; ++ unsigned long max_lines; + }; + + /* indices for address_markers; keep sync'd w/ address_markers below */ +@@ -45,6 +47,7 @@ enum address_markers_idx { + LOW_KERNEL_NR, + VMALLOC_START_NR, + VMEMMAP_START_NR, ++ ESPFIX_START_NR, + HIGH_KERNEL_NR, + MODULES_VADDR_NR, + MODULES_END_NR, +@@ -67,6 +70,7 @@ static struct addr_marker address_markers[] = { + { PAGE_OFFSET, "Low Kernel Mapping" }, + { VMALLOC_START, "vmalloc() Area" }, + { VMEMMAP_START, "Vmemmap" }, ++ { ESPFIX_BASE_ADDR, "ESPfix Area", 16 }, + { __START_KERNEL_map, "High Kernel Mapping" }, + { MODULES_VADDR, "Modules" }, + { MODULES_END, "End Modules" }, +@@ -163,7 +167,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, + pgprot_t new_prot, int level) + { + pgprotval_t prot, cur; +- static const char units[] = "KMGTPE"; ++ static const char units[] = "BKMGTPE"; + + /* + * If we have a "break" in the series, we need to flush the state that +@@ -178,6 +182,7 @@ static void note_page(struct seq_file *m, struct pg_state *st, + st->current_prot = new_prot; + st->level = level; + st->marker = address_markers; ++ st->lines = 0; + seq_printf(m, "---[ %s ]---\n", st->marker->name); + } else if (prot != cur || level != st->level || + st->current_address >= st->marker[1].start_address) { +@@ -188,17 +193,21 @@ static void note_page(struct seq_file *m, struct pg_state *st, + /* + * Now print the actual finished series + */ +- seq_printf(m, "0x%0*lx-0x%0*lx ", +- width, st->start_address, +- width, st->current_address); +- +- delta = (st->current_address - st->start_address) >> 10; +- while (!(delta & 1023) && unit[1]) { +- delta >>= 10; +- unit++; ++ if (!st->marker->max_lines || ++ st->lines < st->marker->max_lines) { ++ seq_printf(m, "0x%0*lx-0x%0*lx ", ++ width, st->start_address, ++ width, st->current_address); ++ ++ delta = (st->current_address - st->start_address); ++ while (!(delta & 1023) && unit[1]) { ++ delta >>= 10; ++ unit++; ++ } ++ seq_printf(m, "%9lu%c ", delta, *unit); ++ printk_prot(m, st->current_prot, st->level); + } +- seq_printf(m, "%9lu%c ", delta, *unit); +- printk_prot(m, st->current_prot, st->level); ++ st->lines++; + + /* + * We print markers for special areas of address space, +@@ -206,7 +215,15 @@ static void note_page(struct seq_file *m, struct pg_state *st, + * This helps in the interpretation. + */ + if (st->current_address >= st->marker[1].start_address) { ++ if (st->marker->max_lines && ++ st->lines > st->marker->max_lines) { ++ unsigned long nskip = ++ st->lines - st->marker->max_lines; ++ seq_printf(m, "... %lu entr%s skipped ... \n", ++ nskip, nskip == 1 ? "y" : "ies"); ++ } + st->marker++; ++ st->lines = 0; + seq_printf(m, "---[ %s ]---\n", st->marker->name); + } + +diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c +index 794b092..2d3c854 100644 +--- a/arch/x86/pci/i386.c ++++ b/arch/x86/pci/i386.c +@@ -73,6 +73,10 @@ pcibios_align_resource(void *data, const struct resource *res, + return start; + if (start & 0x300) + start = (start + 0x3ff) & ~0x3ff; ++ } else if (res->flags & IORESOURCE_MEM) { ++ /* The low 1MB range is reserved for ISA cards */ ++ if (start < BIOS_END) ++ start = BIOS_END; + } + return start; + } +diff --git a/arch/x86/vdso/vdso32-setup.c b/arch/x86/vdso/vdso32-setup.c +index 51bdc05..468d591 100644 +--- a/arch/x86/vdso/vdso32-setup.c ++++ b/arch/x86/vdso/vdso32-setup.c +@@ -41,7 +41,6 @@ enum { + #ifdef CONFIG_X86_64 + #define vdso_enabled sysctl_vsyscall32 + #define arch_setup_additional_pages syscall32_setup_pages +-extern int sysctl_ldt16; + #endif + + /* +@@ -389,13 +388,6 @@ static ctl_table abi_table2[] = { + .mode = 0644, + .proc_handler = proc_dointvec + }, +- { +- .procname = "ldt16", +- .data = &sysctl_ldt16, +- .maxlen = sizeof(int), +- .mode = 0644, +- .proc_handler = proc_dointvec +- }, + {} + }; + +diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c +index d50a821..1a82319 100644 +--- a/arch/x86/xen/time.c ++++ b/arch/x86/xen/time.c +@@ -397,7 +397,7 @@ void xen_setup_timer(int cpu) + irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt, + IRQF_DISABLED|IRQF_PERCPU| + IRQF_NOBALANCING|IRQF_TIMER| +- IRQF_FORCE_RESUME, ++ IRQF_FORCE_RESUME|IRQF_EARLY_RESUME, + name, NULL); + + evt = &per_cpu(xen_clock_events, cpu); +diff --git a/block/blk-tag.c b/block/blk-tag.c +index 4af6f5c..f606487 100644 +--- a/block/blk-tag.c ++++ b/block/blk-tag.c +@@ -27,18 +27,15 @@ struct request *blk_queue_find_tag(struct request_queue *q, int tag) + EXPORT_SYMBOL(blk_queue_find_tag); + + /** +- * __blk_free_tags - release a given set of tag maintenance info ++ * blk_free_tags - release a given set of tag maintenance info + * @bqt: the tag map to free + * +- * Tries to free the specified @bqt. Returns true if it was +- * actually freed and false if there are still references using it ++ * Drop the reference count on @bqt and frees it when the last reference ++ * is dropped. + */ +-static int __blk_free_tags(struct blk_queue_tag *bqt) ++void blk_free_tags(struct blk_queue_tag *bqt) + { +- int retval; +- +- retval = atomic_dec_and_test(&bqt->refcnt); +- if (retval) { ++ if (atomic_dec_and_test(&bqt->refcnt)) { + BUG_ON(find_first_bit(bqt->tag_map, bqt->max_depth) < + bqt->max_depth); + +@@ -50,9 +47,8 @@ static int __blk_free_tags(struct blk_queue_tag *bqt) + + kfree(bqt); + } +- +- return retval; + } ++EXPORT_SYMBOL(blk_free_tags); + + /** + * __blk_queue_free_tags - release tag maintenance info +@@ -69,28 +65,13 @@ void __blk_queue_free_tags(struct request_queue *q) + if (!bqt) + return; + +- __blk_free_tags(bqt); ++ blk_free_tags(bqt); + + q->queue_tags = NULL; + queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q); + } + + /** +- * blk_free_tags - release a given set of tag maintenance info +- * @bqt: the tag map to free +- * +- * For externally managed @bqt frees the map. Callers of this +- * function must guarantee to have released all the queues that +- * might have been using this tag map. +- */ +-void blk_free_tags(struct blk_queue_tag *bqt) +-{ +- if (unlikely(!__blk_free_tags(bqt))) +- BUG(); +-} +-EXPORT_SYMBOL(blk_free_tags); +- +-/** + * blk_queue_free_tags - release tag maintenance info + * @q: the request queue for the device + * +diff --git a/crypto/af_alg.c b/crypto/af_alg.c +index ac33d5f..bf948e1 100644 +--- a/crypto/af_alg.c ++++ b/crypto/af_alg.c +@@ -21,6 +21,7 @@ + #include <linux/module.h> + #include <linux/net.h> + #include <linux/rwsem.h> ++#include <linux/security.h> + + struct alg_type_list { + const struct af_alg_type *type; +@@ -243,6 +244,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock) + + sock_init_data(newsock, sk2); + sock_graft(sk2, newsock); ++ security_sk_clone(sk, sk2); + + err = type->accept(ask->private, sk2); + if (err) { +diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c +index 48fd158..05df096 100644 +--- a/drivers/acpi/ec.c ++++ b/drivers/acpi/ec.c +@@ -193,6 +193,8 @@ static bool advance_transaction(struct acpi_ec *ec) + t->rdata[t->ri++] = acpi_ec_read_data(ec); + if (t->rlen == t->ri) { + t->flags |= ACPI_EC_COMMAND_COMPLETE; ++ if (t->command == ACPI_EC_COMMAND_QUERY) ++ pr_debug("hardware QR_EC completion\n"); + wakeup = true; + } + } else +@@ -204,7 +206,20 @@ static bool advance_transaction(struct acpi_ec *ec) + } + return wakeup; + } else { +- if ((status & ACPI_EC_FLAG_IBF) == 0) { ++ /* ++ * There is firmware refusing to respond QR_EC when SCI_EVT ++ * is not set, for which case, we complete the QR_EC ++ * without issuing it to the firmware. ++ * https://bugzilla.kernel.org/show_bug.cgi?id=86211 ++ */ ++ if (!(status & ACPI_EC_FLAG_SCI) && ++ (t->command == ACPI_EC_COMMAND_QUERY)) { ++ t->flags |= ACPI_EC_COMMAND_POLL; ++ t->rdata[t->ri++] = 0x00; ++ t->flags |= ACPI_EC_COMMAND_COMPLETE; ++ pr_debug("software QR_EC completion\n"); ++ wakeup = true; ++ } else if ((status & ACPI_EC_FLAG_IBF) == 0) { + acpi_ec_write_cmd(ec, t->command); + t->flags |= ACPI_EC_COMMAND_POLL; + } else +diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c +index 44a4434..43b0acf 100644 +--- a/drivers/ata/ahci.c ++++ b/drivers/ata/ahci.c +@@ -463,6 +463,7 @@ static const struct pci_device_id ahci_pci_tbl[] = { + + /* Promise */ + { PCI_VDEVICE(PROMISE, 0x3f20), board_ahci }, /* PDC42819 */ ++ { PCI_VDEVICE(PROMISE, 0x3781), board_ahci }, /* FastTrak TX8660 ahci-mode */ + + /* Asmedia */ + { PCI_VDEVICE(ASMEDIA, 0x0601), board_ahci }, /* ASM1060 */ +diff --git a/drivers/ata/pata_scc.c b/drivers/ata/pata_scc.c +index e265f83..19759d3 100644 +--- a/drivers/ata/pata_scc.c ++++ b/drivers/ata/pata_scc.c +@@ -586,7 +586,7 @@ static int scc_wait_after_reset(struct ata_link *link, unsigned int devmask, + * Note: Original code is ata_bus_softreset(). + */ + +-static unsigned int scc_bus_softreset(struct ata_port *ap, unsigned int devmask, ++static int scc_bus_softreset(struct ata_port *ap, unsigned int devmask, + unsigned long deadline) + { + struct ata_ioports *ioaddr = &ap->ioaddr; +@@ -600,9 +600,7 @@ static unsigned int scc_bus_softreset(struct ata_port *ap, unsigned int devmask, + udelay(20); + out_be32(ioaddr->ctl_addr, ap->ctl); + +- scc_wait_after_reset(&ap->link, devmask, deadline); +- +- return 0; ++ return scc_wait_after_reset(&ap->link, devmask, deadline); + } + + /** +@@ -619,7 +617,8 @@ static int scc_softreset(struct ata_link *link, unsigned int *classes, + { + struct ata_port *ap = link->ap; + unsigned int slave_possible = ap->flags & ATA_FLAG_SLAVE_POSS; +- unsigned int devmask = 0, err_mask; ++ unsigned int devmask = 0; ++ int rc; + u8 err; + + DPRINTK("ENTER\n"); +@@ -635,9 +634,9 @@ static int scc_softreset(struct ata_link *link, unsigned int *classes, + + /* issue bus reset */ + DPRINTK("about to softreset, devmask=%x\n", devmask); +- err_mask = scc_bus_softreset(ap, devmask, deadline); +- if (err_mask) { +- ata_port_err(ap, "SRST failed (err_mask=0x%x)\n", err_mask); ++ rc = scc_bus_softreset(ap, devmask, deadline); ++ if (rc) { ++ ata_port_err(ap, "SRST failed (err_mask=0x%x)\n", rc); + return -EIO; + } + +diff --git a/drivers/char/tpm/tpm.c b/drivers/char/tpm/tpm.c +index 0d91655..c234b9e 100644 +--- a/drivers/char/tpm/tpm.c ++++ b/drivers/char/tpm/tpm.c +@@ -533,11 +533,10 @@ EXPORT_SYMBOL_GPL(tpm_gen_interrupt); + void tpm_get_timeouts(struct tpm_chip *chip) + { + struct tpm_cmd_t tpm_cmd; +- struct timeout_t *timeout_cap; ++ unsigned long new_timeout[4]; ++ unsigned long old_timeout[4]; + struct duration_t *duration_cap; + ssize_t rc; +- u32 timeout; +- unsigned int scale = 1; + + tpm_cmd.header.in = tpm_getcap_header; + tpm_cmd.params.getcap_in.cap = TPM_CAP_PROP; +@@ -554,25 +553,46 @@ void tpm_get_timeouts(struct tpm_chip *chip) + != sizeof(tpm_cmd.header.out) + sizeof(u32) + 4 * sizeof(u32)) + return; + +- timeout_cap = &tpm_cmd.params.getcap_out.cap.timeout; +- /* Don't overwrite default if value is 0 */ +- timeout = be32_to_cpu(timeout_cap->a); +- if (timeout && timeout < 1000) { +- /* timeouts in msec rather usec */ +- scale = 1000; +- chip->vendor.timeout_adjusted = true; ++ old_timeout[0] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.a); ++ old_timeout[1] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.b); ++ old_timeout[2] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.c); ++ old_timeout[3] = be32_to_cpu(tpm_cmd.params.getcap_out.cap.timeout.d); ++ memcpy(new_timeout, old_timeout, sizeof(new_timeout)); ++ ++ /* ++ * Provide ability for vendor overrides of timeout values in case ++ * of misreporting. ++ */ ++ if (chip->vendor.update_timeouts != NULL) ++ chip->vendor.timeout_adjusted = ++ chip->vendor.update_timeouts(chip, new_timeout); ++ ++ if (!chip->vendor.timeout_adjusted) { ++ /* Don't overwrite default if value is 0 */ ++ if (new_timeout[0] != 0 && new_timeout[0] < 1000) { ++ int i; ++ ++ /* timeouts in msec rather usec */ ++ for (i = 0; i != ARRAY_SIZE(new_timeout); i++) ++ new_timeout[i] *= 1000; ++ chip->vendor.timeout_adjusted = true; ++ } + } +- if (timeout) +- chip->vendor.timeout_a = usecs_to_jiffies(timeout * scale); +- timeout = be32_to_cpu(timeout_cap->b); +- if (timeout) +- chip->vendor.timeout_b = usecs_to_jiffies(timeout * scale); +- timeout = be32_to_cpu(timeout_cap->c); +- if (timeout) +- chip->vendor.timeout_c = usecs_to_jiffies(timeout * scale); +- timeout = be32_to_cpu(timeout_cap->d); +- if (timeout) +- chip->vendor.timeout_d = usecs_to_jiffies(timeout * scale); ++ ++ /* Report adjusted timeouts */ ++ if (chip->vendor.timeout_adjusted) { ++ dev_info(chip->dev, ++ HW_ERR "Adjusting reported timeouts: A %lu->%luus B %lu->%luus C %lu->%luus D %lu->%luus\n", ++ old_timeout[0], new_timeout[0], ++ old_timeout[1], new_timeout[1], ++ old_timeout[2], new_timeout[2], ++ old_timeout[3], new_timeout[3]); ++ } ++ ++ chip->vendor.timeout_a = usecs_to_jiffies(new_timeout[0]); ++ chip->vendor.timeout_b = usecs_to_jiffies(new_timeout[1]); ++ chip->vendor.timeout_c = usecs_to_jiffies(new_timeout[2]); ++ chip->vendor.timeout_d = usecs_to_jiffies(new_timeout[3]); + + duration: + tpm_cmd.header.in = tpm_getcap_header; +diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h +index 9c4163c..befbe67 100644 +--- a/drivers/char/tpm/tpm.h ++++ b/drivers/char/tpm/tpm.h +@@ -80,6 +80,9 @@ struct tpm_vendor_specific { + int (*send) (struct tpm_chip *, u8 *, size_t); + void (*cancel) (struct tpm_chip *); + u8 (*status) (struct tpm_chip *); ++ bool (*update_timeouts)(struct tpm_chip *chip, ++ unsigned long *timeout_cap); ++ + void (*release) (struct device *); + struct miscdevice miscdev; + struct attribute_group *attr_group; +diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c +index c7e5282..f8e94fe 100644 +--- a/drivers/char/tpm/tpm_tis.c ++++ b/drivers/char/tpm/tpm_tis.c +@@ -396,6 +396,36 @@ out_err: + return rc; + } + ++struct tis_vendor_timeout_override { ++ u32 did_vid; ++ unsigned long timeout_us[4]; ++}; ++ ++static const struct tis_vendor_timeout_override vendor_timeout_overrides[] = { ++ /* Atmel 3204 */ ++ { 0x32041114, { (TIS_SHORT_TIMEOUT*1000), (TIS_LONG_TIMEOUT*1000), ++ (TIS_SHORT_TIMEOUT*1000), (TIS_SHORT_TIMEOUT*1000) } }, ++}; ++ ++static bool tpm_tis_update_timeouts(struct tpm_chip *chip, ++ unsigned long *timeout_cap) ++{ ++ int i; ++ u32 did_vid; ++ ++ did_vid = ioread32(chip->vendor.iobase + TPM_DID_VID(0)); ++ ++ for (i = 0; i != ARRAY_SIZE(vendor_timeout_overrides); i++) { ++ if (vendor_timeout_overrides[i].did_vid != did_vid) ++ continue; ++ memcpy(timeout_cap, vendor_timeout_overrides[i].timeout_us, ++ sizeof(vendor_timeout_overrides[i].timeout_us)); ++ return true; ++ } ++ ++ return false; ++} ++ + /* + * Early probing for iTPM with STS_DATA_EXPECT flaw. + * Try sending command without itpm flag set and if that +@@ -483,6 +513,7 @@ static struct tpm_vendor_specific tpm_tis = { + .recv = tpm_tis_recv, + .send = tpm_tis_send, + .cancel = tpm_tis_ready, ++ .update_timeouts = tpm_tis_update_timeouts, + .req_complete_mask = TPM_STS_DATA_AVAIL | TPM_STS_VALID, + .req_complete_val = TPM_STS_DATA_AVAIL | TPM_STS_VALID, + .req_canceled = TPM_STS_COMMAND_READY, +diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c +index 5efba47..9b3f787 100644 +--- a/drivers/gpu/drm/radeon/evergreen.c ++++ b/drivers/gpu/drm/radeon/evergreen.c +@@ -2765,6 +2765,7 @@ static u32 evergreen_get_ih_wptr(struct radeon_device *rdev) + tmp = RREG32(IH_RB_CNTL); + tmp |= IH_WPTR_OVERFLOW_CLEAR; + WREG32(IH_RB_CNTL, tmp); ++ wptr &= ~RB_OVERFLOW; + } + return (wptr & rdev->ih.ptr_mask); + } +diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c +index f7e3cc0..ab46a99 100644 +--- a/drivers/gpu/drm/radeon/r600.c ++++ b/drivers/gpu/drm/radeon/r600.c +@@ -3280,6 +3280,7 @@ static u32 r600_get_ih_wptr(struct radeon_device *rdev) + tmp = RREG32(IH_RB_CNTL); + tmp |= IH_WPTR_OVERFLOW_CLEAR; + WREG32(IH_RB_CNTL, tmp); ++ wptr &= ~RB_OVERFLOW; + } + return (wptr & rdev->ih.ptr_mask); + } +diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c +index e4e455e..6d9c32b 100644 +--- a/drivers/gpu/drm/radeon/radeon_atombios.c ++++ b/drivers/gpu/drm/radeon/radeon_atombios.c +@@ -1873,7 +1873,7 @@ static const char *thermal_controller_names[] = { + "adm1032", + "adm1030", + "max6649", +- "lm64", ++ "lm63", /* lm64 */ + "f75375", + "asc7xxx", + }; +@@ -1884,7 +1884,7 @@ static const char *pp_lib_thermal_controller_names[] = { + "adm1032", + "adm1030", + "max6649", +- "lm64", ++ "lm63", /* lm64 */ + "f75375", + "RV6xx", + "RV770", +diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c +index 9e4313e..508c64c 100644 +--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c ++++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c +@@ -398,13 +398,18 @@ static int ttm_pool_get_num_unused_pages(void) + static int ttm_pool_mm_shrink(struct shrinker *shrink, + struct shrink_control *sc) + { +- static atomic_t start_pool = ATOMIC_INIT(0); ++ static DEFINE_MUTEX(lock); ++ static unsigned start_pool; + unsigned i; +- unsigned pool_offset = atomic_add_return(1, &start_pool); ++ unsigned pool_offset; + struct ttm_page_pool *pool; + int shrink_pages = sc->nr_to_scan; + +- pool_offset = pool_offset % NUM_POOLS; ++ if (shrink_pages == 0) ++ goto out; ++ if (!mutex_trylock(&lock)) ++ return -1; ++ pool_offset = ++start_pool % NUM_POOLS; + /* select start pool in round robin fashion */ + for (i = 0; i < NUM_POOLS; ++i) { + unsigned nr_free = shrink_pages; +@@ -413,6 +418,8 @@ static int ttm_pool_mm_shrink(struct shrinker *shrink, + pool = &_manager->pools[(i + pool_offset)%NUM_POOLS]; + shrink_pages = ttm_page_pool_free(pool, nr_free); + } ++ mutex_unlock(&lock); ++out: + /* return estimated number of unused pages in pool */ + return ttm_pool_get_num_unused_pages(); + } +diff --git a/drivers/hid/hid-cherry.c b/drivers/hid/hid-cherry.c +index 888ece6..f870bb3 100644 +--- a/drivers/hid/hid-cherry.c ++++ b/drivers/hid/hid-cherry.c +@@ -29,7 +29,7 @@ + static __u8 *ch_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) + { +- if (*rsize >= 17 && rdesc[11] == 0x3c && rdesc[12] == 0x02) { ++ if (*rsize >= 18 && rdesc[11] == 0x3c && rdesc[12] == 0x02) { + hid_info(hdev, "fixing up Cherry Cymotion report descriptor\n"); + rdesc[11] = rdesc[16] = 0xff; + rdesc[12] = rdesc[17] = 0x03; +diff --git a/drivers/hid/hid-kye.c b/drivers/hid/hid-kye.c +index f2ba9ef..25dfb5f 100644 +--- a/drivers/hid/hid-kye.c ++++ b/drivers/hid/hid-kye.c +@@ -26,7 +26,7 @@ + static __u8 *kye_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) + { +- if (*rsize >= 74 && ++ if (*rsize >= 75 && + rdesc[61] == 0x05 && rdesc[62] == 0x08 && + rdesc[63] == 0x19 && rdesc[64] == 0x08 && + rdesc[65] == 0x29 && rdesc[66] == 0x0f && +diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c +index e7a7bd1..3ad6cd4 100644 +--- a/drivers/hid/hid-lg.c ++++ b/drivers/hid/hid-lg.c +@@ -111,14 +111,14 @@ static __u8 *lg_report_fixup(struct hid_device *hdev, __u8 *rdesc, + { + unsigned long quirks = (unsigned long)hid_get_drvdata(hdev); + +- if ((quirks & LG_RDESC) && *rsize >= 90 && rdesc[83] == 0x26 && ++ if ((quirks & LG_RDESC) && *rsize >= 91 && rdesc[83] == 0x26 && + rdesc[84] == 0x8c && rdesc[85] == 0x02) { + hid_info(hdev, + "fixing up Logitech keyboard report descriptor\n"); + rdesc[84] = rdesc[89] = 0x4d; + rdesc[85] = rdesc[90] = 0x10; + } +- if ((quirks & LG_RDESC_REL_ABS) && *rsize >= 50 && ++ if ((quirks & LG_RDESC_REL_ABS) && *rsize >= 51 && + rdesc[32] == 0x81 && rdesc[33] == 0x06 && + rdesc[49] == 0x81 && rdesc[50] == 0x06) { + hid_info(hdev, +diff --git a/drivers/hid/hid-logitech-dj.c b/drivers/hid/hid-logitech-dj.c +index 828a0dd..488a21a 100644 +--- a/drivers/hid/hid-logitech-dj.c ++++ b/drivers/hid/hid-logitech-dj.c +@@ -230,13 +230,6 @@ static void logi_dj_recv_add_djhid_device(struct dj_receiver_dev *djrcv_dev, + return; + } + +- if ((dj_report->device_index < DJ_DEVICE_INDEX_MIN) || +- (dj_report->device_index > DJ_DEVICE_INDEX_MAX)) { +- dev_err(&djrcv_hdev->dev, "%s: invalid device index:%d\n", +- __func__, dj_report->device_index); +- return; +- } +- + if (djrcv_dev->paired_dj_devices[dj_report->device_index]) { + /* The device is already known. No need to reallocate it. */ + dbg_hid("%s: device is already known\n", __func__); +@@ -686,7 +679,6 @@ static int logi_dj_raw_event(struct hid_device *hdev, + struct dj_receiver_dev *djrcv_dev = hid_get_drvdata(hdev); + struct dj_report *dj_report = (struct dj_report *) data; + unsigned long flags; +- bool report_processed = false; + + dbg_hid("%s, size:%d\n", __func__, size); + +@@ -714,27 +706,41 @@ static int logi_dj_raw_event(struct hid_device *hdev, + * anything else with it. + */ + ++ /* case 1) */ ++ if (data[0] != REPORT_ID_DJ_SHORT) ++ return false; ++ ++ if ((dj_report->device_index < DJ_DEVICE_INDEX_MIN) || ++ (dj_report->device_index > DJ_DEVICE_INDEX_MAX)) { ++ /* ++ * Device index is wrong, bail out. ++ * This driver can ignore safely the receiver notifications, ++ * so ignore those reports too. ++ */ ++ if (dj_report->device_index != DJ_RECEIVER_INDEX) ++ dev_err(&hdev->dev, "%s: invalid device index:%d\n", ++ __func__, dj_report->device_index); ++ return false; ++ } ++ + spin_lock_irqsave(&djrcv_dev->lock, flags); +- if (dj_report->report_id == REPORT_ID_DJ_SHORT) { +- switch (dj_report->report_type) { +- case REPORT_TYPE_NOTIF_DEVICE_PAIRED: +- case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED: +- logi_dj_recv_queue_notification(djrcv_dev, dj_report); +- break; +- case REPORT_TYPE_NOTIF_CONNECTION_STATUS: +- if (dj_report->report_params[CONNECTION_STATUS_PARAM_STATUS] == +- STATUS_LINKLOSS) { +- logi_dj_recv_forward_null_report(djrcv_dev, dj_report); +- } +- break; +- default: +- logi_dj_recv_forward_report(djrcv_dev, dj_report); ++ switch (dj_report->report_type) { ++ case REPORT_TYPE_NOTIF_DEVICE_PAIRED: ++ case REPORT_TYPE_NOTIF_DEVICE_UNPAIRED: ++ logi_dj_recv_queue_notification(djrcv_dev, dj_report); ++ break; ++ case REPORT_TYPE_NOTIF_CONNECTION_STATUS: ++ if (dj_report->report_params[CONNECTION_STATUS_PARAM_STATUS] == ++ STATUS_LINKLOSS) { ++ logi_dj_recv_forward_null_report(djrcv_dev, dj_report); + } +- report_processed = true; ++ break; ++ default: ++ logi_dj_recv_forward_report(djrcv_dev, dj_report); + } + spin_unlock_irqrestore(&djrcv_dev->lock, flags); + +- return report_processed; ++ return true; + } + + static int logi_dj_probe(struct hid_device *hdev, +diff --git a/drivers/hid/hid-logitech-dj.h b/drivers/hid/hid-logitech-dj.h +index 4a40003..daeb0aa 100644 +--- a/drivers/hid/hid-logitech-dj.h ++++ b/drivers/hid/hid-logitech-dj.h +@@ -27,6 +27,7 @@ + + #define DJ_MAX_PAIRED_DEVICES 6 + #define DJ_MAX_NUMBER_NOTIFICATIONS 8 ++#define DJ_RECEIVER_INDEX 0 + #define DJ_DEVICE_INDEX_MIN 1 + #define DJ_DEVICE_INDEX_MAX 6 + +diff --git a/drivers/hid/hid-magicmouse.c b/drivers/hid/hid-magicmouse.c +index 7cf3ffe..81356f6 100644 +--- a/drivers/hid/hid-magicmouse.c ++++ b/drivers/hid/hid-magicmouse.c +@@ -308,6 +308,11 @@ static int magicmouse_raw_event(struct hid_device *hdev, + if (size < 4 || ((size - 4) % 9) != 0) + return 0; + npoints = (size - 4) / 9; ++ if (npoints > 15) { ++ hid_warn(hdev, "invalid size value (%d) for TRACKPAD_REPORT_ID\n", ++ size); ++ return 0; ++ } + msc->ntouches = 0; + for (ii = 0; ii < npoints; ii++) + magicmouse_emit_touch(msc, ii, data + ii * 9 + 4); +@@ -331,6 +336,11 @@ static int magicmouse_raw_event(struct hid_device *hdev, + if (size < 6 || ((size - 6) % 8) != 0) + return 0; + npoints = (size - 6) / 8; ++ if (npoints > 15) { ++ hid_warn(hdev, "invalid size value (%d) for MOUSE_REPORT_ID\n", ++ size); ++ return 0; ++ } + msc->ntouches = 0; + for (ii = 0; ii < npoints; ii++) + magicmouse_emit_touch(msc, ii, data + ii * 8 + 6); +diff --git a/drivers/hid/hid-monterey.c b/drivers/hid/hid-monterey.c +index dedf757..eb0271e 100644 +--- a/drivers/hid/hid-monterey.c ++++ b/drivers/hid/hid-monterey.c +@@ -25,7 +25,7 @@ + static __u8 *mr_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) + { +- if (*rsize >= 30 && rdesc[29] == 0x05 && rdesc[30] == 0x09) { ++ if (*rsize >= 31 && rdesc[29] == 0x05 && rdesc[30] == 0x09) { + hid_info(hdev, "fixing up button/consumer in HID report descriptor\n"); + rdesc[30] = 0x0c; + } +diff --git a/drivers/hid/hid-petalynx.c b/drivers/hid/hid-petalynx.c +index f1ea3ff..99f317a 100644 +--- a/drivers/hid/hid-petalynx.c ++++ b/drivers/hid/hid-petalynx.c +@@ -26,7 +26,7 @@ + static __u8 *pl_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) + { +- if (*rsize >= 60 && rdesc[39] == 0x2a && rdesc[40] == 0xf5 && ++ if (*rsize >= 62 && rdesc[39] == 0x2a && rdesc[40] == 0xf5 && + rdesc[41] == 0x00 && rdesc[59] == 0x26 && + rdesc[60] == 0xf9 && rdesc[61] == 0x00) { + hid_info(hdev, "fixing up Petalynx Maxter Remote report descriptor\n"); +diff --git a/drivers/hid/hid-picolcd.c b/drivers/hid/hid-picolcd.c +index 1daeaca..c952131 100644 +--- a/drivers/hid/hid-picolcd.c ++++ b/drivers/hid/hid-picolcd.c +@@ -2382,6 +2382,12 @@ static int picolcd_raw_event(struct hid_device *hdev, + if (!data) + return 1; + ++ if (size > 64) { ++ hid_warn(hdev, "invalid size value (%d) for picolcd raw event\n", ++ size); ++ return 0; ++ } ++ + if (report->id == REPORT_KEY_STATE) { + if (data->input_keys) + ret = picolcd_raw_keypad(data, report, raw_data+1, size-1); +diff --git a/drivers/hid/hid-sunplus.c b/drivers/hid/hid-sunplus.c +index d484a00..3d6ae7b 100644 +--- a/drivers/hid/hid-sunplus.c ++++ b/drivers/hid/hid-sunplus.c +@@ -25,7 +25,7 @@ + static __u8 *sp_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) + { +- if (*rsize >= 107 && rdesc[104] == 0x26 && rdesc[105] == 0x80 && ++ if (*rsize >= 112 && rdesc[104] == 0x26 && rdesc[105] == 0x80 && + rdesc[106] == 0x03) { + hid_info(hdev, "fixing up Sunplus Wireless Desktop report descriptor\n"); + rdesc[105] = rdesc[110] = 0x03; +diff --git a/drivers/hwmon/ads1015.c b/drivers/hwmon/ads1015.c +index dd87ae9..2f14cad 100644 +--- a/drivers/hwmon/ads1015.c ++++ b/drivers/hwmon/ads1015.c +@@ -186,7 +186,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client) + } + + channel = be32_to_cpup(property); +- if (channel > ADS1015_CHANNELS) { ++ if (channel >= ADS1015_CHANNELS) { + dev_err(&client->dev, + "invalid channel index %d on %s\n", + channel, node->full_name); +@@ -200,6 +200,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client) + dev_err(&client->dev, + "invalid gain on %s\n", + node->full_name); ++ return -EINVAL; + } + } + +@@ -210,6 +211,7 @@ static int ads1015_get_channels_config_of(struct i2c_client *client) + dev_err(&client->dev, + "invalid data_rate on %s\n", + node->full_name); ++ return -EINVAL; + } + } + +diff --git a/drivers/hwmon/amc6821.c b/drivers/hwmon/amc6821.c +index 75be6c4..b7f3356 100644 +--- a/drivers/hwmon/amc6821.c ++++ b/drivers/hwmon/amc6821.c +@@ -360,11 +360,13 @@ static ssize_t set_pwm1_enable( + if (config) + return config; + ++ mutex_lock(&data->update_lock); + config = i2c_smbus_read_byte_data(client, AMC6821_REG_CONF1); + if (config < 0) { + dev_err(&client->dev, + "Error reading configuration register, aborting.\n"); +- return -EIO; ++ count = config; ++ goto unlock; + } + + switch (val) { +@@ -381,14 +383,15 @@ static ssize_t set_pwm1_enable( + config |= AMC6821_CONF1_FDRC1; + break; + default: +- return -EINVAL; ++ count = -EINVAL; ++ goto unlock; + } +- mutex_lock(&data->update_lock); + if (i2c_smbus_write_byte_data(client, AMC6821_REG_CONF1, config)) { + dev_err(&client->dev, + "Configuration register write error, aborting.\n"); + count = -EIO; + } ++unlock: + mutex_unlock(&data->update_lock); + return count; + } +@@ -495,8 +498,9 @@ static ssize_t set_temp_auto_point_temp( + return -EINVAL; + } + +- data->valid = 0; + mutex_lock(&data->update_lock); ++ data->valid = 0; ++ + switch (ix) { + case 0: + ptemp[0] = SENSORS_LIMIT(val / 1000, 0, +@@ -669,13 +673,14 @@ static ssize_t set_fan1_div( + if (config) + return config; + ++ mutex_lock(&data->update_lock); + config = i2c_smbus_read_byte_data(client, AMC6821_REG_CONF4); + if (config < 0) { + dev_err(&client->dev, + "Error reading configuration register, aborting.\n"); +- return -EIO; ++ count = config; ++ goto EXIT; + } +- mutex_lock(&data->update_lock); + switch (val) { + case 2: + config &= ~AMC6821_CONF4_PSPR; +diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c +index 9ba38f3..05c4f47 100644 +--- a/drivers/hwmon/gpio-fan.c ++++ b/drivers/hwmon/gpio-fan.c +@@ -195,7 +195,7 @@ static int get_fan_speed_index(struct gpio_fan_data *fan_data) + return -EINVAL; + } + +-static int rpm_to_speed_index(struct gpio_fan_data *fan_data, int rpm) ++static int rpm_to_speed_index(struct gpio_fan_data *fan_data, unsigned long rpm) + { + struct gpio_fan_speed *speed = fan_data->speed; + int i; +diff --git a/drivers/hwmon/lm78.c b/drivers/hwmon/lm78.c +index a42a7b0..5ce5d5a 100644 +--- a/drivers/hwmon/lm78.c ++++ b/drivers/hwmon/lm78.c +@@ -102,7 +102,7 @@ static inline int FAN_FROM_REG(u8 val, int div) + + /* TEMP: mC (-128C to +127C) + REG: 1C/bit, two's complement */ +-static inline s8 TEMP_TO_REG(int val) ++static inline s8 TEMP_TO_REG(long val) + { + int nval = SENSORS_LIMIT(val, -128000, 127000) ; + return nval<0 ? (nval-500)/1000 : (nval+500)/1000; +diff --git a/drivers/hwmon/lm85.c b/drivers/hwmon/lm85.c +index da72dc1..97bfba2 100644 +--- a/drivers/hwmon/lm85.c ++++ b/drivers/hwmon/lm85.c +@@ -157,7 +157,7 @@ static inline u16 FAN_TO_REG(unsigned long val) + + /* Temperature is reported in .001 degC increments */ + #define TEMP_TO_REG(val) \ +- SENSORS_LIMIT(SCALE(val, 1000, 1), -127, 127) ++ DIV_ROUND_CLOSEST(SENSORS_LIMIT((val), -127000, 127000), 1000) + #define TEMPEXT_FROM_REG(val, ext) \ + SCALE(((val) << 4) + (ext), 16, 1000) + #define TEMP_FROM_REG(val) ((val) * 1000) +@@ -190,7 +190,7 @@ static const int lm85_range_map[] = { + 13300, 16000, 20000, 26600, 32000, 40000, 53300, 80000 + }; + +-static int RANGE_TO_REG(int range) ++static int RANGE_TO_REG(long range) + { + int i; + +@@ -212,7 +212,7 @@ static const int adm1027_freq_map[8] = { /* 1 Hz */ + 11, 15, 22, 29, 35, 44, 59, 88 + }; + +-static int FREQ_TO_REG(const int *map, int freq) ++static int FREQ_TO_REG(const int *map, unsigned long freq) + { + int i; + +@@ -443,7 +443,13 @@ static ssize_t store_vrm_reg(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) + { + struct lm85_data *data = dev_get_drvdata(dev); +- data->vrm = simple_strtoul(buf, NULL, 10); ++ unsigned long val; ++ ++ val = simple_strtoul(buf, NULL, 10); ++ if (val > 255) ++ return -EINVAL; ++ ++ data->vrm = val; + return count; + } + +diff --git a/drivers/hwmon/lm92.c b/drivers/hwmon/lm92.c +index 8fcbd4d4..5d091fa 100644 +--- a/drivers/hwmon/lm92.c ++++ b/drivers/hwmon/lm92.c +@@ -73,12 +73,9 @@ static inline int TEMP_FROM_REG(s16 reg) + return reg / 8 * 625 / 10; + } + +-static inline s16 TEMP_TO_REG(int val) ++static inline s16 TEMP_TO_REG(long val) + { +- if (val <= -60000) +- return -60000 * 10 / 625 * 8; +- if (val >= 160000) +- return 160000 * 10 / 625 * 8; ++ val = clamp_val(val, -60000, 160000); + return val * 10 / 625 * 8; + } + +@@ -192,10 +189,12 @@ static ssize_t set_temp1_crit_hyst(struct device *dev, struct device_attribute * + struct lm92_data *data = i2c_get_clientdata(client); + long val = simple_strtol(buf, NULL, 10); + ++ val = clamp_val(val, -120000, 220000); + mutex_lock(&data->update_lock); +- data->temp1_hyst = TEMP_FROM_REG(data->temp1_crit) - val; ++ data->temp1_hyst = ++ TEMP_TO_REG(TEMP_FROM_REG(data->temp1_crit) - val); + i2c_smbus_write_word_swapped(client, LM92_REG_TEMP_HYST, +- TEMP_TO_REG(data->temp1_hyst)); ++ data->temp1_hyst); + mutex_unlock(&data->update_lock); + return count; + } +diff --git a/drivers/hwmon/sis5595.c b/drivers/hwmon/sis5595.c +index 5ab6953..029a2e1 100644 +--- a/drivers/hwmon/sis5595.c ++++ b/drivers/hwmon/sis5595.c +@@ -149,7 +149,7 @@ static inline int TEMP_FROM_REG(s8 val) + { + return val * 830 + 52120; + } +-static inline s8 TEMP_TO_REG(int val) ++static inline s8 TEMP_TO_REG(long val) + { + int nval = SENSORS_LIMIT(val, -54120, 157530) ; + return nval<0 ? (nval-5212-415)/830 : (nval-5212+415)/830; +diff --git a/drivers/hwmon/smsc47m192.c b/drivers/hwmon/smsc47m192.c +index 40b2667..7d1373d 100644 +--- a/drivers/hwmon/smsc47m192.c ++++ b/drivers/hwmon/smsc47m192.c +@@ -84,7 +84,7 @@ static inline u8 IN_TO_REG(unsigned long val, int n) + REG: 1C/bit, two's complement */ + static inline s8 TEMP_TO_REG(int val) + { +- return SENSORS_LIMIT(SCALE(val, 1, 1000), -128000, 127000); ++ return SCALE(SENSORS_LIMIT(val, -128000, 127000), 1, 1000); + } + + static inline int TEMP_FROM_REG(s8 val) +@@ -349,7 +349,13 @@ static ssize_t set_vrm(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) + { + struct smsc47m192_data *data = dev_get_drvdata(dev); +- data->vrm = simple_strtoul(buf, NULL, 10); ++ unsigned long val; ++ ++ val = simple_strtoul(buf, NULL, 10); ++ if (val > 255) ++ return -EINVAL; ++ ++ data->vrm = val; + return count; + } + static DEVICE_ATTR(vrm, S_IRUGO | S_IWUSR, show_vrm, set_vrm); +diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c +index 1a696f7..2882556 100644 +--- a/drivers/infiniband/core/iwcm.c ++++ b/drivers/infiniband/core/iwcm.c +@@ -46,6 +46,7 @@ + #include <linux/completion.h> + #include <linux/slab.h> + #include <linux/module.h> ++#include <linux/sysctl.h> + + #include <rdma/iw_cm.h> + #include <rdma/ib_addr.h> +@@ -65,6 +66,20 @@ struct iwcm_work { + struct list_head free_list; + }; + ++static unsigned int default_backlog = 256; ++ ++static struct ctl_table_header *iwcm_ctl_table_hdr; ++static struct ctl_table iwcm_ctl_table[] = { ++ { ++ .procname = "default_backlog", ++ .data = &default_backlog, ++ .maxlen = sizeof(default_backlog), ++ .mode = 0644, ++ .proc_handler = proc_dointvec, ++ }, ++ { } ++}; ++ + /* + * The following services provide a mechanism for pre-allocating iwcm_work + * elements. The design pre-allocates them based on the cm_id type: +@@ -419,6 +434,9 @@ int iw_cm_listen(struct iw_cm_id *cm_id, int backlog) + + cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); + ++ if (!backlog) ++ backlog = default_backlog; ++ + ret = alloc_work_entries(cm_id_priv, backlog); + if (ret) + return ret; +@@ -1014,17 +1032,33 @@ int iw_cm_init_qp_attr(struct iw_cm_id *cm_id, + } + EXPORT_SYMBOL(iw_cm_init_qp_attr); + ++static struct ctl_path iwcm_ctl_path[] = { ++ { .procname = "net" }, ++ { .procname = "iw_cm" }, ++ { } ++}; ++ + static int __init iw_cm_init(void) + { + iwcm_wq = create_singlethread_workqueue("iw_cm_wq"); + if (!iwcm_wq) + return -ENOMEM; + ++ iwcm_ctl_table_hdr = register_net_sysctl_table(&init_net, ++ iwcm_ctl_path, ++ iwcm_ctl_table); ++ if (!iwcm_ctl_table_hdr) { ++ pr_err("iw_cm: couldn't register sysctl paths\n"); ++ destroy_workqueue(iwcm_wq); ++ return -ENOMEM; ++ } ++ + return 0; + } + + static void __exit iw_cm_cleanup(void) + { ++ unregister_net_sysctl_table(iwcm_ctl_table_hdr); + destroy_workqueue(iwcm_wq); + } + +diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c +index 6cc8e67..486982f 100644 +--- a/drivers/iommu/amd_iommu.c ++++ b/drivers/iommu/amd_iommu.c +@@ -2592,14 +2592,16 @@ free_domains: + + static void cleanup_domain(struct protection_domain *domain) + { +- struct iommu_dev_data *dev_data, *next; ++ struct iommu_dev_data *entry; + unsigned long flags; + + write_lock_irqsave(&amd_iommu_devtable_lock, flags); + +- list_for_each_entry_safe(dev_data, next, &domain->dev_list, list) { +- __detach_device(dev_data); +- atomic_set(&dev_data->bind, 0); ++ while (!list_empty(&domain->dev_list)) { ++ entry = list_first_entry(&domain->dev_list, ++ struct iommu_dev_data, list); ++ __detach_device(entry); ++ atomic_set(&entry->bind, 0); + } + + write_unlock_irqrestore(&amd_iommu_devtable_lock, flags); +diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c +index 276ef38..e83aa8e 100644 +--- a/drivers/iommu/intel-iommu.c ++++ b/drivers/iommu/intel-iommu.c +@@ -2318,19 +2318,34 @@ static bool device_has_rmrr(struct pci_dev *dev) + return false; + } + ++/* ++ * There are a couple cases where we need to restrict the functionality of ++ * devices associated with RMRRs. The first is when evaluating a device for ++ * identity mapping because problems exist when devices are moved in and out ++ * of domains and their respective RMRR information is lost. This means that ++ * a device with associated RMRRs will never be in a "passthrough" domain. ++ * The second is use of the device through the IOMMU API. This interface ++ * expects to have full control of the IOVA space for the device. We cannot ++ * satisfy both the requirement that RMRR access is maintained and have an ++ * unencumbered IOVA space. We also have no ability to quiesce the device's ++ * use of the RMRR space or even inform the IOMMU API user of the restriction. ++ * We therefore prevent devices associated with an RMRR from participating in ++ * the IOMMU API, which eliminates them from device assignment. ++ * ++ * In both cases we assume that PCI USB devices with RMRRs have them largely ++ * for historical reasons and that the RMRR space is not actively used post ++ * boot. This exclusion may change if vendors begin to abuse it. ++ */ ++static bool device_is_rmrr_locked(struct pci_dev *pdev) ++{ ++ return device_has_rmrr(pdev) && ++ (pdev->class >> 8) != PCI_CLASS_SERIAL_USB; ++} ++ + static int iommu_should_identity_map(struct pci_dev *pdev, int startup) + { + +- /* +- * We want to prevent any device associated with an RMRR from +- * getting placed into the SI Domain. This is done because +- * problems exist when devices are moved in and out of domains +- * and their respective RMRR info is lost. We exempt USB devices +- * from this process due to their usage of RMRRs that are known +- * to not be needed after BIOS hand-off to OS. +- */ +- if (device_has_rmrr(pdev) && +- (pdev->class >> 8) != PCI_CLASS_SERIAL_USB) ++ if (device_is_rmrr_locked(pdev)) + return 0; + + if ((iommu_identity_mapping & IDENTMAP_AZALIA) && IS_AZALIA(pdev)) +@@ -3981,6 +3996,11 @@ static int intel_iommu_attach_device(struct iommu_domain *domain, + struct intel_iommu *iommu; + int addr_width; + ++ if (device_is_rmrr_locked(pdev)) { ++ dev_warn(dev, "Device is ineligible for IOMMU domain attach due to platform RMRR requirement. Contact your platform vendor.\n"); ++ return -EPERM; ++ } ++ + /* normally pdev is not mapped */ + if (unlikely(domain_context_mapped(pdev))) { + struct dmar_domain *old_domain; +diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c +index c706a7b..aec029a 100644 +--- a/drivers/md/raid1.c ++++ b/drivers/md/raid1.c +@@ -1233,12 +1233,12 @@ static void error(struct mddev *mddev, struct md_rdev *rdev) + mddev->degraded++; + set_bit(Faulty, &rdev->flags); + spin_unlock_irqrestore(&conf->device_lock, flags); +- /* +- * if recovery is running, make sure it aborts. +- */ +- set_bit(MD_RECOVERY_INTR, &mddev->recovery); + } else + set_bit(Faulty, &rdev->flags); ++ /* ++ * if recovery is running, make sure it aborts. ++ */ ++ set_bit(MD_RECOVERY_INTR, &mddev->recovery); + set_bit(MD_CHANGE_DEVS, &mddev->flags); + printk(KERN_ALERT + "md/raid1:%s: Disk failure on %s, disabling device.\n" +diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c +index 6d05e26..abac83a 100644 +--- a/drivers/md/raid10.c ++++ b/drivers/md/raid10.c +@@ -1272,11 +1272,11 @@ static void error(struct mddev *mddev, struct md_rdev *rdev) + spin_lock_irqsave(&conf->device_lock, flags); + mddev->degraded++; + spin_unlock_irqrestore(&conf->device_lock, flags); +- /* +- * if recovery is running, make sure it aborts. +- */ +- set_bit(MD_RECOVERY_INTR, &mddev->recovery); + } ++ /* ++ * If recovery is running, make sure it aborts. ++ */ ++ set_bit(MD_RECOVERY_INTR, &mddev->recovery); + set_bit(Blocked, &rdev->flags); + set_bit(Faulty, &rdev->flags); + set_bit(MD_CHANGE_DEVS, &mddev->flags); +diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c +index 7c963c4..c293d9c 100644 +--- a/drivers/md/raid5.c ++++ b/drivers/md/raid5.c +@@ -3240,6 +3240,8 @@ static void handle_stripe(struct stripe_head *sh) + set_bit(R5_Wantwrite, &dev->flags); + if (prexor) + continue; ++ if (s.failed > 1) ++ continue; + if (!test_bit(R5_Insync, &dev->flags) || + ((i == sh->pd_idx || i == sh->qd_idx) && + s.failed == 0)) +diff --git a/drivers/media/dvb/frontends/tda10071.c b/drivers/media/dvb/frontends/tda10071.c +index 0c37434..ba792849 100644 +--- a/drivers/media/dvb/frontends/tda10071.c ++++ b/drivers/media/dvb/frontends/tda10071.c +@@ -644,6 +644,7 @@ static int tda10071_set_frontend(struct dvb_frontend *fe, + struct dtv_frontend_properties *c = &fe->dtv_property_cache; + int ret, i; + u8 mode, rolloff, pilot, inversion, div; ++ fe_modulation_t modulation; + + dbg("%s: delivery_system=%d modulation=%d frequency=%d " \ + "symbol_rate=%d inversion=%d pilot=%d rolloff=%d", __func__, +@@ -677,10 +678,13 @@ static int tda10071_set_frontend(struct dvb_frontend *fe, + + switch (c->delivery_system) { + case SYS_DVBS: ++ modulation = QPSK; + rolloff = 0; + pilot = 2; + break; + case SYS_DVBS2: ++ modulation = c->modulation; ++ + switch (c->rolloff) { + case ROLLOFF_20: + rolloff = 2; +@@ -722,7 +726,7 @@ static int tda10071_set_frontend(struct dvb_frontend *fe, + + for (i = 0, mode = 0xff; i < ARRAY_SIZE(TDA10071_MODCOD); i++) { + if (c->delivery_system == TDA10071_MODCOD[i].delivery_system && +- c->modulation == TDA10071_MODCOD[i].modulation && ++ modulation == TDA10071_MODCOD[i].modulation && + c->fec_inner == TDA10071_MODCOD[i].fec) { + mode = TDA10071_MODCOD[i].val; + dbg("%s: mode found=%02x", __func__, mode); +diff --git a/drivers/media/video/gspca/pac7302.c b/drivers/media/video/gspca/pac7302.c +index 6ddc769..ae433ef 100644 +--- a/drivers/media/video/gspca/pac7302.c ++++ b/drivers/media/video/gspca/pac7302.c +@@ -1190,6 +1190,7 @@ static const struct usb_device_id device_table[] = { + {USB_DEVICE(0x093a, 0x2620)}, + {USB_DEVICE(0x093a, 0x2621)}, + {USB_DEVICE(0x093a, 0x2622), .driver_info = FL_VFLIP}, ++ {USB_DEVICE(0x093a, 0x2623), .driver_info = FL_VFLIP}, + {USB_DEVICE(0x093a, 0x2624), .driver_info = FL_VFLIP}, + {USB_DEVICE(0x093a, 0x2625)}, + {USB_DEVICE(0x093a, 0x2626)}, +diff --git a/drivers/mtd/ftl.c b/drivers/mtd/ftl.c +index c7382bb..65fc4af 100644 +--- a/drivers/mtd/ftl.c ++++ b/drivers/mtd/ftl.c +@@ -1074,7 +1074,6 @@ static void ftl_add_mtd(struct mtd_blktrans_ops *tr, struct mtd_info *mtd) + return; + } + +- ftl_freepart(partition); + kfree(partition); + } + +diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c +index b74cdf6..fed39de 100644 +--- a/drivers/net/macvlan.c ++++ b/drivers/net/macvlan.c +@@ -455,6 +455,7 @@ static int macvlan_init(struct net_device *dev) + (lowerdev->state & MACVLAN_STATE_MASK); + dev->features = lowerdev->features & MACVLAN_FEATURES; + dev->features |= NETIF_F_LLTX; ++ dev->vlan_features = lowerdev->vlan_features & MACVLAN_FEATURES; + dev->gso_max_size = lowerdev->gso_max_size; + dev->iflink = lowerdev->ifindex; + dev->hard_header_len = lowerdev->hard_header_len; +diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c +index 2b349d3..c974581 100644 +--- a/drivers/net/ppp/pptp.c ++++ b/drivers/net/ppp/pptp.c +@@ -281,7 +281,7 @@ static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb) + nf_reset(skb); + + skb->ip_summed = CHECKSUM_NONE; +- ip_select_ident(skb, &rt->dst, NULL); ++ ip_select_ident(skb, NULL); + ip_send_check(iph); + + ip_local_out(skb); +diff --git a/drivers/net/wireless/ath/carl9170/carl9170.h b/drivers/net/wireless/ath/carl9170/carl9170.h +index 6cfbb41..8bcf6b9 100644 +--- a/drivers/net/wireless/ath/carl9170/carl9170.h ++++ b/drivers/net/wireless/ath/carl9170/carl9170.h +@@ -265,6 +265,7 @@ struct ar9170 { + atomic_t rx_work_urbs; + atomic_t rx_pool_urbs; + kernel_ulong_t features; ++ bool usb_ep_cmd_is_bulk; + + /* firmware settings */ + struct completion fw_load_wait; +diff --git a/drivers/net/wireless/ath/carl9170/usb.c b/drivers/net/wireless/ath/carl9170/usb.c +index 333b69e..5538596 100644 +--- a/drivers/net/wireless/ath/carl9170/usb.c ++++ b/drivers/net/wireless/ath/carl9170/usb.c +@@ -614,9 +614,16 @@ int __carl9170_exec_cmd(struct ar9170 *ar, struct carl9170_cmd *cmd, + goto err_free; + } + +- usb_fill_int_urb(urb, ar->udev, usb_sndintpipe(ar->udev, +- AR9170_USB_EP_CMD), cmd, cmd->hdr.len + 4, +- carl9170_usb_cmd_complete, ar, 1); ++ if (ar->usb_ep_cmd_is_bulk) ++ usb_fill_bulk_urb(urb, ar->udev, ++ usb_sndbulkpipe(ar->udev, AR9170_USB_EP_CMD), ++ cmd, cmd->hdr.len + 4, ++ carl9170_usb_cmd_complete, ar); ++ else ++ usb_fill_int_urb(urb, ar->udev, ++ usb_sndintpipe(ar->udev, AR9170_USB_EP_CMD), ++ cmd, cmd->hdr.len + 4, ++ carl9170_usb_cmd_complete, ar, 1); + + if (free_buf) + urb->transfer_flags |= URB_FREE_BUFFER; +@@ -1025,9 +1032,10 @@ static void carl9170_usb_firmware_step2(const struct firmware *fw, + static int carl9170_usb_probe(struct usb_interface *intf, + const struct usb_device_id *id) + { ++ struct usb_endpoint_descriptor *ep; + struct ar9170 *ar; + struct usb_device *udev; +- int err; ++ int i, err; + + err = usb_reset_device(interface_to_usbdev(intf)); + if (err) +@@ -1043,6 +1051,21 @@ static int carl9170_usb_probe(struct usb_interface *intf, + ar->intf = intf; + ar->features = id->driver_info; + ++ /* We need to remember the type of endpoint 4 because it differs ++ * between high- and full-speed configuration. The high-speed ++ * configuration specifies it as interrupt and the full-speed ++ * configuration as bulk endpoint. This information is required ++ * later when sending urbs to that endpoint. ++ */ ++ for (i = 0; i < intf->cur_altsetting->desc.bNumEndpoints; ++i) { ++ ep = &intf->cur_altsetting->endpoint[i].desc; ++ ++ if (usb_endpoint_num(ep) == AR9170_USB_EP_CMD && ++ usb_endpoint_dir_out(ep) && ++ usb_endpoint_type(ep) == USB_ENDPOINT_XFER_BULK) ++ ar->usb_ep_cmd_is_bulk = true; ++ } ++ + usb_set_intfdata(intf, ar); + SET_IEEE80211_DEV(ar->hw, &intf->dev); + +diff --git a/drivers/sbus/char/bbc_envctrl.c b/drivers/sbus/char/bbc_envctrl.c +index 160e751..0787b97 100644 +--- a/drivers/sbus/char/bbc_envctrl.c ++++ b/drivers/sbus/char/bbc_envctrl.c +@@ -452,6 +452,9 @@ static void attach_one_temp(struct bbc_i2c_bus *bp, struct platform_device *op, + if (!tp) + return; + ++ INIT_LIST_HEAD(&tp->bp_list); ++ INIT_LIST_HEAD(&tp->glob_list); ++ + tp->client = bbc_i2c_attach(bp, op); + if (!tp->client) { + kfree(tp); +@@ -497,6 +500,9 @@ static void attach_one_fan(struct bbc_i2c_bus *bp, struct platform_device *op, + if (!fp) + return; + ++ INIT_LIST_HEAD(&fp->bp_list); ++ INIT_LIST_HEAD(&fp->glob_list); ++ + fp->client = bbc_i2c_attach(bp, op); + if (!fp->client) { + kfree(fp); +diff --git a/drivers/sbus/char/bbc_i2c.c b/drivers/sbus/char/bbc_i2c.c +index 5426682..7179f72 100644 +--- a/drivers/sbus/char/bbc_i2c.c ++++ b/drivers/sbus/char/bbc_i2c.c +@@ -301,13 +301,18 @@ static struct bbc_i2c_bus * __init attach_one_i2c(struct platform_device *op, in + if (!bp) + return NULL; + ++ INIT_LIST_HEAD(&bp->temps); ++ INIT_LIST_HEAD(&bp->fans); ++ + bp->i2c_control_regs = of_ioremap(&op->resource[0], 0, 0x2, "bbc_i2c_regs"); + if (!bp->i2c_control_regs) + goto fail; + +- bp->i2c_bussel_reg = of_ioremap(&op->resource[1], 0, 0x1, "bbc_i2c_bussel"); +- if (!bp->i2c_bussel_reg) +- goto fail; ++ if (op->num_resources == 2) { ++ bp->i2c_bussel_reg = of_ioremap(&op->resource[1], 0, 0x1, "bbc_i2c_bussel"); ++ if (!bp->i2c_bussel_reg) ++ goto fail; ++ } + + bp->waiting = 0; + init_waitqueue_head(&bp->wq); +diff --git a/drivers/scsi/bfa/bfa_ioc.h b/drivers/scsi/bfa/bfa_ioc.h +index 546d46b..506a3ee 100644 +--- a/drivers/scsi/bfa/bfa_ioc.h ++++ b/drivers/scsi/bfa/bfa_ioc.h +@@ -72,7 +72,7 @@ struct bfa_sge_s { + } while (0) + + #define bfa_swap_words(_x) ( \ +- ((_x) << 32) | ((_x) >> 32)) ++ ((u64)(_x) << 32) | ((u64)(_x) >> 32)) + + #ifdef __BIG_ENDIAN + #define bfa_sge_to_be(_x) +diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c +index 5b7e1bf..603a2cb 100644 +--- a/drivers/scsi/hpsa.c ++++ b/drivers/scsi/hpsa.c +@@ -2769,7 +2769,7 @@ static int hpsa_big_passthru_ioctl(struct ctlr_info *h, void __user *argp) + } + if (ioc->Request.Type.Direction == XFER_WRITE) { + if (copy_from_user(buff[sg_used], data_ptr, sz)) { +- status = -ENOMEM; ++ status = -EFAULT; + goto cleanup1; + } + } else +diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c +index cd4ac38..0bdc4a7 100644 +--- a/drivers/scsi/scsi_lib.c ++++ b/drivers/scsi/scsi_lib.c +@@ -793,6 +793,14 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes) + scsi_next_command(cmd); + return; + } ++ } else if (blk_rq_bytes(req) == 0 && result && !sense_deferred) { ++ /* ++ * Certain non BLOCK_PC requests are commands that don't ++ * actually transfer anything (FLUSH), so cannot use ++ * good_bytes != blk_rq_bytes(req) as the signal for an error. ++ * This sets the error explicitly for the problem case. ++ */ ++ error = __scsi_error_from_host_byte(cmd, result); + } + + /* no bidi support for !REQ_TYPE_BLOCK_PC yet */ +diff --git a/drivers/staging/hv/storvsc_drv.c b/drivers/staging/hv/storvsc_drv.c +index 8960f1a..c43a9e8 100644 +--- a/drivers/staging/hv/storvsc_drv.c ++++ b/drivers/staging/hv/storvsc_drv.c +@@ -32,6 +32,7 @@ + #include <linux/module.h> + #include <linux/device.h> + #include <linux/hyperv.h> ++#include <linux/blkdev.h> + #include <scsi/scsi.h> + #include <scsi/scsi_cmnd.h> + #include <scsi/scsi_host.h> +@@ -1129,6 +1130,16 @@ static void storvsc_command_completion(struct hv_storvsc_request *request) + kmem_cache_free(host_dev->request_pool, cmd_request); + } + ++/* ++ * The host guarantees to respond to each command, although I/O latencies might ++ * be unbounded on Azure. Reset the timer unconditionally to give the host a ++ * chance to perform EH. ++ */ ++static enum blk_eh_timer_return storvsc_eh_timed_out(struct scsi_cmnd *scmnd) ++{ ++ return BLK_EH_RESET_TIMER; ++} ++ + static bool storvsc_check_scsi_cmd(struct scsi_cmnd *scmnd) + { + bool allowed = true; +@@ -1305,6 +1316,7 @@ static struct scsi_host_template scsi_driver = { + .bios_param = storvsc_get_chs, + .queuecommand = storvsc_queuecommand, + .eh_host_reset_handler = storvsc_host_reset_handler, ++ .eh_timed_out = storvsc_eh_timed_out, + .slave_alloc = storvsc_device_alloc, + .slave_configure = storvsc_device_configure, + .cmd_per_lun = 1, +diff --git a/drivers/staging/vt6655/bssdb.c b/drivers/staging/vt6655/bssdb.c +index 577599e..ed4259c 100644 +--- a/drivers/staging/vt6655/bssdb.c ++++ b/drivers/staging/vt6655/bssdb.c +@@ -1083,7 +1083,7 @@ start: + pDevice->byERPFlag &= ~(WLAN_SET_ERP_USE_PROTECTION(1)); + } + +-{ ++ if (pDevice->eCommandState == WLAN_ASSOCIATE_WAIT) { + pDevice->byReAssocCount++; + if((pDevice->byReAssocCount > 10) && (pDevice->bLinkPass != true)) { //10 sec timeout + printk("Re-association timeout!!!\n"); +diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c +index d8dd784..d540a06 100644 +--- a/drivers/staging/vt6655/device_main.c ++++ b/drivers/staging/vt6655/device_main.c +@@ -2679,6 +2679,7 @@ static irqreturn_t device_intr(int irq, void *dev_instance) { + unsigned char byData = 0; + int ii= 0; + // unsigned char byRSSI; ++ unsigned long flags; + + + MACvReadISR(pDevice->PortOffset, &pDevice->dwIsr); +@@ -2704,7 +2705,8 @@ static irqreturn_t device_intr(int irq, void *dev_instance) { + + handled = 1; + MACvIntDisable(pDevice->PortOffset); +- spin_lock_irq(&pDevice->lock); ++ ++ spin_lock_irqsave(&pDevice->lock, flags); + + //Make sure current page is 0 + VNSvInPortB(pDevice->PortOffset + MAC_REG_PAGE1SEL, &byOrgPageSel); +@@ -2952,7 +2954,8 @@ static irqreturn_t device_intr(int irq, void *dev_instance) { + MACvSelectPage1(pDevice->PortOffset); + } + +- spin_unlock_irq(&pDevice->lock); ++ spin_unlock_irqrestore(&pDevice->lock, flags); ++ + MACvIntEnable(pDevice->PortOffset, IMR_MASK_VALUE); + + return IRQ_RETVAL(handled); +diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c +index 488214a..d7162a2 100644 +--- a/drivers/tty/serial/serial_core.c ++++ b/drivers/tty/serial/serial_core.c +@@ -225,6 +225,9 @@ static void uart_shutdown(struct tty_struct *tty, struct uart_state *state) + /* + * Turn off DTR and RTS early. + */ ++ if (uart_console(uport) && tty) ++ uport->cons->cflag = tty->termios->c_cflag; ++ + if (!tty || (tty->termios->c_cflag & HUPCL)) + uart_clear_mctrl(uport, TIOCM_DTR | TIOCM_RTS); + +diff --git a/drivers/tty/serial/sunsab.c b/drivers/tty/serial/sunsab.c +index b5fa2a5..5d80bb9 100644 +--- a/drivers/tty/serial/sunsab.c ++++ b/drivers/tty/serial/sunsab.c +@@ -156,6 +156,15 @@ receive_chars(struct uart_sunsab_port *up, + (up->port.line == up->port.cons->index)) + saw_console_brk = 1; + ++ if (count == 0) { ++ if (unlikely(stat->sreg.isr1 & SAB82532_ISR1_BRK)) { ++ stat->sreg.isr0 &= ~(SAB82532_ISR0_PERR | ++ SAB82532_ISR0_FERR); ++ up->port.icount.brk++; ++ uart_handle_break(&up->port); ++ } ++ } ++ + for (i = 0; i < count; i++) { + unsigned char ch = buf[i], flag; + +diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c +index 3807294..f08732b 100644 +--- a/drivers/usb/core/hub.c ++++ b/drivers/usb/core/hub.c +@@ -2651,6 +2651,43 @@ static int finish_port_resume(struct usb_device *udev) + } + + /* ++ * There are some SS USB devices which take longer time for link training. ++ * XHCI specs 4.19.4 says that when Link training is successful, port ++ * sets CSC bit to 1. So if SW reads port status before successful link ++ * training, then it will not find device to be present. ++ * USB Analyzer log with such buggy devices show that in some cases ++ * device switch on the RX termination after long delay of host enabling ++ * the VBUS. In few other cases it has been seen that device fails to ++ * negotiate link training in first attempt. It has been ++ * reported till now that few devices take as long as 2000 ms to train ++ * the link after host enabling its VBUS and termination. Following ++ * routine implements a 2000 ms timeout for link training. If in a case ++ * link trains before timeout, loop will exit earlier. ++ * ++ * FIXME: If a device was connected before suspend, but was removed ++ * while system was asleep, then the loop in the following routine will ++ * only exit at timeout. ++ * ++ * This routine should only be called when persist is enabled for a SS ++ * device. ++ */ ++static int wait_for_ss_port_enable(struct usb_device *udev, ++ struct usb_hub *hub, int *port1, ++ u16 *portchange, u16 *portstatus) ++{ ++ int status = 0, delay_ms = 0; ++ ++ while (delay_ms < 2000) { ++ if (status || *portstatus & USB_PORT_STAT_CONNECTION) ++ break; ++ msleep(20); ++ delay_ms += 20; ++ status = hub_port_status(hub, *port1, portstatus, portchange); ++ } ++ return status; ++} ++ ++/* + * usb_port_resume - re-activate a suspended usb device's upstream port + * @udev: device to re-activate, not a root hub + * Context: must be able to sleep; device not locked; pm locks held +@@ -2742,6 +2779,10 @@ int usb_port_resume(struct usb_device *udev, pm_message_t msg) + + clear_bit(port1, hub->busy_bits); + ++ if (udev->persist_enabled && hub_is_superspeed(hub->hdev)) ++ status = wait_for_ss_port_enable(udev, hub, &port1, &portchange, ++ &portstatus); ++ + status = check_port_resume_type(udev, + hub, port1, status, portchange, portstatus); + if (status == 0) +@@ -3354,6 +3395,7 @@ static void hub_port_connect_change(struct usb_hub *hub, int port1, + le16_to_cpu(hub->descriptor->wHubCharacteristics); + struct usb_device *udev; + int status, i; ++ static int unreliable_port = -1; + + dev_dbg (hub_dev, + "port %d, status %04x, change %04x, %s\n", +@@ -3415,10 +3457,11 @@ static void hub_port_connect_change(struct usb_hub *hub, int port1, + USB_PORT_STAT_C_ENABLE)) { + status = hub_port_debounce(hub, port1); + if (status < 0) { +- if (printk_ratelimit()) ++ if (port1 != unreliable_port && printk_ratelimit()) + dev_err(hub_dev, "connect-debounce failed, " + "port %d disabled\n", port1); + portstatus &= ~USB_PORT_STAT_CONNECTION; ++ unreliable_port = port1; + } else { + portstatus = status; + } +diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c +index e0ae777..6c43152 100644 +--- a/drivers/usb/host/ohci-q.c ++++ b/drivers/usb/host/ohci-q.c +@@ -294,8 +294,7 @@ static void periodic_unlink (struct ohci_hcd *ohci, struct ed *ed) + * - ED_OPER: when there's any request queued, the ED gets rescheduled + * immediately. HC should be working on them. + * +- * - ED_IDLE: when there's no TD queue. there's no reason for the HC +- * to care about this ED; safe to disable the endpoint. ++ * - ED_IDLE: when there's no TD queue or the HC isn't running. + * + * When finish_unlinks() runs later, after SOF interrupt, it will often + * complete one or more URB unlinks before making that state change. +@@ -909,6 +908,10 @@ rescan_all: + int completed, modified; + __hc32 *prev; + ++ /* Is this ED already invisible to the hardware? */ ++ if (ed->state == ED_IDLE) ++ goto ed_idle; ++ + /* only take off EDs that the HC isn't using, accounting for + * frame counter wraps and EDs with partially retired TDs + */ +@@ -938,12 +941,20 @@ skip_ed: + } + } + ++ /* ED's now officially unlinked, hc doesn't see */ ++ ed->state = ED_IDLE; ++ if (quirk_zfmicro(ohci) && ed->type == PIPE_INTERRUPT) ++ ohci->eds_scheduled--; ++ ed->hwHeadP &= ~cpu_to_hc32(ohci, ED_H); ++ ed->hwNextED = 0; ++ wmb(); ++ ed->hwINFO &= ~cpu_to_hc32(ohci, ED_SKIP | ED_DEQUEUE); ++ed_idle: ++ + /* reentrancy: if we drop the schedule lock, someone might + * have modified this list. normally it's just prepending + * entries (which we'd ignore), but paranoia won't hurt. + */ +- *last = ed->ed_next; +- ed->ed_next = NULL; + modified = 0; + + /* unlink urbs as requested, but rescan the list after +@@ -1001,19 +1012,20 @@ rescan_this: + if (completed && !list_empty (&ed->td_list)) + goto rescan_this; + +- /* ED's now officially unlinked, hc doesn't see */ +- ed->state = ED_IDLE; +- if (quirk_zfmicro(ohci) && ed->type == PIPE_INTERRUPT) +- ohci->eds_scheduled--; +- ed->hwHeadP &= ~cpu_to_hc32(ohci, ED_H); +- ed->hwNextED = 0; +- wmb (); +- ed->hwINFO &= ~cpu_to_hc32 (ohci, ED_SKIP | ED_DEQUEUE); +- +- /* but if there's work queued, reschedule */ +- if (!list_empty (&ed->td_list)) { +- if (HC_IS_RUNNING(ohci_to_hcd(ohci)->state)) +- ed_schedule (ohci, ed); ++ /* ++ * If no TDs are queued, take ED off the ed_rm_list. ++ * Otherwise, if the HC is running, reschedule. ++ * If not, leave it on the list for further dequeues. ++ */ ++ if (list_empty(&ed->td_list)) { ++ *last = ed->ed_next; ++ ed->ed_next = NULL; ++ } else if (HC_IS_RUNNING(ohci_to_hcd(ohci)->state)) { ++ *last = ed->ed_next; ++ ed->ed_next = NULL; ++ ed_schedule(ohci, ed); ++ } else { ++ last = &ed->ed_next; + } + + if (modified) +diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c +index 15685c3..e9ce957 100644 +--- a/drivers/usb/host/xhci-pci.c ++++ b/drivers/usb/host/xhci-pci.c +@@ -98,6 +98,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci) + /* AMD PLL quirk */ + if (pdev->vendor == PCI_VENDOR_ID_AMD && usb_amd_find_chipset_info()) + xhci->quirks |= XHCI_AMD_PLL_FIX; ++ ++ if (pdev->vendor == PCI_VENDOR_ID_AMD) ++ xhci->quirks |= XHCI_TRUST_TX_LENGTH; ++ + if (pdev->vendor == PCI_VENDOR_ID_INTEL && + pdev->device == PCI_DEVICE_ID_INTEL_PANTHERPOINT_XHCI) { + xhci->quirks |= XHCI_EP_LIMIT_QUIRK; +diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c +index bc5ee84..4b6abb6 100644 +--- a/drivers/usb/host/xhci-ring.c ++++ b/drivers/usb/host/xhci-ring.c +@@ -572,9 +572,12 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci, + struct xhci_virt_device *dev = xhci->devs[slot_id]; + struct xhci_virt_ep *ep = &dev->eps[ep_index]; + struct xhci_ring *ep_ring; +- struct xhci_generic_trb *trb; ++ struct xhci_segment *new_seg; ++ union xhci_trb *new_deq; + dma_addr_t addr; + u64 hw_dequeue; ++ bool cycle_found = false; ++ bool td_last_trb_found = false; + + ep_ring = xhci_triad_to_transfer_ring(xhci, slot_id, + ep_index, stream_id); +@@ -598,44 +601,45 @@ void xhci_find_new_dequeue_state(struct xhci_hcd *xhci, + hw_dequeue = le64_to_cpu(ep_ctx->deq); + } + +- /* Find virtual address and segment of hardware dequeue pointer */ +- state->new_deq_seg = ep_ring->deq_seg; +- state->new_deq_ptr = ep_ring->dequeue; +- while (xhci_trb_virt_to_dma(state->new_deq_seg, state->new_deq_ptr) +- != (dma_addr_t)(hw_dequeue & ~0xf)) { +- next_trb(xhci, ep_ring, &state->new_deq_seg, +- &state->new_deq_ptr); +- if (state->new_deq_ptr == ep_ring->dequeue) { +- WARN_ON(1); +- return; +- } +- } ++ new_seg = ep_ring->deq_seg; ++ new_deq = ep_ring->dequeue; ++ state->new_cycle_state = hw_dequeue & 0x1; ++ + /* +- * Find cycle state for last_trb, starting at old cycle state of +- * hw_dequeue. If there is only one segment ring, find_trb_seg() will +- * return immediately and cannot toggle the cycle state if this search +- * wraps around, so add one more toggle manually in that case. ++ * We want to find the pointer, segment and cycle state of the new trb ++ * (the one after current TD's last_trb). We know the cycle state at ++ * hw_dequeue, so walk the ring until both hw_dequeue and last_trb are ++ * found. + */ +- state->new_cycle_state = hw_dequeue & 0x1; +- if (ep_ring->first_seg == ep_ring->first_seg->next && +- cur_td->last_trb < state->new_deq_ptr) +- state->new_cycle_state ^= 0x1; +- +- state->new_deq_ptr = cur_td->last_trb; +- xhci_dbg(xhci, "Finding segment containing last TRB in TD.\n"); +- state->new_deq_seg = find_trb_seg(state->new_deq_seg, +- state->new_deq_ptr, &state->new_cycle_state); +- if (!state->new_deq_seg) { +- WARN_ON(1); +- return; +- } ++ do { ++ if (!cycle_found && xhci_trb_virt_to_dma(new_seg, new_deq) ++ == (dma_addr_t)(hw_dequeue & ~0xf)) { ++ cycle_found = true; ++ if (td_last_trb_found) ++ break; ++ } ++ if (new_deq == cur_td->last_trb) ++ td_last_trb_found = true; ++ ++ if (cycle_found && ++ TRB_TYPE_LINK_LE32(new_deq->generic.field[3]) && ++ new_deq->generic.field[3] & cpu_to_le32(LINK_TOGGLE)) ++ state->new_cycle_state ^= 0x1; ++ ++ next_trb(xhci, ep_ring, &new_seg, &new_deq); ++ ++ /* Search wrapped around, bail out */ ++ if (new_deq == ep->ring->dequeue) { ++ xhci_err(xhci, "Error: Failed finding new dequeue state\n"); ++ state->new_deq_seg = NULL; ++ state->new_deq_ptr = NULL; ++ return; ++ } ++ ++ } while (!cycle_found || !td_last_trb_found); + +- /* Increment to find next TRB after last_trb. Cycle if appropriate. */ +- trb = &state->new_deq_ptr->generic; +- if (TRB_TYPE_LINK_LE32(trb->field[3]) && +- (trb->field[3] & cpu_to_le32(LINK_TOGGLE))) +- state->new_cycle_state ^= 0x1; +- next_trb(xhci, ep_ring, &state->new_deq_seg, &state->new_deq_ptr); ++ state->new_deq_seg = new_seg; ++ state->new_deq_ptr = new_deq; + + /* Don't update the ring cycle state for the producer (us). */ + xhci_dbg(xhci, "Cycle state = 0x%x\n", state->new_cycle_state); +@@ -2433,7 +2437,8 @@ static int handle_tx_event(struct xhci_hcd *xhci, + * last TRB of the previous TD. The command completion handle + * will take care the rest. + */ +- if (!event_seg && trb_comp_code == COMP_STOP_INVAL) { ++ if (!event_seg && (trb_comp_code == COMP_STOP || ++ trb_comp_code == COMP_STOP_INVAL)) { + ret = 0; + goto cleanup; + } +diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c +index 457a7ac..4cc1804 100644 +--- a/drivers/usb/host/xhci.c ++++ b/drivers/usb/host/xhci.c +@@ -2819,6 +2819,9 @@ void xhci_cleanup_stalled_ring(struct xhci_hcd *xhci, + ep_index, ep->stopped_stream, ep->stopped_td, + &deq_state); + ++ if (!deq_state.new_deq_ptr || !deq_state.new_deq_seg) ++ return; ++ + /* HW with the reset endpoint quirk will use the saved dequeue state to + * issue a configure endpoint command later. + */ +diff --git a/drivers/usb/misc/sisusbvga/sisusb.c b/drivers/usb/misc/sisusbvga/sisusb.c +index 7af163d..f1bfd01 100644 +--- a/drivers/usb/misc/sisusbvga/sisusb.c ++++ b/drivers/usb/misc/sisusbvga/sisusb.c +@@ -3248,6 +3248,7 @@ static const struct usb_device_id sisusb_table[] = { + { USB_DEVICE(0x0711, 0x0918) }, + { USB_DEVICE(0x0711, 0x0920) }, + { USB_DEVICE(0x0711, 0x0950) }, ++ { USB_DEVICE(0x0711, 0x5200) }, + { USB_DEVICE(0x182d, 0x021c) }, + { USB_DEVICE(0x182d, 0x0269) }, + { } +diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c +index d6e6205..0d34f85 100644 +--- a/drivers/usb/serial/ftdi_sio.c ++++ b/drivers/usb/serial/ftdi_sio.c +@@ -162,6 +162,7 @@ static struct usb_device_id id_table_combined [] = { + { USB_DEVICE(FTDI_VID, FTDI_AMC232_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_CANUSB_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_CANDAPTER_PID) }, ++ { USB_DEVICE(FTDI_VID, FTDI_BM_ATOM_NANO_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_NXTCAM_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_EV3CON_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_SCS_DEVICE_0_PID) }, +@@ -684,6 +685,8 @@ static struct usb_device_id id_table_combined [] = { + { USB_DEVICE(FTDI_VID, XSENS_CONVERTER_5_PID) }, + { USB_DEVICE(FTDI_VID, XSENS_CONVERTER_6_PID) }, + { USB_DEVICE(FTDI_VID, XSENS_CONVERTER_7_PID) }, ++ { USB_DEVICE(XSENS_VID, XSENS_CONVERTER_PID) }, ++ { USB_DEVICE(XSENS_VID, XSENS_MTW_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_OMNI1509) }, + { USB_DEVICE(MOBILITY_VID, MOBILITY_USB_SERIAL_PID) }, + { USB_DEVICE(FTDI_VID, FTDI_ACTIVE_ROBOTS_PID) }, +@@ -956,6 +959,8 @@ static struct usb_device_id id_table_combined [] = { + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_2_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_3_PID) }, + { USB_DEVICE(BRAINBOXES_VID, BRAINBOXES_US_842_4_PID) }, ++ /* ekey Devices */ ++ { USB_DEVICE(FTDI_VID, FTDI_EKEY_CONV_USB_PID) }, + { }, /* Optional parameter entry */ + { } /* Terminating entry */ + }; +diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h +index 55af915..cbcb1e6 100644 +--- a/drivers/usb/serial/ftdi_sio_ids.h ++++ b/drivers/usb/serial/ftdi_sio_ids.h +@@ -42,6 +42,8 @@ + /* www.candapter.com Ewert Energy Systems CANdapter device */ + #define FTDI_CANDAPTER_PID 0x9F80 /* Product Id */ + ++#define FTDI_BM_ATOM_NANO_PID 0xa559 /* Basic Micro ATOM Nano USB2Serial */ ++ + /* + * Texas Instruments XDS100v2 JTAG / BeagleBone A3 + * http://processors.wiki.ti.com/index.php/XDS100 +@@ -140,12 +142,15 @@ + /* + * Xsens Technologies BV products (http://www.xsens.com). + */ +-#define XSENS_CONVERTER_0_PID 0xD388 +-#define XSENS_CONVERTER_1_PID 0xD389 ++#define XSENS_VID 0x2639 ++#define XSENS_CONVERTER_PID 0xD00D /* Xsens USB-serial converter */ ++#define XSENS_MTW_PID 0x0200 /* Xsens MTw */ ++#define XSENS_CONVERTER_0_PID 0xD388 /* Xsens USB converter */ ++#define XSENS_CONVERTER_1_PID 0xD389 /* Xsens Wireless Receiver */ + #define XSENS_CONVERTER_2_PID 0xD38A +-#define XSENS_CONVERTER_3_PID 0xD38B +-#define XSENS_CONVERTER_4_PID 0xD38C +-#define XSENS_CONVERTER_5_PID 0xD38D ++#define XSENS_CONVERTER_3_PID 0xD38B /* Xsens USB-serial converter */ ++#define XSENS_CONVERTER_4_PID 0xD38C /* Xsens Wireless Receiver */ ++#define XSENS_CONVERTER_5_PID 0xD38D /* Xsens Awinda Station */ + #define XSENS_CONVERTER_6_PID 0xD38E + #define XSENS_CONVERTER_7_PID 0xD38F + +@@ -1369,3 +1374,8 @@ + #define BRAINBOXES_US_160_6_PID 0x9006 /* US-160 16xRS232 1Mbaud Port 11 and 12 */ + #define BRAINBOXES_US_160_7_PID 0x9007 /* US-160 16xRS232 1Mbaud Port 13 and 14 */ + #define BRAINBOXES_US_160_8_PID 0x9008 /* US-160 16xRS232 1Mbaud Port 15 and 16 */ ++ ++/* ++ * ekey biometric systems GmbH (http://ekey.net/) ++ */ ++#define FTDI_EKEY_CONV_USB_PID 0xCB08 /* Converter USB */ +diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c +index 7a1c91e..d8360be 100644 +--- a/drivers/usb/serial/option.c ++++ b/drivers/usb/serial/option.c +@@ -496,6 +496,10 @@ static void option_instat_callback(struct urb *urb); + #define INOVIA_VENDOR_ID 0x20a6 + #define INOVIA_SEW858 0x1105 + ++/* VIA Telecom */ ++#define VIATELECOM_VENDOR_ID 0x15eb ++#define VIATELECOM_PRODUCT_CDS7 0x0001 ++ + /* some devices interfaces need special handling due to a number of reasons */ + enum option_blacklist_reason { + OPTION_BLACKLIST_NONE = 0, +@@ -1740,6 +1744,7 @@ static const struct usb_device_id option_ids[] = { + { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */ + { USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */ + { USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) }, ++ { USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) }, + { } /* Terminating entry */ + }; + MODULE_DEVICE_TABLE(usb, option_ids); +diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c +index 45a288c..7ba38ea 100644 +--- a/drivers/usb/serial/pl2303.c ++++ b/drivers/usb/serial/pl2303.c +@@ -51,6 +51,7 @@ static const struct usb_device_id id_table[] = { + { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_GPRS) }, + { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_HCR331) }, + { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_MOTOROLA) }, ++ { USB_DEVICE(PL2303_VENDOR_ID, PL2303_PRODUCT_ID_ZTEK) }, + { USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID) }, + { USB_DEVICE(IODATA_VENDOR_ID, IODATA_PRODUCT_ID_RSAQ5) }, + { USB_DEVICE(ATEN_VENDOR_ID, ATEN_PRODUCT_ID) }, +diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h +index 42bc082..71fd9da 100644 +--- a/drivers/usb/serial/pl2303.h ++++ b/drivers/usb/serial/pl2303.h +@@ -22,6 +22,7 @@ + #define PL2303_PRODUCT_ID_GPRS 0x0609 + #define PL2303_PRODUCT_ID_HCR331 0x331a + #define PL2303_PRODUCT_ID_MOTOROLA 0x0307 ++#define PL2303_PRODUCT_ID_ZTEK 0xe1f1 + + #define ATEN_VENDOR_ID 0x0557 + #define ATEN_VENDOR_ID2 0x0547 +diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c +index 8f76a2b..803806c 100644 +--- a/drivers/usb/serial/usb-serial.c ++++ b/drivers/usb/serial/usb-serial.c +@@ -791,29 +791,39 @@ int usb_serial_probe(struct usb_interface *interface, + if (usb_endpoint_is_bulk_in(endpoint)) { + /* we found a bulk in endpoint */ + dbg("found bulk in on endpoint %d", i); +- bulk_in_endpoint[num_bulk_in] = endpoint; +- ++num_bulk_in; ++ if (num_bulk_in < MAX_NUM_PORTS) { ++ bulk_in_endpoint[num_bulk_in] = endpoint; ++ ++num_bulk_in; ++ } + } + + if (usb_endpoint_is_bulk_out(endpoint)) { + /* we found a bulk out endpoint */ + dbg("found bulk out on endpoint %d", i); +- bulk_out_endpoint[num_bulk_out] = endpoint; +- ++num_bulk_out; ++ if (num_bulk_out < MAX_NUM_PORTS) { ++ bulk_out_endpoint[num_bulk_out] = endpoint; ++ ++num_bulk_out; ++ } + } + + if (usb_endpoint_is_int_in(endpoint)) { + /* we found a interrupt in endpoint */ + dbg("found interrupt in on endpoint %d", i); +- interrupt_in_endpoint[num_interrupt_in] = endpoint; +- ++num_interrupt_in; ++ if (num_interrupt_in < MAX_NUM_PORTS) { ++ interrupt_in_endpoint[num_interrupt_in] = ++ endpoint; ++ ++num_interrupt_in; ++ } + } + + if (usb_endpoint_is_int_out(endpoint)) { + /* we found an interrupt out endpoint */ + dbg("found interrupt out on endpoint %d", i); +- interrupt_out_endpoint[num_interrupt_out] = endpoint; +- ++num_interrupt_out; ++ if (num_interrupt_out < MAX_NUM_PORTS) { ++ interrupt_out_endpoint[num_interrupt_out] = ++ endpoint; ++ ++num_interrupt_out; ++ } + } + } + +@@ -836,8 +846,10 @@ int usb_serial_probe(struct usb_interface *interface, + if (usb_endpoint_is_int_in(endpoint)) { + /* we found a interrupt in endpoint */ + dbg("found interrupt in for Prolific device on separate interface"); +- interrupt_in_endpoint[num_interrupt_in] = endpoint; +- ++num_interrupt_in; ++ if (num_interrupt_in < MAX_NUM_PORTS) { ++ interrupt_in_endpoint[num_interrupt_in] = endpoint; ++ ++num_interrupt_in; ++ } + } + } + } +@@ -876,6 +888,11 @@ int usb_serial_probe(struct usb_interface *interface, + num_ports = type->num_ports; + } + ++ if (num_ports > MAX_NUM_PORTS) { ++ dev_warn(&interface->dev, "too many ports requested: %d\n", num_ports); ++ num_ports = MAX_NUM_PORTS; ++ } ++ + serial->num_ports = num_ports; + serial->num_bulk_in = num_bulk_in; + serial->num_bulk_out = num_bulk_out; +diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c +index 0ec60cd..5481809 100644 +--- a/drivers/usb/serial/whiteheat.c ++++ b/drivers/usb/serial/whiteheat.c +@@ -1006,6 +1006,10 @@ static void command_port_read_callback(struct urb *urb) + dbg("%s - command_info is NULL, exiting.", __func__); + return; + } ++ if (!urb->actual_length) { ++ dev_dbg(&urb->dev->dev, "%s - empty response, exiting.\n", __func__); ++ return; ++ } + if (status) { + dbg("%s - nonzero urb status: %d", __func__, status); + if (status != -ENOENT) +@@ -1027,7 +1031,8 @@ static void command_port_read_callback(struct urb *urb) + /* These are unsolicited reports from the firmware, hence no + waiting command to wakeup */ + dbg("%s - event received", __func__); +- } else if (data[0] == WHITEHEAT_GET_DTR_RTS) { ++ } else if ((data[0] == WHITEHEAT_GET_DTR_RTS) && ++ (urb->actual_length - 1 <= sizeof(command_info->result_buffer))) { + memcpy(command_info->result_buffer, &data[1], + urb->actual_length - 1); + command_info->command_finished = WHITEHEAT_CMD_COMPLETE; +diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c +index c7fb3a4..d7c9b68 100644 +--- a/fs/btrfs/file-item.c ++++ b/fs/btrfs/file-item.c +@@ -717,7 +717,7 @@ again: + found_next = 1; + if (ret != 0) + goto insert; +- slot = 0; ++ slot = path->slots[0]; + } + btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot); + if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID || +diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c +index 20431b4..c0c51e1 100644 +--- a/fs/cifs/inode.c ++++ b/fs/cifs/inode.c +@@ -1638,6 +1638,12 @@ unlink_target: + target_dentry, toName); + } + ++ /* force revalidate to go get info when needed */ ++ CIFS_I(source_dir)->time = CIFS_I(target_dir)->time = 0; ++ ++ source_dir->i_ctime = source_dir->i_mtime = target_dir->i_ctime = ++ target_dir->i_mtime = current_fs_time(source_dir->i_sb); ++ + cifs_rename_exit: + kfree(info_buf_source); + kfree(fromName); +diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c +index fb001cd..01951c6b 100644 +--- a/fs/debugfs/inode.c ++++ b/fs/debugfs/inode.c +@@ -380,7 +380,7 @@ EXPORT_SYMBOL_GPL(debugfs_remove); + */ + void debugfs_remove_recursive(struct dentry *dentry) + { +- struct dentry *child, *next, *parent; ++ struct dentry *child, *parent; + + if (!dentry) + return; +@@ -392,31 +392,49 @@ void debugfs_remove_recursive(struct dentry *dentry) + parent = dentry; + down: + mutex_lock(&parent->d_inode->i_mutex); +- list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) { ++ loop: ++ /* ++ * The parent->d_subdirs is protected by the d_lock. Outside that ++ * lock, the child can be unlinked and set to be freed which can ++ * use the d_u.d_child as the rcu head and corrupt this list. ++ */ ++ spin_lock(&parent->d_lock); ++ list_for_each_entry(child, &parent->d_subdirs, d_u.d_child) { + if (!debugfs_positive(child)) + continue; + + /* perhaps simple_empty(child) makes more sense */ + if (!list_empty(&child->d_subdirs)) { ++ spin_unlock(&parent->d_lock); + mutex_unlock(&parent->d_inode->i_mutex); + parent = child; + goto down; + } +- up: ++ ++ spin_unlock(&parent->d_lock); ++ + if (!__debugfs_remove(child, parent)) + simple_release_fs(&debugfs_mount, &debugfs_mount_count); ++ ++ /* ++ * The parent->d_lock protects agaist child from unlinking ++ * from d_subdirs. When releasing the parent->d_lock we can ++ * no longer trust that the next pointer is valid. ++ * Restart the loop. We'll skip this one with the ++ * debugfs_positive() check. ++ */ ++ goto loop; + } ++ spin_unlock(&parent->d_lock); + + mutex_unlock(&parent->d_inode->i_mutex); + child = parent; + parent = parent->d_parent; + mutex_lock(&parent->d_inode->i_mutex); + +- if (child != dentry) { +- next = list_entry(child->d_u.d_child.next, struct dentry, +- d_u.d_child); +- goto up; +- } ++ if (child != dentry) ++ /* go up */ ++ goto loop; + + if (!__debugfs_remove(child, parent)) + simple_release_fs(&debugfs_mount, &debugfs_mount_count); +diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c +index 7168eeb..818b43e 100644 +--- a/fs/ext4/mballoc.c ++++ b/fs/ext4/mballoc.c +@@ -3128,13 +3128,28 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *ac) + static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac) + { + struct ext4_prealloc_space *pa = ac->ac_pa; +- int len; ++ struct ext4_buddy e4b; ++ int err; + +- if (pa && pa->pa_type == MB_INODE_PA) { +- len = ac->ac_b_ex.fe_len; +- pa->pa_free += len; ++ if (pa == NULL) { ++ err = ext4_mb_load_buddy(ac->ac_sb, ac->ac_f_ex.fe_group, &e4b); ++ if (err) { ++ /* ++ * This should never happen since we pin the ++ * pages in the ext4_allocation_context so ++ * ext4_mb_load_buddy() should never fail. ++ */ ++ WARN(1, "mb_load_buddy failed (%d)", err); ++ return; ++ } ++ ext4_lock_group(ac->ac_sb, ac->ac_f_ex.fe_group); ++ mb_free_blocks(ac->ac_inode, &e4b, ac->ac_f_ex.fe_start, ++ ac->ac_f_ex.fe_len); ++ ext4_unlock_group(ac->ac_sb, ac->ac_f_ex.fe_group); ++ return; + } +- ++ if (pa->pa_type == MB_INODE_PA) ++ pa->pa_free += ac->ac_b_ex.fe_len; + } + + /* +diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c +index a5f25a7..2f9197f 100644 +--- a/fs/isofs/inode.c ++++ b/fs/isofs/inode.c +@@ -68,7 +68,7 @@ static void isofs_put_super(struct super_block *sb) + return; + } + +-static int isofs_read_inode(struct inode *); ++static int isofs_read_inode(struct inode *, int relocated); + static int isofs_statfs (struct dentry *, struct kstatfs *); + + static struct kmem_cache *isofs_inode_cachep; +@@ -1263,7 +1263,7 @@ out_toomany: + goto out; + } + +-static int isofs_read_inode(struct inode *inode) ++static int isofs_read_inode(struct inode *inode, int relocated) + { + struct super_block *sb = inode->i_sb; + struct isofs_sb_info *sbi = ISOFS_SB(sb); +@@ -1408,7 +1408,7 @@ static int isofs_read_inode(struct inode *inode) + */ + + if (!high_sierra) { +- parse_rock_ridge_inode(de, inode); ++ parse_rock_ridge_inode(de, inode, relocated); + /* if we want uid/gid set, override the rock ridge setting */ + if (sbi->s_uid_set) + inode->i_uid = sbi->s_uid; +@@ -1487,9 +1487,10 @@ static int isofs_iget5_set(struct inode *ino, void *data) + * offset that point to the underlying meta-data for the inode. The + * code below is otherwise similar to the iget() code in + * include/linux/fs.h */ +-struct inode *isofs_iget(struct super_block *sb, +- unsigned long block, +- unsigned long offset) ++struct inode *__isofs_iget(struct super_block *sb, ++ unsigned long block, ++ unsigned long offset, ++ int relocated) + { + unsigned long hashval; + struct inode *inode; +@@ -1511,7 +1512,7 @@ struct inode *isofs_iget(struct super_block *sb, + return ERR_PTR(-ENOMEM); + + if (inode->i_state & I_NEW) { +- ret = isofs_read_inode(inode); ++ ret = isofs_read_inode(inode, relocated); + if (ret < 0) { + iget_failed(inode); + inode = ERR_PTR(ret); +diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h +index 7d33de8..f9c9793 100644 +--- a/fs/isofs/isofs.h ++++ b/fs/isofs/isofs.h +@@ -107,7 +107,7 @@ extern int iso_date(char *, int); + + struct inode; /* To make gcc happy */ + +-extern int parse_rock_ridge_inode(struct iso_directory_record *, struct inode *); ++extern int parse_rock_ridge_inode(struct iso_directory_record *, struct inode *, int relocated); + extern int get_rock_ridge_filename(struct iso_directory_record *, char *, struct inode *); + extern int isofs_name_translate(struct iso_directory_record *, char *, struct inode *); + +@@ -118,9 +118,24 @@ extern struct dentry *isofs_lookup(struct inode *, struct dentry *, struct namei + extern struct buffer_head *isofs_bread(struct inode *, sector_t); + extern int isofs_get_blocks(struct inode *, sector_t, struct buffer_head **, unsigned long); + +-extern struct inode *isofs_iget(struct super_block *sb, +- unsigned long block, +- unsigned long offset); ++struct inode *__isofs_iget(struct super_block *sb, ++ unsigned long block, ++ unsigned long offset, ++ int relocated); ++ ++static inline struct inode *isofs_iget(struct super_block *sb, ++ unsigned long block, ++ unsigned long offset) ++{ ++ return __isofs_iget(sb, block, offset, 0); ++} ++ ++static inline struct inode *isofs_iget_reloc(struct super_block *sb, ++ unsigned long block, ++ unsigned long offset) ++{ ++ return __isofs_iget(sb, block, offset, 1); ++} + + /* Because the inode number is no longer relevant to finding the + * underlying meta-data for an inode, we are free to choose a more +diff --git a/fs/isofs/rock.c b/fs/isofs/rock.c +index 70e79d0..ee62cc0 100644 +--- a/fs/isofs/rock.c ++++ b/fs/isofs/rock.c +@@ -288,12 +288,16 @@ eio: + goto out; + } + ++#define RR_REGARD_XA 1 ++#define RR_RELOC_DE 2 ++ + static int + parse_rock_ridge_inode_internal(struct iso_directory_record *de, +- struct inode *inode, int regard_xa) ++ struct inode *inode, int flags) + { + int symlink_len = 0; + int cnt, sig; ++ unsigned int reloc_block; + struct inode *reloc; + struct rock_ridge *rr; + int rootflag; +@@ -305,7 +309,7 @@ parse_rock_ridge_inode_internal(struct iso_directory_record *de, + + init_rock_state(&rs, inode); + setup_rock_ridge(de, inode, &rs); +- if (regard_xa) { ++ if (flags & RR_REGARD_XA) { + rs.chr += 14; + rs.len -= 14; + if (rs.len < 0) +@@ -485,12 +489,22 @@ repeat: + "relocated directory\n"); + goto out; + case SIG('C', 'L'): +- ISOFS_I(inode)->i_first_extent = +- isonum_733(rr->u.CL.location); +- reloc = +- isofs_iget(inode->i_sb, +- ISOFS_I(inode)->i_first_extent, +- 0); ++ if (flags & RR_RELOC_DE) { ++ printk(KERN_ERR ++ "ISOFS: Recursive directory relocation " ++ "is not supported\n"); ++ goto eio; ++ } ++ reloc_block = isonum_733(rr->u.CL.location); ++ if (reloc_block == ISOFS_I(inode)->i_iget5_block && ++ ISOFS_I(inode)->i_iget5_offset == 0) { ++ printk(KERN_ERR ++ "ISOFS: Directory relocation points to " ++ "itself\n"); ++ goto eio; ++ } ++ ISOFS_I(inode)->i_first_extent = reloc_block; ++ reloc = isofs_iget_reloc(inode->i_sb, reloc_block, 0); + if (IS_ERR(reloc)) { + ret = PTR_ERR(reloc); + goto out; +@@ -637,9 +651,11 @@ static char *get_symlink_chunk(char *rpnt, struct rock_ridge *rr, char *plimit) + return rpnt; + } + +-int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode) ++int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode, ++ int relocated) + { +- int result = parse_rock_ridge_inode_internal(de, inode, 0); ++ int flags = relocated ? RR_RELOC_DE : 0; ++ int result = parse_rock_ridge_inode_internal(de, inode, flags); + + /* + * if rockridge flag was reset and we didn't look for attributes +@@ -647,7 +663,8 @@ int parse_rock_ridge_inode(struct iso_directory_record *de, struct inode *inode) + */ + if ((ISOFS_SB(inode->i_sb)->s_rock_offset == -1) + && (ISOFS_SB(inode->i_sb)->s_rock == 2)) { +- result = parse_rock_ridge_inode_internal(de, inode, 14); ++ result = parse_rock_ridge_inode_internal(de, inode, ++ flags | RR_REGARD_XA); + } + return result; + } +diff --git a/fs/namespace.c b/fs/namespace.c +index ca4913a..a1e663d 100644 +--- a/fs/namespace.c ++++ b/fs/namespace.c +@@ -2333,6 +2333,14 @@ long do_mount(char *dev_name, char *dir_name, char *type_page, + if (flags & MS_RDONLY) + mnt_flags |= MNT_READONLY; + ++ /* The default atime for remount is preservation */ ++ if ((flags & MS_REMOUNT) && ++ ((flags & (MS_NOATIME | MS_NODIRATIME | MS_RELATIME | ++ MS_STRICTATIME)) == 0)) { ++ mnt_flags &= ~MNT_ATIME_MASK; ++ mnt_flags |= path.mnt->mnt_flags & MNT_ATIME_MASK; ++ } ++ + flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN | + MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT | + MS_STRICTATIME); +diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c +index 5aea30a..c4a2a68 100644 +--- a/fs/nfs/nfs4proc.c ++++ b/fs/nfs/nfs4proc.c +@@ -2004,24 +2004,31 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data) + { + struct nfs4_closedata *calldata = data; + struct nfs4_state *state = calldata->state; ++ bool is_rdonly, is_wronly, is_rdwr; + int call_close = 0; + + if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0) + return; + + task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_DOWNGRADE]; +- calldata->arg.fmode = FMODE_READ|FMODE_WRITE; + spin_lock(&state->owner->so_lock); ++ is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags); ++ is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags); ++ is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags); ++ /* Calculate the current open share mode */ ++ calldata->arg.fmode = 0; ++ if (is_rdonly || is_rdwr) ++ calldata->arg.fmode |= FMODE_READ; ++ if (is_wronly || is_rdwr) ++ calldata->arg.fmode |= FMODE_WRITE; + /* Calculate the change in open mode */ + if (state->n_rdwr == 0) { + if (state->n_rdonly == 0) { +- call_close |= test_bit(NFS_O_RDONLY_STATE, &state->flags); +- call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags); ++ call_close |= is_rdonly || is_rdwr; + calldata->arg.fmode &= ~FMODE_READ; + } + if (state->n_wronly == 0) { +- call_close |= test_bit(NFS_O_WRONLY_STATE, &state->flags); +- call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags); ++ call_close |= is_wronly || is_rdwr; + calldata->arg.fmode &= ~FMODE_WRITE; + } + } +diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c +index eb71106..938a77f 100644 +--- a/fs/reiserfs/journal.c ++++ b/fs/reiserfs/journal.c +@@ -1916,15 +1916,19 @@ static int do_journal_release(struct reiserfs_transaction_handle *th, + } + + reiserfs_mounted_fs_count--; +- /* wait for all commits to finish */ +- cancel_delayed_work(&SB_JOURNAL(sb)->j_work); + + /* + * We must release the write lock here because + * the workqueue job (flush_async_commit) needs this lock + */ + reiserfs_write_unlock(sb); +- flush_workqueue(commit_wq); ++ /* ++ * Cancel flushing of old commits. Note that this work will not ++ * be requeued because superblock is being shutdown and doesn't ++ * have MS_ACTIVE set. ++ */ ++ /* wait for all commits to finish */ ++ cancel_delayed_work_sync(&SB_JOURNAL(sb)->j_work); + + if (!reiserfs_mounted_fs_count) { + destroy_workqueue(commit_wq); +@@ -4211,8 +4215,15 @@ static int do_journal_end(struct reiserfs_transaction_handle *th, + if (flush) { + flush_commit_list(sb, jl, 1); + flush_journal_list(sb, jl, 1); +- } else if (!(jl->j_state & LIST_COMMIT_PENDING)) +- queue_delayed_work(commit_wq, &journal->j_work, HZ / 10); ++ } else if (!(jl->j_state & LIST_COMMIT_PENDING)) { ++ /* ++ * Avoid queueing work when sb is being shut down. Transaction ++ * will be flushed on journal shutdown. ++ */ ++ if (sb->s_flags & MS_ACTIVE) ++ queue_delayed_work(commit_wq, ++ &journal->j_work, HZ / 10); ++ } + + /* if the next transaction has any chance of wrapping, flush + ** transactions that might get overwritten. If any journal lists are very +diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h +index f85c5ab..11670e3 100644 +--- a/include/linux/mempolicy.h ++++ b/include/linux/mempolicy.h +@@ -205,7 +205,7 @@ extern struct zonelist *huge_zonelist(struct vm_area_struct *vma, + extern bool init_nodemask_of_mempolicy(nodemask_t *mask); + extern bool mempolicy_nodemask_intersects(struct task_struct *tsk, + const nodemask_t *mask); +-extern unsigned slab_node(struct mempolicy *policy); ++extern unsigned slab_node(void); + + extern enum zone_type policy_zone; + +diff --git a/include/linux/mount.h b/include/linux/mount.h +index 33fe53d..fc17c4d 100644 +--- a/include/linux/mount.h ++++ b/include/linux/mount.h +@@ -43,6 +43,7 @@ struct mnt_namespace; + */ + #define MNT_SHARED_MASK (MNT_UNBINDABLE) + #define MNT_PROPAGATION_MASK (MNT_SHARED | MNT_UNBINDABLE) ++#define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME ) + + + #define MNT_INTERNAL 0x4000 +diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h +index ba0ddb0..6172a44 100644 +--- a/include/net/inetpeer.h ++++ b/include/net/inetpeer.h +@@ -47,13 +47,12 @@ struct inet_peer { + }; + /* + * Once inet_peer is queued for deletion (refcnt == -1), following fields +- * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp ++ * are not available: rid, tcp_ts, tcp_ts_stamp + * We can share memory with rcu_head to help keep inet_peer small. + */ + union { + struct { + atomic_t rid; /* Frag reception counter */ +- atomic_t ip_id_count; /* IP ID for the next packet */ + __u32 tcp_ts; + __u32 tcp_ts_stamp; + }; +@@ -103,7 +102,7 @@ extern bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout); + extern void inetpeer_invalidate_tree(int family); + + /* +- * temporary check to make sure we dont access rid, ip_id_count, tcp_ts, ++ * temporary check to make sure we dont access rid, tcp_ts, + * tcp_ts_stamp if no refcount is taken on inet_peer + */ + static inline void inet_peer_refcheck(const struct inet_peer *p) +@@ -111,13 +110,4 @@ static inline void inet_peer_refcheck(const struct inet_peer *p) + WARN_ON_ONCE(atomic_read(&p->refcnt) <= 0); + } + +- +-/* can be called with or without local BH being disabled */ +-static inline int inet_getid(struct inet_peer *p, int more) +-{ +- more++; +- inet_peer_refcheck(p); +- return atomic_add_return(more, &p->ip_id_count) - more; +-} +- + #endif /* _NET_INETPEER_H */ +diff --git a/include/net/ip.h b/include/net/ip.h +index b935e6c..1ee535b 100644 +--- a/include/net/ip.h ++++ b/include/net/ip.h +@@ -264,9 +264,10 @@ int ip_dont_fragment(struct sock *sk, struct dst_entry *dst) + !(dst_metric_locked(dst, RTAX_MTU))); + } + +-extern void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more); ++u32 ip_idents_reserve(u32 hash, int segs); ++void __ip_select_ident(struct iphdr *iph, int segs); + +-static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk) ++static inline void ip_select_ident_segs(struct sk_buff *skb, struct sock *sk, int segs) + { + struct iphdr *iph = ip_hdr(skb); + +@@ -276,24 +277,20 @@ static inline void ip_select_ident(struct sk_buff *skb, struct dst_entry *dst, s + * does not change, they drop every other packet in + * a TCP stream using header compression. + */ +- iph->id = (sk && inet_sk(sk)->inet_daddr) ? +- htons(inet_sk(sk)->inet_id++) : 0; +- } else +- __ip_select_ident(iph, dst, 0); +-} +- +-static inline void ip_select_ident_more(struct sk_buff *skb, struct dst_entry *dst, struct sock *sk, int more) +-{ +- struct iphdr *iph = ip_hdr(skb); +- +- if ((iph->frag_off & htons(IP_DF)) && !skb->local_df) { + if (sk && inet_sk(sk)->inet_daddr) { + iph->id = htons(inet_sk(sk)->inet_id); +- inet_sk(sk)->inet_id += 1 + more; +- } else ++ inet_sk(sk)->inet_id += segs; ++ } else { + iph->id = 0; +- } else +- __ip_select_ident(iph, dst, more); ++ } ++ } else { ++ __ip_select_ident(iph, segs); ++ } ++} ++ ++static inline void ip_select_ident(struct sk_buff *skb, struct sock *sk) ++{ ++ ip_select_ident_segs(skb, sk, 1); + } + + /* +diff --git a/include/net/ipip.h b/include/net/ipip.h +index 4dccfe3..e8ee3bb 100644 +--- a/include/net/ipip.h ++++ b/include/net/ipip.h +@@ -50,7 +50,7 @@ struct ip_tunnel_prl_entry { + int pkt_len = skb->len - skb_transport_offset(skb); \ + \ + skb->ip_summed = CHECKSUM_NONE; \ +- ip_select_ident(skb, &rt->dst, NULL); \ ++ ip_select_ident(skb, NULL); \ + \ + err = ip_local_out(skb); \ + if (likely(net_xmit_eval(err) == 0)) { \ +diff --git a/include/net/ipv6.h b/include/net/ipv6.h +index 0580673..00a2eb6 100644 +--- a/include/net/ipv6.h ++++ b/include/net/ipv6.h +@@ -388,14 +388,19 @@ void ip6_frag_init(struct inet_frag_queue *q, void *a); + int ip6_frag_match(struct inet_frag_queue *q, void *a); + + /* more secured version of ipv6_addr_hash() */ +-static inline u32 ipv6_addr_jhash(const struct in6_addr *a) ++static inline u32 __ipv6_addr_jhash(const struct in6_addr *a, const u32 initval) + { + u32 v = (__force u32)a->s6_addr32[0] ^ (__force u32)a->s6_addr32[1]; + + return jhash_3words(v, + (__force u32)a->s6_addr32[2], + (__force u32)a->s6_addr32[3], +- ipv6_hash_secret); ++ initval); ++} ++ ++static inline u32 ipv6_addr_jhash(const struct in6_addr *a) ++{ ++ return __ipv6_addr_jhash(a, ipv6_hash_secret); + } + + static inline int ipv6_addr_any(const struct in6_addr *a) +diff --git a/include/net/netlabel.h b/include/net/netlabel.h +index f674409..c8ba2e2 100644 +--- a/include/net/netlabel.h ++++ b/include/net/netlabel.h +@@ -395,10 +395,10 @@ int netlbl_secattr_catmap_walk(struct netlbl_lsm_secattr_catmap *catmap, + u32 offset); + int netlbl_secattr_catmap_walk_rng(struct netlbl_lsm_secattr_catmap *catmap, + u32 offset); +-int netlbl_secattr_catmap_setbit(struct netlbl_lsm_secattr_catmap *catmap, ++int netlbl_secattr_catmap_setbit(struct netlbl_lsm_secattr_catmap **catmap, + u32 bit, + gfp_t flags); +-int netlbl_secattr_catmap_setrng(struct netlbl_lsm_secattr_catmap *catmap, ++int netlbl_secattr_catmap_setrng(struct netlbl_lsm_secattr_catmap **catmap, + u32 start, + u32 end, + gfp_t flags); +@@ -506,14 +506,14 @@ static inline int netlbl_secattr_catmap_walk_rng( + return -ENOENT; + } + static inline int netlbl_secattr_catmap_setbit( +- struct netlbl_lsm_secattr_catmap *catmap, ++ struct netlbl_lsm_secattr_catmap **catmap, + u32 bit, + gfp_t flags) + { + return 0; + } + static inline int netlbl_secattr_catmap_setrng( +- struct netlbl_lsm_secattr_catmap *catmap, ++ struct netlbl_lsm_secattr_catmap **catmap, + u32 start, + u32 end, + gfp_t flags) +diff --git a/include/net/secure_seq.h b/include/net/secure_seq.h +index c2e542b..b1c3d1c 100644 +--- a/include/net/secure_seq.h ++++ b/include/net/secure_seq.h +@@ -3,8 +3,6 @@ + + #include <linux/types.h> + +-extern __u32 secure_ip_id(__be32 daddr); +-extern __u32 secure_ipv6_id(const __be32 daddr[4]); + extern u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport); + extern u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, + __be16 dport); +diff --git a/init/main.c b/init/main.c +index 7474450..e937d9b 100644 +--- a/init/main.c ++++ b/init/main.c +@@ -610,6 +610,10 @@ asmlinkage void __init start_kernel(void) + if (efi_enabled(EFI_RUNTIME_SERVICES)) + efi_enter_virtual_mode(); + #endif ++#ifdef CONFIG_X86_ESPFIX64 ++ /* Should be run before the first non-init thread is created */ ++ init_espfix_bsp(); ++#endif + thread_info_cache_init(); + cred_init(); + fork_init(totalram_pages); +diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c +index 648f25a..4babd77 100644 +--- a/kernel/trace/ring_buffer.c ++++ b/kernel/trace/ring_buffer.c +@@ -2843,21 +2843,16 @@ static void rb_iter_reset(struct ring_buffer_iter *iter) + struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer; + + /* Iterator usage is expected to have record disabled */ +- if (list_empty(&cpu_buffer->reader_page->list)) { +- iter->head_page = rb_set_head_page(cpu_buffer); +- if (unlikely(!iter->head_page)) +- return; +- iter->head = iter->head_page->read; +- } else { +- iter->head_page = cpu_buffer->reader_page; +- iter->head = cpu_buffer->reader_page->read; +- } ++ iter->head_page = cpu_buffer->reader_page; ++ iter->head = cpu_buffer->reader_page->read; ++ ++ iter->cache_reader_page = iter->head_page; ++ iter->cache_read = iter->head; ++ + if (iter->head) + iter->read_stamp = cpu_buffer->read_stamp; + else + iter->read_stamp = iter->head_page->page->time_stamp; +- iter->cache_reader_page = cpu_buffer->reader_page; +- iter->cache_read = cpu_buffer->read; + } + + /** +@@ -3246,12 +3241,14 @@ rb_iter_peek(struct ring_buffer_iter *iter, u64 *ts) + return NULL; + + /* +- * We repeat when a time extend is encountered. +- * Since the time extend is always attached to a data event, +- * we should never loop more than once. +- * (We never hit the following condition more than twice). ++ * We repeat when a time extend is encountered or we hit ++ * the end of the page. Since the time extend is always attached ++ * to a data event, we should never loop more than three times. ++ * Once for going to next page, once on time extend, and ++ * finally once to get the event. ++ * (We never hit the following condition more than thrice). + */ +- if (RB_WARN_ON(cpu_buffer, ++nr_loops > 2)) ++ if (RB_WARN_ON(cpu_buffer, ++nr_loops > 3)) + return NULL; + + if (rb_per_cpu_empty(cpu_buffer)) +diff --git a/mm/mempolicy.c b/mm/mempolicy.c +index c9f7e6f..a72fa33 100644 +--- a/mm/mempolicy.c ++++ b/mm/mempolicy.c +@@ -1601,8 +1601,14 @@ static unsigned interleave_nodes(struct mempolicy *policy) + * task can change it's policy. The system default policy requires no + * such protection. + */ +-unsigned slab_node(struct mempolicy *policy) ++unsigned slab_node(void) + { ++ struct mempolicy *policy; ++ ++ if (in_interrupt()) ++ return numa_node_id(); ++ ++ policy = current->mempolicy; + if (!policy || policy->flags & MPOL_F_LOCAL) + return numa_node_id(); + +diff --git a/mm/page_alloc.c b/mm/page_alloc.c +index d8762b2..62a7fa23 100644 +--- a/mm/page_alloc.c ++++ b/mm/page_alloc.c +@@ -2054,7 +2054,7 @@ static inline int + gfp_to_alloc_flags(gfp_t gfp_mask) + { + int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; +- const gfp_t wait = gfp_mask & __GFP_WAIT; ++ const bool atomic = !(gfp_mask & (__GFP_WAIT | __GFP_NO_KSWAPD)); + + /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */ + BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH); +@@ -2063,20 +2063,20 @@ gfp_to_alloc_flags(gfp_t gfp_mask) + * The caller may dip into page reserves a bit more if the caller + * cannot run direct reclaim, or if the caller has realtime scheduling + * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will +- * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH). ++ * set both ALLOC_HARDER (atomic == true) and ALLOC_HIGH (__GFP_HIGH). + */ + alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH); + +- if (!wait) { ++ if (atomic) { + /* +- * Not worth trying to allocate harder for +- * __GFP_NOMEMALLOC even if it can't schedule. ++ * Not worth trying to allocate harder for __GFP_NOMEMALLOC even ++ * if it can't schedule. + */ +- if (!(gfp_mask & __GFP_NOMEMALLOC)) ++ if (!(gfp_mask & __GFP_NOMEMALLOC)) + alloc_flags |= ALLOC_HARDER; + /* +- * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc. +- * See also cpuset_zone_allowed() comment in kernel/cpuset.c. ++ * Ignore cpuset mems for GFP_ATOMIC rather than fail, see the ++ * comment for __cpuset_node_allowed_softwall(). + */ + alloc_flags &= ~ALLOC_CPUSET; + } else if (unlikely(rt_task(current)) && !in_interrupt()) +diff --git a/mm/slab.c b/mm/slab.c +index 4c3b671..aea5e42 100644 +--- a/mm/slab.c ++++ b/mm/slab.c +@@ -3270,7 +3270,7 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags) + if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD)) + nid_alloc = cpuset_slab_spread_node(); + else if (current->mempolicy) +- nid_alloc = slab_node(current->mempolicy); ++ nid_alloc = slab_node(); + if (nid_alloc != nid_here) + return ____cache_alloc_node(cachep, flags, nid_alloc); + return NULL; +@@ -3302,7 +3302,7 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags) + + retry_cpuset: + cpuset_mems_cookie = get_mems_allowed(); +- zonelist = node_zonelist(slab_node(current->mempolicy), flags); ++ zonelist = node_zonelist(slab_node(), flags); + + retry: + /* +diff --git a/mm/slub.c b/mm/slub.c +index fc719f7..6a4c2fb 100644 +--- a/mm/slub.c ++++ b/mm/slub.c +@@ -1608,7 +1608,7 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags, + + do { + cpuset_mems_cookie = get_mems_allowed(); +- zonelist = node_zonelist(slab_node(current->mempolicy), flags); ++ zonelist = node_zonelist(slab_node(), flags); + for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { + struct kmem_cache_node *n; + +diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c +index 158887a..74e59cd 100644 +--- a/net/bluetooth/l2cap_sock.c ++++ b/net/bluetooth/l2cap_sock.c +@@ -804,7 +804,8 @@ static int l2cap_sock_shutdown(struct socket *sock, int how) + sk->sk_shutdown = SHUTDOWN_MASK; + l2cap_chan_close(chan, 0); + +- if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) ++ if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && ++ !(current->flags & PF_EXITING)) + err = bt_sock_wait_state(sk, BT_CLOSED, + sk->sk_lingertime); + } +diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c +index 14c4864..93a8241 100644 +--- a/net/bluetooth/rfcomm/sock.c ++++ b/net/bluetooth/rfcomm/sock.c +@@ -901,7 +901,8 @@ static int rfcomm_sock_shutdown(struct socket *sock, int how) + sk->sk_shutdown = SHUTDOWN_MASK; + __rfcomm_sock_close(sk); + +- if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) ++ if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && ++ !(current->flags & PF_EXITING)) + err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); + } + release_sock(sk); +diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c +index a324b00..2e80aee7 100644 +--- a/net/bluetooth/sco.c ++++ b/net/bluetooth/sco.c +@@ -774,7 +774,8 @@ static int sco_sock_shutdown(struct socket *sock, int how) + sco_sock_clear_timer(sk); + __sco_sock_close(sk); + +- if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) ++ if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && ++ !(current->flags & PF_EXITING)) + err = bt_sock_wait_state(sk, BT_CLOSED, + sk->sk_lingertime); + } +@@ -794,7 +795,8 @@ static int sco_sock_release(struct socket *sock) + + sco_sock_close(sk); + +- if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) { ++ if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime && ++ !(current->flags & PF_EXITING)) { + lock_sock(sk); + err = bt_sock_wait_state(sk, BT_CLOSED, sk->sk_lingertime); + release_sock(sk); +diff --git a/net/compat.c b/net/compat.c +index 41724c9..759e542 100644 +--- a/net/compat.c ++++ b/net/compat.c +@@ -85,7 +85,7 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov, + { + int tot_len; + +- if (kern_msg->msg_namelen) { ++ if (kern_msg->msg_name && kern_msg->msg_namelen) { + if (mode == VERIFY_READ) { + int err = move_addr_to_kernel(kern_msg->msg_name, + kern_msg->msg_namelen, +@@ -93,10 +93,11 @@ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov, + if (err < 0) + return err; + } +- if (kern_msg->msg_name) +- kern_msg->msg_name = kern_address; +- } else ++ kern_msg->msg_name = kern_address; ++ } else { + kern_msg->msg_name = NULL; ++ kern_msg->msg_namelen = 0; ++ } + + tot_len = iov_from_user_compat_to_kern(kern_iov, + (struct compat_iovec __user *)kern_msg->msg_iov, +diff --git a/net/core/iovec.c b/net/core/iovec.c +index 139ef93..66e3f1f 100644 +--- a/net/core/iovec.c ++++ b/net/core/iovec.c +@@ -39,7 +39,7 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, + { + int size, ct, err; + +- if (m->msg_namelen) { ++ if (m->msg_name && m->msg_namelen) { + if (mode == VERIFY_READ) { + void __user *namep; + namep = (void __user __force *) m->msg_name; +@@ -48,10 +48,10 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, + if (err < 0) + return err; + } +- if (m->msg_name) +- m->msg_name = address; ++ m->msg_name = address; + } else { + m->msg_name = NULL; ++ m->msg_namelen = 0; + } + + size = m->msg_iovlen * sizeof(struct iovec); +@@ -157,6 +157,10 @@ EXPORT_SYMBOL(memcpy_fromiovec); + int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, + int offset, int len) + { ++ /* No data? Done! */ ++ if (len == 0) ++ return 0; ++ + /* Skip over the finished iovecs */ + while (offset >= iov->iov_len) { + offset -= iov->iov_len; +diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c +index 925991a..fd53919 100644 +--- a/net/core/secure_seq.c ++++ b/net/core/secure_seq.c +@@ -79,29 +79,6 @@ u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr, + #endif + + #ifdef CONFIG_INET +-__u32 secure_ip_id(__be32 daddr) +-{ +- u32 hash[MD5_DIGEST_WORDS]; +- +- hash[0] = (__force __u32) daddr; +- hash[1] = net_secret[13]; +- hash[2] = net_secret[14]; +- hash[3] = net_secret[15]; +- +- md5_transform(hash, net_secret); +- +- return hash[0]; +-} +- +-__u32 secure_ipv6_id(const __be32 daddr[4]) +-{ +- __u32 hash[4]; +- +- memcpy(hash, daddr, 16); +- md5_transform(hash, net_secret); +- +- return hash[0]; +-} + + __u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr, + __be16 sport, __be16 dport) +diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c +index afaa735..dbec8b5 100644 +--- a/net/ipv4/cipso_ipv4.c ++++ b/net/ipv4/cipso_ipv4.c +@@ -974,7 +974,7 @@ static int cipso_v4_map_cat_rbm_ntoh(const struct cipso_v4_doi *doi_def, + return -EPERM; + break; + } +- ret_val = netlbl_secattr_catmap_setbit(secattr->attr.mls.cat, ++ ret_val = netlbl_secattr_catmap_setbit(&secattr->attr.mls.cat, + host_spot, + GFP_ATOMIC); + if (ret_val != 0) +@@ -1076,7 +1076,7 @@ static int cipso_v4_map_cat_enum_ntoh(const struct cipso_v4_doi *doi_def, + u32 iter; + + for (iter = 0; iter < net_cat_len; iter += 2) { +- ret_val = netlbl_secattr_catmap_setbit(secattr->attr.mls.cat, ++ ret_val = netlbl_secattr_catmap_setbit(&secattr->attr.mls.cat, + get_unaligned_be16(&net_cat[iter]), + GFP_ATOMIC); + if (ret_val != 0) +@@ -1218,7 +1218,7 @@ static int cipso_v4_map_cat_rng_ntoh(const struct cipso_v4_doi *doi_def, + else + cat_low = 0; + +- ret_val = netlbl_secattr_catmap_setrng(secattr->attr.mls.cat, ++ ret_val = netlbl_secattr_catmap_setrng(&secattr->attr.mls.cat, + cat_low, + cat_high, + GFP_ATOMIC); +diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c +index 7f7e670..7fe66d9 100644 +--- a/net/ipv4/igmp.c ++++ b/net/ipv4/igmp.c +@@ -342,7 +342,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) + pip->saddr = fl4.saddr; + pip->protocol = IPPROTO_IGMP; + pip->tot_len = 0; /* filled in later */ +- ip_select_ident(skb, &rt->dst, NULL); ++ ip_select_ident(skb, NULL); + ((u8*)&pip[1])[0] = IPOPT_RA; + ((u8*)&pip[1])[1] = 4; + ((u8*)&pip[1])[2] = 0; +@@ -683,7 +683,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, + iph->daddr = dst; + iph->saddr = fl4.saddr; + iph->protocol = IPPROTO_IGMP; +- ip_select_ident(skb, &rt->dst, NULL); ++ ip_select_ident(skb, NULL); + ((u8*)&iph[1])[0] = IPOPT_RA; + ((u8*)&iph[1])[1] = 4; + ((u8*)&iph[1])[2] = 0; +diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c +index 58c4e696..9d74cc7 100644 +--- a/net/ipv4/inetpeer.c ++++ b/net/ipv4/inetpeer.c +@@ -26,20 +26,7 @@ + * Theory of operations. + * We keep one entry for each peer IP address. The nodes contains long-living + * information about the peer which doesn't depend on routes. +- * At this moment this information consists only of ID field for the next +- * outgoing IP packet. This field is incremented with each packet as encoded +- * in inet_getid() function (include/net/inetpeer.h). +- * At the moment of writing this notes identifier of IP packets is generated +- * to be unpredictable using this code only for packets subjected +- * (actually or potentially) to defragmentation. I.e. DF packets less than +- * PMTU in size when local fragmentation is disabled use a constant ID and do +- * not use this code (see ip_select_ident() in include/net/ip.h). + * +- * Route cache entries hold references to our nodes. +- * New cache entries get references via lookup by destination IP address in +- * the avl tree. The reference is grabbed only when it's needed i.e. only +- * when we try to output IP packet which needs an unpredictable ID (see +- * __ip_select_ident() in net/ipv4/route.c). + * Nodes are removed only when reference counter goes to 0. + * When it's happened the node may be removed when a sufficient amount of + * time has been passed since its last use. The less-recently-used entry can +@@ -62,7 +49,6 @@ + * refcnt: atomically against modifications on other CPU; + * usually under some other lock to prevent node disappearing + * daddr: unchangeable +- * ip_id_count: atomic value (no lock needed) + */ + + static struct kmem_cache *peer_cachep __read_mostly; +@@ -488,10 +474,6 @@ relookup: + p->daddr = *daddr; + atomic_set(&p->refcnt, 1); + atomic_set(&p->rid, 0); +- atomic_set(&p->ip_id_count, +- (daddr->family == AF_INET) ? +- secure_ip_id(daddr->addr.a4) : +- secure_ipv6_id(daddr->addr.a6)); + p->tcp_ts_stamp = 0; + p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; + p->rate_tokens = 0; +diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c +index 16191f0..223085f 100644 +--- a/net/ipv4/ip_output.c ++++ b/net/ipv4/ip_output.c +@@ -162,7 +162,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, + iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); + iph->saddr = saddr; + iph->protocol = sk->sk_protocol; +- ip_select_ident(skb, &rt->dst, sk); ++ ip_select_ident(skb, sk); + + if (opt && opt->opt.optlen) { + iph->ihl += opt->opt.optlen>>2; +@@ -390,8 +390,7 @@ packet_routed: + ip_options_build(skb, &inet_opt->opt, inet->inet_daddr, rt, 0); + } + +- ip_select_ident_more(skb, &rt->dst, sk, +- (skb_shinfo(skb)->gso_segs ?: 1) - 1); ++ ip_select_ident_segs(skb, sk, skb_shinfo(skb)->gso_segs ?: 1); + + skb->priority = sk->sk_priority; + skb->mark = sk->sk_mark; +@@ -1334,7 +1333,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, + iph->ihl = 5; + iph->tos = inet->tos; + iph->frag_off = df; +- ip_select_ident(skb, &rt->dst, sk); ++ ip_select_ident(skb, sk); + iph->ttl = ttl; + iph->protocol = sk->sk_protocol; + iph->saddr = fl4->saddr; +diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c +index 140d377..7993d16 100644 +--- a/net/ipv4/ipmr.c ++++ b/net/ipv4/ipmr.c +@@ -1579,7 +1579,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) + iph->protocol = IPPROTO_IPIP; + iph->ihl = 5; + iph->tot_len = htons(skb->len); +- ip_select_ident(skb, skb_dst(skb), NULL); ++ ip_select_ident(skb, NULL); + ip_send_check(iph); + + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); +diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c +index cfded93..75fea1f 100644 +--- a/net/ipv4/raw.c ++++ b/net/ipv4/raw.c +@@ -380,7 +380,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, + iph->check = 0; + iph->tot_len = htons(length); + if (!iph->id) +- ip_select_ident(skb, &rt->dst, NULL); ++ ip_select_ident(skb, NULL); + + iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl); + } +diff --git a/net/ipv4/route.c b/net/ipv4/route.c +index 6526110..d361dc0 100644 +--- a/net/ipv4/route.c ++++ b/net/ipv4/route.c +@@ -1344,46 +1344,53 @@ void rt_bind_peer(struct rtable *rt, __be32 daddr, int create) + rt->rt_peer_genid = rt_peer_genid(); + } + +-/* +- * Peer allocation may fail only in serious out-of-memory conditions. However +- * we still can generate some output. +- * Random ID selection looks a bit dangerous because we have no chances to +- * select ID being unique in a reasonable period of time. +- * But broken packet identifier may be better than no packet at all. ++#define IP_IDENTS_SZ 2048u ++struct ip_ident_bucket { ++ atomic_t id; ++ u32 stamp32; ++}; ++ ++static struct ip_ident_bucket *ip_idents __read_mostly; ++ ++/* In order to protect privacy, we add a perturbation to identifiers ++ * if one generator is seldom used. This makes hard for an attacker ++ * to infer how many packets were sent between two points in time. + */ +-static void ip_select_fb_ident(struct iphdr *iph) ++u32 ip_idents_reserve(u32 hash, int segs) + { +- static DEFINE_SPINLOCK(ip_fb_id_lock); +- static u32 ip_fallback_id; +- u32 salt; ++ struct ip_ident_bucket *bucket = ip_idents + hash % IP_IDENTS_SZ; ++ u32 old = ACCESS_ONCE(bucket->stamp32); ++ u32 now = (u32)jiffies; ++ u32 delta = 0; ++ ++ if (old != now && cmpxchg(&bucket->stamp32, old, now) == old) { ++ u64 x = random32(); ++ ++ x *= (now - old); ++ delta = (u32)(x >> 32); ++ } + +- spin_lock_bh(&ip_fb_id_lock); +- salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr); +- iph->id = htons(salt & 0xFFFF); +- ip_fallback_id = salt; +- spin_unlock_bh(&ip_fb_id_lock); ++ return atomic_add_return(segs + delta, &bucket->id) - segs; + } ++EXPORT_SYMBOL(ip_idents_reserve); + +-void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) ++void __ip_select_ident(struct iphdr *iph, int segs) + { +- struct rtable *rt = (struct rtable *) dst; +- +- if (rt && !(rt->dst.flags & DST_NOPEER)) { +- if (rt->peer == NULL) +- rt_bind_peer(rt, rt->rt_dst, 1); ++ static u32 ip_idents_hashrnd __read_mostly; ++ static bool hashrnd_initialized = false; ++ u32 hash, id; + +- /* If peer is attached to destination, it is never detached, +- so that we need not to grab a lock to dereference it. +- */ +- if (rt->peer) { +- iph->id = htons(inet_getid(rt->peer, more)); +- return; +- } +- } else if (!rt) +- printk(KERN_DEBUG "rt_bind_peer(0) @%p\n", +- __builtin_return_address(0)); ++ if (unlikely(!hashrnd_initialized)) { ++ hashrnd_initialized = true; ++ get_random_bytes(&ip_idents_hashrnd, sizeof(ip_idents_hashrnd)); ++ } + +- ip_select_fb_ident(iph); ++ hash = jhash_3words((__force u32)iph->daddr, ++ (__force u32)iph->saddr, ++ iph->protocol, ++ ip_idents_hashrnd); ++ id = ip_idents_reserve(hash, segs); ++ iph->id = htons(id); + } + EXPORT_SYMBOL(__ip_select_ident); + +@@ -3023,7 +3030,6 @@ static int rt_fill_info(struct net *net, + error = rt->dst.error; + if (peer) { + inet_peer_refcheck(rt->peer); +- id = atomic_read(&peer->ip_id_count) & 0xffff; + if (peer->tcp_ts_stamp) { + ts = peer->tcp_ts; + tsage = get_seconds() - peer->tcp_ts_stamp; +@@ -3455,6 +3461,12 @@ int __init ip_rt_init(void) + { + int rc = 0; + ++ ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL); ++ if (!ip_idents) ++ panic("IP: failed to allocate ip_idents\n"); ++ ++ get_random_bytes(ip_idents, IP_IDENTS_SZ * sizeof(*ip_idents)); ++ + #ifdef CONFIG_IP_ROUTE_CLASSID + ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct)); + if (!ip_rt_acct) +diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c +index 80fa2bf..c042e52 100644 +--- a/net/ipv4/tcp_vegas.c ++++ b/net/ipv4/tcp_vegas.c +@@ -218,7 +218,8 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) + * This is: + * (actual rate in segments) * baseRTT + */ +- target_cwnd = tp->snd_cwnd * vegas->baseRTT / rtt; ++ target_cwnd = (u64)tp->snd_cwnd * vegas->baseRTT; ++ do_div(target_cwnd, rtt); + + /* Calculate the difference between the window we had, + * and the window we would like to have. This quantity +diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c +index ac43cd7..b4d1858 100644 +--- a/net/ipv4/tcp_veno.c ++++ b/net/ipv4/tcp_veno.c +@@ -144,7 +144,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) + + rtt = veno->minrtt; + +- target_cwnd = (tp->snd_cwnd * veno->basertt); ++ target_cwnd = (u64)tp->snd_cwnd * veno->basertt; + target_cwnd <<= V_PARAM_SHIFT; + do_div(target_cwnd, rtt); + +diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c +index 938553e..5531eb2 100644 +--- a/net/ipv4/xfrm4_mode_tunnel.c ++++ b/net/ipv4/xfrm4_mode_tunnel.c +@@ -54,12 +54,12 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) + + top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? + 0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF)); +- ip_select_ident(skb, dst->child, NULL); + + top_iph->ttl = ip4_dst_hoplimit(dst->child); + + top_iph->saddr = x->props.saddr.a4; + top_iph->daddr = x->id.daddr.a4; ++ ip_select_ident(skb, NULL); + + return 0; + } +diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c +index 064b5c9..46fc6a3 100644 +--- a/net/ipv6/ip6_output.c ++++ b/net/ipv6/ip6_output.c +@@ -600,22 +600,19 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) + + void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) + { +- static atomic_t ipv6_fragmentation_id; +- int ident; ++ static u32 ip6_idents_hashrnd __read_mostly; ++ static bool hashrnd_initialized = false; ++ u32 hash, id; + +- if (rt && !(rt->dst.flags & DST_NOPEER)) { +- struct inet_peer *peer; +- +- if (!rt->rt6i_peer) +- rt6_bind_peer(rt, 1); +- peer = rt->rt6i_peer; +- if (peer) { +- fhdr->identification = htonl(inet_getid(peer, 0)); +- return; +- } ++ if (unlikely(!hashrnd_initialized)) { ++ hashrnd_initialized = true; ++ get_random_bytes(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd)); + } +- ident = atomic_inc_return(&ipv6_fragmentation_id); +- fhdr->identification = htonl(ident); ++ hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd); ++ hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash); ++ ++ id = ip_idents_reserve(hash, 1); ++ fhdr->identification = htonl(id); + } + + int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) +diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c +index 38c0813..cc8f8b4 100644 +--- a/net/netfilter/ipvs/ip_vs_xmit.c ++++ b/net/netfilter/ipvs/ip_vs_xmit.c +@@ -853,7 +853,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, + iph->daddr = cp->daddr.ip; + iph->saddr = saddr; + iph->ttl = old_iph->ttl; +- ip_select_ident(skb, &rt->dst, NULL); ++ ip_select_ident(skb, NULL); + + /* Another hack: avoid icmp_send in ip_fragment */ + skb->local_df = 1; +diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c +index 824f184..bcecae0 100644 +--- a/net/netlabel/netlabel_kapi.c ++++ b/net/netlabel/netlabel_kapi.c +@@ -523,7 +523,7 @@ int netlbl_secattr_catmap_walk_rng(struct netlbl_lsm_secattr_catmap *catmap, + + /** + * netlbl_secattr_catmap_setbit - Set a bit in a LSM secattr catmap +- * @catmap: the category bitmap ++ * @catmap: pointer to the category bitmap + * @bit: the bit to set + * @flags: memory allocation flags + * +@@ -532,18 +532,25 @@ int netlbl_secattr_catmap_walk_rng(struct netlbl_lsm_secattr_catmap *catmap, + * negative values on failure. + * + */ +-int netlbl_secattr_catmap_setbit(struct netlbl_lsm_secattr_catmap *catmap, ++int netlbl_secattr_catmap_setbit(struct netlbl_lsm_secattr_catmap **catmap, + u32 bit, + gfp_t flags) + { +- struct netlbl_lsm_secattr_catmap *iter = catmap; ++ struct netlbl_lsm_secattr_catmap *iter = *catmap; + u32 node_bit; + u32 node_idx; + + while (iter->next != NULL && + bit >= (iter->startbit + NETLBL_CATMAP_SIZE)) + iter = iter->next; +- if (bit >= (iter->startbit + NETLBL_CATMAP_SIZE)) { ++ if (bit < iter->startbit) { ++ iter = netlbl_secattr_catmap_alloc(flags); ++ if (iter == NULL) ++ return -ENOMEM; ++ iter->next = *catmap; ++ iter->startbit = bit & ~(NETLBL_CATMAP_SIZE - 1); ++ *catmap = iter; ++ } else if (bit >= (iter->startbit + NETLBL_CATMAP_SIZE)) { + iter->next = netlbl_secattr_catmap_alloc(flags); + if (iter->next == NULL) + return -ENOMEM; +@@ -561,7 +568,7 @@ int netlbl_secattr_catmap_setbit(struct netlbl_lsm_secattr_catmap *catmap, + + /** + * netlbl_secattr_catmap_setrng - Set a range of bits in a LSM secattr catmap +- * @catmap: the category bitmap ++ * @catmap: pointer to the category bitmap + * @start: the starting bit + * @end: the last bit in the string + * @flags: memory allocation flags +@@ -571,15 +578,16 @@ int netlbl_secattr_catmap_setbit(struct netlbl_lsm_secattr_catmap *catmap, + * on success, negative values on failure. + * + */ +-int netlbl_secattr_catmap_setrng(struct netlbl_lsm_secattr_catmap *catmap, ++int netlbl_secattr_catmap_setrng(struct netlbl_lsm_secattr_catmap **catmap, + u32 start, + u32 end, + gfp_t flags) + { + int ret_val = 0; +- struct netlbl_lsm_secattr_catmap *iter = catmap; ++ struct netlbl_lsm_secattr_catmap *iter = *catmap; + u32 iter_max_spot; + u32 spot; ++ u32 orig_spot = iter->startbit; + + /* XXX - This could probably be made a bit faster by combining writes + * to the catmap instead of setting a single bit each time, but for +@@ -597,7 +605,9 @@ int netlbl_secattr_catmap_setrng(struct netlbl_lsm_secattr_catmap *catmap, + iter = iter->next; + iter_max_spot = iter->startbit + NETLBL_CATMAP_SIZE; + } +- ret_val = netlbl_secattr_catmap_setbit(iter, spot, GFP_ATOMIC); ++ ret_val = netlbl_secattr_catmap_setbit(&iter, spot, flags); ++ if (iter->startbit < orig_spot) ++ *catmap = iter; + } + + return ret_val; +diff --git a/net/sctp/associola.c b/net/sctp/associola.c +index 25b207b..da54d29 100644 +--- a/net/sctp/associola.c ++++ b/net/sctp/associola.c +@@ -1188,6 +1188,7 @@ void sctp_assoc_update(struct sctp_association *asoc, + asoc->c = new->c; + asoc->peer.rwnd = new->peer.rwnd; + asoc->peer.sack_needed = new->peer.sack_needed; ++ asoc->peer.auth_capable = new->peer.auth_capable; + asoc->peer.i = new->peer.i; + sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, + asoc->peer.i.initial_tsn, GFP_ATOMIC); +diff --git a/net/sctp/output.c b/net/sctp/output.c +index cf3e22c..5bd9aa9 100644 +--- a/net/sctp/output.c ++++ b/net/sctp/output.c +@@ -587,7 +587,7 @@ out: + return err; + no_route: + kfree_skb(nskb); +- IP_INC_STATS_BH(&init_net, IPSTATS_MIB_OUTNOROUTES); ++ IP_INC_STATS(&init_net, IPSTATS_MIB_OUTNOROUTES); + + /* FIXME: Returning the 'err' will effect all the associations + * associated with a socket, although only one of the paths of the +diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c +index 7db62b4..e3adb49 100644 +--- a/security/smack/smack_lsm.c ++++ b/security/smack/smack_lsm.c +@@ -1842,7 +1842,7 @@ static void smack_set_catset(char *catset, struct netlbl_lsm_secattr *sap) + for (m = 0x80; m != 0; m >>= 1, cat++) { + if ((m & *cp) == 0) + continue; +- rc = netlbl_secattr_catmap_setbit(sap->attr.mls.cat, ++ rc = netlbl_secattr_catmap_setbit(&sap->attr.mls.cat, + cat, GFP_ATOMIC); + } + } +diff --git a/sound/pci/Kconfig b/sound/pci/Kconfig +index e7244ac..e2e4829 100644 +--- a/sound/pci/Kconfig ++++ b/sound/pci/Kconfig +@@ -852,8 +852,8 @@ config SND_VIRTUOSO + select SND_JACK if INPUT=y || INPUT=SND + help + Say Y here to include support for sound cards based on the +- Asus AV66/AV100/AV200 chips, i.e., Xonar D1, DX, D2, D2X, DS, +- Essence ST (Deluxe), and Essence STX. ++ Asus AV66/AV100/AV200 chips, i.e., Xonar D1, DX, D2, D2X, DS, DSX, ++ Essence ST (Deluxe), and Essence STX (II). + Support for the HDAV1.3 (Deluxe) and HDAV1.3 Slim is experimental; + for the Xense, missing. + +diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c +index 400168e..491cdf0 100644 +--- a/sound/pci/hda/patch_realtek.c ++++ b/sound/pci/hda/patch_realtek.c +@@ -436,6 +436,8 @@ static void alc_fix_pll(struct hda_codec *codec) + spec->pll_coef_idx); + val = snd_hda_codec_read(codec, spec->pll_nid, 0, + AC_VERB_GET_PROC_COEF, 0); ++ if (val == -1) ++ return; + snd_hda_codec_write(codec, spec->pll_nid, 0, AC_VERB_SET_COEF_INDEX, + spec->pll_coef_idx); + snd_hda_codec_write(codec, spec->pll_nid, 0, AC_VERB_SET_PROC_COEF, +@@ -4773,6 +4775,8 @@ static int alc269_parse_auto_config(struct hda_codec *codec) + static void alc269_toggle_power_output(struct hda_codec *codec, int power_up) + { + int val = alc_read_coef_idx(codec, 0x04); ++ if (val == -1) ++ return; + if (power_up) + val |= 1 << 11; + else +@@ -5184,27 +5188,30 @@ static int alc269_fill_coef(struct hda_codec *codec) + if ((alc_get_coef0(codec) & 0x00ff) == 0x017) { + val = alc_read_coef_idx(codec, 0x04); + /* Power up output pin */ +- alc_write_coef_idx(codec, 0x04, val | (1<<11)); ++ if (val != -1) ++ alc_write_coef_idx(codec, 0x04, val | (1<<11)); + } + + if ((alc_get_coef0(codec) & 0x00ff) == 0x018) { + val = alc_read_coef_idx(codec, 0xd); +- if ((val & 0x0c00) >> 10 != 0x1) { ++ if (val != -1 && (val & 0x0c00) >> 10 != 0x1) { + /* Capless ramp up clock control */ + alc_write_coef_idx(codec, 0xd, val | (1<<10)); + } + val = alc_read_coef_idx(codec, 0x17); +- if ((val & 0x01c0) >> 6 != 0x4) { ++ if (val != -1 && (val & 0x01c0) >> 6 != 0x4) { + /* Class D power on reset */ + alc_write_coef_idx(codec, 0x17, val | (1<<7)); + } + } + + val = alc_read_coef_idx(codec, 0xd); /* Class D */ +- alc_write_coef_idx(codec, 0xd, val | (1<<14)); ++ if (val != -1) ++ alc_write_coef_idx(codec, 0xd, val | (1<<14)); + + val = alc_read_coef_idx(codec, 0x4); /* HP */ +- alc_write_coef_idx(codec, 0x4, val | (1<<11)); ++ if (val != -1) ++ alc_write_coef_idx(codec, 0x4, val | (1<<11)); + + return 0; + } +diff --git a/sound/pci/oxygen/virtuoso.c b/sound/pci/oxygen/virtuoso.c +index 4149a0c..7edd5e4 100644 +--- a/sound/pci/oxygen/virtuoso.c ++++ b/sound/pci/oxygen/virtuoso.c +@@ -52,6 +52,8 @@ static DEFINE_PCI_DEVICE_TABLE(xonar_ids) = { + { OXYGEN_PCI_SUBID(0x1043, 0x835d) }, + { OXYGEN_PCI_SUBID(0x1043, 0x835e) }, + { OXYGEN_PCI_SUBID(0x1043, 0x838e) }, ++ { OXYGEN_PCI_SUBID(0x1043, 0x8522) }, ++ { OXYGEN_PCI_SUBID(0x1043, 0x85f4) }, + { OXYGEN_PCI_SUBID_BROKEN_EEPROM }, + { } + }; +diff --git a/sound/pci/oxygen/xonar_pcm179x.c b/sound/pci/oxygen/xonar_pcm179x.c +index 8433aa7..4cac06a 100644 +--- a/sound/pci/oxygen/xonar_pcm179x.c ++++ b/sound/pci/oxygen/xonar_pcm179x.c +@@ -100,8 +100,8 @@ + */ + + /* +- * Xonar Essence ST (Deluxe)/STX +- * ----------------------------- ++ * Xonar Essence ST (Deluxe)/STX (II) ++ * ---------------------------------- + * + * CMI8788: + * +@@ -1138,6 +1138,14 @@ int __devinit get_xonar_pcm179x_model(struct oxygen *chip, + chip->model.resume = xonar_stx_resume; + chip->model.set_dac_params = set_pcm1796_params; + break; ++ case 0x85f4: ++ chip->model = model_xonar_st; ++ /* TODO: daughterboard support */ ++ chip->model.shortname = "Xonar STX II"; ++ chip->model.init = xonar_stx_init; ++ chip->model.resume = xonar_stx_resume; ++ chip->model.set_dac_params = set_pcm1796_params; ++ break; + default: + return -EINVAL; + } +diff --git a/sound/pci/oxygen/xonar_wm87x6.c b/sound/pci/oxygen/xonar_wm87x6.c +index 915546a..30495b8 100644 +--- a/sound/pci/oxygen/xonar_wm87x6.c ++++ b/sound/pci/oxygen/xonar_wm87x6.c +@@ -1255,7 +1255,6 @@ static void dump_wm87x6_registers(struct oxygen *chip, + } + + static const struct oxygen_model model_xonar_ds = { +- .shortname = "Xonar DS", + .longname = "Asus Virtuoso 66", + .chip = "AV200", + .init = xonar_ds_init, +@@ -1325,6 +1324,11 @@ int __devinit get_xonar_wm87x6_model(struct oxygen *chip, + switch (id->subdevice) { + case 0x838e: + chip->model = model_xonar_ds; ++ chip->model.shortname = "Xonar DS"; ++ break; ++ case 0x8522: ++ chip->model = model_xonar_ds; ++ chip->model.shortname = "Xonar DSX"; + break; + case 0x835e: + chip->model = model_xonar_hdav_slim; +diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c +index b583e60..72886e3 100644 +--- a/sound/soc/pxa/pxa-ssp.c ++++ b/sound/soc/pxa/pxa-ssp.c +@@ -778,9 +778,7 @@ static int pxa_ssp_remove(struct snd_soc_dai *dai) + SNDRV_PCM_RATE_44100 | SNDRV_PCM_RATE_48000 | \ + SNDRV_PCM_RATE_88200 | SNDRV_PCM_RATE_96000) + +-#define PXA_SSP_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\ +- SNDRV_PCM_FMTBIT_S24_LE | \ +- SNDRV_PCM_FMTBIT_S32_LE) ++#define PXA_SSP_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S32_LE) + + static struct snd_soc_dai_ops pxa_ssp_dai_ops = { + .startup = pxa_ssp_startup, +diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c +index bff42bf..ad22bd9 100644 +--- a/sound/soc/samsung/i2s.c ++++ b/sound/soc/samsung/i2s.c +@@ -824,11 +824,9 @@ static int i2s_suspend(struct snd_soc_dai *dai) + { + struct i2s_dai *i2s = to_info(dai); + +- if (dai->active) { +- i2s->suspend_i2smod = readl(i2s->addr + I2SMOD); +- i2s->suspend_i2scon = readl(i2s->addr + I2SCON); +- i2s->suspend_i2spsr = readl(i2s->addr + I2SPSR); +- } ++ i2s->suspend_i2smod = readl(i2s->addr + I2SMOD); ++ i2s->suspend_i2scon = readl(i2s->addr + I2SCON); ++ i2s->suspend_i2spsr = readl(i2s->addr + I2SPSR); + + return 0; + } +@@ -837,11 +835,9 @@ static int i2s_resume(struct snd_soc_dai *dai) + { + struct i2s_dai *i2s = to_info(dai); + +- if (dai->active) { +- writel(i2s->suspend_i2scon, i2s->addr + I2SCON); +- writel(i2s->suspend_i2smod, i2s->addr + I2SMOD); +- writel(i2s->suspend_i2spsr, i2s->addr + I2SPSR); +- } ++ writel(i2s->suspend_i2scon, i2s->addr + I2SCON); ++ writel(i2s->suspend_i2smod, i2s->addr + I2SMOD); ++ writel(i2s->suspend_i2spsr, i2s->addr + I2SPSR); + + return 0; + } +diff --git a/virt/kvm/iommu.c b/virt/kvm/iommu.c +index 5dbb35d..c946700 100644 +--- a/virt/kvm/iommu.c ++++ b/virt/kvm/iommu.c +@@ -61,6 +61,14 @@ static pfn_t kvm_pin_pages(struct kvm *kvm, struct kvm_memory_slot *slot, + return pfn; + } + ++static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) ++{ ++ unsigned long i; ++ ++ for (i = 0; i < npages; ++i) ++ kvm_release_pfn_clean(pfn + i); ++} ++ + int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) + { + gfn_t gfn, end_gfn; +@@ -121,6 +129,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) + if (r) { + printk(KERN_ERR "kvm_iommu_map_address:" + "iommu failed to map pfn=%llx\n", pfn); ++ kvm_unpin_pages(kvm, pfn, page_size); + goto unmap_pages; + } + +@@ -132,7 +141,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot) + return 0; + + unmap_pages: +- kvm_iommu_put_pages(kvm, slot->base_gfn, gfn); ++ kvm_iommu_put_pages(kvm, slot->base_gfn, gfn - slot->base_gfn); + return r; + } + +@@ -273,14 +282,6 @@ out_unlock: + return r; + } + +-static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages) +-{ +- unsigned long i; +- +- for (i = 0; i < npages; ++i) +- kvm_release_pfn_clean(pfn + i); +-} +- + static void kvm_iommu_put_pages(struct kvm *kvm, + gfn_t base_gfn, unsigned long npages) + { |