diff options
| author |   Mike Pagano <mpagano@gentoo.org> | 2020-09-12 13:29:01 -0400 |
|---|---|---|
| committer | Mike Pagano <mpagano@gentoo.org> | 2020-09-12 13:29:01 -0400 |
| commit | 62586c138759076143ca13e338ada9923b297343 (patch) | |
| tree | aed8d993c4e2976712b142c6cd45c901cae5f1f0 | |
| parent | Linux patch 4.9.235 (diff) | |
| download | linux-patches-62586c138759076143ca13e338ada9923b297343.tar.gz linux-patches-62586c138759076143ca13e338ada9923b297343.tar.bz2 linux-patches-62586c138759076143ca13e338ada9923b297343.zip | |
Linux patch 4.9.2364.9-240
Signed-off-by: Mike Pagano <mpagano@gentoo.org>
| -rw-r--r-- | 0000_README | 4 | ||||
| -rw-r--r-- | 1235_linux-4.9.236.patch | 3781 |
2 files changed, 3785 insertions, 0 deletions
diff --git a/0000_README b/0000_README index 52a8befe..540ceed1 100644 --- a/0000_README +++ b/0000_README @@ -983,6 +983,10 @@ Patch: 1234_linux-4.9.235.patch From: http://www.kernel.org Desc: Linux 4.9.235 +Patch: 1235_linux-4.9.236.patch +From: http://www.kernel.org +Desc: Linux 4.9.236 + Patch: 1500_XATTR_USER_PREFIX.patch From: https://bugs.gentoo.org/show_bug.cgi?id=470644 Desc: Support for namespace user.pax.* on tmpfs. diff --git a/1235_linux-4.9.236.patch b/1235_linux-4.9.236.patch new file mode 100644 index 00000000..43e9051e --- /dev/null +++ b/1235_linux-4.9.236.patch @@ -0,0 +1,3781 @@ +diff --git a/Documentation/filesystems/affs.txt b/Documentation/filesystems/affs.txt +index 71b63c2b98410..a8f1a58e36922 100644 +--- a/Documentation/filesystems/affs.txt ++++ b/Documentation/filesystems/affs.txt +@@ -93,13 +93,15 @@ The Amiga protection flags RWEDRWEDHSPARWED are handled as follows: + + - R maps to r for user, group and others. On directories, R implies x. + +- - If both W and D are allowed, w will be set. ++ - W maps to w. + + - E maps to x. + +- - H and P are always retained and ignored under Linux. ++ - D is ignored. + +- - A is always reset when a file is written to. ++ - H, S and P are always retained and ignored under Linux. ++ ++ - A is cleared when a file is written to. + + User id and group id will be used unless set[gu]id are given as mount + options. Since most of the Amiga file systems are single user systems +@@ -111,11 +113,13 @@ Linux -> Amiga: + + The Linux rwxrwxrwx file mode is handled as follows: + +- - r permission will set R for user, group and others. ++ - r permission will allow R for user, group and others. ++ ++ - w permission will allow W for user, group and others. + +- - w permission will set W and D for user, group and others. ++ - x permission of the user will allow E for plain files. + +- - x permission of the user will set E for plain files. ++ - D will be allowed for user, group and others. + + - All other flags (suid, sgid, ...) are ignored and will + not be retained. +diff --git a/Makefile b/Makefile +index d21084a36bd4d..a454c9cd126e0 100644 +--- a/Makefile ++++ b/Makefile +@@ -1,6 +1,6 @@ + VERSION = 4 + PATCHLEVEL = 9 +-SUBLEVEL = 235 ++SUBLEVEL = 236 + EXTRAVERSION = + NAME = Roaring Lionus + +diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h +index a11c8c2915c93..e8cb69b0cf4fb 100644 +--- a/arch/arm64/include/asm/kvm_arm.h ++++ b/arch/arm64/include/asm/kvm_arm.h +@@ -78,10 +78,11 @@ + * IMO: Override CPSR.I and enable signaling with VI + * FMO: Override CPSR.F and enable signaling with VF + * SWIO: Turn set/way invalidates into set/way clean+invalidate ++ * PTW: Take a stage2 fault if a stage1 walk steps in device memory + */ + #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ + HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \ +- HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW) ++ HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_PTW) + #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) + #define HCR_INT_OVERRIDE (HCR_FMO | HCR_IMO) + #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK) +diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h +index 8f5cf83b23396..3d2fddac25b91 100644 +--- a/arch/arm64/include/asm/kvm_asm.h ++++ b/arch/arm64/include/asm/kvm_asm.h +@@ -82,6 +82,34 @@ extern u32 __init_stage2_translation(void); + *__hyp_this_cpu_ptr(sym); \ + }) + ++#define __KVM_EXTABLE(from, to) \ ++ " .pushsection __kvm_ex_table, \"a\"\n" \ ++ " .align 3\n" \ ++ " .long (" #from " - .), (" #to " - .)\n" \ ++ " .popsection\n" ++ ++ ++#define __kvm_at(at_op, addr) \ ++( { \ ++ int __kvm_at_err = 0; \ ++ u64 spsr, elr; \ ++ asm volatile( \ ++ " mrs %1, spsr_el2\n" \ ++ " mrs %2, elr_el2\n" \ ++ "1: at "at_op", %3\n" \ ++ " isb\n" \ ++ " b 9f\n" \ ++ "2: msr spsr_el2, %1\n" \ ++ " msr elr_el2, %2\n" \ ++ " mov %w0, %4\n" \ ++ "9:\n" \ ++ __KVM_EXTABLE(1b, 2b) \ ++ : "+r" (__kvm_at_err), "=&r" (spsr), "=&r" (elr) \ ++ : "r" (addr), "i" (-EFAULT)); \ ++ __kvm_at_err; \ ++} ) ++ ++ + #else /* __ASSEMBLY__ */ + + .macro hyp_adr_this_cpu reg, sym, tmp +@@ -106,6 +134,21 @@ extern u32 __init_stage2_translation(void); + kern_hyp_va \vcpu + .endm + ++/* ++ * KVM extable for unexpected exceptions. ++ * In the same format _asm_extable, but output to a different section so that ++ * it can be mapped to EL2. The KVM version is not sorted. The caller must ++ * ensure: ++ * x18 has the hypervisor value to allow any Shadow-Call-Stack instrumented ++ * code to write to it, and that SPSR_EL2 and ELR_EL2 are restored by the fixup. ++ */ ++.macro _kvm_extable, from, to ++ .pushsection __kvm_ex_table, "a" ++ .align 3 ++ .long (\from - .), (\to - .) ++ .popsection ++.endm ++ + #endif + + #endif /* __ARM_KVM_ASM_H__ */ +diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S +index 6a584558b29d2..fa3ffad50a61c 100644 +--- a/arch/arm64/kernel/vmlinux.lds.S ++++ b/arch/arm64/kernel/vmlinux.lds.S +@@ -23,6 +23,13 @@ ENTRY(_text) + + jiffies = jiffies_64; + ++ ++#define HYPERVISOR_EXTABLE \ ++ . = ALIGN(SZ_8); \ ++ VMLINUX_SYMBOL(__start___kvm_ex_table) = .; \ ++ *(__kvm_ex_table) \ ++ VMLINUX_SYMBOL(__stop___kvm_ex_table) = .; ++ + #define HYPERVISOR_TEXT \ + /* \ + * Align to 4 KB so that \ +@@ -38,6 +45,7 @@ jiffies = jiffies_64; + VMLINUX_SYMBOL(__hyp_idmap_text_end) = .; \ + VMLINUX_SYMBOL(__hyp_text_start) = .; \ + *(.hyp.text) \ ++ HYPERVISOR_EXTABLE \ + VMLINUX_SYMBOL(__hyp_text_end) = .; + + #define IDMAP_TEXT \ +diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S +index a360ac6e89e9d..4e0eac361f87c 100644 +--- a/arch/arm64/kvm/hyp/entry.S ++++ b/arch/arm64/kvm/hyp/entry.S +@@ -17,6 +17,7 @@ + + #include <linux/linkage.h> + ++#include <asm/alternative.h> + #include <asm/asm-offsets.h> + #include <asm/assembler.h> + #include <asm/fpsimdmacros.h> +@@ -62,6 +63,15 @@ ENTRY(__guest_enter) + // Store the host regs + save_callee_saved_regs x1 + ++ // Now the host state is stored if we have a pending RAS SError it must ++ // affect the host. If any asynchronous exception is pending we defer ++ // the guest entry. ++ mrs x1, isr_el1 ++ cbz x1, 1f ++ mov x0, #ARM_EXCEPTION_IRQ ++ ret ++ ++1: + add x18, x0, #VCPU_CONTEXT + + // Restore guest regs x0-x17 +@@ -135,18 +145,22 @@ ENTRY(__guest_exit) + // This is our single instruction exception window. A pending + // SError is guaranteed to occur at the earliest when we unmask + // it, and at the latest just after the ISB. +- .global abort_guest_exit_start + abort_guest_exit_start: + + isb + +- .global abort_guest_exit_end + abort_guest_exit_end: ++ msr daifset, #4 // Mask aborts ++ ret ++ ++ _kvm_extable abort_guest_exit_start, 9997f ++ _kvm_extable abort_guest_exit_end, 9997f ++9997: ++ msr daifset, #4 // Mask aborts ++ mov x0, #(1 << ARM_EXIT_WITH_SERROR_BIT) + +- // If the exception took place, restore the EL1 exception +- // context so that we can report some information. +- // Merge the exception code with the SError pending bit. +- tbz x0, #ARM_EXIT_WITH_SERROR_BIT, 1f ++ // restore the EL1 exception context so that we can report some ++ // information. Merge the exception code with the SError pending bit. + msr elr_el2, x2 + msr esr_el2, x3 + msr spsr_el2, x4 +diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S +index bf4988f9dae8f..7ced1fb93d077 100644 +--- a/arch/arm64/kvm/hyp/hyp-entry.S ++++ b/arch/arm64/kvm/hyp/hyp-entry.S +@@ -25,6 +25,30 @@ + #include <asm/kvm_asm.h> + #include <asm/kvm_mmu.h> + ++.macro save_caller_saved_regs_vect ++ stp x0, x1, [sp, #-16]! ++ stp x2, x3, [sp, #-16]! ++ stp x4, x5, [sp, #-16]! ++ stp x6, x7, [sp, #-16]! ++ stp x8, x9, [sp, #-16]! ++ stp x10, x11, [sp, #-16]! ++ stp x12, x13, [sp, #-16]! ++ stp x14, x15, [sp, #-16]! ++ stp x16, x17, [sp, #-16]! ++.endm ++ ++.macro restore_caller_saved_regs_vect ++ ldp x16, x17, [sp], #16 ++ ldp x14, x15, [sp], #16 ++ ldp x12, x13, [sp], #16 ++ ldp x10, x11, [sp], #16 ++ ldp x8, x9, [sp], #16 ++ ldp x6, x7, [sp], #16 ++ ldp x4, x5, [sp], #16 ++ ldp x2, x3, [sp], #16 ++ ldp x0, x1, [sp], #16 ++.endm ++ + .text + .pushsection .hyp.text, "ax" + +@@ -177,26 +201,24 @@ el1_error: + mov x0, #ARM_EXCEPTION_EL1_SERROR + b __guest_exit + ++el2_sync: ++ save_caller_saved_regs_vect ++ stp x29, x30, [sp, #-16]! ++ bl kvm_unexpected_el2_exception ++ ldp x29, x30, [sp], #16 ++ restore_caller_saved_regs_vect ++ ++ eret ++ + el2_error: +- /* +- * Only two possibilities: +- * 1) Either we come from the exit path, having just unmasked +- * PSTATE.A: change the return code to an EL2 fault, and +- * carry on, as we're already in a sane state to handle it. +- * 2) Or we come from anywhere else, and that's a bug: we panic. +- * +- * For (1), x0 contains the original return code and x1 doesn't +- * contain anything meaningful at that stage. We can reuse them +- * as temp registers. +- * For (2), who cares? +- */ +- mrs x0, elr_el2 +- adr x1, abort_guest_exit_start +- cmp x0, x1 +- adr x1, abort_guest_exit_end +- ccmp x0, x1, #4, ne +- b.ne __hyp_panic +- mov x0, #(1 << ARM_EXIT_WITH_SERROR_BIT) ++ save_caller_saved_regs_vect ++ stp x29, x30, [sp, #-16]! ++ ++ bl kvm_unexpected_el2_exception ++ ++ ldp x29, x30, [sp], #16 ++ restore_caller_saved_regs_vect ++ + eret + + ENTRY(__hyp_do_panic) +@@ -225,7 +247,6 @@ ENDPROC(\label) + invalid_vector el2t_irq_invalid + invalid_vector el2t_fiq_invalid + invalid_vector el2t_error_invalid +- invalid_vector el2h_sync_invalid + invalid_vector el2h_irq_invalid + invalid_vector el2h_fiq_invalid + invalid_vector el1_sync_invalid +@@ -242,7 +263,7 @@ ENTRY(__kvm_hyp_vector) + ventry el2t_fiq_invalid // FIQ EL2t + ventry el2t_error_invalid // Error EL2t + +- ventry el2h_sync_invalid // Synchronous EL2h ++ ventry el2_sync // Synchronous EL2h + ventry el2h_irq_invalid // IRQ EL2h + ventry el2h_fiq_invalid // FIQ EL2h + ventry el2_error // Error EL2h +diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c +index ed7e3a288b4e5..0a2f37bceab0a 100644 +--- a/arch/arm64/kvm/hyp/switch.c ++++ b/arch/arm64/kvm/hyp/switch.c +@@ -25,6 +25,10 @@ + #include <asm/kvm_asm.h> + #include <asm/kvm_emulate.h> + #include <asm/kvm_hyp.h> ++#include <asm/uaccess.h> ++ ++extern struct exception_table_entry __start___kvm_ex_table; ++extern struct exception_table_entry __stop___kvm_ex_table; + + static bool __hyp_text __fpsimd_enabled_nvhe(void) + { +@@ -202,10 +206,10 @@ static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar) + * saved the guest context yet, and we may return early... + */ + par = read_sysreg(par_el1); +- asm volatile("at s1e1r, %0" : : "r" (far)); +- isb(); +- +- tmp = read_sysreg(par_el1); ++ if (!__kvm_at("s1e1r", far)) ++ tmp = read_sysreg(par_el1); ++ else ++ tmp = 1; /* back to the guest */ + write_sysreg(par, par_el1); + + if (unlikely(tmp & 1)) +@@ -454,3 +458,30 @@ void __hyp_text __noreturn hyp_panic(struct kvm_cpu_context *host_ctxt) + + unreachable(); + } ++ ++asmlinkage void __hyp_text kvm_unexpected_el2_exception(void) ++{ ++ unsigned long addr, fixup; ++ struct kvm_cpu_context *host_ctxt; ++ struct exception_table_entry *entry, *end; ++ unsigned long elr_el2 = read_sysreg(elr_el2); ++ ++ entry = hyp_symbol_addr(__start___kvm_ex_table); ++ end = hyp_symbol_addr(__stop___kvm_ex_table); ++ host_ctxt = __hyp_this_cpu_ptr(kvm_host_cpu_state); ++ ++ while (entry < end) { ++ addr = (unsigned long)&entry->insn + entry->insn; ++ fixup = (unsigned long)&entry->fixup + entry->fixup; ++ ++ if (addr != elr_el2) { ++ entry++; ++ continue; ++ } ++ ++ write_sysreg(fixup, elr_el2); ++ return; ++ } ++ ++ hyp_panic(host_ctxt); ++} +diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c +index 416d53f587e7c..6e36717527754 100644 +--- a/arch/mips/kernel/smp-bmips.c ++++ b/arch/mips/kernel/smp-bmips.c +@@ -236,6 +236,8 @@ static void bmips_boot_secondary(int cpu, struct task_struct *idle) + */ + static void bmips_init_secondary(void) + { ++ bmips_cpu_setup(); ++ + switch (current_cpu_type()) { + case CPU_BMIPS4350: + case CPU_BMIPS4380: +diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c +index 0ff379f0cc4a7..cb877f86f5fc9 100644 +--- a/arch/mips/mm/c-r4k.c ++++ b/arch/mips/mm/c-r4k.c +@@ -1746,7 +1746,11 @@ static void setup_scache(void) + printk("MIPS secondary cache %ldkB, %s, linesize %d bytes.\n", + scache_size >> 10, + way_string[c->scache.ways], c->scache.linesz); ++ ++ if (current_cpu_type() == CPU_BMIPS5000) ++ c->options |= MIPS_CPU_INCLUSIVE_CACHES; + } ++ + #else + if (!(c->scache.flags & MIPS_CACHE_NOT_PRESENT)) + panic("Dunno how to handle MIPS32 / MIPS64 second level cache"); +diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h +index 90240dfef76a1..5889c1ed84c46 100644 +--- a/arch/s390/include/asm/percpu.h ++++ b/arch/s390/include/asm/percpu.h +@@ -28,7 +28,7 @@ + typedef typeof(pcp) pcp_op_T__; \ + pcp_op_T__ old__, new__, prev__; \ + pcp_op_T__ *ptr__; \ +- preempt_disable(); \ ++ preempt_disable_notrace(); \ + ptr__ = raw_cpu_ptr(&(pcp)); \ + prev__ = *ptr__; \ + do { \ +@@ -36,7 +36,7 @@ + new__ = old__ op (val); \ + prev__ = cmpxchg(ptr__, old__, new__); \ + } while (prev__ != old__); \ +- preempt_enable(); \ ++ preempt_enable_notrace(); \ + new__; \ + }) + +@@ -67,7 +67,7 @@ + typedef typeof(pcp) pcp_op_T__; \ + pcp_op_T__ val__ = (val); \ + pcp_op_T__ old__, *ptr__; \ +- preempt_disable(); \ ++ preempt_disable_notrace(); \ + ptr__ = raw_cpu_ptr(&(pcp)); \ + if (__builtin_constant_p(val__) && \ + ((szcast)val__ > -129) && ((szcast)val__ < 128)) { \ +@@ -83,7 +83,7 @@ + : [val__] "d" (val__) \ + : "cc"); \ + } \ +- preempt_enable(); \ ++ preempt_enable_notrace(); \ + } + + #define this_cpu_add_4(pcp, val) arch_this_cpu_add(pcp, val, "laa", "asi", int) +@@ -94,14 +94,14 @@ + typedef typeof(pcp) pcp_op_T__; \ + pcp_op_T__ val__ = (val); \ + pcp_op_T__ old__, *ptr__; \ +- preempt_disable(); \ ++ preempt_disable_notrace(); \ + ptr__ = raw_cpu_ptr(&(pcp)); \ + asm volatile( \ + op " %[old__],%[val__],%[ptr__]\n" \ + : [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \ + : [val__] "d" (val__) \ + : "cc"); \ +- preempt_enable(); \ ++ preempt_enable_notrace(); \ + old__ + val__; \ + }) + +@@ -113,14 +113,14 @@ + typedef typeof(pcp) pcp_op_T__; \ + pcp_op_T__ val__ = (val); \ + pcp_op_T__ old__, *ptr__; \ +- preempt_disable(); \ ++ preempt_disable_notrace(); \ + ptr__ = raw_cpu_ptr(&(pcp)); \ + asm volatile( \ + op " %[old__],%[val__],%[ptr__]\n" \ + : [old__] "=d" (old__), [ptr__] "+Q" (*ptr__) \ + : [val__] "d" (val__) \ + : "cc"); \ +- preempt_enable(); \ ++ preempt_enable_notrace(); \ + } + + #define this_cpu_and_4(pcp, val) arch_this_cpu_to_op(pcp, val, "lan") +@@ -135,10 +135,10 @@ + typedef typeof(pcp) pcp_op_T__; \ + pcp_op_T__ ret__; \ + pcp_op_T__ *ptr__; \ +- preempt_disable(); \ ++ preempt_disable_notrace(); \ + ptr__ = raw_cpu_ptr(&(pcp)); \ + ret__ = cmpxchg(ptr__, oval, nval); \ +- preempt_enable(); \ ++ preempt_enable_notrace(); \ + ret__; \ + }) + +@@ -151,10 +151,10 @@ + ({ \ + typeof(pcp) *ptr__; \ + typeof(pcp) ret__; \ +- preempt_disable(); \ ++ preempt_disable_notrace(); \ + ptr__ = raw_cpu_ptr(&(pcp)); \ + ret__ = xchg(ptr__, nval); \ +- preempt_enable(); \ ++ preempt_enable_notrace(); \ + ret__; \ + }) + +@@ -170,11 +170,11 @@ + typeof(pcp1) *p1__; \ + typeof(pcp2) *p2__; \ + int ret__; \ +- preempt_disable(); \ ++ preempt_disable_notrace(); \ + p1__ = raw_cpu_ptr(&(pcp1)); \ + p2__ = raw_cpu_ptr(&(pcp2)); \ + ret__ = __cmpxchg_double(p1__, p2__, o1__, o2__, n1__, n2__); \ +- preempt_enable(); \ ++ preempt_enable_notrace(); \ + ret__; \ + }) + +diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c +index ede04cca30dde..82fb5102d8244 100644 +--- a/arch/xtensa/platforms/iss/simdisk.c ++++ b/arch/xtensa/platforms/iss/simdisk.c +@@ -21,7 +21,6 @@ + #include <platform/simcall.h> + + #define SIMDISK_MAJOR 240 +-#define SECTOR_SHIFT 9 + #define SIMDISK_MINORS 1 + #define MAX_SIMDISK_COUNT 10 + +diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c +index 46bf7e9d00aba..2aa10cd4c5b75 100644 +--- a/drivers/ata/libata-core.c ++++ b/drivers/ata/libata-core.c +@@ -4371,9 +4371,8 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { + /* https://bugzilla.kernel.org/show_bug.cgi?id=15573 */ + { "C300-CTFDDAC128MAG", "0001", ATA_HORKAGE_NONCQ, }, + +- /* Some Sandisk SSDs lock up hard with NCQ enabled. Reported on +- SD7SN6S256G and SD8SN8U256G */ +- { "SanDisk SD[78]SN*G", NULL, ATA_HORKAGE_NONCQ, }, ++ /* Sandisk SD7/8/9s lock up hard on large trims */ ++ { "SanDisk SD[789]*", NULL, ATA_HORKAGE_MAX_TRIM_128M, }, + + /* devices which puke on READ_NATIVE_MAX */ + { "HDS724040KLSA80", "KFAOA20N", ATA_HORKAGE_BROKEN_HPA, }, +diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c +index f4b38adb9d8a7..76ba83e245c23 100644 +--- a/drivers/ata/libata-scsi.c ++++ b/drivers/ata/libata-scsi.c +@@ -2314,6 +2314,7 @@ static unsigned int ata_scsiop_inq_89(struct ata_scsi_args *args, u8 *rbuf) + + static unsigned int ata_scsiop_inq_b0(struct ata_scsi_args *args, u8 *rbuf) + { ++ struct ata_device *dev = args->dev; + u16 min_io_sectors; + + rbuf[1] = 0xb0; +@@ -2339,7 +2340,12 @@ static unsigned int ata_scsiop_inq_b0(struct ata_scsi_args *args, u8 *rbuf) + * with the unmap bit set. + */ + if (ata_id_has_trim(args->id)) { +- put_unaligned_be64(65535 * ATA_MAX_TRIM_RNUM, &rbuf[36]); ++ u64 max_blocks = 65535 * ATA_MAX_TRIM_RNUM; ++ ++ if (dev->horkage & ATA_HORKAGE_MAX_TRIM_128M) ++ max_blocks = 128 << (20 - SECTOR_SHIFT); ++ ++ put_unaligned_be64(max_blocks, &rbuf[36]); + put_unaligned_be32(1, &rbuf[28]); + } + +diff --git a/drivers/block/brd.c b/drivers/block/brd.c +index 7e35574a17dfc..9d81ac8b4512a 100644 +--- a/drivers/block/brd.c ++++ b/drivers/block/brd.c +@@ -25,7 +25,6 @@ + + #include <asm/uaccess.h> + +-#define SECTOR_SHIFT 9 + #define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) + #define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) + +diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c +index 8a93ca4d6840c..19f336752ad75 100644 +--- a/drivers/block/rbd.c ++++ b/drivers/block/rbd.c +@@ -50,15 +50,6 @@ + + #define RBD_DEBUG /* Activate rbd_assert() calls */ + +-/* +- * The basic unit of block I/O is a sector. It is interpreted in a +- * number of contexts in Linux (blk, bio, genhd), but the default is +- * universally 512 bytes. These symbols are just slightly more +- * meaningful than the bare numbers they represent. +- */ +-#define SECTOR_SHIFT 9 +-#define SECTOR_SIZE (1ULL << SECTOR_SHIFT) +- + /* + * Increment the given counter and return its updated value. + * If the counter is already 0 it will not be incremented. +diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h +index 74fcf10da3749..6d2475a39e84b 100644 +--- a/drivers/block/zram/zram_drv.h ++++ b/drivers/block/zram/zram_drv.h +@@ -37,7 +37,6 @@ static const size_t max_zpage_size = PAGE_SIZE / 4 * 3; + + /*-- End of configurable params */ + +-#define SECTOR_SHIFT 9 + #define SECTORS_PER_PAGE_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) + #define SECTORS_PER_PAGE (1 << SECTORS_PER_PAGE_SHIFT) + #define ZRAM_LOGICAL_BLOCK_SHIFT 12 +diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c +index a32cd71f94bbe..cb72b8c915c73 100644 +--- a/drivers/dma/at_hdmac.c ++++ b/drivers/dma/at_hdmac.c +@@ -1810,6 +1810,8 @@ static struct dma_chan *at_dma_xlate(struct of_phandle_args *dma_spec, + return NULL; + + dmac_pdev = of_find_device_by_node(dma_spec->np); ++ if (!dmac_pdev) ++ return NULL; + + dma_cap_zero(mask); + dma_cap_set(DMA_SLAVE, mask); +diff --git a/drivers/dma/of-dma.c b/drivers/dma/of-dma.c +index faae0bfe1109e..757cf48c1c5ed 100644 +--- a/drivers/dma/of-dma.c ++++ b/drivers/dma/of-dma.c +@@ -72,12 +72,12 @@ static struct dma_chan *of_dma_router_xlate(struct of_phandle_args *dma_spec, + return NULL; + + chan = ofdma_target->of_dma_xlate(&dma_spec_target, ofdma_target); +- if (chan) { +- chan->router = ofdma->dma_router; +- chan->route_data = route_data; +- } else { ++ if (IS_ERR_OR_NULL(chan)) { + ofdma->dma_router->route_free(ofdma->dma_router->dev, + route_data); ++ } else { ++ chan->router = ofdma->dma_router; ++ chan->route_data = route_data; + } + + /* +diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c +index 57b375d0de292..16c08846ea0e1 100644 +--- a/drivers/dma/pl330.c ++++ b/drivers/dma/pl330.c +@@ -2677,6 +2677,7 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst, + while (burst != (1 << desc->rqcfg.brst_size)) + desc->rqcfg.brst_size++; + ++ desc->rqcfg.brst_len = get_burst_len(desc, len); + /* + * If burst size is smaller than bus width then make sure we only + * transfer one at a time to avoid a burst stradling an MFIFO entry. +@@ -2684,7 +2685,6 @@ pl330_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dst, + if (desc->rqcfg.brst_size * 8 < pl330->pcfg.data_bus_width) + desc->rqcfg.brst_len = 1; + +- desc->rqcfg.brst_len = get_burst_len(desc, len); + desc->bytes_requested = len; + + desc->txd.flags = flags; +diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c +index b4b9d81525369..d99c9ed5dfe39 100644 +--- a/drivers/hid/hid-core.c ++++ b/drivers/hid/hid-core.c +@@ -1406,6 +1406,17 @@ static void hid_output_field(const struct hid_device *hid, + } + } + ++/* ++ * Compute the size of a report. ++ */ ++static size_t hid_compute_report_size(struct hid_report *report) ++{ ++ if (report->size) ++ return ((report->size - 1) >> 3) + 1; ++ ++ return 0; ++} ++ + /* + * Create a report. 'data' has to be allocated using + * hid_alloc_report_buf() so that it has proper size. +@@ -1418,7 +1429,7 @@ void hid_output_report(struct hid_report *report, __u8 *data) + if (report->id > 0) + *data++ = report->id; + +- memset(data, 0, ((report->size - 1) >> 3) + 1); ++ memset(data, 0, hid_compute_report_size(report)); + for (n = 0; n < report->maxfield; n++) + hid_output_field(report->device, report->field[n], data); + } +@@ -1545,7 +1556,7 @@ int hid_report_raw_event(struct hid_device *hid, int type, u8 *data, u32 size, + csize--; + } + +- rsize = ((report->size - 1) >> 3) + 1; ++ rsize = hid_compute_report_size(report); + + if (report_enum->numbered && rsize >= HID_MAX_BUFFER_SIZE) + rsize = HID_MAX_BUFFER_SIZE - 1; +diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c +index 26e9677309972..5e1a51ba6500f 100644 +--- a/drivers/hid/hid-input.c ++++ b/drivers/hid/hid-input.c +@@ -1026,6 +1026,10 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel + } + + mapped: ++ /* Mapping failed, bail out */ ++ if (!bit) ++ return; ++ + if (device->driver->input_mapped && + device->driver->input_mapped(device, hidinput, field, usage, + &bit, &max) < 0) { +diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c +index 1207102823de3..258a50ec15727 100644 +--- a/drivers/hid/hid-multitouch.c ++++ b/drivers/hid/hid-multitouch.c +@@ -567,6 +567,8 @@ static int mt_touch_input_mapping(struct hid_device *hdev, struct hid_input *hi, + case HID_UP_BUTTON: + code = BTN_MOUSE + ((usage->hid - 1) & HID_USAGE); + hid_map_usage(hi, usage, bit, max, EV_KEY, code); ++ if (!*bit) ++ return -1; + input_set_capability(hi->input, EV_KEY, code); + return 1; + +diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c +index 0af7fd311979d..587fc5c686b3c 100644 +--- a/drivers/hwmon/applesmc.c ++++ b/drivers/hwmon/applesmc.c +@@ -758,15 +758,18 @@ static ssize_t applesmc_light_show(struct device *dev, + } + + ret = applesmc_read_key(LIGHT_SENSOR_LEFT_KEY, buffer, data_length); ++ if (ret) ++ goto out; + /* newer macbooks report a single 10-bit bigendian value */ + if (data_length == 10) { + left = be16_to_cpu(*(__be16 *)(buffer + 6)) >> 2; + goto out; + } + left = buffer[2]; ++ ++ ret = applesmc_read_key(LIGHT_SENSOR_RIGHT_KEY, buffer, data_length); + if (ret) + goto out; +- ret = applesmc_read_key(LIGHT_SENSOR_RIGHT_KEY, buffer, data_length); + right = buffer[2]; + + out: +@@ -814,12 +817,11 @@ static ssize_t applesmc_show_fan_speed(struct device *dev, + sprintf(newkey, fan_speed_fmt[to_option(attr)], to_index(attr)); + + ret = applesmc_read_key(newkey, buffer, 2); +- speed = ((buffer[0] << 8 | buffer[1]) >> 2); +- + if (ret) + return ret; +- else +- return snprintf(sysfsbuf, PAGE_SIZE, "%u\n", speed); ++ ++ speed = ((buffer[0] << 8 | buffer[1]) >> 2); ++ return snprintf(sysfsbuf, PAGE_SIZE, "%u\n", speed); + } + + static ssize_t applesmc_store_fan_speed(struct device *dev, +@@ -854,12 +856,11 @@ static ssize_t applesmc_show_fan_manual(struct device *dev, + u8 buffer[2]; + + ret = applesmc_read_key(FANS_MANUAL, buffer, 2); +- manual = ((buffer[0] << 8 | buffer[1]) >> to_index(attr)) & 0x01; +- + if (ret) + return ret; +- else +- return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", manual); ++ ++ manual = ((buffer[0] << 8 | buffer[1]) >> to_index(attr)) & 0x01; ++ return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", manual); + } + + static ssize_t applesmc_store_fan_manual(struct device *dev, +@@ -875,10 +876,11 @@ static ssize_t applesmc_store_fan_manual(struct device *dev, + return -EINVAL; + + ret = applesmc_read_key(FANS_MANUAL, buffer, 2); +- val = (buffer[0] << 8 | buffer[1]); + if (ret) + goto out; + ++ val = (buffer[0] << 8 | buffer[1]); ++ + if (input) + val = val | (0x01 << to_index(attr)); + else +@@ -954,13 +956,12 @@ static ssize_t applesmc_key_count_show(struct device *dev, + u32 count; + + ret = applesmc_read_key(KEY_COUNT_KEY, buffer, 4); +- count = ((u32)buffer[0]<<24) + ((u32)buffer[1]<<16) + +- ((u32)buffer[2]<<8) + buffer[3]; +- + if (ret) + return ret; +- else +- return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", count); ++ ++ count = ((u32)buffer[0]<<24) + ((u32)buffer[1]<<16) + ++ ((u32)buffer[2]<<8) + buffer[3]; ++ return snprintf(sysfsbuf, PAGE_SIZE, "%d\n", count); + } + + static ssize_t applesmc_key_at_index_read_show(struct device *dev, +diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c +index 883fe2cdd42cc..6e3b3a5a3c36f 100644 +--- a/drivers/ide/ide-cd.c ++++ b/drivers/ide/ide-cd.c +@@ -704,7 +704,7 @@ static ide_startstop_t cdrom_start_rw(ide_drive_t *drive, struct request *rq) + struct request_queue *q = drive->queue; + int write = rq_data_dir(rq) == WRITE; + unsigned short sectors_per_frame = +- queue_logical_block_size(q) >> SECTOR_BITS; ++ queue_logical_block_size(q) >> SECTOR_SHIFT; + + ide_debug_log(IDE_DBG_RQ, "rq->cmd[0]: 0x%x, rq->cmd_flags: 0x%x, " + "secs_per_frame: %u", +@@ -900,7 +900,7 @@ static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity, + * end up being bogus. + */ + blocklen = be32_to_cpu(capbuf.blocklen); +- blocklen = (blocklen >> SECTOR_BITS) << SECTOR_BITS; ++ blocklen = (blocklen >> SECTOR_SHIFT) << SECTOR_SHIFT; + switch (blocklen) { + case 512: + case 1024: +@@ -916,7 +916,7 @@ static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity, + } + + *capacity = 1 + be32_to_cpu(capbuf.lba); +- *sectors_per_frame = blocklen >> SECTOR_BITS; ++ *sectors_per_frame = blocklen >> SECTOR_SHIFT; + + ide_debug_log(IDE_DBG_PROBE, "cap: %lu, sectors_per_frame: %lu", + *capacity, *sectors_per_frame); +@@ -993,7 +993,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense) + drive->probed_capacity = toc->capacity * sectors_per_frame; + + blk_queue_logical_block_size(drive->queue, +- sectors_per_frame << SECTOR_BITS); ++ sectors_per_frame << SECTOR_SHIFT); + + /* first read just the header, so we know how long the TOC is */ + stat = cdrom_read_tocentry(drive, 0, 1, 0, (char *) &toc->hdr, +diff --git a/drivers/ide/ide-cd.h b/drivers/ide/ide-cd.h +index 1efc936f5b667..7c6d017e84e9e 100644 +--- a/drivers/ide/ide-cd.h ++++ b/drivers/ide/ide-cd.h +@@ -20,11 +20,7 @@ + + /************************************************************************/ + +-#define SECTOR_BITS 9 +-#ifndef SECTOR_SIZE +-#define SECTOR_SIZE (1 << SECTOR_BITS) +-#endif +-#define SECTORS_PER_FRAME (CD_FRAMESIZE >> SECTOR_BITS) ++#define SECTORS_PER_FRAME (CD_FRAMESIZE >> SECTOR_SHIFT) + #define SECTOR_BUFFER_SIZE (CD_FRAMESIZE * 32) + + /* Capabilities Page size including 8 bytes of Mode Page Header */ +diff --git a/drivers/iommu/intel_irq_remapping.c b/drivers/iommu/intel_irq_remapping.c +index ac596928f6b40..ce125ec23d2a5 100644 +--- a/drivers/iommu/intel_irq_remapping.c ++++ b/drivers/iommu/intel_irq_remapping.c +@@ -486,12 +486,18 @@ static void iommu_enable_irq_remapping(struct intel_iommu *iommu) + + /* Enable interrupt-remapping */ + iommu->gcmd |= DMA_GCMD_IRE; +- iommu->gcmd &= ~DMA_GCMD_CFI; /* Block compatibility-format MSIs */ + writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG); +- + IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, + readl, (sts & DMA_GSTS_IRES), sts); + ++ /* Block compatibility-format MSIs */ ++ if (sts & DMA_GSTS_CFIS) { ++ iommu->gcmd &= ~DMA_GCMD_CFI; ++ writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG); ++ IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, ++ readl, !(sts & DMA_GSTS_CFIS), sts); ++ } ++ + /* + * With CFI clear in the Global Command register, we should be + * protected from dangerous (i.e. compatibility) interrupts +diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c +index 62eb4b7caff33..a9208ab127080 100644 +--- a/drivers/md/dm-cache-metadata.c ++++ b/drivers/md/dm-cache-metadata.c +@@ -508,12 +508,16 @@ static int __create_persistent_data_objects(struct dm_cache_metadata *cmd, + CACHE_MAX_CONCURRENT_LOCKS); + if (IS_ERR(cmd->bm)) { + DMERR("could not create block manager"); +- return PTR_ERR(cmd->bm); ++ r = PTR_ERR(cmd->bm); ++ cmd->bm = NULL; ++ return r; + } + + r = __open_or_format_metadata(cmd, may_format_device); +- if (r) ++ if (r) { + dm_block_manager_destroy(cmd->bm); ++ cmd->bm = NULL; ++ } + + return r; + } +diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c +index d20f4023f6c12..b5bf2ecfaf913 100644 +--- a/drivers/md/dm-thin-metadata.c ++++ b/drivers/md/dm-thin-metadata.c +@@ -700,12 +700,16 @@ static int __create_persistent_data_objects(struct dm_pool_metadata *pmd, bool f + THIN_MAX_CONCURRENT_LOCKS); + if (IS_ERR(pmd->bm)) { + DMERR("could not create block manager"); +- return PTR_ERR(pmd->bm); ++ r = PTR_ERR(pmd->bm); ++ pmd->bm = NULL; ++ return r; + } + + r = __open_or_format_metadata(pmd, format_device); +- if (r) ++ if (r) { + dm_block_manager_destroy(pmd->bm); ++ pmd->bm = NULL; ++ } + + return r; + } +diff --git a/drivers/net/ethernet/arc/emac_mdio.c b/drivers/net/ethernet/arc/emac_mdio.c +index a22403c688c95..337cfce78aef2 100644 +--- a/drivers/net/ethernet/arc/emac_mdio.c ++++ b/drivers/net/ethernet/arc/emac_mdio.c +@@ -152,6 +152,7 @@ int arc_mdio_probe(struct arc_emac_priv *priv) + if (IS_ERR(data->reset_gpio)) { + error = PTR_ERR(data->reset_gpio); + dev_err(priv->dev, "Failed to request gpio: %d\n", error); ++ mdiobus_free(bus); + return error; + } + +diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c +index 421cbba9a3bc8..dc34cfa2a58fc 100644 +--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c ++++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c +@@ -5589,14 +5589,14 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) + } + } + +- bnxt_enable_napi(bp); +- + rc = bnxt_init_nic(bp, irq_re_init); + if (rc) { + netdev_err(bp->dev, "bnxt_init_nic err: %x\n", rc); +- goto open_err; ++ goto open_err_irq; + } + ++ bnxt_enable_napi(bp); ++ + if (link_re_init) { + mutex_lock(&bp->link_lock); + rc = bnxt_update_phy_setting(bp); +@@ -5618,9 +5618,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) + + return 0; + +-open_err: +- bnxt_disable_napi(bp); +- + open_err_irq: + bnxt_del_napi(bp); + +@@ -7085,6 +7082,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) + + bnxt_parse_log_pcie_link(bp); + ++ pci_save_state(pdev); + return 0; + + init_err: +@@ -7158,6 +7156,8 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev) + "Cannot re-enable PCI device after reset.\n"); + } else { + pci_set_master(pdev); ++ pci_restore_state(pdev); ++ pci_save_state(pdev); + + if (netif_running(netdev)) + err = bnxt_open(netdev); +diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +index 427d4dbc97354..ac03bba10e4fd 100644 +--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c ++++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +@@ -1457,6 +1457,9 @@ static int bnxt_get_nvram_directory(struct net_device *dev, u32 len, u8 *data) + if (rc != 0) + return rc; + ++ if (!dir_entries || !entry_length) ++ return -EIO; ++ + /* Insert 2 bytes of directory info (count and size of entries) */ + if (len < 2) + return -EINVAL; +diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c +index 5790b35064a8d..2db6102ed5848 100644 +--- a/drivers/net/ethernet/broadcom/tg3.c ++++ b/drivers/net/ethernet/broadcom/tg3.c +@@ -7201,8 +7201,8 @@ static inline void tg3_reset_task_schedule(struct tg3 *tp) + + static inline void tg3_reset_task_cancel(struct tg3 *tp) + { +- cancel_work_sync(&tp->reset_task); +- tg3_flag_clear(tp, RESET_TASK_PENDING); ++ if (test_and_clear_bit(TG3_FLAG_RESET_TASK_PENDING, tp->tg3_flags)) ++ cancel_work_sync(&tp->reset_task); + tg3_flag_clear(tp, TX_RECOVERY_PENDING); + } + +@@ -11174,18 +11174,27 @@ static void tg3_reset_task(struct work_struct *work) + + tg3_halt(tp, RESET_KIND_SHUTDOWN, 0); + err = tg3_init_hw(tp, true); +- if (err) ++ if (err) { ++ tg3_full_unlock(tp); ++ tp->irq_sync = 0; ++ tg3_napi_enable(tp); ++ /* Clear this flag so that tg3_reset_task_cancel() will not ++ * call cancel_work_sync() and wait forever. ++ */ ++ tg3_flag_clear(tp, RESET_TASK_PENDING); ++ dev_close(tp->dev); + goto out; ++ } + + tg3_netif_start(tp); + +-out: + tg3_full_unlock(tp); + + if (!err) + tg3_phy_start(tp); + + tg3_flag_clear(tp, RESET_TASK_PENDING); ++out: + rtnl_unlock(); + } + +diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c +index 24a815997ec57..796f81106b432 100644 +--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c ++++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c +@@ -1990,8 +1990,10 @@ static int hns_nic_dev_probe(struct platform_device *pdev) + priv->enet_ver = AE_VERSION_1; + else if (acpi_dev_found(hns_enet_acpi_match[1].id)) + priv->enet_ver = AE_VERSION_2; +- else +- return -ENXIO; ++ else { ++ ret = -ENXIO; ++ goto out_read_prop_fail; ++ } + + /* try to find port-idx-in-ae first */ + ret = acpi_node_get_property_reference(dev->fwnode, +@@ -2003,7 +2005,8 @@ static int hns_nic_dev_probe(struct platform_device *pdev) + priv->fwnode = acpi_fwnode_handle(args.adev); + } else { + dev_err(dev, "cannot read cfg data from OF or acpi\n"); +- return -ENXIO; ++ ret = -ENXIO; ++ goto out_read_prop_fail; + } + + ret = device_property_read_u32(dev, "port-idx-in-ae", &port_id); +diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c +index 3637474cab8a0..50683693d9fc3 100644 +--- a/drivers/net/ethernet/mellanox/mlx4/mr.c ++++ b/drivers/net/ethernet/mellanox/mlx4/mr.c +@@ -114,7 +114,7 @@ static int mlx4_buddy_init(struct mlx4_buddy *buddy, int max_order) + goto err_out; + + for (i = 0; i <= buddy->max_order; ++i) { +- s = BITS_TO_LONGS(1 << (buddy->max_order - i)); ++ s = BITS_TO_LONGS(1UL << (buddy->max_order - i)); + buddy->bits[i] = kcalloc(s, sizeof (long), GFP_KERNEL | __GFP_NOWARN); + if (!buddy->bits[i]) { + buddy->bits[i] = vzalloc(s * sizeof(long)); +diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c +index 93d3152752ff4..a5de56bcbac08 100644 +--- a/drivers/net/ethernet/renesas/ravb_main.c ++++ b/drivers/net/ethernet/renesas/ravb_main.c +@@ -1336,6 +1336,51 @@ static inline int ravb_hook_irq(unsigned int irq, irq_handler_t handler, + return error; + } + ++/* MDIO bus init function */ ++static int ravb_mdio_init(struct ravb_private *priv) ++{ ++ struct platform_device *pdev = priv->pdev; ++ struct device *dev = &pdev->dev; ++ int error; ++ ++ /* Bitbang init */ ++ priv->mdiobb.ops = &bb_ops; ++ ++ /* MII controller setting */ ++ priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb); ++ if (!priv->mii_bus) ++ return -ENOMEM; ++ ++ /* Hook up MII support for ethtool */ ++ priv->mii_bus->name = "ravb_mii"; ++ priv->mii_bus->parent = dev; ++ snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", ++ pdev->name, pdev->id); ++ ++ /* Register MDIO bus */ ++ error = of_mdiobus_register(priv->mii_bus, dev->of_node); ++ if (error) ++ goto out_free_bus; ++ ++ return 0; ++ ++out_free_bus: ++ free_mdio_bitbang(priv->mii_bus); ++ return error; ++} ++ ++/* MDIO bus release function */ ++static int ravb_mdio_release(struct ravb_private *priv) ++{ ++ /* Unregister mdio bus */ ++ mdiobus_unregister(priv->mii_bus); ++ ++ /* Free bitbang info */ ++ free_mdio_bitbang(priv->mii_bus); ++ ++ return 0; ++} ++ + /* Network device open function for Ethernet AVB */ + static int ravb_open(struct net_device *ndev) + { +@@ -1344,6 +1389,13 @@ static int ravb_open(struct net_device *ndev) + struct device *dev = &pdev->dev; + int error; + ++ /* MDIO bus init */ ++ error = ravb_mdio_init(priv); ++ if (error) { ++ netdev_err(ndev, "failed to initialize MDIO\n"); ++ return error; ++ } ++ + napi_enable(&priv->napi[RAVB_BE]); + napi_enable(&priv->napi[RAVB_NC]); + +@@ -1421,6 +1473,7 @@ out_free_irq: + out_napi_off: + napi_disable(&priv->napi[RAVB_NC]); + napi_disable(&priv->napi[RAVB_BE]); ++ ravb_mdio_release(priv); + return error; + } + +@@ -1718,6 +1771,8 @@ static int ravb_close(struct net_device *ndev) + ravb_ring_free(ndev, RAVB_BE); + ravb_ring_free(ndev, RAVB_NC); + ++ ravb_mdio_release(priv); ++ + return 0; + } + +@@ -1820,51 +1875,6 @@ static const struct net_device_ops ravb_netdev_ops = { + .ndo_change_mtu = eth_change_mtu, + }; + +-/* MDIO bus init function */ +-static int ravb_mdio_init(struct ravb_private *priv) +-{ +- struct platform_device *pdev = priv->pdev; +- struct device *dev = &pdev->dev; +- int error; +- +- /* Bitbang init */ +- priv->mdiobb.ops = &bb_ops; +- +- /* MII controller setting */ +- priv->mii_bus = alloc_mdio_bitbang(&priv->mdiobb); +- if (!priv->mii_bus) +- return -ENOMEM; +- +- /* Hook up MII support for ethtool */ +- priv->mii_bus->name = "ravb_mii"; +- priv->mii_bus->parent = dev; +- snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", +- pdev->name, pdev->id); +- +- /* Register MDIO bus */ +- error = of_mdiobus_register(priv->mii_bus, dev->of_node); +- if (error) +- goto out_free_bus; +- +- return 0; +- +-out_free_bus: +- free_mdio_bitbang(priv->mii_bus); +- return error; +-} +- +-/* MDIO bus release function */ +-static int ravb_mdio_release(struct ravb_private *priv) +-{ +- /* Unregister mdio bus */ +- mdiobus_unregister(priv->mii_bus); +- +- /* Free bitbang info */ +- free_mdio_bitbang(priv->mii_bus); +- +- return 0; +-} +- + static const struct of_device_id ravb_match_table[] = { + { .compatible = "renesas,etheravb-r8a7790", .data = (void *)RCAR_GEN2 }, + { .compatible = "renesas,etheravb-r8a7794", .data = (void *)RCAR_GEN2 }, +@@ -2069,13 +2079,6 @@ static int ravb_probe(struct platform_device *pdev) + eth_hw_addr_random(ndev); + } + +- /* MDIO bus init */ +- error = ravb_mdio_init(priv); +- if (error) { +- dev_err(&pdev->dev, "failed to initialize MDIO\n"); +- goto out_dma_free; +- } +- + netif_napi_add(ndev, &priv->napi[RAVB_BE], ravb_poll, 64); + netif_napi_add(ndev, &priv->napi[RAVB_NC], ravb_poll, 64); + +@@ -2095,8 +2098,6 @@ static int ravb_probe(struct platform_device *pdev) + out_napi_del: + netif_napi_del(&priv->napi[RAVB_NC]); + netif_napi_del(&priv->napi[RAVB_BE]); +- ravb_mdio_release(priv); +-out_dma_free: + dma_free_coherent(ndev->dev.parent, priv->desc_bat_size, priv->desc_bat, + priv->desc_bat_dma); + +@@ -2129,7 +2130,6 @@ static int ravb_remove(struct platform_device *pdev) + unregister_netdev(ndev); + netif_napi_del(&priv->napi[RAVB_NC]); + netif_napi_del(&priv->napi[RAVB_BE]); +- ravb_mdio_release(priv); + pm_runtime_disable(&pdev->dev); + free_netdev(ndev); + platform_set_drvdata(pdev, NULL); +diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c +index 3dbb0646b0245..541c06c884e55 100644 +--- a/drivers/net/usb/asix_common.c ++++ b/drivers/net/usb/asix_common.c +@@ -277,7 +277,7 @@ int asix_read_phy_addr(struct usbnet *dev, int internal) + + netdev_dbg(dev->net, "asix_get_phy_addr()\n"); + +- if (ret < 0) { ++ if (ret < 2) { + netdev_err(dev->net, "Error reading PHYID register: %02x\n", ret); + goto out; + } +diff --git a/drivers/net/usb/dm9601.c b/drivers/net/usb/dm9601.c +index 0b4bdd39106b0..fb18801d0fe7b 100644 +--- a/drivers/net/usb/dm9601.c ++++ b/drivers/net/usb/dm9601.c +@@ -624,6 +624,10 @@ static const struct usb_device_id products[] = { + USB_DEVICE(0x0a46, 0x1269), /* DM9621A USB to Fast Ethernet Adapter */ + .driver_info = (unsigned long)&dm9601_info, + }, ++ { ++ USB_DEVICE(0x0586, 0x3427), /* ZyXEL Keenetic Plus DSL xDSL modem */ ++ .driver_info = (unsigned long)&dm9601_info, ++ }, + {}, // END + }; + +diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c +index 254a27295f41d..74c925cd19a93 100644 +--- a/drivers/net/usb/qmi_wwan.c ++++ b/drivers/net/usb/qmi_wwan.c +@@ -890,6 +890,7 @@ static const struct usb_device_id products[] = { + {QMI_FIXED_INTF(0x19d2, 0x2002, 4)}, /* ZTE (Vodafone) K3765-Z */ + {QMI_FIXED_INTF(0x2001, 0x7e19, 4)}, /* D-Link DWM-221 B1 */ + {QMI_FIXED_INTF(0x2001, 0x7e35, 4)}, /* D-Link DWM-222 */ ++ {QMI_FIXED_INTF(0x2001, 0x7e3d, 4)}, /* D-Link DWM-222 A2 */ + {QMI_FIXED_INTF(0x2020, 0x2031, 4)}, /* Olicard 600 */ + {QMI_FIXED_INTF(0x2020, 0x2033, 4)}, /* BroadMobi BM806U */ + {QMI_FIXED_INTF(0x2020, 0x2060, 4)}, /* BroadMobi BM818 */ +@@ -910,6 +911,8 @@ static const struct usb_device_id products[] = { + {QMI_FIXED_INTF(0x1199, 0x9056, 8)}, /* Sierra Wireless Modem */ + {QMI_FIXED_INTF(0x1199, 0x9057, 8)}, + {QMI_FIXED_INTF(0x1199, 0x9061, 8)}, /* Sierra Wireless Modem */ ++ {QMI_FIXED_INTF(0x1199, 0x9063, 8)}, /* Sierra Wireless EM7305 */ ++ {QMI_FIXED_INTF(0x1199, 0x9063, 10)}, /* Sierra Wireless EM7305 */ + {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx */ + {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx */ + {QMI_FIXED_INTF(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ +@@ -923,10 +926,13 @@ static const struct usb_device_id products[] = { + {QMI_FIXED_INTF(0x2357, 0x9000, 4)}, /* TP-LINK MA260 */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1031, 3)}, /* Telit LE910C1-EUX */ + {QMI_QUIRK_SET_DTR(0x1bc7, 0x1040, 2)}, /* Telit LE922A */ ++ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)}, /* Telit FN980 */ + {QMI_FIXED_INTF(0x1bc7, 0x1100, 3)}, /* Telit ME910 */ + {QMI_FIXED_INTF(0x1bc7, 0x1101, 3)}, /* Telit ME910 dual modem */ + {QMI_FIXED_INTF(0x1bc7, 0x1200, 5)}, /* Telit LE920 */ +- {QMI_FIXED_INTF(0x1bc7, 0x1201, 2)}, /* Telit LE920 */ ++ {QMI_QUIRK_SET_DTR(0x1bc7, 0x1201, 2)}, /* Telit LE920, LE920A4 */ ++ {QMI_FIXED_INTF(0x1c9e, 0x9801, 3)}, /* Telewell TW-3G HSPA+ */ ++ {QMI_FIXED_INTF(0x1c9e, 0x9803, 4)}, /* Telewell TW-3G HSPA+ */ + {QMI_FIXED_INTF(0x1c9e, 0x9b01, 3)}, /* XS Stick W100-2 from 4G Systems */ + {QMI_FIXED_INTF(0x0b3c, 0xc000, 4)}, /* Olivetti Olicard 100 */ + {QMI_FIXED_INTF(0x0b3c, 0xc001, 4)}, /* Olivetti Olicard 120 */ +diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h +index bd29e598bac18..2a820c1fdfcde 100644 +--- a/drivers/nvdimm/nd.h ++++ b/drivers/nvdimm/nd.h +@@ -29,7 +29,6 @@ enum { + * BTT instance + */ + ND_MAX_LANES = 256, +- SECTOR_SHIFT = 9, + INT_LBASIZE_ALIGNMENT = 64, + }; + +diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c +index 96ea6c76be6e5..63b87a8472762 100644 +--- a/drivers/nvme/target/core.c ++++ b/drivers/nvme/target/core.c +@@ -205,6 +205,9 @@ static void nvmet_keep_alive_timer(struct work_struct *work) + + static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl) + { ++ if (unlikely(ctrl->kato == 0)) ++ return; ++ + pr_debug("ctrl %d start keep-alive timer for %d secs\n", + ctrl->cntlid, ctrl->kato); + +@@ -214,6 +217,9 @@ static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl) + + static void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl) + { ++ if (unlikely(ctrl->kato == 0)) ++ return; ++ + pr_debug("ctrl %d stop keep-alive\n", ctrl->cntlid); + + cancel_delayed_work_sync(&ctrl->ka_work); +diff --git a/drivers/scsi/gdth.h b/drivers/scsi/gdth.h +index 3fd8b83ffbf9f..8039c809cef27 100644 +--- a/drivers/scsi/gdth.h ++++ b/drivers/scsi/gdth.h +@@ -177,9 +177,6 @@ + #define MSG_SIZE 34 /* size of message structure */ + #define MSG_REQUEST 0 /* async. event: message */ + +-/* cacheservice defines */ +-#define SECTOR_SIZE 0x200 /* always 512 bytes per sec. */ +- + /* DPMEM constants */ + #define DPMEM_MAGIC 0xC0FFEE11 + #define IC_HEADER_BYTES 48 +diff --git a/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c b/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c +index d255d33da9eb3..02e71d461d5c5 100644 +--- a/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c ++++ b/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c +@@ -49,20 +49,21 @@ static struct temp_sensor_data omap4430_mpu_temp_sensor_data = { + + /* + * Temperature values in milli degree celsius +- * ADC code values from 530 to 923 ++ * ADC code values from 13 to 107, see TRM ++ * "18.4.10.2.3 ADC Codes Versus Temperature". + */ + static const int + omap4430_adc_to_temp[OMAP4430_ADC_END_VALUE - OMAP4430_ADC_START_VALUE + 1] = { +- -38000, -35000, -34000, -32000, -30000, -28000, -26000, -24000, -22000, +- -20000, -18000, -17000, -15000, -13000, -12000, -10000, -8000, -6000, +- -5000, -3000, -1000, 0, 2000, 3000, 5000, 6000, 8000, 10000, 12000, +- 13000, 15000, 17000, 19000, 21000, 23000, 25000, 27000, 28000, 30000, +- 32000, 33000, 35000, 37000, 38000, 40000, 42000, 43000, 45000, 47000, +- 48000, 50000, 52000, 53000, 55000, 57000, 58000, 60000, 62000, 64000, +- 66000, 68000, 70000, 71000, 73000, 75000, 77000, 78000, 80000, 82000, +- 83000, 85000, 87000, 88000, 90000, 92000, 93000, 95000, 97000, 98000, +- 100000, 102000, 103000, 105000, 107000, 109000, 111000, 113000, 115000, +- 117000, 118000, 120000, 122000, 123000, ++ -40000, -38000, -35000, -34000, -32000, -30000, -28000, -26000, -24000, ++ -22000, -20000, -18500, -17000, -15000, -13500, -12000, -10000, -8000, ++ -6500, -5000, -3500, -1500, 0, 2000, 3500, 5000, 6500, 8500, 10000, ++ 12000, 13500, 15000, 17000, 19000, 21000, 23000, 25000, 27000, 28500, ++ 30000, 32000, 33500, 35000, 37000, 38500, 40000, 42000, 43500, 45000, ++ 47000, 48500, 50000, 52000, 53500, 55000, 57000, 58500, 60000, 62000, ++ 64000, 66000, 68000, 70000, 71500, 73500, 75000, 77000, 78500, 80000, ++ 82000, 83500, 85000, 87000, 88500, 90000, 92000, 93500, 95000, 97000, ++ 98500, 100000, 102000, 103500, 105000, 107000, 109000, 111000, 113000, ++ 115000, 117000, 118500, 120000, 122000, 123500, 125000, + }; + + /* OMAP4430 data */ +diff --git a/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h b/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h +index 6f2de3a3356d4..86850082b24b9 100644 +--- a/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h ++++ b/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h +@@ -67,9 +67,13 @@ + * and thresholds for OMAP4430. + */ + +-/* ADC conversion table limits */ +-#define OMAP4430_ADC_START_VALUE 0 +-#define OMAP4430_ADC_END_VALUE 127 ++/* ++ * ADC conversion table limits. Ignore values outside the TRM listed ++ * range to avoid bogus thermal shutdowns. See omap4430 TRM chapter ++ * "18.4.10.2.3 ADC Codes Versus Temperature". ++ */ ++#define OMAP4430_ADC_START_VALUE 13 ++#define OMAP4430_ADC_END_VALUE 107 + /* bandgap clock limits (no control on 4430) */ + #define OMAP4430_MAX_FREQ 32768 + #define OMAP4430_MIN_FREQ 32768 +diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c +index c94167d871789..2254c281cc766 100644 +--- a/drivers/vfio/pci/vfio_pci.c ++++ b/drivers/vfio/pci/vfio_pci.c +@@ -29,6 +29,7 @@ + #include <linux/vfio.h> + #include <linux/vgaarb.h> + #include <linux/nospec.h> ++#include <linux/mm.h> + + #include "vfio_pci_private.h" + +@@ -181,6 +182,7 @@ no_mmap: + + static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev); + static void vfio_pci_disable(struct vfio_pci_device *vdev); ++static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data); + + /* + * INTx masking requires the ability to disable INTx signaling via PCI_COMMAND +@@ -656,6 +658,12 @@ int vfio_pci_register_dev_region(struct vfio_pci_device *vdev, + return 0; + } + ++struct vfio_devices { ++ struct vfio_device **devices; ++ int cur_index; ++ int max_index; ++}; ++ + static long vfio_pci_ioctl(void *device_data, + unsigned int cmd, unsigned long arg) + { +@@ -729,7 +737,7 @@ static long vfio_pci_ioctl(void *device_data, + { + void __iomem *io; + size_t size; +- u16 orig_cmd; ++ u16 cmd; + + info.offset = VFIO_PCI_INDEX_TO_OFFSET(info.index); + info.flags = 0; +@@ -749,10 +757,7 @@ static long vfio_pci_ioctl(void *device_data, + * Is it really there? Enable memory decode for + * implicit access in pci_map_rom(). + */ +- pci_read_config_word(pdev, PCI_COMMAND, &orig_cmd); +- pci_write_config_word(pdev, PCI_COMMAND, +- orig_cmd | PCI_COMMAND_MEMORY); +- ++ cmd = vfio_pci_memory_lock_and_enable(vdev); + io = pci_map_rom(pdev, &size); + if (io) { + info.flags = VFIO_REGION_INFO_FLAG_READ; +@@ -760,8 +765,8 @@ static long vfio_pci_ioctl(void *device_data, + } else { + info.size = 0; + } ++ vfio_pci_memory_unlock_and_restore(vdev, cmd); + +- pci_write_config_word(pdev, PCI_COMMAND, orig_cmd); + break; + } + case VFIO_PCI_VGA_REGION_INDEX: +@@ -909,8 +914,16 @@ static long vfio_pci_ioctl(void *device_data, + return ret; + + } else if (cmd == VFIO_DEVICE_RESET) { +- return vdev->reset_works ? +- pci_try_reset_function(vdev->pdev) : -EINVAL; ++ int ret; ++ ++ if (!vdev->reset_works) ++ return -EINVAL; ++ ++ vfio_pci_zap_and_down_write_memory_lock(vdev); ++ ret = pci_try_reset_function(vdev->pdev); ++ up_write(&vdev->memory_lock); ++ ++ return ret; + + } else if (cmd == VFIO_DEVICE_GET_PCI_HOT_RESET_INFO) { + struct vfio_pci_hot_reset_info hdr; +@@ -990,8 +1003,9 @@ reset_info_exit: + int32_t *group_fds; + struct vfio_pci_group_entry *groups; + struct vfio_pci_group_info info; ++ struct vfio_devices devs = { .cur_index = 0 }; + bool slot = false; +- int i, count = 0, ret = 0; ++ int i, group_idx, mem_idx = 0, count = 0, ret = 0; + + minsz = offsetofend(struct vfio_pci_hot_reset, count); + +@@ -1043,9 +1057,9 @@ reset_info_exit: + * user interface and store the group and iommu ID. This + * ensures the group is held across the reset. + */ +- for (i = 0; i < hdr.count; i++) { ++ for (group_idx = 0; group_idx < hdr.count; group_idx++) { + struct vfio_group *group; +- struct fd f = fdget(group_fds[i]); ++ struct fd f = fdget(group_fds[group_idx]); + if (!f.file) { + ret = -EBADF; + break; +@@ -1058,8 +1072,9 @@ reset_info_exit: + break; + } + +- groups[i].group = group; +- groups[i].id = vfio_external_user_iommu_id(group); ++ groups[group_idx].group = group; ++ groups[group_idx].id = ++ vfio_external_user_iommu_id(group); + } + + kfree(group_fds); +@@ -1078,14 +1093,65 @@ reset_info_exit: + ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, + vfio_pci_validate_devs, + &info, slot); +- if (!ret) +- /* User has access, do the reset */ +- ret = slot ? pci_try_reset_slot(vdev->pdev->slot) : +- pci_try_reset_bus(vdev->pdev->bus); ++ ++ if (ret) ++ goto hot_reset_release; ++ ++ devs.max_index = count; ++ devs.devices = kcalloc(count, sizeof(struct vfio_device *), ++ GFP_KERNEL); ++ if (!devs.devices) { ++ ret = -ENOMEM; ++ goto hot_reset_release; ++ } ++ ++ /* ++ * We need to get memory_lock for each device, but devices ++ * can share mmap_sem, therefore we need to zap and hold ++ * the vma_lock for each device, and only then get each ++ * memory_lock. ++ */ ++ ret = vfio_pci_for_each_slot_or_bus(vdev->pdev, ++ vfio_pci_try_zap_and_vma_lock_cb, ++ &devs, slot); ++ if (ret) ++ goto hot_reset_release; ++ ++ for (; mem_idx < devs.cur_index; mem_idx++) { ++ struct vfio_pci_device *tmp; ++ ++ tmp = vfio_device_data(devs.devices[mem_idx]); ++ ++ ret = down_write_trylock(&tmp->memory_lock); ++ if (!ret) { ++ ret = -EBUSY; ++ goto hot_reset_release; ++ } ++ mutex_unlock(&tmp->vma_lock); ++ } ++ ++ /* User has access, do the reset */ ++ ret = slot ? pci_try_reset_slot(vdev->pdev->slot) : ++ pci_try_reset_bus(vdev->pdev->bus); + + hot_reset_release: +- for (i--; i >= 0; i--) +- vfio_group_put_external_user(groups[i].group); ++ for (i = 0; i < devs.cur_index; i++) { ++ struct vfio_device *device; ++ struct vfio_pci_device *tmp; ++ ++ device = devs.devices[i]; ++ tmp = vfio_device_data(device); ++ ++ if (i < mem_idx) ++ up_write(&tmp->memory_lock); ++ else ++ mutex_unlock(&tmp->vma_lock); ++ vfio_device_put(device); ++ } ++ kfree(devs.devices); ++ ++ for (group_idx--; group_idx >= 0; group_idx--) ++ vfio_group_put_external_user(groups[group_idx].group); + + kfree(groups); + return ret; +@@ -1144,6 +1210,201 @@ static ssize_t vfio_pci_write(void *device_data, const char __user *buf, + return vfio_pci_rw(device_data, (char __user *)buf, count, ppos, true); + } + ++/* Return 1 on zap and vma_lock acquired, 0 on contention (only with @try) */ ++static int vfio_pci_zap_and_vma_lock(struct vfio_pci_device *vdev, bool try) ++{ ++ struct vfio_pci_mmap_vma *mmap_vma, *tmp; ++ ++ /* ++ * Lock ordering: ++ * vma_lock is nested under mmap_sem for vm_ops callback paths. ++ * The memory_lock semaphore is used by both code paths calling ++ * into this function to zap vmas and the vm_ops.fault callback ++ * to protect the memory enable state of the device. ++ * ++ * When zapping vmas we need to maintain the mmap_sem => vma_lock ++ * ordering, which requires using vma_lock to walk vma_list to ++ * acquire an mm, then dropping vma_lock to get the mmap_sem and ++ * reacquiring vma_lock. This logic is derived from similar ++ * requirements in uverbs_user_mmap_disassociate(). ++ * ++ * mmap_sem must always be the top-level lock when it is taken. ++ * Therefore we can only hold the memory_lock write lock when ++ * vma_list is empty, as we'd need to take mmap_sem to clear ++ * entries. vma_list can only be guaranteed empty when holding ++ * vma_lock, thus memory_lock is nested under vma_lock. ++ * ++ * This enables the vm_ops.fault callback to acquire vma_lock, ++ * followed by memory_lock read lock, while already holding ++ * mmap_sem without risk of deadlock. ++ */ ++ while (1) { ++ struct mm_struct *mm = NULL; ++ ++ if (try) { ++ if (!mutex_trylock(&vdev->vma_lock)) ++ return 0; ++ } else { ++ mutex_lock(&vdev->vma_lock); ++ } ++ while (!list_empty(&vdev->vma_list)) { ++ mmap_vma = list_first_entry(&vdev->vma_list, ++ struct vfio_pci_mmap_vma, ++ vma_next); ++ mm = mmap_vma->vma->vm_mm; ++ if (mmget_not_zero(mm)) ++ break; ++ ++ list_del(&mmap_vma->vma_next); ++ kfree(mmap_vma); ++ mm = NULL; ++ } ++ if (!mm) ++ return 1; ++ mutex_unlock(&vdev->vma_lock); ++ ++ if (try) { ++ if (!down_read_trylock(&mm->mmap_sem)) { ++ mmput(mm); ++ return 0; ++ } ++ } else { ++ down_read(&mm->mmap_sem); ++ } ++ if (mmget_still_valid(mm)) { ++ if (try) { ++ if (!mutex_trylock(&vdev->vma_lock)) { ++ up_read(&mm->mmap_sem); ++ mmput(mm); ++ return 0; ++ } ++ } else { ++ mutex_lock(&vdev->vma_lock); ++ } ++ list_for_each_entry_safe(mmap_vma, tmp, ++ &vdev->vma_list, vma_next) { ++ struct vm_area_struct *vma = mmap_vma->vma; ++ ++ if (vma->vm_mm != mm) ++ continue; ++ ++ list_del(&mmap_vma->vma_next); ++ kfree(mmap_vma); ++ ++ zap_vma_ptes(vma, vma->vm_start, ++ vma->vm_end - vma->vm_start); ++ } ++ mutex_unlock(&vdev->vma_lock); ++ } ++ up_read(&mm->mmap_sem); ++ mmput(mm); ++ } ++} ++ ++void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_device *vdev) ++{ ++ vfio_pci_zap_and_vma_lock(vdev, false); ++ down_write(&vdev->memory_lock); ++ mutex_unlock(&vdev->vma_lock); ++} ++ ++u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_device *vdev) ++{ ++ u16 cmd; ++ ++ down_write(&vdev->memory_lock); ++ pci_read_config_word(vdev->pdev, PCI_COMMAND, &cmd); ++ if (!(cmd & PCI_COMMAND_MEMORY)) ++ pci_write_config_word(vdev->pdev, PCI_COMMAND, ++ cmd | PCI_COMMAND_MEMORY); ++ ++ return cmd; ++} ++ ++void vfio_pci_memory_unlock_and_restore(struct vfio_pci_device *vdev, u16 cmd) ++{ ++ pci_write_config_word(vdev->pdev, PCI_COMMAND, cmd); ++ up_write(&vdev->memory_lock); ++} ++ ++/* Caller holds vma_lock */ ++static int __vfio_pci_add_vma(struct vfio_pci_device *vdev, ++ struct vm_area_struct *vma) ++{ ++ struct vfio_pci_mmap_vma *mmap_vma; ++ ++ mmap_vma = kmalloc(sizeof(*mmap_vma), GFP_KERNEL); ++ if (!mmap_vma) ++ return -ENOMEM; ++ ++ mmap_vma->vma = vma; ++ list_add(&mmap_vma->vma_next, &vdev->vma_list); ++ ++ return 0; ++} ++ ++/* ++ * Zap mmaps on open so that we can fault them in on access and therefore ++ * our vma_list only tracks mappings accessed since last zap. ++ */ ++static void vfio_pci_mmap_open(struct vm_area_struct *vma) ++{ ++ zap_vma_ptes(vma, vma->vm_start, vma->vm_end - vma->vm_start); ++} ++ ++static void vfio_pci_mmap_close(struct vm_area_struct *vma) ++{ ++ struct vfio_pci_device *vdev = vma->vm_private_data; ++ struct vfio_pci_mmap_vma *mmap_vma; ++ ++ mutex_lock(&vdev->vma_lock); ++ list_for_each_entry(mmap_vma, &vdev->vma_list, vma_next) { ++ if (mmap_vma->vma == vma) { ++ list_del(&mmap_vma->vma_next); ++ kfree(mmap_vma); ++ break; ++ } ++ } ++ mutex_unlock(&vdev->vma_lock); ++} ++ ++static int vfio_pci_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) ++{ ++ struct vfio_pci_device *vdev = vma->vm_private_data; ++ int ret = VM_FAULT_NOPAGE; ++ ++ mutex_lock(&vdev->vma_lock); ++ down_read(&vdev->memory_lock); ++ ++ if (!__vfio_pci_memory_enabled(vdev)) { ++ ret = VM_FAULT_SIGBUS; ++ mutex_unlock(&vdev->vma_lock); ++ goto up_out; ++ } ++ ++ if (__vfio_pci_add_vma(vdev, vma)) { ++ ret = VM_FAULT_OOM; ++ mutex_unlock(&vdev->vma_lock); ++ goto up_out; ++ } ++ ++ mutex_unlock(&vdev->vma_lock); ++ ++ if (remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, ++ vma->vm_end - vma->vm_start, vma->vm_page_prot)) ++ ret = VM_FAULT_SIGBUS; ++ ++up_out: ++ up_read(&vdev->memory_lock); ++ return ret; ++} ++ ++static const struct vm_operations_struct vfio_pci_mmap_ops = { ++ .open = vfio_pci_mmap_open, ++ .close = vfio_pci_mmap_close, ++ .fault = vfio_pci_mmap_fault, ++}; ++ + static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma) + { + struct vfio_pci_device *vdev = device_data; +@@ -1209,8 +1470,14 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma) + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + vma->vm_pgoff = (pci_resource_start(pdev, index) >> PAGE_SHIFT) + pgoff; + +- return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, +- req_len, vma->vm_page_prot); ++ /* ++ * See remap_pfn_range(), called from vfio_pci_fault() but we can't ++ * change vm_flags within the fault handler. Set them now. ++ */ ++ vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP; ++ vma->vm_ops = &vfio_pci_mmap_ops; ++ ++ return 0; + } + + static void vfio_pci_request(void *device_data, unsigned int count) +@@ -1268,6 +1535,9 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) + mutex_init(&vdev->igate); + spin_lock_init(&vdev->irqlock); + ++ mutex_init(&vdev->vma_lock); ++ INIT_LIST_HEAD(&vdev->vma_list); ++ init_rwsem(&vdev->memory_lock); + ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev); + if (ret) { + vfio_iommu_group_put(group, &pdev->dev); +@@ -1361,12 +1631,6 @@ static struct pci_driver vfio_pci_driver = { + .err_handler = &vfio_err_handlers, + }; + +-struct vfio_devices { +- struct vfio_device **devices; +- int cur_index; +- int max_index; +-}; +- + static int vfio_pci_get_devs(struct pci_dev *pdev, void *data) + { + struct vfio_devices *devs = data; +@@ -1388,6 +1652,39 @@ static int vfio_pci_get_devs(struct pci_dev *pdev, void *data) + return 0; + } + ++static int vfio_pci_try_zap_and_vma_lock_cb(struct pci_dev *pdev, void *data) ++{ ++ struct vfio_devices *devs = data; ++ struct vfio_device *device; ++ struct vfio_pci_device *vdev; ++ ++ if (devs->cur_index == devs->max_index) ++ return -ENOSPC; ++ ++ device = vfio_device_get_from_dev(&pdev->dev); ++ if (!device) ++ return -EINVAL; ++ ++ if (pci_dev_driver(pdev) != &vfio_pci_driver) { ++ vfio_device_put(device); ++ return -EBUSY; ++ } ++ ++ vdev = vfio_device_data(device); ++ ++ /* ++ * Locking multiple devices is prone to deadlock, runaway and ++ * unwind if we hit contention. ++ */ ++ if (!vfio_pci_zap_and_vma_lock(vdev, true)) { ++ vfio_device_put(device); ++ return -EBUSY; ++ } ++ ++ devs->devices[devs->cur_index++] = device; ++ return 0; ++} ++ + /* + * Attempt to do a bus/slot reset if there are devices affected by a reset for + * this device that are needs_reset and all of the affected devices are unused +diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c +index ef45b8f5bf510..f3c2de04b20d3 100644 +--- a/drivers/vfio/pci/vfio_pci_config.c ++++ b/drivers/vfio/pci/vfio_pci_config.c +@@ -400,6 +400,20 @@ static inline void p_setd(struct perm_bits *p, int off, u32 virt, u32 write) + *(__le32 *)(&p->write[off]) = cpu_to_le32(write); + } + ++/* Caller should hold memory_lock semaphore */ ++bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev) ++{ ++ struct pci_dev *pdev = vdev->pdev; ++ u16 cmd = le16_to_cpu(*(__le16 *)&vdev->vconfig[PCI_COMMAND]); ++ ++ /* ++ * SR-IOV VF memory enable is handled by the MSE bit in the ++ * PF SR-IOV capability, there's therefore no need to trigger ++ * faults based on the virtual value. ++ */ ++ return pdev->is_virtfn || (cmd & PCI_COMMAND_MEMORY); ++} ++ + /* + * Restore the *real* BARs after we detect a FLR or backdoor reset. + * (backdoor = some device specific technique that we didn't catch) +@@ -560,13 +574,18 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos, + + new_cmd = le32_to_cpu(val); + ++ phys_io = !!(phys_cmd & PCI_COMMAND_IO); ++ virt_io = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_IO); ++ new_io = !!(new_cmd & PCI_COMMAND_IO); ++ + phys_mem = !!(phys_cmd & PCI_COMMAND_MEMORY); + virt_mem = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_MEMORY); + new_mem = !!(new_cmd & PCI_COMMAND_MEMORY); + +- phys_io = !!(phys_cmd & PCI_COMMAND_IO); +- virt_io = !!(le16_to_cpu(*virt_cmd) & PCI_COMMAND_IO); +- new_io = !!(new_cmd & PCI_COMMAND_IO); ++ if (!new_mem) ++ vfio_pci_zap_and_down_write_memory_lock(vdev); ++ else ++ down_write(&vdev->memory_lock); + + /* + * If the user is writing mem/io enable (new_mem/io) and we +@@ -583,8 +602,11 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos, + } + + count = vfio_default_config_write(vdev, pos, count, perm, offset, val); +- if (count < 0) ++ if (count < 0) { ++ if (offset == PCI_COMMAND) ++ up_write(&vdev->memory_lock); + return count; ++ } + + /* + * Save current memory/io enable bits in vconfig to allow for +@@ -595,6 +617,8 @@ static int vfio_basic_config_write(struct vfio_pci_device *vdev, int pos, + + *virt_cmd &= cpu_to_le16(~mask); + *virt_cmd |= cpu_to_le16(new_cmd & mask); ++ ++ up_write(&vdev->memory_lock); + } + + /* Emulate INTx disable */ +@@ -832,8 +856,11 @@ static int vfio_exp_config_write(struct vfio_pci_device *vdev, int pos, + pos - offset + PCI_EXP_DEVCAP, + &cap); + +- if (!ret && (cap & PCI_EXP_DEVCAP_FLR)) ++ if (!ret && (cap & PCI_EXP_DEVCAP_FLR)) { ++ vfio_pci_zap_and_down_write_memory_lock(vdev); + pci_try_reset_function(vdev->pdev); ++ up_write(&vdev->memory_lock); ++ } + } + + /* +@@ -911,8 +938,11 @@ static int vfio_af_config_write(struct vfio_pci_device *vdev, int pos, + pos - offset + PCI_AF_CAP, + &cap); + +- if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP)) ++ if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP)) { ++ vfio_pci_zap_and_down_write_memory_lock(vdev); + pci_try_reset_function(vdev->pdev); ++ up_write(&vdev->memory_lock); ++ } + } + + return count; +@@ -1705,6 +1735,15 @@ int vfio_config_init(struct vfio_pci_device *vdev) + vconfig[PCI_INTERRUPT_PIN]); + + vconfig[PCI_INTERRUPT_PIN] = 0; /* Gratuitous for good VFs */ ++ ++ /* ++ * VFs do no implement the memory enable bit of the COMMAND ++ * register therefore we'll not have it set in our initial ++ * copy of config space after pci_enable_device(). For ++ * consistency with PFs, set the virtual enable bit here. ++ */ ++ *(__le16 *)&vconfig[PCI_COMMAND] |= ++ cpu_to_le16(PCI_COMMAND_MEMORY); + } + + if (!IS_ENABLED(CONFIG_VFIO_PCI_INTX) || vdev->nointx) +diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c +index 94594dc63c417..bdfdd506bc588 100644 +--- a/drivers/vfio/pci/vfio_pci_intrs.c ++++ b/drivers/vfio/pci/vfio_pci_intrs.c +@@ -252,6 +252,7 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix) + struct pci_dev *pdev = vdev->pdev; + unsigned int flag = msix ? PCI_IRQ_MSIX : PCI_IRQ_MSI; + int ret; ++ u16 cmd; + + if (!is_irq_none(vdev)) + return -EINVAL; +@@ -261,13 +262,16 @@ static int vfio_msi_enable(struct vfio_pci_device *vdev, int nvec, bool msix) + return -ENOMEM; + + /* return the number of supported vectors if we can't get all: */ ++ cmd = vfio_pci_memory_lock_and_enable(vdev); + ret = pci_alloc_irq_vectors(pdev, 1, nvec, flag); + if (ret < nvec) { + if (ret > 0) + pci_free_irq_vectors(pdev); ++ vfio_pci_memory_unlock_and_restore(vdev, cmd); + kfree(vdev->ctx); + return ret; + } ++ vfio_pci_memory_unlock_and_restore(vdev, cmd); + + vdev->num_ctx = nvec; + vdev->irq_type = msix ? VFIO_PCI_MSIX_IRQ_INDEX : +@@ -290,6 +294,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev, + struct pci_dev *pdev = vdev->pdev; + struct eventfd_ctx *trigger; + int irq, ret; ++ u16 cmd; + + if (vector < 0 || vector >= vdev->num_ctx) + return -EINVAL; +@@ -298,7 +303,11 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev, + + if (vdev->ctx[vector].trigger) { + irq_bypass_unregister_producer(&vdev->ctx[vector].producer); ++ ++ cmd = vfio_pci_memory_lock_and_enable(vdev); + free_irq(irq, vdev->ctx[vector].trigger); ++ vfio_pci_memory_unlock_and_restore(vdev, cmd); ++ + kfree(vdev->ctx[vector].name); + eventfd_ctx_put(vdev->ctx[vector].trigger); + vdev->ctx[vector].trigger = NULL; +@@ -326,6 +335,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev, + * such a reset it would be unsuccessful. To avoid this, restore the + * cached value of the message prior to enabling. + */ ++ cmd = vfio_pci_memory_lock_and_enable(vdev); + if (msix) { + struct msi_msg msg; + +@@ -335,6 +345,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev, + + ret = request_irq(irq, vfio_msihandler, 0, + vdev->ctx[vector].name, trigger); ++ vfio_pci_memory_unlock_and_restore(vdev, cmd); + if (ret) { + kfree(vdev->ctx[vector].name); + eventfd_ctx_put(trigger); +@@ -379,6 +390,7 @@ static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix) + { + struct pci_dev *pdev = vdev->pdev; + int i; ++ u16 cmd; + + for (i = 0; i < vdev->num_ctx; i++) { + vfio_virqfd_disable(&vdev->ctx[i].unmask); +@@ -387,7 +399,9 @@ static void vfio_msi_disable(struct vfio_pci_device *vdev, bool msix) + + vfio_msi_set_block(vdev, 0, vdev->num_ctx, NULL, msix); + ++ cmd = vfio_pci_memory_lock_and_enable(vdev); + pci_free_irq_vectors(pdev); ++ vfio_pci_memory_unlock_and_restore(vdev, cmd); + + /* + * Both disable paths above use pci_intx_for_msi() to clear DisINTx +diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h +index f561ac1c78a0d..f896cebb5c2c2 100644 +--- a/drivers/vfio/pci/vfio_pci_private.h ++++ b/drivers/vfio/pci/vfio_pci_private.h +@@ -63,6 +63,11 @@ struct vfio_pci_dummy_resource { + struct list_head res_next; + }; + ++struct vfio_pci_mmap_vma { ++ struct vm_area_struct *vma; ++ struct list_head vma_next; ++}; ++ + struct vfio_pci_device { + struct pci_dev *pdev; + void __iomem *barmap[PCI_STD_RESOURCE_END + 1]; +@@ -95,6 +100,9 @@ struct vfio_pci_device { + struct eventfd_ctx *err_trigger; + struct eventfd_ctx *req_trigger; + struct list_head dummy_resources_list; ++ struct mutex vma_lock; ++ struct list_head vma_list; ++ struct rw_semaphore memory_lock; + }; + + #define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX) +@@ -130,6 +138,14 @@ extern int vfio_pci_register_dev_region(struct vfio_pci_device *vdev, + unsigned int type, unsigned int subtype, + const struct vfio_pci_regops *ops, + size_t size, u32 flags, void *data); ++ ++extern bool __vfio_pci_memory_enabled(struct vfio_pci_device *vdev); ++extern void vfio_pci_zap_and_down_write_memory_lock(struct vfio_pci_device ++ *vdev); ++extern u16 vfio_pci_memory_lock_and_enable(struct vfio_pci_device *vdev); ++extern void vfio_pci_memory_unlock_and_restore(struct vfio_pci_device *vdev, ++ u16 cmd); ++ + #ifdef CONFIG_VFIO_PCI_IGD + extern int vfio_pci_igd_init(struct vfio_pci_device *vdev); + #else +diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c +index 357243d76f108..6445461a56013 100644 +--- a/drivers/vfio/pci/vfio_pci_rdwr.c ++++ b/drivers/vfio/pci/vfio_pci_rdwr.c +@@ -122,6 +122,7 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, + size_t x_start = 0, x_end = 0; + resource_size_t end; + void __iomem *io; ++ struct resource *res = &vdev->pdev->resource[bar]; + ssize_t done; + + if (pci_resource_start(pdev, bar)) +@@ -137,6 +138,14 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, + + count = min(count, (size_t)(end - pos)); + ++ if (res->flags & IORESOURCE_MEM) { ++ down_read(&vdev->memory_lock); ++ if (!__vfio_pci_memory_enabled(vdev)) { ++ up_read(&vdev->memory_lock); ++ return -EIO; ++ } ++ } ++ + if (bar == PCI_ROM_RESOURCE) { + /* + * The ROM can fill less space than the BAR, so we start the +@@ -144,20 +153,21 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, + * filling large ROM BARs much faster. + */ + io = pci_map_rom(pdev, &x_start); +- if (!io) +- return -ENOMEM; ++ if (!io) { ++ done = -ENOMEM; ++ goto out; ++ } + x_end = end; + } else if (!vdev->barmap[bar]) { +- int ret; +- +- ret = pci_request_selected_regions(pdev, 1 << bar, "vfio"); +- if (ret) +- return ret; ++ done = pci_request_selected_regions(pdev, 1 << bar, "vfio"); ++ if (done) ++ goto out; + + io = pci_iomap(pdev, bar, 0); + if (!io) { + pci_release_selected_regions(pdev, 1 << bar); +- return -ENOMEM; ++ done = -ENOMEM; ++ goto out; + } + + vdev->barmap[bar] = io; +@@ -176,6 +186,9 @@ ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf, + + if (bar == PCI_ROM_RESOURCE) + pci_unmap_rom(pdev, io); ++out: ++ if (res->flags & IORESOURCE_MEM) ++ up_read(&vdev->memory_lock); + + return done; + } +diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c +index a9f58f3867f02..ccef02ceaad93 100644 +--- a/drivers/vfio/vfio_iommu_type1.c ++++ b/drivers/vfio/vfio_iommu_type1.c +@@ -213,6 +213,32 @@ static int put_pfn(unsigned long pfn, int prot) + return 0; + } + ++static int follow_fault_pfn(struct vm_area_struct *vma, struct mm_struct *mm, ++ unsigned long vaddr, unsigned long *pfn, ++ bool write_fault) ++{ ++ int ret; ++ ++ ret = follow_pfn(vma, vaddr, pfn); ++ if (ret) { ++ bool unlocked = false; ++ ++ ret = fixup_user_fault(NULL, mm, vaddr, ++ FAULT_FLAG_REMOTE | ++ (write_fault ? FAULT_FLAG_WRITE : 0), ++ &unlocked); ++ if (unlocked) ++ return -EAGAIN; ++ ++ if (ret) ++ return ret; ++ ++ ret = follow_pfn(vma, vaddr, pfn); ++ } ++ ++ return ret; ++} ++ + static int vaddr_get_pfn(unsigned long vaddr, int prot, unsigned long *pfn) + { + struct page *page[1]; +@@ -226,12 +252,16 @@ static int vaddr_get_pfn(unsigned long vaddr, int prot, unsigned long *pfn) + + down_read(¤t->mm->mmap_sem); + ++retry: + vma = find_vma_intersection(current->mm, vaddr, vaddr + 1); + + if (vma && vma->vm_flags & VM_PFNMAP) { +- if (!follow_pfn(vma, vaddr, pfn) && +- is_invalid_reserved_pfn(*pfn)) +- ret = 0; ++ ret = follow_fault_pfn(vma, current->mm, vaddr, pfn, prot & IOMMU_WRITE); ++ if (ret == -EAGAIN) ++ goto retry; ++ ++ if (!ret && !is_invalid_reserved_pfn(*pfn)) ++ ret = -EFAULT; + } + + up_read(¤t->mm->mmap_sem); +diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c +index df27cefb2fa35..266f446ba331c 100644 +--- a/drivers/xen/xenbus/xenbus_client.c ++++ b/drivers/xen/xenbus/xenbus_client.c +@@ -384,8 +384,14 @@ int xenbus_grant_ring(struct xenbus_device *dev, void *vaddr, + int i, j; + + for (i = 0; i < nr_pages; i++) { +- err = gnttab_grant_foreign_access(dev->otherend_id, +- virt_to_gfn(vaddr), 0); ++ unsigned long gfn; ++ ++ if (is_vmalloc_addr(vaddr)) ++ gfn = pfn_to_gfn(vmalloc_to_pfn(vaddr)); ++ else ++ gfn = virt_to_gfn(vaddr); ++ ++ err = gnttab_grant_foreign_access(dev->otherend_id, gfn, 0); + if (err < 0) { + xenbus_dev_fatal(dev, err, + "granting access to ring page"); +diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c +index 0ec65c133b934..e57f12317ab62 100644 +--- a/fs/affs/amigaffs.c ++++ b/fs/affs/amigaffs.c +@@ -391,23 +391,23 @@ prot_to_mode(u32 prot) + umode_t mode = 0; + + if (!(prot & FIBF_NOWRITE)) +- mode |= S_IWUSR; ++ mode |= 0200; + if (!(prot & FIBF_NOREAD)) +- mode |= S_IRUSR; ++ mode |= 0400; + if (!(prot & FIBF_NOEXECUTE)) +- mode |= S_IXUSR; ++ mode |= 0100; + if (prot & FIBF_GRP_WRITE) +- mode |= S_IWGRP; ++ mode |= 0020; + if (prot & FIBF_GRP_READ) +- mode |= S_IRGRP; ++ mode |= 0040; + if (prot & FIBF_GRP_EXECUTE) +- mode |= S_IXGRP; ++ mode |= 0010; + if (prot & FIBF_OTR_WRITE) +- mode |= S_IWOTH; ++ mode |= 0002; + if (prot & FIBF_OTR_READ) +- mode |= S_IROTH; ++ mode |= 0004; + if (prot & FIBF_OTR_EXECUTE) +- mode |= S_IXOTH; ++ mode |= 0001; + + return mode; + } +@@ -418,24 +418,51 @@ mode_to_prot(struct inode *inode) + u32 prot = AFFS_I(inode)->i_protect; + umode_t mode = inode->i_mode; + +- if (!(mode & S_IXUSR)) ++ /* ++ * First, clear all RWED bits for owner, group, other. ++ * Then, recalculate them afresh. ++ * ++ * We'll always clear the delete-inhibit bit for the owner, as that is ++ * the classic single-user mode AmigaOS protection bit and we need to ++ * stay compatible with all scenarios. ++ * ++ * Since multi-user AmigaOS is an extension, we'll only set the ++ * delete-allow bit if any of the other bits in the same user class ++ * (group/other) are used. ++ */ ++ prot &= ~(FIBF_NOEXECUTE | FIBF_NOREAD ++ | FIBF_NOWRITE | FIBF_NODELETE ++ | FIBF_GRP_EXECUTE | FIBF_GRP_READ ++ | FIBF_GRP_WRITE | FIBF_GRP_DELETE ++ | FIBF_OTR_EXECUTE | FIBF_OTR_READ ++ | FIBF_OTR_WRITE | FIBF_OTR_DELETE); ++ ++ /* Classic single-user AmigaOS flags. These are inverted. */ ++ if (!(mode & 0100)) + prot |= FIBF_NOEXECUTE; +- if (!(mode & S_IRUSR)) ++ if (!(mode & 0400)) + prot |= FIBF_NOREAD; +- if (!(mode & S_IWUSR)) ++ if (!(mode & 0200)) + prot |= FIBF_NOWRITE; +- if (mode & S_IXGRP) ++ ++ /* Multi-user extended flags. Not inverted. */ ++ if (mode & 0010) + prot |= FIBF_GRP_EXECUTE; +- if (mode & S_IRGRP) ++ if (mode & 0040) + prot |= FIBF_GRP_READ; +- if (mode & S_IWGRP) ++ if (mode & 0020) + prot |= FIBF_GRP_WRITE; +- if (mode & S_IXOTH) ++ if (mode & 0070) ++ prot |= FIBF_GRP_DELETE; ++ ++ if (mode & 0001) + prot |= FIBF_OTR_EXECUTE; +- if (mode & S_IROTH) ++ if (mode & 0004) + prot |= FIBF_OTR_READ; +- if (mode & S_IWOTH) ++ if (mode & 0002) + prot |= FIBF_OTR_WRITE; ++ if (mode & 0007) ++ prot |= FIBF_OTR_DELETE; + + AFFS_I(inode)->i_protect = prot; + } +diff --git a/fs/affs/file.c b/fs/affs/file.c +index 0deec9cc2362c..0daca9d00cd8b 100644 +--- a/fs/affs/file.c ++++ b/fs/affs/file.c +@@ -427,6 +427,24 @@ static int affs_write_begin(struct file *file, struct address_space *mapping, + return ret; + } + ++static int affs_write_end(struct file *file, struct address_space *mapping, ++ loff_t pos, unsigned int len, unsigned int copied, ++ struct page *page, void *fsdata) ++{ ++ struct inode *inode = mapping->host; ++ int ret; ++ ++ ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); ++ ++ /* Clear Archived bit on file writes, as AmigaOS would do */ ++ if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) { ++ AFFS_I(inode)->i_protect &= ~FIBF_ARCHIVED; ++ mark_inode_dirty(inode); ++ } ++ ++ return ret; ++} ++ + static sector_t _affs_bmap(struct address_space *mapping, sector_t block) + { + return generic_block_bmap(mapping,block,affs_get_block); +@@ -436,7 +454,7 @@ const struct address_space_operations affs_aops = { + .readpage = affs_readpage, + .writepage = affs_writepage, + .write_begin = affs_write_begin, +- .write_end = generic_write_end, ++ .write_end = affs_write_end, + .direct_IO = affs_direct_IO, + .bmap = _affs_bmap + }; +@@ -793,6 +811,12 @@ done: + if (tmp > inode->i_size) + inode->i_size = AFFS_I(inode)->mmu_private = tmp; + ++ /* Clear Archived bit on file writes, as AmigaOS would do */ ++ if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) { ++ AFFS_I(inode)->i_protect &= ~FIBF_ARCHIVED; ++ mark_inode_dirty(inode); ++ } ++ + err_first_bh: + unlock_page(page); + put_page(page); +diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c +index b5ebb43b1824f..65689cbc362db 100644 +--- a/fs/btrfs/ctree.c ++++ b/fs/btrfs/ctree.c +@@ -1360,7 +1360,8 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path, + btrfs_tree_read_unlock_blocking(eb); + free_extent_buffer(eb); + +- extent_buffer_get(eb_rewin); ++ btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb_rewin), ++ eb_rewin, btrfs_header_level(eb_rewin)); + btrfs_tree_read_lock(eb_rewin); + __tree_mod_log_rewind(fs_info, eb_rewin, time_seq, tm); + WARN_ON(btrfs_header_nritems(eb_rewin) > +@@ -1430,8 +1431,6 @@ get_old_root(struct btrfs_root *root, u64 time_seq) + + if (!eb) + return NULL; +- extent_buffer_get(eb); +- btrfs_tree_read_lock(eb); + if (old_root) { + btrfs_set_header_bytenr(eb, eb->start); + btrfs_set_header_backref_rev(eb, BTRFS_MIXED_BACKREF_REV); +@@ -1439,6 +1438,9 @@ get_old_root(struct btrfs_root *root, u64 time_seq) + btrfs_set_header_level(eb, old_root->level); + btrfs_set_header_generation(eb, old_generation); + } ++ btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb), eb, ++ btrfs_header_level(eb)); ++ btrfs_tree_read_lock(eb); + if (tm) + __tree_mod_log_rewind(root->fs_info, eb, time_seq, tm); + else +diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c +index fa22bb29eee6f..d6c827a9ebc56 100644 +--- a/fs/btrfs/extent_io.c ++++ b/fs/btrfs/extent_io.c +@@ -5488,9 +5488,9 @@ void read_extent_buffer(const struct extent_buffer *eb, void *dstv, + } + } + +-int read_extent_buffer_to_user(const struct extent_buffer *eb, +- void __user *dstv, +- unsigned long start, unsigned long len) ++int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb, ++ void __user *dstv, ++ unsigned long start, unsigned long len) + { + size_t cur; + size_t offset; +@@ -5511,7 +5511,7 @@ int read_extent_buffer_to_user(const struct extent_buffer *eb, + + cur = min(len, (PAGE_SIZE - offset)); + kaddr = page_address(page); +- if (copy_to_user(dst, kaddr + offset, cur)) { ++ if (probe_user_write(dst, kaddr + offset, cur)) { + ret = -EFAULT; + break; + } +diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h +index 9ecdc9584df77..75c03aa1800fe 100644 +--- a/fs/btrfs/extent_io.h ++++ b/fs/btrfs/extent_io.h +@@ -401,9 +401,9 @@ int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv, + void read_extent_buffer(const struct extent_buffer *eb, void *dst, + unsigned long start, + unsigned long len); +-int read_extent_buffer_to_user(const struct extent_buffer *eb, +- void __user *dst, unsigned long start, +- unsigned long len); ++int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb, ++ void __user *dst, unsigned long start, ++ unsigned long len); + void write_extent_buffer(struct extent_buffer *eb, const void *src, + unsigned long start, unsigned long len); + void copy_extent_buffer(struct extent_buffer *dst, struct extent_buffer *src, +diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c +index eefe103c65daa..6db46daeed16b 100644 +--- a/fs/btrfs/ioctl.c ++++ b/fs/btrfs/ioctl.c +@@ -2041,9 +2041,14 @@ static noinline int copy_to_sk(struct btrfs_path *path, + sh.len = item_len; + sh.transid = found_transid; + +- /* copy search result header */ +- if (copy_to_user(ubuf + *sk_offset, &sh, sizeof(sh))) { +- ret = -EFAULT; ++ /* ++ * Copy search result header. If we fault then loop again so we ++ * can fault in the pages and -EFAULT there if there's a ++ * problem. Otherwise we'll fault and then copy the buffer in ++ * properly this next time through ++ */ ++ if (probe_user_write(ubuf + *sk_offset, &sh, sizeof(sh))) { ++ ret = 0; + goto out; + } + +@@ -2051,10 +2056,14 @@ static noinline int copy_to_sk(struct btrfs_path *path, + + if (item_len) { + char __user *up = ubuf + *sk_offset; +- /* copy the item */ +- if (read_extent_buffer_to_user(leaf, up, +- item_off, item_len)) { +- ret = -EFAULT; ++ /* ++ * Copy the item, same behavior as above, but reset the ++ * * sk_offset so we copy the full thing again. ++ */ ++ if (read_extent_buffer_to_user_nofault(leaf, up, ++ item_off, item_len)) { ++ ret = 0; ++ *sk_offset -= sizeof(sh); + goto out; + } + +@@ -2142,6 +2151,10 @@ static noinline int search_ioctl(struct inode *inode, + key.offset = sk->min_offset; + + while (1) { ++ ret = fault_in_pages_writeable(ubuf, *buf_size - sk_offset); ++ if (ret) ++ break; ++ + ret = btrfs_search_forward(root, &key, path, sk->min_transid); + if (ret != 0) { + if (ret > 0) +diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c +index bace03a546b2d..c31b02692f706 100644 +--- a/fs/btrfs/volumes.c ++++ b/fs/btrfs/volumes.c +@@ -4181,6 +4181,7 @@ static int btrfs_uuid_scan_kthread(void *data) + goto skip; + } + update_tree: ++ btrfs_release_path(path); + if (!btrfs_is_empty_uuid(root_item.uuid)) { + ret = btrfs_uuid_tree_add(trans, fs_info->uuid_root, + root_item.uuid, +@@ -4206,6 +4207,7 @@ update_tree: + } + + skip: ++ btrfs_release_path(path); + if (trans) { + ret = btrfs_end_transaction(trans, fs_info->uuid_root); + trans = NULL; +@@ -4213,7 +4215,6 @@ skip: + break; + } + +- btrfs_release_path(path); + if (key.offset < (u64)-1) { + key.offset++; + } else if (key.type < BTRFS_ROOT_ITEM_KEY) { +diff --git a/fs/ceph/file.c b/fs/ceph/file.c +index e7ddb23d9bb73..e818344a052cb 100644 +--- a/fs/ceph/file.c ++++ b/fs/ceph/file.c +@@ -1773,6 +1773,7 @@ const struct file_operations ceph_file_fops = { + .mmap = ceph_mmap, + .fsync = ceph_fsync, + .lock = ceph_lock, ++ .setlease = simple_nosetlease, + .flock = ceph_flock, + .splice_write = iter_file_splice_write, + .unlocked_ioctl = ceph_ioctl, +diff --git a/fs/eventpoll.c b/fs/eventpoll.c +index aad52e1858363..8c40d6652a9a9 100644 +--- a/fs/eventpoll.c ++++ b/fs/eventpoll.c +@@ -1748,9 +1748,9 @@ static int ep_loop_check_proc(void *priv, void *cookie, int call_nests) + * during ep_insert(). + */ + if (list_empty(&epi->ffd.file->f_tfile_llink)) { +- get_file(epi->ffd.file); +- list_add(&epi->ffd.file->f_tfile_llink, +- &tfile_check_list); ++ if (get_file_rcu(epi->ffd.file)) ++ list_add(&epi->ffd.file->f_tfile_llink, ++ &tfile_check_list); + } + } + } +diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h +index 060881478e59e..848aab6c69823 100644 +--- a/include/linux/blkdev.h ++++ b/include/linux/blkdev.h +@@ -850,6 +850,19 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev) + return bdev->bd_disk->queue; /* this is never NULL */ + } + ++/* ++ * The basic unit of block I/O is a sector. It is used in a number of contexts ++ * in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9 ++ * bytes. Variables of type sector_t represent an offset or size that is a ++ * multiple of 512 bytes. Hence these two constants. ++ */ ++#ifndef SECTOR_SHIFT ++#define SECTOR_SHIFT 9 ++#endif ++#ifndef SECTOR_SIZE ++#define SECTOR_SIZE (1 << SECTOR_SHIFT) ++#endif ++ + /* + * blk_rq_pos() : the current sector + * blk_rq_bytes() : bytes left in the entire request +@@ -877,19 +890,20 @@ extern unsigned int blk_rq_err_bytes(const struct request *rq); + + static inline unsigned int blk_rq_sectors(const struct request *rq) + { +- return blk_rq_bytes(rq) >> 9; ++ return blk_rq_bytes(rq) >> SECTOR_SHIFT; + } + + static inline unsigned int blk_rq_cur_sectors(const struct request *rq) + { +- return blk_rq_cur_bytes(rq) >> 9; ++ return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT; + } + + static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, + int op) + { + if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)) +- return min(q->limits.max_discard_sectors, UINT_MAX >> 9); ++ return min(q->limits.max_discard_sectors, ++ UINT_MAX >> SECTOR_SHIFT); + + if (unlikely(op == REQ_OP_WRITE_SAME)) + return q->limits.max_write_same_sectors; +@@ -1162,16 +1176,21 @@ extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, + static inline int sb_issue_discard(struct super_block *sb, sector_t block, + sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags) + { +- return blkdev_issue_discard(sb->s_bdev, block << (sb->s_blocksize_bits - 9), +- nr_blocks << (sb->s_blocksize_bits - 9), ++ return blkdev_issue_discard(sb->s_bdev, ++ block << (sb->s_blocksize_bits - ++ SECTOR_SHIFT), ++ nr_blocks << (sb->s_blocksize_bits - ++ SECTOR_SHIFT), + gfp_mask, flags); + } + static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, + sector_t nr_blocks, gfp_t gfp_mask) + { + return blkdev_issue_zeroout(sb->s_bdev, +- block << (sb->s_blocksize_bits - 9), +- nr_blocks << (sb->s_blocksize_bits - 9), ++ block << (sb->s_blocksize_bits - ++ SECTOR_SHIFT), ++ nr_blocks << (sb->s_blocksize_bits - ++ SECTOR_SHIFT), + gfp_mask, true); + } + +@@ -1278,7 +1297,8 @@ static inline int queue_alignment_offset(struct request_queue *q) + static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) + { + unsigned int granularity = max(lim->physical_block_size, lim->io_min); +- unsigned int alignment = sector_div(sector, granularity >> 9) << 9; ++ unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT) ++ << SECTOR_SHIFT; + + return (granularity + lim->alignment_offset - alignment) % granularity; + } +@@ -1312,8 +1332,8 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector + return 0; + + /* Why are these in bytes, not sectors? */ +- alignment = lim->discard_alignment >> 9; +- granularity = lim->discard_granularity >> 9; ++ alignment = lim->discard_alignment >> SECTOR_SHIFT; ++ granularity = lim->discard_granularity >> SECTOR_SHIFT; + if (!granularity) + return 0; + +@@ -1324,7 +1344,7 @@ static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector + offset = (granularity + alignment - offset) % granularity; + + /* Turn it back into bytes, gaah */ +- return offset << 9; ++ return offset << SECTOR_SHIFT; + } + + static inline int bdev_discard_alignment(struct block_device *bdev) +diff --git a/include/linux/bvec.h b/include/linux/bvec.h +index 89b65b82d98f5..8047c3ad77a64 100644 +--- a/include/linux/bvec.h ++++ b/include/linux/bvec.h +@@ -88,10 +88,17 @@ static inline void bvec_iter_advance(const struct bio_vec *bv, + } + } + ++static inline void bvec_iter_skip_zero_bvec(struct bvec_iter *iter) ++{ ++ iter->bi_bvec_done = 0; ++ iter->bi_idx++; ++} ++ + #define for_each_bvec(bvl, bio_vec, iter, start) \ + for (iter = (start); \ + (iter).bi_size && \ + ((bvl = bvec_iter_bvec((bio_vec), (iter))), 1); \ +- bvec_iter_advance((bio_vec), &(iter), (bvl).bv_len)) ++ (bvl).bv_len ? (void)bvec_iter_advance((bio_vec), &(iter), \ ++ (bvl).bv_len) : bvec_iter_skip_zero_bvec(&(iter))) + + #endif /* __LINUX_BVEC_ITER_H */ +diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h +index 9661bb2fbe221..165ddd482f0d7 100644 +--- a/include/linux/device-mapper.h ++++ b/include/linux/device-mapper.h +@@ -576,8 +576,6 @@ extern struct ratelimit_state dm_ratelimit_state; + #define DMEMIT(x...) sz += ((sz >= maxlen) ? \ + 0 : scnprintf(result + sz, maxlen - sz, x)) + +-#define SECTOR_SHIFT 9 +- + /* + * Definitions of return values from target end_io function. + */ +diff --git a/include/linux/hid.h b/include/linux/hid.h +index eda06f7ee84af..981657075f051 100644 +--- a/include/linux/hid.h ++++ b/include/linux/hid.h +@@ -874,34 +874,49 @@ static inline void hid_device_io_stop(struct hid_device *hid) { + * @max: maximal valid usage->code to consider later (out parameter) + * @type: input event type (EV_KEY, EV_REL, ...) + * @c: code which corresponds to this usage and type ++ * ++ * The value pointed to by @bit will be set to NULL if either @type is ++ * an unhandled event type, or if @c is out of range for @type. This ++ * can be used as an error condition. + */ + static inline void hid_map_usage(struct hid_input *hidinput, + struct hid_usage *usage, unsigned long **bit, int *max, +- __u8 type, __u16 c) ++ __u8 type, unsigned int c) + { + struct input_dev *input = hidinput->input; +- +- usage->type = type; +- usage->code = c; ++ unsigned long *bmap = NULL; ++ unsigned int limit = 0; + + switch (type) { + case EV_ABS: +- *bit = input->absbit; +- *max = ABS_MAX; ++ bmap = input->absbit; ++ limit = ABS_MAX; + break; + case EV_REL: +- *bit = input->relbit; +- *max = REL_MAX; ++ bmap = input->relbit; ++ limit = REL_MAX; + break; + case EV_KEY: +- *bit = input->keybit; +- *max = KEY_MAX; ++ bmap = input->keybit; ++ limit = KEY_MAX; + break; + case EV_LED: +- *bit = input->ledbit; +- *max = LED_MAX; ++ bmap = input->ledbit; ++ limit = LED_MAX; + break; + } ++ ++ if (unlikely(c > limit || !bmap)) { ++ pr_warn_ratelimited("%s: Invalid code %d type %d\n", ++ input->name, c, type); ++ *bit = NULL; ++ return; ++ } ++ ++ usage->type = type; ++ usage->code = c; ++ *max = limit; ++ *bit = bmap; + } + + /** +@@ -915,7 +930,8 @@ static inline void hid_map_usage_clear(struct hid_input *hidinput, + __u8 type, __u16 c) + { + hid_map_usage(hidinput, usage, bit, max, type, c); +- clear_bit(c, *bit); ++ if (*bit) ++ clear_bit(usage->code, *bit); + } + + /** +diff --git a/include/linux/ide.h b/include/linux/ide.h +index a633898f36ac8..eb2ac48c99db3 100644 +--- a/include/linux/ide.h ++++ b/include/linux/ide.h +@@ -128,7 +128,6 @@ struct ide_io_ports { + */ + #define PARTN_BITS 6 /* number of minor dev bits for partitions */ + #define MAX_DRIVES 2 /* per interface; 2 assumed by lots of code */ +-#define SECTOR_SIZE 512 + + /* + * Timeouts for various operations: +diff --git a/include/linux/libata.h b/include/linux/libata.h +index 780ccde2c3127..e2dac33eae964 100644 +--- a/include/linux/libata.h ++++ b/include/linux/libata.h +@@ -435,6 +435,7 @@ enum { + ATA_HORKAGE_NO_NCQ_LOG = (1 << 23), /* don't use NCQ for log read */ + ATA_HORKAGE_NOTRIM = (1 << 24), /* don't use TRIM */ + ATA_HORKAGE_MAX_SEC_1024 = (1 << 25), /* Limit max sects to 1024 */ ++ ATA_HORKAGE_MAX_TRIM_128M = (1 << 26), /* Limit max trim size to 128M */ + + /* DMA mask for user DMA control: User visible values; DO NOT + renumber */ +diff --git a/include/linux/log2.h b/include/linux/log2.h +index c373295f359fa..cca606609e1bc 100644 +--- a/include/linux/log2.h ++++ b/include/linux/log2.h +@@ -159,7 +159,7 @@ unsigned long __rounddown_pow_of_two(unsigned long n) + #define roundup_pow_of_two(n) \ + ( \ + __builtin_constant_p(n) ? ( \ +- (n == 1) ? 1 : \ ++ ((n) == 1) ? 1 : \ + (1UL << (ilog2((n) - 1) + 1)) \ + ) : \ + __roundup_pow_of_two(n) \ +diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h +index 9442423979c1c..cc5ba47062e87 100644 +--- a/include/linux/uaccess.h ++++ b/include/linux/uaccess.h +@@ -90,6 +90,17 @@ static inline unsigned long __copy_from_user_nocache(void *to, + extern long probe_kernel_read(void *dst, const void *src, size_t size); + extern long __probe_kernel_read(void *dst, const void *src, size_t size); + ++/* ++ * probe_user_read(): safely attempt to read from a location in user space ++ * @dst: pointer to the buffer that shall take the data ++ * @src: address to read from ++ * @size: size of the data chunk ++ * ++ * Safely read from address @src to the buffer at @dst. If a kernel fault ++ * happens, handle that and return -EFAULT. ++ */ ++extern long probe_user_read(void *dst, const void __user *src, size_t size); ++ + /* + * probe_kernel_write(): safely attempt to write to a location + * @dst: address to write to +@@ -102,7 +113,22 @@ extern long __probe_kernel_read(void *dst, const void *src, size_t size); + extern long notrace probe_kernel_write(void *dst, const void *src, size_t size); + extern long notrace __probe_kernel_write(void *dst, const void *src, size_t size); + ++/* ++ * probe_user_write(): safely attempt to write to a location in user space ++ * @dst: address to write to ++ * @src: pointer to the data that shall be written ++ * @size: size of the data chunk ++ * ++ * Safely write to address @dst from the buffer at @src. If a kernel fault ++ * happens, handle that and return -EFAULT. ++ */ ++extern long notrace probe_user_write(void __user *dst, const void *src, size_t size); ++extern long notrace __probe_user_write(void __user *dst, const void *src, size_t size); ++ + extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); ++extern long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr, ++ long count); ++extern long strnlen_unsafe_user(const void __user *unsafe_addr, long count); + + /** + * probe_kernel_address(): safely attempt to read from a location +diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h +index 146054ceea8e0..5bb56ebf3c9f9 100644 +--- a/include/net/inet_connection_sock.h ++++ b/include/net/inet_connection_sock.h +@@ -319,5 +319,9 @@ int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname, + int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen); + ++/* update the fast reuse flag when adding a socket */ ++void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, ++ struct sock *sk); ++ + struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu); + #endif /* _INET_CONNECTION_SOCK_H */ +diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h +index 7ba9a624090fb..91e395fd0a65c 100644 +--- a/include/net/netfilter/nf_tables.h ++++ b/include/net/netfilter/nf_tables.h +@@ -119,6 +119,8 @@ static inline u8 nft_reg_load8(u32 *sreg) + static inline void nft_data_copy(u32 *dst, const struct nft_data *src, + unsigned int len) + { ++ if (len % NFT_REG32_SIZE) ++ dst[len / NFT_REG32_SIZE] = 0; + memcpy(dst, src, len); + } + +diff --git a/include/uapi/linux/msdos_fs.h b/include/uapi/linux/msdos_fs.h +index e956704f5fb1b..95b8a9395ec10 100644 +--- a/include/uapi/linux/msdos_fs.h ++++ b/include/uapi/linux/msdos_fs.h +@@ -9,7 +9,9 @@ + * The MS-DOS filesystem constants/structures + */ + ++#ifndef SECTOR_SIZE + #define SECTOR_SIZE 512 /* sector size (bytes) */ ++#endif + #define SECTOR_BITS 9 /* log2(SECTOR_SIZE) */ + #define MSDOS_DPB (MSDOS_DPS) /* dir entries per block */ + #define MSDOS_DPB_BITS 4 /* log2(MSDOS_DPB) */ +diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h +index c6c4477c136b9..d121c22bf9284 100644 +--- a/include/uapi/linux/netfilter/nf_tables.h ++++ b/include/uapi/linux/netfilter/nf_tables.h +@@ -114,7 +114,7 @@ enum nf_tables_msg_types { + * @NFTA_LIST_ELEM: list element (NLA_NESTED) + */ + enum nft_list_attributes { +- NFTA_LIST_UNPEC, ++ NFTA_LIST_UNSPEC, + NFTA_LIST_ELEM, + __NFTA_LIST_MAX + }; +diff --git a/mm/hugetlb.c b/mm/hugetlb.c +index 2c22ea7a20131..b469d099dc5f6 100644 +--- a/mm/hugetlb.c ++++ b/mm/hugetlb.c +@@ -2921,6 +2921,22 @@ static unsigned int cpuset_mems_nr(unsigned int *array) + } + + #ifdef CONFIG_SYSCTL ++static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write, ++ void *buffer, size_t *length, ++ loff_t *ppos, unsigned long *out) ++{ ++ struct ctl_table dup_table; ++ ++ /* ++ * In order to avoid races with __do_proc_doulongvec_minmax(), we ++ * can duplicate the @table and alter the duplicate of it. ++ */ ++ dup_table = *table; ++ dup_table.data = out; ++ ++ return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos); ++} ++ + static int hugetlb_sysctl_handler_common(bool obey_mempolicy, + struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +@@ -2932,9 +2948,8 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy, + if (!hugepages_supported()) + return -EOPNOTSUPP; + +- table->data = &tmp; +- table->maxlen = sizeof(unsigned long); +- ret = proc_doulongvec_minmax(table, write, buffer, length, ppos); ++ ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, ++ &tmp); + if (ret) + goto out; + +@@ -2978,9 +2993,8 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, + if (write && hstate_is_gigantic(h)) + return -EINVAL; + +- table->data = &tmp; +- table->maxlen = sizeof(unsigned long); +- ret = proc_doulongvec_minmax(table, write, buffer, length, ppos); ++ ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, ++ &tmp); + if (ret) + goto out; + +diff --git a/mm/maccess.c b/mm/maccess.c +index 78f9274dd49d0..03ea550f5a743 100644 +--- a/mm/maccess.c ++++ b/mm/maccess.c +@@ -5,8 +5,32 @@ + #include <linux/mm.h> + #include <linux/uaccess.h> + ++static __always_inline long ++probe_read_common(void *dst, const void __user *src, size_t size) ++{ ++ long ret; ++ ++ pagefault_disable(); ++ ret = __copy_from_user_inatomic(dst, src, size); ++ pagefault_enable(); ++ ++ return ret ? -EFAULT : 0; ++} ++ ++static __always_inline long ++probe_write_common(void __user *dst, const void *src, size_t size) ++{ ++ long ret; ++ ++ pagefault_disable(); ++ ret = __copy_to_user_inatomic(dst, src, size); ++ pagefault_enable(); ++ ++ return ret ? -EFAULT : 0; ++} ++ + /** +- * probe_kernel_read(): safely attempt to read from a location ++ * probe_kernel_read(): safely attempt to read from a kernel-space location + * @dst: pointer to the buffer that shall take the data + * @src: address to read from + * @size: size of the data chunk +@@ -29,16 +53,40 @@ long __probe_kernel_read(void *dst, const void *src, size_t size) + mm_segment_t old_fs = get_fs(); + + set_fs(KERNEL_DS); +- pagefault_disable(); +- ret = __copy_from_user_inatomic(dst, +- (__force const void __user *)src, size); +- pagefault_enable(); ++ ret = probe_read_common(dst, (__force const void __user *)src, size); + set_fs(old_fs); + +- return ret ? -EFAULT : 0; ++ return ret; + } + EXPORT_SYMBOL_GPL(probe_kernel_read); + ++/** ++ * probe_user_read(): safely attempt to read from a user-space location ++ * @dst: pointer to the buffer that shall take the data ++ * @src: address to read from. This must be a user address. ++ * @size: size of the data chunk ++ * ++ * Safely read from user address @src to the buffer at @dst. If a kernel fault ++ * happens, handle that and return -EFAULT. ++ */ ++ ++long __weak probe_user_read(void *dst, const void __user *src, size_t size) ++ __attribute__((alias("__probe_user_read"))); ++ ++long __probe_user_read(void *dst, const void __user *src, size_t size) ++{ ++ long ret = -EFAULT; ++ mm_segment_t old_fs = get_fs(); ++ ++ set_fs(USER_DS); ++ if (access_ok(VERIFY_READ, src, size)) ++ ret = probe_read_common(dst, src, size); ++ set_fs(old_fs); ++ ++ return ret; ++} ++EXPORT_SYMBOL_GPL(probe_user_read); ++ + /** + * probe_kernel_write(): safely attempt to write to a location + * @dst: address to write to +@@ -48,6 +96,7 @@ EXPORT_SYMBOL_GPL(probe_kernel_read); + * Safely write to address @dst from the buffer at @src. If a kernel fault + * happens, handle that and return -EFAULT. + */ ++ + long __weak probe_kernel_write(void *dst, const void *src, size_t size) + __attribute__((alias("__probe_kernel_write"))); + +@@ -57,15 +106,40 @@ long __probe_kernel_write(void *dst, const void *src, size_t size) + mm_segment_t old_fs = get_fs(); + + set_fs(KERNEL_DS); +- pagefault_disable(); +- ret = __copy_to_user_inatomic((__force void __user *)dst, src, size); +- pagefault_enable(); ++ ret = probe_write_common((__force void __user *)dst, src, size); + set_fs(old_fs); + +- return ret ? -EFAULT : 0; ++ return ret; + } + EXPORT_SYMBOL_GPL(probe_kernel_write); + ++/** ++ * probe_user_write(): safely attempt to write to a user-space location ++ * @dst: address to write to ++ * @src: pointer to the data that shall be written ++ * @size: size of the data chunk ++ * ++ * Safely write to address @dst from the buffer at @src. If a kernel fault ++ * happens, handle that and return -EFAULT. ++ */ ++ ++long __weak probe_user_write(void __user *dst, const void *src, size_t size) ++ __attribute__((alias("__probe_user_write"))); ++ ++long __probe_user_write(void __user *dst, const void *src, size_t size) ++{ ++ long ret = -EFAULT; ++ mm_segment_t old_fs = get_fs(); ++ ++ set_fs(USER_DS); ++ if (access_ok(VERIFY_WRITE, dst, size)) ++ ret = probe_write_common(dst, src, size); ++ set_fs(old_fs); ++ ++ return ret; ++} ++EXPORT_SYMBOL_GPL(probe_user_write); ++ + /** + * strncpy_from_unsafe: - Copy a NUL terminated string from unsafe address. + * @dst: Destination address, in kernel space. This buffer must be at +@@ -105,3 +179,76 @@ long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count) + + return ret ? -EFAULT : src - unsafe_addr; + } ++ ++/** ++ * strncpy_from_unsafe_user: - Copy a NUL terminated string from unsafe user ++ * address. ++ * @dst: Destination address, in kernel space. This buffer must be at ++ * least @count bytes long. ++ * @unsafe_addr: Unsafe user address. ++ * @count: Maximum number of bytes to copy, including the trailing NUL. ++ * ++ * Copies a NUL-terminated string from unsafe user address to kernel buffer. ++ * ++ * On success, returns the length of the string INCLUDING the trailing NUL. ++ * ++ * If access fails, returns -EFAULT (some data may have been copied ++ * and the trailing NUL added). ++ * ++ * If @count is smaller than the length of the string, copies @count-1 bytes, ++ * sets the last byte of @dst buffer to NUL and returns @count. ++ */ ++long strncpy_from_unsafe_user(char *dst, const void __user *unsafe_addr, ++ long count) ++{ ++ mm_segment_t old_fs = get_fs(); ++ long ret; ++ ++ if (unlikely(count <= 0)) ++ return 0; ++ ++ set_fs(USER_DS); ++ pagefault_disable(); ++ ret = strncpy_from_user(dst, unsafe_addr, count); ++ pagefault_enable(); ++ set_fs(old_fs); ++ ++ if (ret >= count) { ++ ret = count; ++ dst[ret - 1] = '\0'; ++ } else if (ret > 0) { ++ ret++; ++ } ++ ++ return ret; ++} ++ ++/** ++ * strnlen_unsafe_user: - Get the size of a user string INCLUDING final NUL. ++ * @unsafe_addr: The string to measure. ++ * @count: Maximum count (including NUL) ++ * ++ * Get the size of a NUL-terminated string in user space without pagefault. ++ * ++ * Returns the size of the string INCLUDING the terminating NUL. ++ * ++ * If the string is too long, returns a number larger than @count. User ++ * has to check the return value against "> count". ++ * On exception (or invalid count), returns 0. ++ * ++ * Unlike strnlen_user, this can be used from IRQ handler etc. because ++ * it disables pagefaults. ++ */ ++long strnlen_unsafe_user(const void __user *unsafe_addr, long count) ++{ ++ mm_segment_t old_fs = get_fs(); ++ int ret; ++ ++ set_fs(USER_DS); ++ pagefault_disable(); ++ ret = strnlen_user(unsafe_addr, count); ++ pagefault_enable(); ++ set_fs(old_fs); ++ ++ return ret; ++} +diff --git a/mm/slub.c b/mm/slub.c +index 454c1d550ad22..51a73d2d1082e 100644 +--- a/mm/slub.c ++++ b/mm/slub.c +@@ -625,12 +625,12 @@ static void slab_fix(struct kmem_cache *s, char *fmt, ...) + } + + static bool freelist_corrupted(struct kmem_cache *s, struct page *page, +- void *freelist, void *nextfree) ++ void **freelist, void *nextfree) + { + if ((s->flags & SLAB_CONSISTENCY_CHECKS) && +- !check_valid_pointer(s, page, nextfree)) { +- object_err(s, page, freelist, "Freechain corrupt"); +- freelist = NULL; ++ !check_valid_pointer(s, page, nextfree) && freelist) { ++ object_err(s, page, *freelist, "Freechain corrupt"); ++ *freelist = NULL; + slab_fix(s, "Isolate corrupted freechain"); + return true; + } +@@ -1320,7 +1320,7 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node, + int objects) {} + + static bool freelist_corrupted(struct kmem_cache *s, struct page *page, +- void *freelist, void *nextfree) ++ void **freelist, void *nextfree) + { + return false; + } +@@ -2040,7 +2040,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page, + * 'freelist' is already corrupted. So isolate all objects + * starting at 'freelist'. + */ +- if (freelist_corrupted(s, page, freelist, nextfree)) ++ if (freelist_corrupted(s, page, &freelist, nextfree)) + break; + + do { +diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c +index 00123064eb26d..e545b42ab0b98 100644 +--- a/net/batman-adv/bridge_loop_avoidance.c ++++ b/net/batman-adv/bridge_loop_avoidance.c +@@ -451,7 +451,10 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, u8 *mac, + skb->len + ETH_HLEN); + soft_iface->last_rx = jiffies; + +- netif_rx(skb); ++ if (in_interrupt()) ++ netif_rx(skb); ++ else ++ netif_rx_ni(skb); + out: + if (primary_if) + batadv_hardif_put(primary_if); +diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c +index 3bd7ed6b6b3e1..9727afc030d8c 100644 +--- a/net/batman-adv/gateway_client.c ++++ b/net/batman-adv/gateway_client.c +@@ -673,8 +673,10 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len, + + chaddr_offset = *header_len + BATADV_DHCP_CHADDR_OFFSET; + /* store the client address if the message is going to a client */ +- if (ret == BATADV_DHCP_TO_CLIENT && +- pskb_may_pull(skb, chaddr_offset + ETH_ALEN)) { ++ if (ret == BATADV_DHCP_TO_CLIENT) { ++ if (!pskb_may_pull(skb, chaddr_offset + ETH_ALEN)) ++ return BATADV_DHCP_NO; ++ + /* check if the DHCP packet carries an Ethernet DHCP */ + p = skb->data + *header_len + BATADV_DHCP_HTYPE_OFFSET; + if (*p != BATADV_DHCP_HTYPE_ETHERNET) +diff --git a/net/core/dev.c b/net/core/dev.c +index dd8d36feb69f4..9ac591dd16d50 100644 +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -5188,13 +5188,14 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, + pr_err_once("netif_napi_add() called with weight %d on device %s\n", + weight, dev->name); + napi->weight = weight; +- list_add(&napi->dev_list, &dev->napi_list); + napi->dev = dev; + #ifdef CONFIG_NETPOLL + spin_lock_init(&napi->poll_lock); + napi->poll_owner = -1; + #endif + set_bit(NAPI_STATE_SCHED, &napi->state); ++ set_bit(NAPI_STATE_NPSVC, &napi->state); ++ list_add_rcu(&napi->dev_list, &dev->napi_list); + napi_hash_add(napi); + } + EXPORT_SYMBOL(netif_napi_add); +diff --git a/net/core/netpoll.c b/net/core/netpoll.c +index 5de180a9b7f5a..9c1bad3909bd7 100644 +--- a/net/core/netpoll.c ++++ b/net/core/netpoll.c +@@ -178,7 +178,7 @@ static void poll_napi(struct net_device *dev) + { + struct napi_struct *napi; + +- list_for_each_entry(napi, &dev->napi_list, dev_list) { ++ list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { + if (napi->poll_owner != smp_processor_id() && + spin_trylock(&napi->poll_lock)) { + poll_one_napi(napi); +diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c +index 1bcbb7399fe69..5a0352ccadd3d 100644 +--- a/net/ipv4/inet_connection_sock.c ++++ b/net/ipv4/inet_connection_sock.c +@@ -89,6 +89,28 @@ int inet_csk_bind_conflict(const struct sock *sk, + } + EXPORT_SYMBOL_GPL(inet_csk_bind_conflict); + ++void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, ++ struct sock *sk) ++{ ++ kuid_t uid = sock_i_uid(sk); ++ bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; ++ ++ if (!hlist_empty(&tb->owners)) { ++ if (!reuse) ++ tb->fastreuse = 0; ++ if (!sk->sk_reuseport || !uid_eq(tb->fastuid, uid)) ++ tb->fastreuseport = 0; ++ } else { ++ tb->fastreuse = reuse; ++ if (sk->sk_reuseport) { ++ tb->fastreuseport = 1; ++ tb->fastuid = uid; ++ } else { ++ tb->fastreuseport = 0; ++ } ++ } ++} ++ + /* Obtain a reference to a local port for the given sock, + * if snum is zero it means select any available local port. + * We try to allocate an odd port (and leave even ports for connect()) +@@ -218,19 +240,10 @@ tb_found: + } + goto fail_unlock; + } +- if (!reuse) +- tb->fastreuse = 0; +- if (!sk->sk_reuseport || !uid_eq(tb->fastuid, uid)) +- tb->fastreuseport = 0; +- } else { +- tb->fastreuse = reuse; +- if (sk->sk_reuseport) { +- tb->fastreuseport = 1; +- tb->fastuid = uid; +- } else { +- tb->fastreuseport = 0; +- } + } ++ ++ inet_csk_update_fastreuse(tb, sk); ++ + success: + if (!inet_csk(sk)->icsk_bind_hash) + inet_bind_hash(sk, tb, port); +diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c +index 4bf542f4d9809..8876338707636 100644 +--- a/net/ipv4/inet_hashtables.c ++++ b/net/ipv4/inet_hashtables.c +@@ -163,6 +163,7 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child) + return -ENOMEM; + } + } ++ inet_csk_update_fastreuse(tb, child); + } + inet_bind_hash(child, tb, port); + spin_unlock(&head->lock); +diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c +index 2fa1c4f2e94e0..ec460aedfc617 100644 +--- a/net/netfilter/nf_tables_api.c ++++ b/net/netfilter/nf_tables_api.c +@@ -2592,7 +2592,8 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, + goto nla_put_failure; + } + +- if (nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata)) ++ if (set->udata && ++ nla_put(skb, NFTA_SET_USERDATA, set->udlen, set->udata)) + goto nla_put_failure; + + desc = nla_nest_start(skb, NFTA_SET_DESC); +diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c +index b2f88617611aa..f73d47b3ffb72 100644 +--- a/net/netfilter/nft_payload.c ++++ b/net/netfilter/nft_payload.c +@@ -74,7 +74,9 @@ static void nft_payload_eval(const struct nft_expr *expr, + u32 *dest = ®s->data[priv->dreg]; + int offset; + +- dest[priv->len / NFT_REG32_SIZE] = 0; ++ if (priv->len % NFT_REG32_SIZE) ++ dest[priv->len / NFT_REG32_SIZE] = 0; ++ + switch (priv->base) { + case NFT_PAYLOAD_LL_HEADER: + if (!skb_mac_header_was_set(skb)) +diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c +index 41d0e95d171e1..b1a1718495f34 100644 +--- a/net/netlabel/netlabel_domainhash.c ++++ b/net/netlabel/netlabel_domainhash.c +@@ -99,6 +99,7 @@ static void netlbl_domhsh_free_entry(struct rcu_head *entry) + kfree(netlbl_domhsh_addr6_entry(iter6)); + } + #endif /* IPv6 */ ++ kfree(ptr->def.addrsel); + } + kfree(ptr->domain); + kfree(ptr); +@@ -550,6 +551,8 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry, + goto add_return; + } + #endif /* IPv6 */ ++ /* cleanup the new entry since we've moved everything over */ ++ netlbl_domhsh_free_entry(&entry->rcu); + } else + ret_val = -EINVAL; + +@@ -593,6 +596,12 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry, + { + int ret_val = 0; + struct audit_buffer *audit_buf; ++ struct netlbl_af4list *iter4; ++ struct netlbl_domaddr4_map *map4; ++#if IS_ENABLED(CONFIG_IPV6) ++ struct netlbl_af6list *iter6; ++ struct netlbl_domaddr6_map *map6; ++#endif /* IPv6 */ + + if (entry == NULL) + return -ENOENT; +@@ -610,6 +619,9 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry, + ret_val = -ENOENT; + spin_unlock(&netlbl_domhsh_lock); + ++ if (ret_val) ++ return ret_val; ++ + audit_buf = netlbl_audit_start_common(AUDIT_MAC_MAP_DEL, audit_info); + if (audit_buf != NULL) { + audit_log_format(audit_buf, +@@ -619,40 +631,29 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry, + audit_log_end(audit_buf); + } + +- if (ret_val == 0) { +- struct netlbl_af4list *iter4; +- struct netlbl_domaddr4_map *map4; +-#if IS_ENABLED(CONFIG_IPV6) +- struct netlbl_af6list *iter6; +- struct netlbl_domaddr6_map *map6; +-#endif /* IPv6 */ +- +- switch (entry->def.type) { +- case NETLBL_NLTYPE_ADDRSELECT: +- netlbl_af4list_foreach_rcu(iter4, +- &entry->def.addrsel->list4) { +- map4 = netlbl_domhsh_addr4_entry(iter4); +- cipso_v4_doi_putdef(map4->def.cipso); +- } ++ switch (entry->def.type) { ++ case NETLBL_NLTYPE_ADDRSELECT: ++ netlbl_af4list_foreach_rcu(iter4, &entry->def.addrsel->list4) { ++ map4 = netlbl_domhsh_addr4_entry(iter4); ++ cipso_v4_doi_putdef(map4->def.cipso); ++ } + #if IS_ENABLED(CONFIG_IPV6) +- netlbl_af6list_foreach_rcu(iter6, +- &entry->def.addrsel->list6) { +- map6 = netlbl_domhsh_addr6_entry(iter6); +- calipso_doi_putdef(map6->def.calipso); +- } ++ netlbl_af6list_foreach_rcu(iter6, &entry->def.addrsel->list6) { ++ map6 = netlbl_domhsh_addr6_entry(iter6); ++ calipso_doi_putdef(map6->def.calipso); ++ } + #endif /* IPv6 */ +- break; +- case NETLBL_NLTYPE_CIPSOV4: +- cipso_v4_doi_putdef(entry->def.cipso); +- break; ++ break; ++ case NETLBL_NLTYPE_CIPSOV4: ++ cipso_v4_doi_putdef(entry->def.cipso); ++ break; + #if IS_ENABLED(CONFIG_IPV6) +- case NETLBL_NLTYPE_CALIPSO: +- calipso_doi_putdef(entry->def.calipso); +- break; ++ case NETLBL_NLTYPE_CALIPSO: ++ calipso_doi_putdef(entry->def.calipso); ++ break; + #endif /* IPv6 */ +- } +- call_rcu(&entry->rcu, netlbl_domhsh_free_entry); + } ++ call_rcu(&entry->rcu, netlbl_domhsh_free_entry); + + return ret_val; + } +diff --git a/net/sctp/socket.c b/net/sctp/socket.c +index 95f39dde1e08e..c0fe647dd4acb 100644 +--- a/net/sctp/socket.c ++++ b/net/sctp/socket.c +@@ -6687,8 +6687,6 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) + + pr_debug("%s: begins, snum:%d\n", __func__, snum); + +- local_bh_disable(); +- + if (snum == 0) { + /* Search for an available port. */ + int low, high, remaining, index; +@@ -6707,20 +6705,21 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) + continue; + index = sctp_phashfn(sock_net(sk), rover); + head = &sctp_port_hashtable[index]; +- spin_lock(&head->lock); ++ spin_lock_bh(&head->lock); + sctp_for_each_hentry(pp, &head->chain) + if ((pp->port == rover) && + net_eq(sock_net(sk), pp->net)) + goto next; + break; + next: +- spin_unlock(&head->lock); ++ spin_unlock_bh(&head->lock); ++ cond_resched(); + } while (--remaining > 0); + + /* Exhausted local port range during search? */ + ret = 1; + if (remaining <= 0) +- goto fail; ++ return ret; + + /* OK, here is the one we will use. HEAD (the port + * hash table list entry) is non-NULL and we hold it's +@@ -6735,7 +6734,7 @@ static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr) + * port iterator, pp being NULL. + */ + head = &sctp_port_hashtable[sctp_phashfn(sock_net(sk), snum)]; +- spin_lock(&head->lock); ++ spin_lock_bh(&head->lock); + sctp_for_each_hentry(pp, &head->chain) { + if ((pp->port == snum) && net_eq(pp->net, sock_net(sk))) + goto pp_found; +@@ -6819,10 +6818,7 @@ success: + ret = 0; + + fail_unlock: +- spin_unlock(&head->lock); +- +-fail: +- local_bh_enable(); ++ spin_unlock_bh(&head->lock); + return ret; + } + +diff --git a/net/wireless/reg.c b/net/wireless/reg.c +index 6d5f3f737207d..a649763b854d5 100644 +--- a/net/wireless/reg.c ++++ b/net/wireless/reg.c +@@ -2321,6 +2321,9 @@ int regulatory_hint_user(const char *alpha2, + if (WARN_ON(!alpha2)) + return -EINVAL; + ++ if (!is_world_regdom(alpha2) && !is_an_alpha2(alpha2)) ++ return -EINVAL; ++ + request = kzalloc(sizeof(struct regulatory_request), GFP_KERNEL); + if (!request) + return -ENOMEM; +diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl +index 55171647f5167..9432387dc1789 100755 +--- a/scripts/checkpatch.pl ++++ b/scripts/checkpatch.pl +@@ -2375,8 +2375,8 @@ sub process { + + # Check if the commit log has what seems like a diff which can confuse patch + if ($in_commit_log && !$commit_log_has_diff && +- (($line =~ m@^\s+diff\b.*a/[\w/]+@ && +- $line =~ m@^\s+diff\b.*a/([\w/]+)\s+b/$1\b@) || ++ (($line =~ m@^\s+diff\b.*a/([\w/]+)@ && ++ $line =~ m@^\s+diff\b.*a/[\w/]+\s+b/$1\b@) || + $line =~ m@^\s*(?:\-\-\-\s+a/|\+\+\+\s+b/)@ || + $line =~ m/^\s*\@\@ \-\d+,\d+ \+\d+,\d+ \@\@/)) { + ERROR("DIFF_IN_COMMIT_MSG", +diff --git a/sound/core/oss/mulaw.c b/sound/core/oss/mulaw.c +index 3788906421a73..fe27034f28460 100644 +--- a/sound/core/oss/mulaw.c ++++ b/sound/core/oss/mulaw.c +@@ -329,8 +329,8 @@ int snd_pcm_plugin_build_mulaw(struct snd_pcm_substream *plug, + snd_BUG(); + return -EINVAL; + } +- if (snd_BUG_ON(!snd_pcm_format_linear(format->format))) +- return -ENXIO; ++ if (!snd_pcm_format_linear(format->format)) ++ return -EINVAL; + + err = snd_pcm_plugin_build(plug, "Mu-Law<->linear conversion", + src_format, dst_format, +diff --git a/sound/firewire/digi00x/digi00x.c b/sound/firewire/digi00x/digi00x.c +index ef689997d6a5b..bf53e342788e2 100644 +--- a/sound/firewire/digi00x/digi00x.c ++++ b/sound/firewire/digi00x/digi00x.c +@@ -15,6 +15,7 @@ MODULE_LICENSE("GPL v2"); + #define VENDOR_DIGIDESIGN 0x00a07e + #define MODEL_CONSOLE 0x000001 + #define MODEL_RACK 0x000002 ++#define SPEC_VERSION 0x000001 + + static int name_card(struct snd_dg00x *dg00x) + { +@@ -185,14 +186,18 @@ static const struct ieee1394_device_id snd_dg00x_id_table[] = { + /* Both of 002/003 use the same ID. */ + { + .match_flags = IEEE1394_MATCH_VENDOR_ID | ++ IEEE1394_MATCH_VERSION | + IEEE1394_MATCH_MODEL_ID, + .vendor_id = VENDOR_DIGIDESIGN, ++ .version = SPEC_VERSION, + .model_id = MODEL_CONSOLE, + }, + { + .match_flags = IEEE1394_MATCH_VENDOR_ID | ++ IEEE1394_MATCH_VERSION | + IEEE1394_MATCH_MODEL_ID, + .vendor_id = VENDOR_DIGIDESIGN, ++ .version = SPEC_VERSION, + .model_id = MODEL_RACK, + }, + {} +diff --git a/sound/firewire/tascam/tascam.c b/sound/firewire/tascam/tascam.c +index 4c967ac1c0e83..40ed4c92e48bd 100644 +--- a/sound/firewire/tascam/tascam.c ++++ b/sound/firewire/tascam/tascam.c +@@ -225,11 +225,39 @@ static void snd_tscm_remove(struct fw_unit *unit) + } + + static const struct ieee1394_device_id snd_tscm_id_table[] = { ++ // Tascam, FW-1884. + { + .match_flags = IEEE1394_MATCH_VENDOR_ID | +- IEEE1394_MATCH_SPECIFIER_ID, ++ IEEE1394_MATCH_SPECIFIER_ID | ++ IEEE1394_MATCH_VERSION, + .vendor_id = 0x00022e, + .specifier_id = 0x00022e, ++ .version = 0x800000, ++ }, ++ // Tascam, FE-8 (.version = 0x800001) ++ // This kernel module doesn't support FE-8 because the most of features ++ // can be implemented in userspace without any specific support of this ++ // module. ++ // ++ // .version = 0x800002 is unknown. ++ // ++ // Tascam, FW-1082. ++ { ++ .match_flags = IEEE1394_MATCH_VENDOR_ID | ++ IEEE1394_MATCH_SPECIFIER_ID | ++ IEEE1394_MATCH_VERSION, ++ .vendor_id = 0x00022e, ++ .specifier_id = 0x00022e, ++ .version = 0x800003, ++ }, ++ // Tascam, FW-1804. ++ { ++ .match_flags = IEEE1394_MATCH_VENDOR_ID | ++ IEEE1394_MATCH_SPECIFIER_ID | ++ IEEE1394_MATCH_VERSION, ++ .vendor_id = 0x00022e, ++ .specifier_id = 0x00022e, ++ .version = 0x800004, + }, + /* FE-08 requires reverse-engineering because it just has faders. */ + {} +diff --git a/sound/pci/ca0106/ca0106_main.c b/sound/pci/ca0106/ca0106_main.c +index 6165a57a94aea..2c30a0672c17f 100644 +--- a/sound/pci/ca0106/ca0106_main.c ++++ b/sound/pci/ca0106/ca0106_main.c +@@ -551,7 +551,8 @@ static int snd_ca0106_pcm_power_dac(struct snd_ca0106 *chip, int channel_id, + else + /* Power down */ + chip->spi_dac_reg[reg] |= bit; +- return snd_ca0106_spi_write(chip, chip->spi_dac_reg[reg]); ++ if (snd_ca0106_spi_write(chip, chip->spi_dac_reg[reg]) != 0) ++ return -ENXIO; + } + return 0; + } +diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt +index 92335193dc338..d443ca3abf27d 100644 +--- a/tools/perf/Documentation/perf-record.txt ++++ b/tools/perf/Documentation/perf-record.txt +@@ -33,6 +33,10 @@ OPTIONS + - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a + hexadecimal event descriptor. + ++ - a symbolic or raw PMU event followed by an optional colon ++ and a list of event modifiers, e.g., cpu-cycles:p. See the ++ linkperf:perf-list[1] man page for details on event modifiers. ++ + - a symbolically formed PMU event like 'pmu/param1=0x3,param2/' where + 'param1', 'param2', etc are defined as formats for the PMU in + /sys/bus/event_source/devices/<pmu>/format/*. +diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt +index d96ccd4844df9..b099ac1de8546 100644 +--- a/tools/perf/Documentation/perf-stat.txt ++++ b/tools/perf/Documentation/perf-stat.txt +@@ -39,6 +39,10 @@ report:: + - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a + hexadecimal event descriptor. + ++ - a symbolic or raw PMU event followed by an optional colon ++ and a list of event modifiers, e.g., cpu-cycles:p. See the ++ linkperf:perf-list[1] man page for details on event modifiers. ++ + - a symbolically formed event like 'pmu/param1=0x3,param2/' where + param1 and param2 are defined as formats for the PMU in + /sys/bus/event_sources/devices/<pmu>/format/* |