commit:     c054eed8e07c74be300906a57710035d78899d71
Author:     Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Tue Jul 17 16:18:10 2018 +0000
Commit:     Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Tue Jul 17 16:18:10 2018 +0000
URL:        https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=c054eed8

Linux patch 4.17.7

 0000_README             |    4 +
 1006_linux-4.17.7.patch | 4347 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 4351 insertions(+)

diff --git a/0000_README b/0000_README
index b414442..a165e9a 100644
--- a/0000_README
+++ b/0000_README
@@ -67,6 +67,10 @@ Patch:  1005_linux-4.17.6.patch
 From:   http://www.kernel.org
 Desc:   Linux 4.17.6
 
+Patch:  1006_linux-4.17.7.patch
+From:   http://www.kernel.org
+Desc:   Linux 4.17.7
+
 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/1006_linux-4.17.7.patch b/1006_linux-4.17.7.patch
new file mode 100644
index 0000000..2f4965d
--- /dev/null
+++ b/1006_linux-4.17.7.patch
@@ -0,0 +1,4347 @@
+diff --git a/Documentation/kbuild/kbuild.txt b/Documentation/kbuild/kbuild.txt
+index 6c9c69ec3986..0fa16b461256 100644
+--- a/Documentation/kbuild/kbuild.txt
++++ b/Documentation/kbuild/kbuild.txt
+@@ -148,15 +148,6 @@ stripped after they are installed.  If INSTALL_MOD_STRIP 
is '1', then
+ the default option --strip-debug will be used.  Otherwise,
+ INSTALL_MOD_STRIP value will be used as the options to the strip command.
+ 
+-INSTALL_FW_PATH
+---------------------------------------------------
+-INSTALL_FW_PATH specifies where to install the firmware blobs.
+-The default value is:
+-
+-    $(INSTALL_MOD_PATH)/lib/firmware
+-
+-The value can be overridden in which case the default value is ignored.
+-
+ INSTALL_HDR_PATH
+ --------------------------------------------------
+ INSTALL_HDR_PATH specifies where to install user space headers when
+diff --git a/Makefile b/Makefile
+index 1a885c8f82ef..5c9f331f29c0 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0
+ VERSION = 4
+ PATCHLEVEL = 17
+-SUBLEVEL = 6
++SUBLEVEL = 7
+ EXTRAVERSION =
+ NAME = Merciless Moray
+ 
+diff --git a/arch/arm/boot/dts/armada-38x.dtsi 
b/arch/arm/boot/dts/armada-38x.dtsi
+index 4cc09e43eea2..e8309ecc32b9 100644
+--- a/arch/arm/boot/dts/armada-38x.dtsi
++++ b/arch/arm/boot/dts/armada-38x.dtsi
+@@ -547,7 +547,7 @@
+ 
+                       thermal: thermal@e8078 {
+                               compatible = "marvell,armada380-thermal";
+-                              reg = <0xe4078 0x4>, <0xe4074 0x4>;
++                              reg = <0xe4078 0x4>, <0xe4070 0x8>;
+                               status = "okay";
+                       };
+ 
+diff --git a/arch/arm64/include/asm/simd.h b/arch/arm64/include/asm/simd.h
+index fa8b3fe932e6..6495cc51246f 100644
+--- a/arch/arm64/include/asm/simd.h
++++ b/arch/arm64/include/asm/simd.h
+@@ -29,20 +29,15 @@ DECLARE_PER_CPU(bool, kernel_neon_busy);
+ static __must_check inline bool may_use_simd(void)
+ {
+       /*
+-       * The raw_cpu_read() is racy if called with preemption enabled.
+-       * This is not a bug: kernel_neon_busy is only set when
+-       * preemption is disabled, so we cannot migrate to another CPU
+-       * while it is set, nor can we migrate to a CPU where it is set.
+-       * So, if we find it clear on some CPU then we're guaranteed to
+-       * find it clear on any CPU we could migrate to.
+-       *
+-       * If we are in between kernel_neon_begin()...kernel_neon_end(),
+-       * the flag will be set, but preemption is also disabled, so we
+-       * can't migrate to another CPU and spuriously see it become
+-       * false.
++       * kernel_neon_busy is only set while preemption is disabled,
++       * and is clear whenever preemption is enabled. Since
++       * this_cpu_read() is atomic w.r.t. preemption, kernel_neon_busy
++       * cannot change under our feet -- if it's set we cannot be
++       * migrated, and if it's clear we cannot be migrated to a CPU
++       * where it is set.
+        */
+       return !in_irq() && !irqs_disabled() && !in_nmi() &&
+-              !raw_cpu_read(kernel_neon_busy);
++              !this_cpu_read(kernel_neon_busy);
+ }
+ 
+ #else /* ! CONFIG_KERNEL_MODE_NEON */
+diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
+index 3775a8d694fb..d4c59d9dca5b 100644
+--- a/arch/mips/kernel/process.c
++++ b/arch/mips/kernel/process.c
+@@ -29,6 +29,7 @@
+ #include <linux/kallsyms.h>
+ #include <linux/random.h>
+ #include <linux/prctl.h>
++#include <linux/nmi.h>
+ 
+ #include <asm/asm.h>
+ #include <asm/bootinfo.h>
+@@ -655,28 +656,42 @@ unsigned long arch_align_stack(unsigned long sp)
+       return sp & ALMASK;
+ }
+ 
+-static void arch_dump_stack(void *info)
++static DEFINE_PER_CPU(call_single_data_t, backtrace_csd);
++static struct cpumask backtrace_csd_busy;
++
++static void handle_backtrace(void *info)
+ {
+-      struct pt_regs *regs;
++      nmi_cpu_backtrace(get_irq_regs());
++      cpumask_clear_cpu(smp_processor_id(), &backtrace_csd_busy);
++}
+ 
+-      regs = get_irq_regs();
++static void raise_backtrace(cpumask_t *mask)
++{
++      call_single_data_t *csd;
++      int cpu;
+ 
+-      if (regs)
+-              show_regs(regs);
++      for_each_cpu(cpu, mask) {
++              /*
++               * If we previously sent an IPI to the target CPU & it hasn't
++               * cleared its bit in the busy cpumask then it didn't handle
++               * our previous IPI & it's not safe for us to reuse the
++               * call_single_data_t.
++               */
++              if (cpumask_test_and_set_cpu(cpu, &backtrace_csd_busy)) {
++                      pr_warn("Unable to send backtrace IPI to CPU%u - 
perhaps it hung?\n",
++                              cpu);
++                      continue;
++              }
+ 
+-      dump_stack();
++              csd = &per_cpu(backtrace_csd, cpu);
++              csd->func = handle_backtrace;
++              smp_call_function_single_async(cpu, csd);
++      }
+ }
+ 
+ void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self)
+ {
+-      long this_cpu = get_cpu();
+-
+-      if (cpumask_test_cpu(this_cpu, mask) && !exclude_self)
+-              dump_stack();
+-
+-      smp_call_function_many(mask, arch_dump_stack, NULL, 1);
+-
+-      put_cpu();
++      nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_backtrace);
+ }
+ 
+ int mips_get_process_fp_mode(struct task_struct *task)
+diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
+index 967e9e4e795e..a91777630045 100644
+--- a/arch/mips/kernel/traps.c
++++ b/arch/mips/kernel/traps.c
+@@ -351,6 +351,7 @@ static void __show_regs(const struct pt_regs *regs)
+ void show_regs(struct pt_regs *regs)
+ {
+       __show_regs((struct pt_regs *)regs);
++      dump_stack();
+ }
+ 
+ void show_registers(struct pt_regs *regs)
+diff --git a/arch/mips/mm/ioremap.c b/arch/mips/mm/ioremap.c
+index 1986e09fb457..1601d90b087b 100644
+--- a/arch/mips/mm/ioremap.c
++++ b/arch/mips/mm/ioremap.c
+@@ -9,6 +9,7 @@
+ #include <linux/export.h>
+ #include <asm/addrspace.h>
+ #include <asm/byteorder.h>
++#include <linux/ioport.h>
+ #include <linux/sched.h>
+ #include <linux/slab.h>
+ #include <linux/vmalloc.h>
+@@ -98,6 +99,20 @@ static int remap_area_pages(unsigned long address, 
phys_addr_t phys_addr,
+       return error;
+ }
+ 
++static int __ioremap_check_ram(unsigned long start_pfn, unsigned long 
nr_pages,
++                             void *arg)
++{
++      unsigned long i;
++
++      for (i = 0; i < nr_pages; i++) {
++              if (pfn_valid(start_pfn + i) &&
++                  !PageReserved(pfn_to_page(start_pfn + i)))
++                      return 1;
++      }
++
++      return 0;
++}
++
+ /*
+  * Generic mapping function (not visible outside):
+  */
+@@ -116,8 +131,8 @@ static int remap_area_pages(unsigned long address, 
phys_addr_t phys_addr,
+ 
+ void __iomem * __ioremap(phys_addr_t phys_addr, phys_addr_t size, unsigned 
long flags)
+ {
++      unsigned long offset, pfn, last_pfn;
+       struct vm_struct * area;
+-      unsigned long offset;
+       phys_addr_t last_addr;
+       void * addr;
+ 
+@@ -137,18 +152,16 @@ void __iomem * __ioremap(phys_addr_t phys_addr, 
phys_addr_t size, unsigned long
+               return (void __iomem *) CKSEG1ADDR(phys_addr);
+ 
+       /*
+-       * Don't allow anybody to remap normal RAM that we're using..
++       * Don't allow anybody to remap RAM that may be allocated by the page
++       * allocator, since that could lead to races & data clobbering.
+        */
+-      if (phys_addr < virt_to_phys(high_memory)) {
+-              char *t_addr, *t_end;
+-              struct page *page;
+-
+-              t_addr = __va(phys_addr);
+-              t_end = t_addr + (size - 1);
+-
+-              for(page = virt_to_page(t_addr); page <= virt_to_page(t_end); 
page++)
+-                      if(!PageReserved(page))
+-                              return NULL;
++      pfn = PFN_DOWN(phys_addr);
++      last_pfn = PFN_DOWN(last_addr);
++      if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
++                                __ioremap_check_ram) == 1) {
++              WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n",
++                        &phys_addr, &last_addr);
++              return NULL;
+       }
+ 
+       /*
+diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
+index 5f07333bb224..9c903a420cda 100644
+--- a/arch/x86/crypto/Makefile
++++ b/arch/x86/crypto/Makefile
+@@ -15,7 +15,6 @@ obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o
+ 
+ obj-$(CONFIG_CRYPTO_AES_586) += aes-i586.o
+ obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o
+-obj-$(CONFIG_CRYPTO_SALSA20_586) += salsa20-i586.o
+ obj-$(CONFIG_CRYPTO_SERPENT_SSE2_586) += serpent-sse2-i586.o
+ 
+ obj-$(CONFIG_CRYPTO_AES_X86_64) += aes-x86_64.o
+@@ -24,7 +23,6 @@ obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o
+ obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
+ obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
+ obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o
+-obj-$(CONFIG_CRYPTO_SALSA20_X86_64) += salsa20-x86_64.o
+ obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha20-x86_64.o
+ obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o
+ obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
+@@ -59,7 +57,6 @@ endif
+ 
+ aes-i586-y := aes-i586-asm_32.o aes_glue.o
+ twofish-i586-y := twofish-i586-asm_32.o twofish_glue.o
+-salsa20-i586-y := salsa20-i586-asm_32.o salsa20_glue.o
+ serpent-sse2-i586-y := serpent-sse2-i586-asm_32.o serpent_sse2_glue.o
+ 
+ aes-x86_64-y := aes-x86_64-asm_64.o aes_glue.o
+@@ -68,7 +65,6 @@ camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o
+ blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
+ twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o
+ twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o
+-salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o
+ chacha20-x86_64-y := chacha20-ssse3-x86_64.o chacha20_glue.o
+ serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
+ 
+diff --git a/arch/x86/crypto/salsa20-i586-asm_32.S 
b/arch/x86/crypto/salsa20-i586-asm_32.S
+deleted file mode 100644
+index 6014b7b9e52a..000000000000
+--- a/arch/x86/crypto/salsa20-i586-asm_32.S
++++ /dev/null
+@@ -1,938 +0,0 @@
+-# Derived from:
+-#     salsa20_pm.s version 20051229
+-#     D. J. Bernstein
+-#     Public domain.
+-
+-#include <linux/linkage.h>
+-
+-.text
+-
+-# enter salsa20_encrypt_bytes
+-ENTRY(salsa20_encrypt_bytes)
+-      mov     %esp,%eax
+-      and     $31,%eax
+-      add     $256,%eax
+-      sub     %eax,%esp
+-      # eax_stack = eax
+-      movl    %eax,80(%esp)
+-      # ebx_stack = ebx
+-      movl    %ebx,84(%esp)
+-      # esi_stack = esi
+-      movl    %esi,88(%esp)
+-      # edi_stack = edi
+-      movl    %edi,92(%esp)
+-      # ebp_stack = ebp
+-      movl    %ebp,96(%esp)
+-      # x = arg1
+-      movl    4(%esp,%eax),%edx
+-      # m = arg2
+-      movl    8(%esp,%eax),%esi
+-      # out = arg3
+-      movl    12(%esp,%eax),%edi
+-      # bytes = arg4
+-      movl    16(%esp,%eax),%ebx
+-      # bytes -= 0
+-      sub     $0,%ebx
+-      # goto done if unsigned<=
+-      jbe     ._done
+-._start:
+-      # in0 = *(uint32 *) (x + 0)
+-      movl    0(%edx),%eax
+-      # in1 = *(uint32 *) (x + 4)
+-      movl    4(%edx),%ecx
+-      # in2 = *(uint32 *) (x + 8)
+-      movl    8(%edx),%ebp
+-      # j0 = in0
+-      movl    %eax,164(%esp)
+-      # in3 = *(uint32 *) (x + 12)
+-      movl    12(%edx),%eax
+-      # j1 = in1
+-      movl    %ecx,168(%esp)
+-      # in4 = *(uint32 *) (x + 16)
+-      movl    16(%edx),%ecx
+-      # j2 = in2
+-      movl    %ebp,172(%esp)
+-      # in5 = *(uint32 *) (x + 20)
+-      movl    20(%edx),%ebp
+-      # j3 = in3
+-      movl    %eax,176(%esp)
+-      # in6 = *(uint32 *) (x + 24)
+-      movl    24(%edx),%eax
+-      # j4 = in4
+-      movl    %ecx,180(%esp)
+-      # in7 = *(uint32 *) (x + 28)
+-      movl    28(%edx),%ecx
+-      # j5 = in5
+-      movl    %ebp,184(%esp)
+-      # in8 = *(uint32 *) (x + 32)
+-      movl    32(%edx),%ebp
+-      # j6 = in6
+-      movl    %eax,188(%esp)
+-      # in9 = *(uint32 *) (x + 36)
+-      movl    36(%edx),%eax
+-      # j7 = in7
+-      movl    %ecx,192(%esp)
+-      # in10 = *(uint32 *) (x + 40)
+-      movl    40(%edx),%ecx
+-      # j8 = in8
+-      movl    %ebp,196(%esp)
+-      # in11 = *(uint32 *) (x + 44)
+-      movl    44(%edx),%ebp
+-      # j9 = in9
+-      movl    %eax,200(%esp)
+-      # in12 = *(uint32 *) (x + 48)
+-      movl    48(%edx),%eax
+-      # j10 = in10
+-      movl    %ecx,204(%esp)
+-      # in13 = *(uint32 *) (x + 52)
+-      movl    52(%edx),%ecx
+-      # j11 = in11
+-      movl    %ebp,208(%esp)
+-      # in14 = *(uint32 *) (x + 56)
+-      movl    56(%edx),%ebp
+-      # j12 = in12
+-      movl    %eax,212(%esp)
+-      # in15 = *(uint32 *) (x + 60)
+-      movl    60(%edx),%eax
+-      # j13 = in13
+-      movl    %ecx,216(%esp)
+-      # j14 = in14
+-      movl    %ebp,220(%esp)
+-      # j15 = in15
+-      movl    %eax,224(%esp)
+-      # x_backup = x
+-      movl    %edx,64(%esp)
+-._bytesatleast1:
+-      #   bytes - 64
+-      cmp     $64,%ebx
+-      #   goto nocopy if unsigned>=
+-      jae     ._nocopy
+-      #     ctarget = out
+-      movl    %edi,228(%esp)
+-      #     out = &tmp
+-      leal    0(%esp),%edi
+-      #     i = bytes
+-      mov     %ebx,%ecx
+-      #     while (i) { *out++ = *m++; --i }
+-      rep     movsb
+-      #     out = &tmp
+-      leal    0(%esp),%edi
+-      #     m = &tmp
+-      leal    0(%esp),%esi
+-._nocopy:
+-      #   out_backup = out
+-      movl    %edi,72(%esp)
+-      #   m_backup = m
+-      movl    %esi,68(%esp)
+-      #   bytes_backup = bytes
+-      movl    %ebx,76(%esp)
+-      #   in0 = j0
+-      movl    164(%esp),%eax
+-      #   in1 = j1
+-      movl    168(%esp),%ecx
+-      #   in2 = j2
+-      movl    172(%esp),%edx
+-      #   in3 = j3
+-      movl    176(%esp),%ebx
+-      #   x0 = in0
+-      movl    %eax,100(%esp)
+-      #   x1 = in1
+-      movl    %ecx,104(%esp)
+-      #   x2 = in2
+-      movl    %edx,108(%esp)
+-      #   x3 = in3
+-      movl    %ebx,112(%esp)
+-      #   in4 = j4
+-      movl    180(%esp),%eax
+-      #   in5 = j5
+-      movl    184(%esp),%ecx
+-      #   in6 = j6
+-      movl    188(%esp),%edx
+-      #   in7 = j7
+-      movl    192(%esp),%ebx
+-      #   x4 = in4
+-      movl    %eax,116(%esp)
+-      #   x5 = in5
+-      movl    %ecx,120(%esp)
+-      #   x6 = in6
+-      movl    %edx,124(%esp)
+-      #   x7 = in7
+-      movl    %ebx,128(%esp)
+-      #   in8 = j8
+-      movl    196(%esp),%eax
+-      #   in9 = j9
+-      movl    200(%esp),%ecx
+-      #   in10 = j10
+-      movl    204(%esp),%edx
+-      #   in11 = j11
+-      movl    208(%esp),%ebx
+-      #   x8 = in8
+-      movl    %eax,132(%esp)
+-      #   x9 = in9
+-      movl    %ecx,136(%esp)
+-      #   x10 = in10
+-      movl    %edx,140(%esp)
+-      #   x11 = in11
+-      movl    %ebx,144(%esp)
+-      #   in12 = j12
+-      movl    212(%esp),%eax
+-      #   in13 = j13
+-      movl    216(%esp),%ecx
+-      #   in14 = j14
+-      movl    220(%esp),%edx
+-      #   in15 = j15
+-      movl    224(%esp),%ebx
+-      #   x12 = in12
+-      movl    %eax,148(%esp)
+-      #   x13 = in13
+-      movl    %ecx,152(%esp)
+-      #   x14 = in14
+-      movl    %edx,156(%esp)
+-      #   x15 = in15
+-      movl    %ebx,160(%esp)
+-      #   i = 20
+-      mov     $20,%ebp
+-      # p = x0
+-      movl    100(%esp),%eax
+-      # s = x5
+-      movl    120(%esp),%ecx
+-      # t = x10
+-      movl    140(%esp),%edx
+-      # w = x15
+-      movl    160(%esp),%ebx
+-._mainloop:
+-      # x0 = p
+-      movl    %eax,100(%esp)
+-      #                               x10 = t
+-      movl    %edx,140(%esp)
+-      # p += x12
+-      addl    148(%esp),%eax
+-      #               x5 = s
+-      movl    %ecx,120(%esp)
+-      #                               t += x6
+-      addl    124(%esp),%edx
+-      #                                               x15 = w
+-      movl    %ebx,160(%esp)
+-      #               r = x1
+-      movl    104(%esp),%esi
+-      #               r += s
+-      add     %ecx,%esi
+-      #                                               v = x11
+-      movl    144(%esp),%edi
+-      #                                               v += w
+-      add     %ebx,%edi
+-      # p <<<= 7
+-      rol     $7,%eax
+-      # p ^= x4
+-      xorl    116(%esp),%eax
+-      #                               t <<<= 7
+-      rol     $7,%edx
+-      #                               t ^= x14
+-      xorl    156(%esp),%edx
+-      #               r <<<= 7
+-      rol     $7,%esi
+-      #               r ^= x9
+-      xorl    136(%esp),%esi
+-      #                                               v <<<= 7
+-      rol     $7,%edi
+-      #                                               v ^= x3
+-      xorl    112(%esp),%edi
+-      # x4 = p
+-      movl    %eax,116(%esp)
+-      #                               x14 = t
+-      movl    %edx,156(%esp)
+-      # p += x0
+-      addl    100(%esp),%eax
+-      #               x9 = r
+-      movl    %esi,136(%esp)
+-      #                               t += x10
+-      addl    140(%esp),%edx
+-      #                                               x3 = v
+-      movl    %edi,112(%esp)
+-      # p <<<= 9
+-      rol     $9,%eax
+-      # p ^= x8
+-      xorl    132(%esp),%eax
+-      #                               t <<<= 9
+-      rol     $9,%edx
+-      #                               t ^= x2
+-      xorl    108(%esp),%edx
+-      #               s += r
+-      add     %esi,%ecx
+-      #               s <<<= 9
+-      rol     $9,%ecx
+-      #               s ^= x13
+-      xorl    152(%esp),%ecx
+-      #                                               w += v
+-      add     %edi,%ebx
+-      #                                               w <<<= 9
+-      rol     $9,%ebx
+-      #                                               w ^= x7
+-      xorl    128(%esp),%ebx
+-      # x8 = p
+-      movl    %eax,132(%esp)
+-      #                               x2 = t
+-      movl    %edx,108(%esp)
+-      # p += x4
+-      addl    116(%esp),%eax
+-      #               x13 = s
+-      movl    %ecx,152(%esp)
+-      #                               t += x14
+-      addl    156(%esp),%edx
+-      #                                               x7 = w
+-      movl    %ebx,128(%esp)
+-      # p <<<= 13
+-      rol     $13,%eax
+-      # p ^= x12
+-      xorl    148(%esp),%eax
+-      #                               t <<<= 13
+-      rol     $13,%edx
+-      #                               t ^= x6
+-      xorl    124(%esp),%edx
+-      #               r += s
+-      add     %ecx,%esi
+-      #               r <<<= 13
+-      rol     $13,%esi
+-      #               r ^= x1
+-      xorl    104(%esp),%esi
+-      #                                               v += w
+-      add     %ebx,%edi
+-      #                                               v <<<= 13
+-      rol     $13,%edi
+-      #                                               v ^= x11
+-      xorl    144(%esp),%edi
+-      # x12 = p
+-      movl    %eax,148(%esp)
+-      #                               x6 = t
+-      movl    %edx,124(%esp)
+-      # p += x8
+-      addl    132(%esp),%eax
+-      #               x1 = r
+-      movl    %esi,104(%esp)
+-      #                               t += x2
+-      addl    108(%esp),%edx
+-      #                                               x11 = v
+-      movl    %edi,144(%esp)
+-      # p <<<= 18
+-      rol     $18,%eax
+-      # p ^= x0
+-      xorl    100(%esp),%eax
+-      #                               t <<<= 18
+-      rol     $18,%edx
+-      #                               t ^= x10
+-      xorl    140(%esp),%edx
+-      #               s += r
+-      add     %esi,%ecx
+-      #               s <<<= 18
+-      rol     $18,%ecx
+-      #               s ^= x5
+-      xorl    120(%esp),%ecx
+-      #                                               w += v
+-      add     %edi,%ebx
+-      #                                               w <<<= 18
+-      rol     $18,%ebx
+-      #                                               w ^= x15
+-      xorl    160(%esp),%ebx
+-      # x0 = p
+-      movl    %eax,100(%esp)
+-      #                               x10 = t
+-      movl    %edx,140(%esp)
+-      # p += x3
+-      addl    112(%esp),%eax
+-      # p <<<= 7
+-      rol     $7,%eax
+-      #               x5 = s
+-      movl    %ecx,120(%esp)
+-      #                               t += x9
+-      addl    136(%esp),%edx
+-      #                                               x15 = w
+-      movl    %ebx,160(%esp)
+-      #               r = x4
+-      movl    116(%esp),%esi
+-      #               r += s
+-      add     %ecx,%esi
+-      #                                               v = x14
+-      movl    156(%esp),%edi
+-      #                                               v += w
+-      add     %ebx,%edi
+-      # p ^= x1
+-      xorl    104(%esp),%eax
+-      #                               t <<<= 7
+-      rol     $7,%edx
+-      #                               t ^= x11
+-      xorl    144(%esp),%edx
+-      #               r <<<= 7
+-      rol     $7,%esi
+-      #               r ^= x6
+-      xorl    124(%esp),%esi
+-      #                                               v <<<= 7
+-      rol     $7,%edi
+-      #                                               v ^= x12
+-      xorl    148(%esp),%edi
+-      # x1 = p
+-      movl    %eax,104(%esp)
+-      #                               x11 = t
+-      movl    %edx,144(%esp)
+-      # p += x0
+-      addl    100(%esp),%eax
+-      #               x6 = r
+-      movl    %esi,124(%esp)
+-      #                               t += x10
+-      addl    140(%esp),%edx
+-      #                                               x12 = v
+-      movl    %edi,148(%esp)
+-      # p <<<= 9
+-      rol     $9,%eax
+-      # p ^= x2
+-      xorl    108(%esp),%eax
+-      #                               t <<<= 9
+-      rol     $9,%edx
+-      #                               t ^= x8
+-      xorl    132(%esp),%edx
+-      #               s += r
+-      add     %esi,%ecx
+-      #               s <<<= 9
+-      rol     $9,%ecx
+-      #               s ^= x7
+-      xorl    128(%esp),%ecx
+-      #                                               w += v
+-      add     %edi,%ebx
+-      #                                               w <<<= 9
+-      rol     $9,%ebx
+-      #                                               w ^= x13
+-      xorl    152(%esp),%ebx
+-      # x2 = p
+-      movl    %eax,108(%esp)
+-      #                               x8 = t
+-      movl    %edx,132(%esp)
+-      # p += x1
+-      addl    104(%esp),%eax
+-      #               x7 = s
+-      movl    %ecx,128(%esp)
+-      #                               t += x11
+-      addl    144(%esp),%edx
+-      #                                               x13 = w
+-      movl    %ebx,152(%esp)
+-      # p <<<= 13
+-      rol     $13,%eax
+-      # p ^= x3
+-      xorl    112(%esp),%eax
+-      #                               t <<<= 13
+-      rol     $13,%edx
+-      #                               t ^= x9
+-      xorl    136(%esp),%edx
+-      #               r += s
+-      add     %ecx,%esi
+-      #               r <<<= 13
+-      rol     $13,%esi
+-      #               r ^= x4
+-      xorl    116(%esp),%esi
+-      #                                               v += w
+-      add     %ebx,%edi
+-      #                                               v <<<= 13
+-      rol     $13,%edi
+-      #                                               v ^= x14
+-      xorl    156(%esp),%edi
+-      # x3 = p
+-      movl    %eax,112(%esp)
+-      #                               x9 = t
+-      movl    %edx,136(%esp)
+-      # p += x2
+-      addl    108(%esp),%eax
+-      #               x4 = r
+-      movl    %esi,116(%esp)
+-      #                               t += x8
+-      addl    132(%esp),%edx
+-      #                                               x14 = v
+-      movl    %edi,156(%esp)
+-      # p <<<= 18
+-      rol     $18,%eax
+-      # p ^= x0
+-      xorl    100(%esp),%eax
+-      #                               t <<<= 18
+-      rol     $18,%edx
+-      #                               t ^= x10
+-      xorl    140(%esp),%edx
+-      #               s += r
+-      add     %esi,%ecx
+-      #               s <<<= 18
+-      rol     $18,%ecx
+-      #               s ^= x5
+-      xorl    120(%esp),%ecx
+-      #                                               w += v
+-      add     %edi,%ebx
+-      #                                               w <<<= 18
+-      rol     $18,%ebx
+-      #                                               w ^= x15
+-      xorl    160(%esp),%ebx
+-      # x0 = p
+-      movl    %eax,100(%esp)
+-      #                               x10 = t
+-      movl    %edx,140(%esp)
+-      # p += x12
+-      addl    148(%esp),%eax
+-      #               x5 = s
+-      movl    %ecx,120(%esp)
+-      #                               t += x6
+-      addl    124(%esp),%edx
+-      #                                               x15 = w
+-      movl    %ebx,160(%esp)
+-      #               r = x1
+-      movl    104(%esp),%esi
+-      #               r += s
+-      add     %ecx,%esi
+-      #                                               v = x11
+-      movl    144(%esp),%edi
+-      #                                               v += w
+-      add     %ebx,%edi
+-      # p <<<= 7
+-      rol     $7,%eax
+-      # p ^= x4
+-      xorl    116(%esp),%eax
+-      #                               t <<<= 7
+-      rol     $7,%edx
+-      #                               t ^= x14
+-      xorl    156(%esp),%edx
+-      #               r <<<= 7
+-      rol     $7,%esi
+-      #               r ^= x9
+-      xorl    136(%esp),%esi
+-      #                                               v <<<= 7
+-      rol     $7,%edi
+-      #                                               v ^= x3
+-      xorl    112(%esp),%edi
+-      # x4 = p
+-      movl    %eax,116(%esp)
+-      #                               x14 = t
+-      movl    %edx,156(%esp)
+-      # p += x0
+-      addl    100(%esp),%eax
+-      #               x9 = r
+-      movl    %esi,136(%esp)
+-      #                               t += x10
+-      addl    140(%esp),%edx
+-      #                                               x3 = v
+-      movl    %edi,112(%esp)
+-      # p <<<= 9
+-      rol     $9,%eax
+-      # p ^= x8
+-      xorl    132(%esp),%eax
+-      #                               t <<<= 9
+-      rol     $9,%edx
+-      #                               t ^= x2
+-      xorl    108(%esp),%edx
+-      #               s += r
+-      add     %esi,%ecx
+-      #               s <<<= 9
+-      rol     $9,%ecx
+-      #               s ^= x13
+-      xorl    152(%esp),%ecx
+-      #                                               w += v
+-      add     %edi,%ebx
+-      #                                               w <<<= 9
+-      rol     $9,%ebx
+-      #                                               w ^= x7
+-      xorl    128(%esp),%ebx
+-      # x8 = p
+-      movl    %eax,132(%esp)
+-      #                               x2 = t
+-      movl    %edx,108(%esp)
+-      # p += x4
+-      addl    116(%esp),%eax
+-      #               x13 = s
+-      movl    %ecx,152(%esp)
+-      #                               t += x14
+-      addl    156(%esp),%edx
+-      #                                               x7 = w
+-      movl    %ebx,128(%esp)
+-      # p <<<= 13
+-      rol     $13,%eax
+-      # p ^= x12
+-      xorl    148(%esp),%eax
+-      #                               t <<<= 13
+-      rol     $13,%edx
+-      #                               t ^= x6
+-      xorl    124(%esp),%edx
+-      #               r += s
+-      add     %ecx,%esi
+-      #               r <<<= 13
+-      rol     $13,%esi
+-      #               r ^= x1
+-      xorl    104(%esp),%esi
+-      #                                               v += w
+-      add     %ebx,%edi
+-      #                                               v <<<= 13
+-      rol     $13,%edi
+-      #                                               v ^= x11
+-      xorl    144(%esp),%edi
+-      # x12 = p
+-      movl    %eax,148(%esp)
+-      #                               x6 = t
+-      movl    %edx,124(%esp)
+-      # p += x8
+-      addl    132(%esp),%eax
+-      #               x1 = r
+-      movl    %esi,104(%esp)
+-      #                               t += x2
+-      addl    108(%esp),%edx
+-      #                                               x11 = v
+-      movl    %edi,144(%esp)
+-      # p <<<= 18
+-      rol     $18,%eax
+-      # p ^= x0
+-      xorl    100(%esp),%eax
+-      #                               t <<<= 18
+-      rol     $18,%edx
+-      #                               t ^= x10
+-      xorl    140(%esp),%edx
+-      #               s += r
+-      add     %esi,%ecx
+-      #               s <<<= 18
+-      rol     $18,%ecx
+-      #               s ^= x5
+-      xorl    120(%esp),%ecx
+-      #                                               w += v
+-      add     %edi,%ebx
+-      #                                               w <<<= 18
+-      rol     $18,%ebx
+-      #                                               w ^= x15
+-      xorl    160(%esp),%ebx
+-      # x0 = p
+-      movl    %eax,100(%esp)
+-      #                               x10 = t
+-      movl    %edx,140(%esp)
+-      # p += x3
+-      addl    112(%esp),%eax
+-      # p <<<= 7
+-      rol     $7,%eax
+-      #               x5 = s
+-      movl    %ecx,120(%esp)
+-      #                               t += x9
+-      addl    136(%esp),%edx
+-      #                                               x15 = w
+-      movl    %ebx,160(%esp)
+-      #               r = x4
+-      movl    116(%esp),%esi
+-      #               r += s
+-      add     %ecx,%esi
+-      #                                               v = x14
+-      movl    156(%esp),%edi
+-      #                                               v += w
+-      add     %ebx,%edi
+-      # p ^= x1
+-      xorl    104(%esp),%eax
+-      #                               t <<<= 7
+-      rol     $7,%edx
+-      #                               t ^= x11
+-      xorl    144(%esp),%edx
+-      #               r <<<= 7
+-      rol     $7,%esi
+-      #               r ^= x6
+-      xorl    124(%esp),%esi
+-      #                                               v <<<= 7
+-      rol     $7,%edi
+-      #                                               v ^= x12
+-      xorl    148(%esp),%edi
+-      # x1 = p
+-      movl    %eax,104(%esp)
+-      #                               x11 = t
+-      movl    %edx,144(%esp)
+-      # p += x0
+-      addl    100(%esp),%eax
+-      #               x6 = r
+-      movl    %esi,124(%esp)
+-      #                               t += x10
+-      addl    140(%esp),%edx
+-      #                                               x12 = v
+-      movl    %edi,148(%esp)
+-      # p <<<= 9
+-      rol     $9,%eax
+-      # p ^= x2
+-      xorl    108(%esp),%eax
+-      #                               t <<<= 9
+-      rol     $9,%edx
+-      #                               t ^= x8
+-      xorl    132(%esp),%edx
+-      #               s += r
+-      add     %esi,%ecx
+-      #               s <<<= 9
+-      rol     $9,%ecx
+-      #               s ^= x7
+-      xorl    128(%esp),%ecx
+-      #                                               w += v
+-      add     %edi,%ebx
+-      #                                               w <<<= 9
+-      rol     $9,%ebx
+-      #                                               w ^= x13
+-      xorl    152(%esp),%ebx
+-      # x2 = p
+-      movl    %eax,108(%esp)
+-      #                               x8 = t
+-      movl    %edx,132(%esp)
+-      # p += x1
+-      addl    104(%esp),%eax
+-      #               x7 = s
+-      movl    %ecx,128(%esp)
+-      #                               t += x11
+-      addl    144(%esp),%edx
+-      #                                               x13 = w
+-      movl    %ebx,152(%esp)
+-      # p <<<= 13
+-      rol     $13,%eax
+-      # p ^= x3
+-      xorl    112(%esp),%eax
+-      #                               t <<<= 13
+-      rol     $13,%edx
+-      #                               t ^= x9
+-      xorl    136(%esp),%edx
+-      #               r += s
+-      add     %ecx,%esi
+-      #               r <<<= 13
+-      rol     $13,%esi
+-      #               r ^= x4
+-      xorl    116(%esp),%esi
+-      #                                               v += w
+-      add     %ebx,%edi
+-      #                                               v <<<= 13
+-      rol     $13,%edi
+-      #                                               v ^= x14
+-      xorl    156(%esp),%edi
+-      # x3 = p
+-      movl    %eax,112(%esp)
+-      #                               x9 = t
+-      movl    %edx,136(%esp)
+-      # p += x2
+-      addl    108(%esp),%eax
+-      #               x4 = r
+-      movl    %esi,116(%esp)
+-      #                               t += x8
+-      addl    132(%esp),%edx
+-      #                                               x14 = v
+-      movl    %edi,156(%esp)
+-      # p <<<= 18
+-      rol     $18,%eax
+-      # p ^= x0
+-      xorl    100(%esp),%eax
+-      #                               t <<<= 18
+-      rol     $18,%edx
+-      #                               t ^= x10
+-      xorl    140(%esp),%edx
+-      #               s += r
+-      add     %esi,%ecx
+-      #               s <<<= 18
+-      rol     $18,%ecx
+-      #               s ^= x5
+-      xorl    120(%esp),%ecx
+-      #                                               w += v
+-      add     %edi,%ebx
+-      #                                               w <<<= 18
+-      rol     $18,%ebx
+-      #                                               w ^= x15
+-      xorl    160(%esp),%ebx
+-      # i -= 4
+-      sub     $4,%ebp
+-      # goto mainloop if unsigned >
+-      ja      ._mainloop
+-      # x0 = p
+-      movl    %eax,100(%esp)
+-      # x5 = s
+-      movl    %ecx,120(%esp)
+-      # x10 = t
+-      movl    %edx,140(%esp)
+-      # x15 = w
+-      movl    %ebx,160(%esp)
+-      #   out = out_backup
+-      movl    72(%esp),%edi
+-      #   m = m_backup
+-      movl    68(%esp),%esi
+-      #   in0 = x0
+-      movl    100(%esp),%eax
+-      #   in1 = x1
+-      movl    104(%esp),%ecx
+-      #   in0 += j0
+-      addl    164(%esp),%eax
+-      #   in1 += j1
+-      addl    168(%esp),%ecx
+-      #   in0 ^= *(uint32 *) (m + 0)
+-      xorl    0(%esi),%eax
+-      #   in1 ^= *(uint32 *) (m + 4)
+-      xorl    4(%esi),%ecx
+-      #   *(uint32 *) (out + 0) = in0
+-      movl    %eax,0(%edi)
+-      #   *(uint32 *) (out + 4) = in1
+-      movl    %ecx,4(%edi)
+-      #   in2 = x2
+-      movl    108(%esp),%eax
+-      #   in3 = x3
+-      movl    112(%esp),%ecx
+-      #   in2 += j2
+-      addl    172(%esp),%eax
+-      #   in3 += j3
+-      addl    176(%esp),%ecx
+-      #   in2 ^= *(uint32 *) (m + 8)
+-      xorl    8(%esi),%eax
+-      #   in3 ^= *(uint32 *) (m + 12)
+-      xorl    12(%esi),%ecx
+-      #   *(uint32 *) (out + 8) = in2
+-      movl    %eax,8(%edi)
+-      #   *(uint32 *) (out + 12) = in3
+-      movl    %ecx,12(%edi)
+-      #   in4 = x4
+-      movl    116(%esp),%eax
+-      #   in5 = x5
+-      movl    120(%esp),%ecx
+-      #   in4 += j4
+-      addl    180(%esp),%eax
+-      #   in5 += j5
+-      addl    184(%esp),%ecx
+-      #   in4 ^= *(uint32 *) (m + 16)
+-      xorl    16(%esi),%eax
+-      #   in5 ^= *(uint32 *) (m + 20)
+-      xorl    20(%esi),%ecx
+-      #   *(uint32 *) (out + 16) = in4
+-      movl    %eax,16(%edi)
+-      #   *(uint32 *) (out + 20) = in5
+-      movl    %ecx,20(%edi)
+-      #   in6 = x6
+-      movl    124(%esp),%eax
+-      #   in7 = x7
+-      movl    128(%esp),%ecx
+-      #   in6 += j6
+-      addl    188(%esp),%eax
+-      #   in7 += j7
+-      addl    192(%esp),%ecx
+-      #   in6 ^= *(uint32 *) (m + 24)
+-      xorl    24(%esi),%eax
+-      #   in7 ^= *(uint32 *) (m + 28)
+-      xorl    28(%esi),%ecx
+-      #   *(uint32 *) (out + 24) = in6
+-      movl    %eax,24(%edi)
+-      #   *(uint32 *) (out + 28) = in7
+-      movl    %ecx,28(%edi)
+-      #   in8 = x8
+-      movl    132(%esp),%eax
+-      #   in9 = x9
+-      movl    136(%esp),%ecx
+-      #   in8 += j8
+-      addl    196(%esp),%eax
+-      #   in9 += j9
+-      addl    200(%esp),%ecx
+-      #   in8 ^= *(uint32 *) (m + 32)
+-      xorl    32(%esi),%eax
+-      #   in9 ^= *(uint32 *) (m + 36)
+-      xorl    36(%esi),%ecx
+-      #   *(uint32 *) (out + 32) = in8
+-      movl    %eax,32(%edi)
+-      #   *(uint32 *) (out + 36) = in9
+-      movl    %ecx,36(%edi)
+-      #   in10 = x10
+-      movl    140(%esp),%eax
+-      #   in11 = x11
+-      movl    144(%esp),%ecx
+-      #   in10 += j10
+-      addl    204(%esp),%eax
+-      #   in11 += j11
+-      addl    208(%esp),%ecx
+-      #   in10 ^= *(uint32 *) (m + 40)
+-      xorl    40(%esi),%eax
+-      #   in11 ^= *(uint32 *) (m + 44)
+-      xorl    44(%esi),%ecx
+-      #   *(uint32 *) (out + 40) = in10
+-      movl    %eax,40(%edi)
+-      #   *(uint32 *) (out + 44) = in11
+-      movl    %ecx,44(%edi)
+-      #   in12 = x12
+-      movl    148(%esp),%eax
+-      #   in13 = x13
+-      movl    152(%esp),%ecx
+-      #   in12 += j12
+-      addl    212(%esp),%eax
+-      #   in13 += j13
+-      addl    216(%esp),%ecx
+-      #   in12 ^= *(uint32 *) (m + 48)
+-      xorl    48(%esi),%eax
+-      #   in13 ^= *(uint32 *) (m + 52)
+-      xorl    52(%esi),%ecx
+-      #   *(uint32 *) (out + 48) = in12
+-      movl    %eax,48(%edi)
+-      #   *(uint32 *) (out + 52) = in13
+-      movl    %ecx,52(%edi)
+-      #   in14 = x14
+-      movl    156(%esp),%eax
+-      #   in15 = x15
+-      movl    160(%esp),%ecx
+-      #   in14 += j14
+-      addl    220(%esp),%eax
+-      #   in15 += j15
+-      addl    224(%esp),%ecx
+-      #   in14 ^= *(uint32 *) (m + 56)
+-      xorl    56(%esi),%eax
+-      #   in15 ^= *(uint32 *) (m + 60)
+-      xorl    60(%esi),%ecx
+-      #   *(uint32 *) (out + 56) = in14
+-      movl    %eax,56(%edi)
+-      #   *(uint32 *) (out + 60) = in15
+-      movl    %ecx,60(%edi)
+-      #   bytes = bytes_backup
+-      movl    76(%esp),%ebx
+-      #   in8 = j8
+-      movl    196(%esp),%eax
+-      #   in9 = j9
+-      movl    200(%esp),%ecx
+-      #   in8 += 1
+-      add     $1,%eax
+-      #   in9 += 0 + carry
+-      adc     $0,%ecx
+-      #   j8 = in8
+-      movl    %eax,196(%esp)
+-      #   j9 = in9
+-      movl    %ecx,200(%esp)
+-      #   bytes - 64
+-      cmp     $64,%ebx
+-      #   goto bytesatleast65 if unsigned>
+-      ja      ._bytesatleast65
+-      #     goto bytesatleast64 if unsigned>=
+-      jae     ._bytesatleast64
+-      #       m = out
+-      mov     %edi,%esi
+-      #       out = ctarget
+-      movl    228(%esp),%edi
+-      #       i = bytes
+-      mov     %ebx,%ecx
+-      #       while (i) { *out++ = *m++; --i }
+-      rep     movsb
+-._bytesatleast64:
+-      #     x = x_backup
+-      movl    64(%esp),%eax
+-      #     in8 = j8
+-      movl    196(%esp),%ecx
+-      #     in9 = j9
+-      movl    200(%esp),%edx
+-      #     *(uint32 *) (x + 32) = in8
+-      movl    %ecx,32(%eax)
+-      #     *(uint32 *) (x + 36) = in9
+-      movl    %edx,36(%eax)
+-._done:
+-      #     eax = eax_stack
+-      movl    80(%esp),%eax
+-      #     ebx = ebx_stack
+-      movl    84(%esp),%ebx
+-      #     esi = esi_stack
+-      movl    88(%esp),%esi
+-      #     edi = edi_stack
+-      movl    92(%esp),%edi
+-      #     ebp = ebp_stack
+-      movl    96(%esp),%ebp
+-      #     leave
+-      add     %eax,%esp
+-      ret
+-._bytesatleast65:
+-      #   bytes -= 64
+-      sub     $64,%ebx
+-      #   out += 64
+-      add     $64,%edi
+-      #   m += 64
+-      add     $64,%esi
+-      # goto bytesatleast1
+-      jmp     ._bytesatleast1
+-ENDPROC(salsa20_encrypt_bytes)
+diff --git a/arch/x86/crypto/salsa20-x86_64-asm_64.S 
b/arch/x86/crypto/salsa20-x86_64-asm_64.S
+deleted file mode 100644
+index 03a4918f41ee..000000000000
+--- a/arch/x86/crypto/salsa20-x86_64-asm_64.S
++++ /dev/null
+@@ -1,805 +0,0 @@
+-/* SPDX-License-Identifier: GPL-2.0 */
+-#include <linux/linkage.h>
+-
+-# enter salsa20_encrypt_bytes
+-ENTRY(salsa20_encrypt_bytes)
+-      mov     %rsp,%r11
+-      and     $31,%r11
+-      add     $256,%r11
+-      sub     %r11,%rsp
+-      # x = arg1
+-      mov     %rdi,%r8
+-      # m = arg2
+-      mov     %rsi,%rsi
+-      # out = arg3
+-      mov     %rdx,%rdi
+-      # bytes = arg4
+-      mov     %rcx,%rdx
+-      #               unsigned>? bytes - 0
+-      cmp     $0,%rdx
+-      # comment:fp stack unchanged by jump
+-      # goto done if !unsigned>
+-      jbe     ._done
+-      # comment:fp stack unchanged by fallthrough
+-# start:
+-._start:
+-      # r11_stack = r11
+-      movq    %r11,0(%rsp)
+-      # r12_stack = r12
+-      movq    %r12,8(%rsp)
+-      # r13_stack = r13
+-      movq    %r13,16(%rsp)
+-      # r14_stack = r14
+-      movq    %r14,24(%rsp)
+-      # r15_stack = r15
+-      movq    %r15,32(%rsp)
+-      # rbx_stack = rbx
+-      movq    %rbx,40(%rsp)
+-      # rbp_stack = rbp
+-      movq    %rbp,48(%rsp)
+-      # in0 = *(uint64 *) (x + 0)
+-      movq    0(%r8),%rcx
+-      # in2 = *(uint64 *) (x + 8)
+-      movq    8(%r8),%r9
+-      # in4 = *(uint64 *) (x + 16)
+-      movq    16(%r8),%rax
+-      # in6 = *(uint64 *) (x + 24)
+-      movq    24(%r8),%r10
+-      # in8 = *(uint64 *) (x + 32)
+-      movq    32(%r8),%r11
+-      # in10 = *(uint64 *) (x + 40)
+-      movq    40(%r8),%r12
+-      # in12 = *(uint64 *) (x + 48)
+-      movq    48(%r8),%r13
+-      # in14 = *(uint64 *) (x + 56)
+-      movq    56(%r8),%r14
+-      # j0 = in0
+-      movq    %rcx,56(%rsp)
+-      # j2 = in2
+-      movq    %r9,64(%rsp)
+-      # j4 = in4
+-      movq    %rax,72(%rsp)
+-      # j6 = in6
+-      movq    %r10,80(%rsp)
+-      # j8 = in8
+-      movq    %r11,88(%rsp)
+-      # j10 = in10
+-      movq    %r12,96(%rsp)
+-      # j12 = in12
+-      movq    %r13,104(%rsp)
+-      # j14 = in14
+-      movq    %r14,112(%rsp)
+-      # x_backup = x
+-      movq    %r8,120(%rsp)
+-# bytesatleast1:
+-._bytesatleast1:
+-      #                   unsigned<? bytes - 64
+-      cmp     $64,%rdx
+-      # comment:fp stack unchanged by jump
+-      #   goto nocopy if !unsigned<
+-      jae     ._nocopy
+-      #     ctarget = out
+-      movq    %rdi,128(%rsp)
+-      #     out = &tmp
+-      leaq    192(%rsp),%rdi
+-      #     i = bytes
+-      mov     %rdx,%rcx
+-      #     while (i) { *out++ = *m++; --i }
+-      rep     movsb
+-      #     out = &tmp
+-      leaq    192(%rsp),%rdi
+-      #     m = &tmp
+-      leaq    192(%rsp),%rsi
+-      # comment:fp stack unchanged by fallthrough
+-#   nocopy:
+-._nocopy:
+-      #   out_backup = out
+-      movq    %rdi,136(%rsp)
+-      #   m_backup = m
+-      movq    %rsi,144(%rsp)
+-      #   bytes_backup = bytes
+-      movq    %rdx,152(%rsp)
+-      #   x1 = j0
+-      movq    56(%rsp),%rdi
+-      #   x0 = x1
+-      mov     %rdi,%rdx
+-      #   (uint64) x1 >>= 32
+-      shr     $32,%rdi
+-      #               x3 = j2
+-      movq    64(%rsp),%rsi
+-      #               x2 = x3
+-      mov     %rsi,%rcx
+-      #               (uint64) x3 >>= 32
+-      shr     $32,%rsi
+-      #   x5 = j4
+-      movq    72(%rsp),%r8
+-      #   x4 = x5
+-      mov     %r8,%r9
+-      #   (uint64) x5 >>= 32
+-      shr     $32,%r8
+-      #   x5_stack = x5
+-      movq    %r8,160(%rsp)
+-      #               x7 = j6
+-      movq    80(%rsp),%r8
+-      #               x6 = x7
+-      mov     %r8,%rax
+-      #               (uint64) x7 >>= 32
+-      shr     $32,%r8
+-      #   x9 = j8
+-      movq    88(%rsp),%r10
+-      #   x8 = x9
+-      mov     %r10,%r11
+-      #   (uint64) x9 >>= 32
+-      shr     $32,%r10
+-      #               x11 = j10
+-      movq    96(%rsp),%r12
+-      #               x10 = x11
+-      mov     %r12,%r13
+-      #               x10_stack = x10
+-      movq    %r13,168(%rsp)
+-      #               (uint64) x11 >>= 32
+-      shr     $32,%r12
+-      #   x13 = j12
+-      movq    104(%rsp),%r13
+-      #   x12 = x13
+-      mov     %r13,%r14
+-      #   (uint64) x13 >>= 32
+-      shr     $32,%r13
+-      #               x15 = j14
+-      movq    112(%rsp),%r15
+-      #               x14 = x15
+-      mov     %r15,%rbx
+-      #               (uint64) x15 >>= 32
+-      shr     $32,%r15
+-      #               x15_stack = x15
+-      movq    %r15,176(%rsp)
+-      #   i = 20
+-      mov     $20,%r15
+-#   mainloop:
+-._mainloop:
+-      #   i_backup = i
+-      movq    %r15,184(%rsp)
+-      #               x5 = x5_stack
+-      movq    160(%rsp),%r15
+-      # a = x12 + x0
+-      lea     (%r14,%rdx),%rbp
+-      # (uint32) a <<<= 7
+-      rol     $7,%ebp
+-      # x4 ^= a
+-      xor     %rbp,%r9
+-      #               b = x1 + x5
+-      lea     (%rdi,%r15),%rbp
+-      #               (uint32) b <<<= 7
+-      rol     $7,%ebp
+-      #               x9 ^= b
+-      xor     %rbp,%r10
+-      # a = x0 + x4
+-      lea     (%rdx,%r9),%rbp
+-      # (uint32) a <<<= 9
+-      rol     $9,%ebp
+-      # x8 ^= a
+-      xor     %rbp,%r11
+-      #               b = x5 + x9
+-      lea     (%r15,%r10),%rbp
+-      #               (uint32) b <<<= 9
+-      rol     $9,%ebp
+-      #               x13 ^= b
+-      xor     %rbp,%r13
+-      # a = x4 + x8
+-      lea     (%r9,%r11),%rbp
+-      # (uint32) a <<<= 13
+-      rol     $13,%ebp
+-      # x12 ^= a
+-      xor     %rbp,%r14
+-      #               b = x9 + x13
+-      lea     (%r10,%r13),%rbp
+-      #               (uint32) b <<<= 13
+-      rol     $13,%ebp
+-      #               x1 ^= b
+-      xor     %rbp,%rdi
+-      # a = x8 + x12
+-      lea     (%r11,%r14),%rbp
+-      # (uint32) a <<<= 18
+-      rol     $18,%ebp
+-      # x0 ^= a
+-      xor     %rbp,%rdx
+-      #               b = x13 + x1
+-      lea     (%r13,%rdi),%rbp
+-      #               (uint32) b <<<= 18
+-      rol     $18,%ebp
+-      #               x5 ^= b
+-      xor     %rbp,%r15
+-      #                               x10 = x10_stack
+-      movq    168(%rsp),%rbp
+-      #               x5_stack = x5
+-      movq    %r15,160(%rsp)
+-      #                               c = x6 + x10
+-      lea     (%rax,%rbp),%r15
+-      #                               (uint32) c <<<= 7
+-      rol     $7,%r15d
+-      #                               x14 ^= c
+-      xor     %r15,%rbx
+-      #                               c = x10 + x14
+-      lea     (%rbp,%rbx),%r15
+-      #                               (uint32) c <<<= 9
+-      rol     $9,%r15d
+-      #                               x2 ^= c
+-      xor     %r15,%rcx
+-      #                               c = x14 + x2
+-      lea     (%rbx,%rcx),%r15
+-      #                               (uint32) c <<<= 13
+-      rol     $13,%r15d
+-      #                               x6 ^= c
+-      xor     %r15,%rax
+-      #                               c = x2 + x6
+-      lea     (%rcx,%rax),%r15
+-      #                               (uint32) c <<<= 18
+-      rol     $18,%r15d
+-      #                               x10 ^= c
+-      xor     %r15,%rbp
+-      #                                               x15 = x15_stack
+-      movq    176(%rsp),%r15
+-      #                               x10_stack = x10
+-      movq    %rbp,168(%rsp)
+-      #                                               d = x11 + x15
+-      lea     (%r12,%r15),%rbp
+-      #                                               (uint32) d <<<= 7
+-      rol     $7,%ebp
+-      #                                               x3 ^= d
+-      xor     %rbp,%rsi
+-      #                                               d = x15 + x3
+-      lea     (%r15,%rsi),%rbp
+-      #                                               (uint32) d <<<= 9
+-      rol     $9,%ebp
+-      #                                               x7 ^= d
+-      xor     %rbp,%r8
+-      #                                               d = x3 + x7
+-      lea     (%rsi,%r8),%rbp
+-      #                                               (uint32) d <<<= 13
+-      rol     $13,%ebp
+-      #                                               x11 ^= d
+-      xor     %rbp,%r12
+-      #                                               d = x7 + x11
+-      lea     (%r8,%r12),%rbp
+-      #                                               (uint32) d <<<= 18
+-      rol     $18,%ebp
+-      #                                               x15 ^= d
+-      xor     %rbp,%r15
+-      #                                               x15_stack = x15
+-      movq    %r15,176(%rsp)
+-      #               x5 = x5_stack
+-      movq    160(%rsp),%r15
+-      # a = x3 + x0
+-      lea     (%rsi,%rdx),%rbp
+-      # (uint32) a <<<= 7
+-      rol     $7,%ebp
+-      # x1 ^= a
+-      xor     %rbp,%rdi
+-      #               b = x4 + x5
+-      lea     (%r9,%r15),%rbp
+-      #               (uint32) b <<<= 7
+-      rol     $7,%ebp
+-      #               x6 ^= b
+-      xor     %rbp,%rax
+-      # a = x0 + x1
+-      lea     (%rdx,%rdi),%rbp
+-      # (uint32) a <<<= 9
+-      rol     $9,%ebp
+-      # x2 ^= a
+-      xor     %rbp,%rcx
+-      #               b = x5 + x6
+-      lea     (%r15,%rax),%rbp
+-      #               (uint32) b <<<= 9
+-      rol     $9,%ebp
+-      #               x7 ^= b
+-      xor     %rbp,%r8
+-      # a = x1 + x2
+-      lea     (%rdi,%rcx),%rbp
+-      # (uint32) a <<<= 13
+-      rol     $13,%ebp
+-      # x3 ^= a
+-      xor     %rbp,%rsi
+-      #               b = x6 + x7
+-      lea     (%rax,%r8),%rbp
+-      #               (uint32) b <<<= 13
+-      rol     $13,%ebp
+-      #               x4 ^= b
+-      xor     %rbp,%r9
+-      # a = x2 + x3
+-      lea     (%rcx,%rsi),%rbp
+-      # (uint32) a <<<= 18
+-      rol     $18,%ebp
+-      # x0 ^= a
+-      xor     %rbp,%rdx
+-      #               b = x7 + x4
+-      lea     (%r8,%r9),%rbp
+-      #               (uint32) b <<<= 18
+-      rol     $18,%ebp
+-      #               x5 ^= b
+-      xor     %rbp,%r15
+-      #                               x10 = x10_stack
+-      movq    168(%rsp),%rbp
+-      #               x5_stack = x5
+-      movq    %r15,160(%rsp)
+-      #                               c = x9 + x10
+-      lea     (%r10,%rbp),%r15
+-      #                               (uint32) c <<<= 7
+-      rol     $7,%r15d
+-      #                               x11 ^= c
+-      xor     %r15,%r12
+-      #                               c = x10 + x11
+-      lea     (%rbp,%r12),%r15
+-      #                               (uint32) c <<<= 9
+-      rol     $9,%r15d
+-      #                               x8 ^= c
+-      xor     %r15,%r11
+-      #                               c = x11 + x8
+-      lea     (%r12,%r11),%r15
+-      #                               (uint32) c <<<= 13
+-      rol     $13,%r15d
+-      #                               x9 ^= c
+-      xor     %r15,%r10
+-      #                               c = x8 + x9
+-      lea     (%r11,%r10),%r15
+-      #                               (uint32) c <<<= 18
+-      rol     $18,%r15d
+-      #                               x10 ^= c
+-      xor     %r15,%rbp
+-      #                                               x15 = x15_stack
+-      movq    176(%rsp),%r15
+-      #                               x10_stack = x10
+-      movq    %rbp,168(%rsp)
+-      #                                               d = x14 + x15
+-      lea     (%rbx,%r15),%rbp
+-      #                                               (uint32) d <<<= 7
+-      rol     $7,%ebp
+-      #                                               x12 ^= d
+-      xor     %rbp,%r14
+-      #                                               d = x15 + x12
+-      lea     (%r15,%r14),%rbp
+-      #                                               (uint32) d <<<= 9
+-      rol     $9,%ebp
+-      #                                               x13 ^= d
+-      xor     %rbp,%r13
+-      #                                               d = x12 + x13
+-      lea     (%r14,%r13),%rbp
+-      #                                               (uint32) d <<<= 13
+-      rol     $13,%ebp
+-      #                                               x14 ^= d
+-      xor     %rbp,%rbx
+-      #                                               d = x13 + x14
+-      lea     (%r13,%rbx),%rbp
+-      #                                               (uint32) d <<<= 18
+-      rol     $18,%ebp
+-      #                                               x15 ^= d
+-      xor     %rbp,%r15
+-      #                                               x15_stack = x15
+-      movq    %r15,176(%rsp)
+-      #               x5 = x5_stack
+-      movq    160(%rsp),%r15
+-      # a = x12 + x0
+-      lea     (%r14,%rdx),%rbp
+-      # (uint32) a <<<= 7
+-      rol     $7,%ebp
+-      # x4 ^= a
+-      xor     %rbp,%r9
+-      #               b = x1 + x5
+-      lea     (%rdi,%r15),%rbp
+-      #               (uint32) b <<<= 7
+-      rol     $7,%ebp
+-      #               x9 ^= b
+-      xor     %rbp,%r10
+-      # a = x0 + x4
+-      lea     (%rdx,%r9),%rbp
+-      # (uint32) a <<<= 9
+-      rol     $9,%ebp
+-      # x8 ^= a
+-      xor     %rbp,%r11
+-      #               b = x5 + x9
+-      lea     (%r15,%r10),%rbp
+-      #               (uint32) b <<<= 9
+-      rol     $9,%ebp
+-      #               x13 ^= b
+-      xor     %rbp,%r13
+-      # a = x4 + x8
+-      lea     (%r9,%r11),%rbp
+-      # (uint32) a <<<= 13
+-      rol     $13,%ebp
+-      # x12 ^= a
+-      xor     %rbp,%r14
+-      #               b = x9 + x13
+-      lea     (%r10,%r13),%rbp
+-      #               (uint32) b <<<= 13
+-      rol     $13,%ebp
+-      #               x1 ^= b
+-      xor     %rbp,%rdi
+-      # a = x8 + x12
+-      lea     (%r11,%r14),%rbp
+-      # (uint32) a <<<= 18
+-      rol     $18,%ebp
+-      # x0 ^= a
+-      xor     %rbp,%rdx
+-      #               b = x13 + x1
+-      lea     (%r13,%rdi),%rbp
+-      #               (uint32) b <<<= 18
+-      rol     $18,%ebp
+-      #               x5 ^= b
+-      xor     %rbp,%r15
+-      #                               x10 = x10_stack
+-      movq    168(%rsp),%rbp
+-      #               x5_stack = x5
+-      movq    %r15,160(%rsp)
+-      #                               c = x6 + x10
+-      lea     (%rax,%rbp),%r15
+-      #                               (uint32) c <<<= 7
+-      rol     $7,%r15d
+-      #                               x14 ^= c
+-      xor     %r15,%rbx
+-      #                               c = x10 + x14
+-      lea     (%rbp,%rbx),%r15
+-      #                               (uint32) c <<<= 9
+-      rol     $9,%r15d
+-      #                               x2 ^= c
+-      xor     %r15,%rcx
+-      #                               c = x14 + x2
+-      lea     (%rbx,%rcx),%r15
+-      #                               (uint32) c <<<= 13
+-      rol     $13,%r15d
+-      #                               x6 ^= c
+-      xor     %r15,%rax
+-      #                               c = x2 + x6
+-      lea     (%rcx,%rax),%r15
+-      #                               (uint32) c <<<= 18
+-      rol     $18,%r15d
+-      #                               x10 ^= c
+-      xor     %r15,%rbp
+-      #                                               x15 = x15_stack
+-      movq    176(%rsp),%r15
+-      #                               x10_stack = x10
+-      movq    %rbp,168(%rsp)
+-      #                                               d = x11 + x15
+-      lea     (%r12,%r15),%rbp
+-      #                                               (uint32) d <<<= 7
+-      rol     $7,%ebp
+-      #                                               x3 ^= d
+-      xor     %rbp,%rsi
+-      #                                               d = x15 + x3
+-      lea     (%r15,%rsi),%rbp
+-      #                                               (uint32) d <<<= 9
+-      rol     $9,%ebp
+-      #                                               x7 ^= d
+-      xor     %rbp,%r8
+-      #                                               d = x3 + x7
+-      lea     (%rsi,%r8),%rbp
+-      #                                               (uint32) d <<<= 13
+-      rol     $13,%ebp
+-      #                                               x11 ^= d
+-      xor     %rbp,%r12
+-      #                                               d = x7 + x11
+-      lea     (%r8,%r12),%rbp
+-      #                                               (uint32) d <<<= 18
+-      rol     $18,%ebp
+-      #                                               x15 ^= d
+-      xor     %rbp,%r15
+-      #                                               x15_stack = x15
+-      movq    %r15,176(%rsp)
+-      #               x5 = x5_stack
+-      movq    160(%rsp),%r15
+-      # a = x3 + x0
+-      lea     (%rsi,%rdx),%rbp
+-      # (uint32) a <<<= 7
+-      rol     $7,%ebp
+-      # x1 ^= a
+-      xor     %rbp,%rdi
+-      #               b = x4 + x5
+-      lea     (%r9,%r15),%rbp
+-      #               (uint32) b <<<= 7
+-      rol     $7,%ebp
+-      #               x6 ^= b
+-      xor     %rbp,%rax
+-      # a = x0 + x1
+-      lea     (%rdx,%rdi),%rbp
+-      # (uint32) a <<<= 9
+-      rol     $9,%ebp
+-      # x2 ^= a
+-      xor     %rbp,%rcx
+-      #               b = x5 + x6
+-      lea     (%r15,%rax),%rbp
+-      #               (uint32) b <<<= 9
+-      rol     $9,%ebp
+-      #               x7 ^= b
+-      xor     %rbp,%r8
+-      # a = x1 + x2
+-      lea     (%rdi,%rcx),%rbp
+-      # (uint32) a <<<= 13
+-      rol     $13,%ebp
+-      # x3 ^= a
+-      xor     %rbp,%rsi
+-      #               b = x6 + x7
+-      lea     (%rax,%r8),%rbp
+-      #               (uint32) b <<<= 13
+-      rol     $13,%ebp
+-      #               x4 ^= b
+-      xor     %rbp,%r9
+-      # a = x2 + x3
+-      lea     (%rcx,%rsi),%rbp
+-      # (uint32) a <<<= 18
+-      rol     $18,%ebp
+-      # x0 ^= a
+-      xor     %rbp,%rdx
+-      #               b = x7 + x4
+-      lea     (%r8,%r9),%rbp
+-      #               (uint32) b <<<= 18
+-      rol     $18,%ebp
+-      #               x5 ^= b
+-      xor     %rbp,%r15
+-      #                               x10 = x10_stack
+-      movq    168(%rsp),%rbp
+-      #               x5_stack = x5
+-      movq    %r15,160(%rsp)
+-      #                               c = x9 + x10
+-      lea     (%r10,%rbp),%r15
+-      #                               (uint32) c <<<= 7
+-      rol     $7,%r15d
+-      #                               x11 ^= c
+-      xor     %r15,%r12
+-      #                               c = x10 + x11
+-      lea     (%rbp,%r12),%r15
+-      #                               (uint32) c <<<= 9
+-      rol     $9,%r15d
+-      #                               x8 ^= c
+-      xor     %r15,%r11
+-      #                               c = x11 + x8
+-      lea     (%r12,%r11),%r15
+-      #                               (uint32) c <<<= 13
+-      rol     $13,%r15d
+-      #                               x9 ^= c
+-      xor     %r15,%r10
+-      #                               c = x8 + x9
+-      lea     (%r11,%r10),%r15
+-      #                               (uint32) c <<<= 18
+-      rol     $18,%r15d
+-      #                               x10 ^= c
+-      xor     %r15,%rbp
+-      #                                               x15 = x15_stack
+-      movq    176(%rsp),%r15
+-      #                               x10_stack = x10
+-      movq    %rbp,168(%rsp)
+-      #                                               d = x14 + x15
+-      lea     (%rbx,%r15),%rbp
+-      #                                               (uint32) d <<<= 7
+-      rol     $7,%ebp
+-      #                                               x12 ^= d
+-      xor     %rbp,%r14
+-      #                                               d = x15 + x12
+-      lea     (%r15,%r14),%rbp
+-      #                                               (uint32) d <<<= 9
+-      rol     $9,%ebp
+-      #                                               x13 ^= d
+-      xor     %rbp,%r13
+-      #                                               d = x12 + x13
+-      lea     (%r14,%r13),%rbp
+-      #                                               (uint32) d <<<= 13
+-      rol     $13,%ebp
+-      #                                               x14 ^= d
+-      xor     %rbp,%rbx
+-      #                                               d = x13 + x14
+-      lea     (%r13,%rbx),%rbp
+-      #                                               (uint32) d <<<= 18
+-      rol     $18,%ebp
+-      #                                               x15 ^= d
+-      xor     %rbp,%r15
+-      #                                               x15_stack = x15
+-      movq    %r15,176(%rsp)
+-      #   i = i_backup
+-      movq    184(%rsp),%r15
+-      #                  unsigned>? i -= 4
+-      sub     $4,%r15
+-      # comment:fp stack unchanged by jump
+-      # goto mainloop if unsigned>
+-      ja      ._mainloop
+-      #   (uint32) x2 += j2
+-      addl    64(%rsp),%ecx
+-      #   x3 <<= 32
+-      shl     $32,%rsi
+-      #   x3 += j2
+-      addq    64(%rsp),%rsi
+-      #   (uint64) x3 >>= 32
+-      shr     $32,%rsi
+-      #   x3 <<= 32
+-      shl     $32,%rsi
+-      #   x2 += x3
+-      add     %rsi,%rcx
+-      #   (uint32) x6 += j6
+-      addl    80(%rsp),%eax
+-      #   x7 <<= 32
+-      shl     $32,%r8
+-      #   x7 += j6
+-      addq    80(%rsp),%r8
+-      #   (uint64) x7 >>= 32
+-      shr     $32,%r8
+-      #   x7 <<= 32
+-      shl     $32,%r8
+-      #   x6 += x7
+-      add     %r8,%rax
+-      #   (uint32) x8 += j8
+-      addl    88(%rsp),%r11d
+-      #   x9 <<= 32
+-      shl     $32,%r10
+-      #   x9 += j8
+-      addq    88(%rsp),%r10
+-      #   (uint64) x9 >>= 32
+-      shr     $32,%r10
+-      #   x9 <<= 32
+-      shl     $32,%r10
+-      #   x8 += x9
+-      add     %r10,%r11
+-      #   (uint32) x12 += j12
+-      addl    104(%rsp),%r14d
+-      #   x13 <<= 32
+-      shl     $32,%r13
+-      #   x13 += j12
+-      addq    104(%rsp),%r13
+-      #   (uint64) x13 >>= 32
+-      shr     $32,%r13
+-      #   x13 <<= 32
+-      shl     $32,%r13
+-      #   x12 += x13
+-      add     %r13,%r14
+-      #   (uint32) x0 += j0
+-      addl    56(%rsp),%edx
+-      #   x1 <<= 32
+-      shl     $32,%rdi
+-      #   x1 += j0
+-      addq    56(%rsp),%rdi
+-      #   (uint64) x1 >>= 32
+-      shr     $32,%rdi
+-      #   x1 <<= 32
+-      shl     $32,%rdi
+-      #   x0 += x1
+-      add     %rdi,%rdx
+-      #   x5 = x5_stack
+-      movq    160(%rsp),%rdi
+-      #   (uint32) x4 += j4
+-      addl    72(%rsp),%r9d
+-      #   x5 <<= 32
+-      shl     $32,%rdi
+-      #   x5 += j4
+-      addq    72(%rsp),%rdi
+-      #   (uint64) x5 >>= 32
+-      shr     $32,%rdi
+-      #   x5 <<= 32
+-      shl     $32,%rdi
+-      #   x4 += x5
+-      add     %rdi,%r9
+-      #   x10 = x10_stack
+-      movq    168(%rsp),%r8
+-      #   (uint32) x10 += j10
+-      addl    96(%rsp),%r8d
+-      #   x11 <<= 32
+-      shl     $32,%r12
+-      #   x11 += j10
+-      addq    96(%rsp),%r12
+-      #   (uint64) x11 >>= 32
+-      shr     $32,%r12
+-      #   x11 <<= 32
+-      shl     $32,%r12
+-      #   x10 += x11
+-      add     %r12,%r8
+-      #   x15 = x15_stack
+-      movq    176(%rsp),%rdi
+-      #   (uint32) x14 += j14
+-      addl    112(%rsp),%ebx
+-      #   x15 <<= 32
+-      shl     $32,%rdi
+-      #   x15 += j14
+-      addq    112(%rsp),%rdi
+-      #   (uint64) x15 >>= 32
+-      shr     $32,%rdi
+-      #   x15 <<= 32
+-      shl     $32,%rdi
+-      #   x14 += x15
+-      add     %rdi,%rbx
+-      #   out = out_backup
+-      movq    136(%rsp),%rdi
+-      #   m = m_backup
+-      movq    144(%rsp),%rsi
+-      #   x0 ^= *(uint64 *) (m + 0)
+-      xorq    0(%rsi),%rdx
+-      #   *(uint64 *) (out + 0) = x0
+-      movq    %rdx,0(%rdi)
+-      #   x2 ^= *(uint64 *) (m + 8)
+-      xorq    8(%rsi),%rcx
+-      #   *(uint64 *) (out + 8) = x2
+-      movq    %rcx,8(%rdi)
+-      #   x4 ^= *(uint64 *) (m + 16)
+-      xorq    16(%rsi),%r9
+-      #   *(uint64 *) (out + 16) = x4
+-      movq    %r9,16(%rdi)
+-      #   x6 ^= *(uint64 *) (m + 24)
+-      xorq    24(%rsi),%rax
+-      #   *(uint64 *) (out + 24) = x6
+-      movq    %rax,24(%rdi)
+-      #   x8 ^= *(uint64 *) (m + 32)
+-      xorq    32(%rsi),%r11
+-      #   *(uint64 *) (out + 32) = x8
+-      movq    %r11,32(%rdi)
+-      #   x10 ^= *(uint64 *) (m + 40)
+-      xorq    40(%rsi),%r8
+-      #   *(uint64 *) (out + 40) = x10
+-      movq    %r8,40(%rdi)
+-      #   x12 ^= *(uint64 *) (m + 48)
+-      xorq    48(%rsi),%r14
+-      #   *(uint64 *) (out + 48) = x12
+-      movq    %r14,48(%rdi)
+-      #   x14 ^= *(uint64 *) (m + 56)
+-      xorq    56(%rsi),%rbx
+-      #   *(uint64 *) (out + 56) = x14
+-      movq    %rbx,56(%rdi)
+-      #   bytes = bytes_backup
+-      movq    152(%rsp),%rdx
+-      #   in8 = j8
+-      movq    88(%rsp),%rcx
+-      #   in8 += 1
+-      add     $1,%rcx
+-      #   j8 = in8
+-      movq    %rcx,88(%rsp)
+-      #                          unsigned>? unsigned<? bytes - 64
+-      cmp     $64,%rdx
+-      # comment:fp stack unchanged by jump
+-      #   goto bytesatleast65 if unsigned>
+-      ja      ._bytesatleast65
+-      # comment:fp stack unchanged by jump
+-      #     goto bytesatleast64 if !unsigned<
+-      jae     ._bytesatleast64
+-      #       m = out
+-      mov     %rdi,%rsi
+-      #       out = ctarget
+-      movq    128(%rsp),%rdi
+-      #       i = bytes
+-      mov     %rdx,%rcx
+-      #       while (i) { *out++ = *m++; --i }
+-      rep     movsb
+-      # comment:fp stack unchanged by fallthrough
+-#     bytesatleast64:
+-._bytesatleast64:
+-      #     x = x_backup
+-      movq    120(%rsp),%rdi
+-      #     in8 = j8
+-      movq    88(%rsp),%rsi
+-      #     *(uint64 *) (x + 32) = in8
+-      movq    %rsi,32(%rdi)
+-      #     r11 = r11_stack
+-      movq    0(%rsp),%r11
+-      #     r12 = r12_stack
+-      movq    8(%rsp),%r12
+-      #     r13 = r13_stack
+-      movq    16(%rsp),%r13
+-      #     r14 = r14_stack
+-      movq    24(%rsp),%r14
+-      #     r15 = r15_stack
+-      movq    32(%rsp),%r15
+-      #     rbx = rbx_stack
+-      movq    40(%rsp),%rbx
+-      #     rbp = rbp_stack
+-      movq    48(%rsp),%rbp
+-      # comment:fp stack unchanged by fallthrough
+-#     done:
+-._done:
+-      #     leave
+-      add     %r11,%rsp
+-      mov     %rdi,%rax
+-      mov     %rsi,%rdx
+-      ret
+-#   bytesatleast65:
+-._bytesatleast65:
+-      #   bytes -= 64
+-      sub     $64,%rdx
+-      #   out += 64
+-      add     $64,%rdi
+-      #   m += 64
+-      add     $64,%rsi
+-      # comment:fp stack unchanged by jump
+-      # goto bytesatleast1
+-      jmp     ._bytesatleast1
+-ENDPROC(salsa20_encrypt_bytes)
+diff --git a/arch/x86/crypto/salsa20_glue.c b/arch/x86/crypto/salsa20_glue.c
+deleted file mode 100644
+index b07d7d959806..000000000000
+--- a/arch/x86/crypto/salsa20_glue.c
++++ /dev/null
+@@ -1,91 +0,0 @@
+-/*
+- * Glue code for optimized assembly version of  Salsa20.
+- *
+- * Copyright (c) 2007 Tan Swee Heng <[email protected]>
+- *
+- * The assembly codes are public domain assembly codes written by Daniel. J.
+- * Bernstein <[email protected]>. The codes are modified to include indentation
+- * and to remove extraneous comments and functions that are not needed.
+- * - i586 version, renamed as salsa20-i586-asm_32.S
+- *   available from <http://cr.yp.to/snuffle/salsa20/x86-pm/salsa20.s>
+- * - x86-64 version, renamed as salsa20-x86_64-asm_64.S
+- *   available from <http://cr.yp.to/snuffle/salsa20/amd64-3/salsa20.s>
+- *
+- * Also modified to set up the initial state using the generic C code rather
+- * than in assembly.
+- *
+- * This program is free software; you can redistribute it and/or modify it
+- * under the terms of the GNU General Public License as published by the Free
+- * Software Foundation; either version 2 of the License, or (at your option)
+- * any later version.
+- *
+- */
+-
+-#include <asm/unaligned.h>
+-#include <crypto/internal/skcipher.h>
+-#include <crypto/salsa20.h>
+-#include <linux/module.h>
+-
+-asmlinkage void salsa20_encrypt_bytes(u32 state[16], const u8 *src, u8 *dst,
+-                                    u32 bytes);
+-
+-static int salsa20_asm_crypt(struct skcipher_request *req)
+-{
+-      struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+-      const struct salsa20_ctx *ctx = crypto_skcipher_ctx(tfm);
+-      struct skcipher_walk walk;
+-      u32 state[16];
+-      int err;
+-
+-      err = skcipher_walk_virt(&walk, req, true);
+-
+-      crypto_salsa20_init(state, ctx, walk.iv);
+-
+-      while (walk.nbytes > 0) {
+-              unsigned int nbytes = walk.nbytes;
+-
+-              if (nbytes < walk.total)
+-                      nbytes = round_down(nbytes, walk.stride);
+-
+-              salsa20_encrypt_bytes(state, walk.src.virt.addr,
+-                                    walk.dst.virt.addr, nbytes);
+-              err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+-      }
+-
+-      return err;
+-}
+-
+-static struct skcipher_alg alg = {
+-      .base.cra_name          = "salsa20",
+-      .base.cra_driver_name   = "salsa20-asm",
+-      .base.cra_priority      = 200,
+-      .base.cra_blocksize     = 1,
+-      .base.cra_ctxsize       = sizeof(struct salsa20_ctx),
+-      .base.cra_module        = THIS_MODULE,
+-
+-      .min_keysize            = SALSA20_MIN_KEY_SIZE,
+-      .max_keysize            = SALSA20_MAX_KEY_SIZE,
+-      .ivsize                 = SALSA20_IV_SIZE,
+-      .chunksize              = SALSA20_BLOCK_SIZE,
+-      .setkey                 = crypto_salsa20_setkey,
+-      .encrypt                = salsa20_asm_crypt,
+-      .decrypt                = salsa20_asm_crypt,
+-};
+-
+-static int __init init(void)
+-{
+-      return crypto_register_skcipher(&alg);
+-}
+-
+-static void __exit fini(void)
+-{
+-      crypto_unregister_skcipher(&alg);
+-}
+-
+-module_init(init);
+-module_exit(fini);
+-
+-MODULE_LICENSE("GPL");
+-MODULE_DESCRIPTION ("Salsa20 stream cipher algorithm (optimized assembly 
version)");
+-MODULE_ALIAS_CRYPTO("salsa20");
+-MODULE_ALIAS_CRYPTO("salsa20-asm");
+diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
+index 5db8b0b10766..7cc81c586d71 100644
+--- a/arch/x86/include/asm/vmx.h
++++ b/arch/x86/include/asm/vmx.h
+@@ -114,6 +114,7 @@
+ #define VMX_MISC_PREEMPTION_TIMER_RATE_MASK   0x0000001f
+ #define VMX_MISC_SAVE_EFER_LMA                        0x00000020
+ #define VMX_MISC_ACTIVITY_HLT                 0x00000040
++#define VMX_MISC_ZERO_LEN_INS                 0x40000000
+ 
+ /* VMFUNC functions */
+ #define VMX_VMFUNC_EPTP_SWITCHING               0x00000001
+@@ -349,11 +350,13 @@ enum vmcs_field {
+ #define VECTORING_INFO_VALID_MASK             INTR_INFO_VALID_MASK
+ 
+ #define INTR_TYPE_EXT_INTR              (0 << 8) /* external interrupt */
++#define INTR_TYPE_RESERVED              (1 << 8) /* reserved */
+ #define INTR_TYPE_NMI_INTR            (2 << 8) /* NMI */
+ #define INTR_TYPE_HARD_EXCEPTION      (3 << 8) /* processor exception */
+ #define INTR_TYPE_SOFT_INTR             (4 << 8) /* software interrupt */
+ #define INTR_TYPE_PRIV_SW_EXCEPTION   (5 << 8) /* ICE breakpoint - 
undocumented */
+ #define INTR_TYPE_SOFT_EXCEPTION      (6 << 8) /* software exception */
++#define INTR_TYPE_OTHER_EVENT           (7 << 8) /* other event */
+ 
+ /* GUEST_INTERRUPTIBILITY_INFO flags. */
+ #define GUEST_INTR_STATE_STI          0x00000001
+diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
+index c84bb5396958..442fae7b8b61 100644
+--- a/arch/x86/kernel/uprobes.c
++++ b/arch/x86/kernel/uprobes.c
+@@ -293,7 +293,7 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, 
struct insn *insn, bool
+       insn_init(insn, auprobe->insn, sizeof(auprobe->insn), x86_64);
+       /* has the side-effect of processing the entire instruction */
+       insn_get_length(insn);
+-      if (WARN_ON_ONCE(!insn_complete(insn)))
++      if (!insn_complete(insn))
+               return -ENOEXEC;
+ 
+       if (is_prefix_bad(insn))
+diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
+index 82f5e915e568..dd4366edc200 100644
+--- a/arch/x86/kvm/vmx.c
++++ b/arch/x86/kvm/vmx.c
+@@ -1510,6 +1510,17 @@ static inline unsigned 
nested_cpu_vmx_misc_cr3_count(struct kvm_vcpu *vcpu)
+       return vmx_misc_cr3_count(to_vmx(vcpu)->nested.msrs.misc_low);
+ }
+ 
++static inline bool nested_cpu_has_zero_length_injection(struct kvm_vcpu *vcpu)
++{
++      return to_vmx(vcpu)->nested.msrs.misc_low & VMX_MISC_ZERO_LEN_INS;
++}
++
++static inline bool nested_cpu_supports_monitor_trap_flag(struct kvm_vcpu 
*vcpu)
++{
++      return to_vmx(vcpu)->nested.msrs.procbased_ctls_high &
++                      CPU_BASED_MONITOR_TRAP_FLAG;
++}
++
+ static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit)
+ {
+       return vmcs12->cpu_based_vm_exec_control & bit;
+@@ -11364,6 +11375,62 @@ static int check_vmentry_prereqs(struct kvm_vcpu 
*vcpu, struct vmcs12 *vmcs12)
+           !nested_cr3_valid(vcpu, vmcs12->host_cr3))
+               return VMXERR_ENTRY_INVALID_HOST_STATE_FIELD;
+ 
++      /*
++       * From the Intel SDM, volume 3:
++       * Fields relevant to VM-entry event injection must be set properly.
++       * These fields are the VM-entry interruption-information field, the
++       * VM-entry exception error code, and the VM-entry instruction length.
++       */
++      if (vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) {
++              u32 intr_info = vmcs12->vm_entry_intr_info_field;
++              u8 vector = intr_info & INTR_INFO_VECTOR_MASK;
++              u32 intr_type = intr_info & INTR_INFO_INTR_TYPE_MASK;
++              bool has_error_code = intr_info & INTR_INFO_DELIVER_CODE_MASK;
++              bool should_have_error_code;
++              bool urg = nested_cpu_has2(vmcs12,
++                                         SECONDARY_EXEC_UNRESTRICTED_GUEST);
++              bool prot_mode = !urg || vmcs12->guest_cr0 & X86_CR0_PE;
++
++              /* VM-entry interruption-info field: interruption type */
++              if (intr_type == INTR_TYPE_RESERVED ||
++                  (intr_type == INTR_TYPE_OTHER_EVENT &&
++                   !nested_cpu_supports_monitor_trap_flag(vcpu)))
++                      return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
++
++              /* VM-entry interruption-info field: vector */
++              if ((intr_type == INTR_TYPE_NMI_INTR && vector != NMI_VECTOR) ||
++                  (intr_type == INTR_TYPE_HARD_EXCEPTION && vector > 31) ||
++                  (intr_type == INTR_TYPE_OTHER_EVENT && vector != 0))
++                      return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
++
++              /* VM-entry interruption-info field: deliver error code */
++              should_have_error_code =
++                      intr_type == INTR_TYPE_HARD_EXCEPTION && prot_mode &&
++                      x86_exception_has_error_code(vector);
++              if (has_error_code != should_have_error_code)
++                      return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
++
++              /* VM-entry exception error code */
++              if (has_error_code &&
++                  vmcs12->vm_entry_exception_error_code & GENMASK(31, 15))
++                      return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
++
++              /* VM-entry interruption-info field: reserved bits */
++              if (intr_info & INTR_INFO_RESVD_BITS_MASK)
++                      return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
++
++              /* VM-entry instruction length */
++              switch (intr_type) {
++              case INTR_TYPE_SOFT_EXCEPTION:
++              case INTR_TYPE_SOFT_INTR:
++              case INTR_TYPE_PRIV_SW_EXCEPTION:
++                      if ((vmcs12->vm_entry_instruction_len > 15) ||
++                          (vmcs12->vm_entry_instruction_len == 0 &&
++                           !nested_cpu_has_zero_length_injection(vcpu)))
++                              return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
++              }
++      }
++
+       return 0;
+ }
+ 
+diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
+index 331993c49dae..257f27620bc2 100644
+--- a/arch/x86/kvm/x86.h
++++ b/arch/x86/kvm/x86.h
+@@ -110,6 +110,15 @@ static inline bool is_la57_mode(struct kvm_vcpu *vcpu)
+ #endif
+ }
+ 
++static inline bool x86_exception_has_error_code(unsigned int vector)
++{
++      static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) |
++                      BIT(NP_VECTOR) | BIT(SS_VECTOR) | BIT(GP_VECTOR) |
++                      BIT(PF_VECTOR) | BIT(AC_VECTOR);
++
++      return (1U << vector) & exception_has_error_code;
++}
++
+ static inline bool mmu_is_nested(struct kvm_vcpu *vcpu)
+ {
+       return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu;
+diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
+index 2e9ee023e6bc..81a8e33115ad 100644
+--- a/arch/x86/purgatory/Makefile
++++ b/arch/x86/purgatory/Makefile
+@@ -6,7 +6,7 @@ purgatory-y := purgatory.o stack.o setup-x86_$(BITS).o 
sha256.o entry64.o string
+ targets += $(purgatory-y)
+ PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
+ 
+-$(obj)/sha256.o: $(srctree)/lib/sha256.c
++$(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE
+       $(call if_changed_rule,cc_o_c)
+ 
+ LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib -z 
nodefaultlib
+diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
+index 357969a3697c..ce8f6a8d4ac9 100644
+--- a/arch/x86/xen/enlighten_pv.c
++++ b/arch/x86/xen/enlighten_pv.c
+@@ -1206,12 +1206,20 @@ asmlinkage __visible void __init xen_start_kernel(void)
+ 
+       xen_setup_features();
+ 
+-      xen_setup_machphys_mapping();
+-
+       /* Install Xen paravirt ops */
+       pv_info = xen_info;
+       pv_init_ops.patch = paravirt_patch_default;
+       pv_cpu_ops = xen_cpu_ops;
++      xen_init_irq_ops();
++
++      /*
++       * Setup xen_vcpu early because it is needed for
++       * local_irq_disable(), irqs_disabled(), e.g. in printk().
++       *
++       * Don't do the full vcpu_info placement stuff until we have
++       * the cpu_possible_mask and a non-dummy shared_info.
++       */
++      xen_vcpu_info_reset(0);
+ 
+       x86_platform.get_nmi_reason = xen_get_nmi_reason;
+ 
+@@ -1224,10 +1232,12 @@ asmlinkage __visible void __init xen_start_kernel(void)
+        * Set up some pagetable state before starting to set any ptes.
+        */
+ 
++      xen_setup_machphys_mapping();
+       xen_init_mmu_ops();
+ 
+       /* Prevent unwanted bits from being set in PTEs. */
+       __supported_pte_mask &= ~_PAGE_GLOBAL;
++      __default_kernel_pte_mask &= ~_PAGE_GLOBAL;
+ 
+       /*
+        * Prevent page tables from being allocated in highmem, even
+@@ -1248,20 +1258,9 @@ asmlinkage __visible void __init xen_start_kernel(void)
+       get_cpu_cap(&boot_cpu_data);
+       x86_configure_nx();
+ 
+-      xen_init_irq_ops();
+-
+       /* Let's presume PV guests always boot on vCPU with id 0. */
+       per_cpu(xen_vcpu_id, 0) = 0;
+ 
+-      /*
+-       * Setup xen_vcpu early because idt_setup_early_handler needs it for
+-       * local_irq_disable(), irqs_disabled().
+-       *
+-       * Don't do the full vcpu_info placement stuff until we have
+-       * the cpu_possible_mask and a non-dummy shared_info.
+-       */
+-      xen_vcpu_info_reset(0);
+-
+       idt_setup_early_handler();
+ 
+       xen_init_capabilities();
+diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
+index 74179852e46c..7515a19fd324 100644
+--- a/arch/x86/xen/irq.c
++++ b/arch/x86/xen/irq.c
+@@ -128,8 +128,6 @@ static const struct pv_irq_ops xen_irq_ops __initconst = {
+ 
+ void __init xen_init_irq_ops(void)
+ {
+-      /* For PVH we use default pv_irq_ops settings. */
+-      if (!xen_feature(XENFEAT_hvm_callback_vector))
+-              pv_irq_ops = xen_irq_ops;
++      pv_irq_ops = xen_irq_ops;
+       x86_init.irqs.intr_init = xen_init_IRQ;
+ }
+diff --git a/block/bsg.c b/block/bsg.c
+index defa06c11858..7a54b645d469 100644
+--- a/block/bsg.c
++++ b/block/bsg.c
+@@ -268,8 +268,6 @@ bsg_map_hdr(struct request_queue *q, struct sg_io_v4 *hdr, 
fmode_t mode)
+       } else if (hdr->din_xfer_len) {
+               ret = blk_rq_map_user(q, rq, NULL, uptr64(hdr->din_xferp),
+                               hdr->din_xfer_len, GFP_KERNEL);
+-      } else {
+-              ret = blk_rq_map_user(q, rq, NULL, NULL, 0, GFP_KERNEL);
+       }
+ 
+       if (ret)
+diff --git a/crypto/Kconfig b/crypto/Kconfig
+index 76e8c88c97b4..2f4d4f711950 100644
+--- a/crypto/Kconfig
++++ b/crypto/Kconfig
+@@ -1335,34 +1335,6 @@ config CRYPTO_SALSA20
+         The Salsa20 stream cipher algorithm is designed by Daniel J.
+         Bernstein <[email protected]>. See <http://cr.yp.to/snuffle.html>
+ 
+-config CRYPTO_SALSA20_586
+-      tristate "Salsa20 stream cipher algorithm (i586)"
+-      depends on (X86 || UML_X86) && !64BIT
+-      select CRYPTO_BLKCIPHER
+-      select CRYPTO_SALSA20
+-      help
+-        Salsa20 stream cipher algorithm.
+-
+-        Salsa20 is a stream cipher submitted to eSTREAM, the ECRYPT
+-        Stream Cipher Project. See <http://www.ecrypt.eu.org/stream/>
+-
+-        The Salsa20 stream cipher algorithm is designed by Daniel J.
+-        Bernstein <[email protected]>. See <http://cr.yp.to/snuffle.html>
+-
+-config CRYPTO_SALSA20_X86_64
+-      tristate "Salsa20 stream cipher algorithm (x86_64)"
+-      depends on (X86 || UML_X86) && 64BIT
+-      select CRYPTO_BLKCIPHER
+-      select CRYPTO_SALSA20
+-      help
+-        Salsa20 stream cipher algorithm.
+-
+-        Salsa20 is a stream cipher submitted to eSTREAM, the ECRYPT
+-        Stream Cipher Project. See <http://www.ecrypt.eu.org/stream/>
+-
+-        The Salsa20 stream cipher algorithm is designed by Daniel J.
+-        Bernstein <[email protected]>. See <http://cr.yp.to/snuffle.html>
+-
+ config CRYPTO_CHACHA20
+       tristate "ChaCha20 cipher algorithm"
+       select CRYPTO_BLKCIPHER
+diff --git a/crypto/sha3_generic.c b/crypto/sha3_generic.c
+index 264ec12c0b9c..7f6735d9003f 100644
+--- a/crypto/sha3_generic.c
++++ b/crypto/sha3_generic.c
+@@ -152,7 +152,7 @@ static SHA3_INLINE void keccakf_round(u64 st[25])
+       st[24] ^= bc[ 4];
+ }
+ 
+-static void __optimize("O3") keccakf(u64 st[25])
++static void keccakf(u64 st[25])
+ {
+       int round;
+ 
+diff --git a/drivers/acpi/acpica/hwsleep.c b/drivers/acpi/acpica/hwsleep.c
+index fc0c2e2328cd..fe9d46d81750 100644
+--- a/drivers/acpi/acpica/hwsleep.c
++++ b/drivers/acpi/acpica/hwsleep.c
+@@ -51,16 +51,23 @@ acpi_status acpi_hw_legacy_sleep(u8 sleep_state)
+               return_ACPI_STATUS(status);
+       }
+ 
+-      /*
+-       * 1) Disable all GPEs
+-       * 2) Enable all wakeup GPEs
+-       */
++      /* Disable all GPEs */
+       status = acpi_hw_disable_all_gpes();
+       if (ACPI_FAILURE(status)) {
+               return_ACPI_STATUS(status);
+       }
++      /*
++       * If the target sleep state is S5, clear all GPEs and fixed events too
++       */
++      if (sleep_state == ACPI_STATE_S5) {
++              status = acpi_hw_clear_acpi_status();
++              if (ACPI_FAILURE(status)) {
++                      return_ACPI_STATUS(status);
++              }
++      }
+       acpi_gbl_system_awake_and_running = FALSE;
+ 
++       /* Enable all wakeup GPEs */
+       status = acpi_hw_enable_all_wakeup_gpes();
+       if (ACPI_FAILURE(status)) {
+               return_ACPI_STATUS(status);
+diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
+index e2235ed3e4be..964106d173bd 100644
+--- a/drivers/acpi/nfit/core.c
++++ b/drivers/acpi/nfit/core.c
+@@ -1272,7 +1272,7 @@ static ssize_t scrub_show(struct device *dev,
+ 
+               mutex_lock(&acpi_desc->init_mutex);
+               rc = sprintf(buf, "%d%s", acpi_desc->scrub_count,
+-                              work_busy(&acpi_desc->dwork.work)
++                              acpi_desc->scrub_busy
+                               && !acpi_desc->cancel ? "+\n" : "\n");
+               mutex_unlock(&acpi_desc->init_mutex);
+       }
+@@ -2949,6 +2949,32 @@ static unsigned int __acpi_nfit_scrub(struct 
acpi_nfit_desc *acpi_desc,
+       return 0;
+ }
+ 
++static void __sched_ars(struct acpi_nfit_desc *acpi_desc, unsigned int tmo)
++{
++      lockdep_assert_held(&acpi_desc->init_mutex);
++
++      acpi_desc->scrub_busy = 1;
++      /* note this should only be set from within the workqueue */
++      if (tmo)
++              acpi_desc->scrub_tmo = tmo;
++      queue_delayed_work(nfit_wq, &acpi_desc->dwork, tmo * HZ);
++}
++
++static void sched_ars(struct acpi_nfit_desc *acpi_desc)
++{
++      __sched_ars(acpi_desc, 0);
++}
++
++static void notify_ars_done(struct acpi_nfit_desc *acpi_desc)
++{
++      lockdep_assert_held(&acpi_desc->init_mutex);
++
++      acpi_desc->scrub_busy = 0;
++      acpi_desc->scrub_count++;
++      if (acpi_desc->scrub_count_state)
++              sysfs_notify_dirent(acpi_desc->scrub_count_state);
++}
++
+ static void acpi_nfit_scrub(struct work_struct *work)
+ {
+       struct acpi_nfit_desc *acpi_desc;
+@@ -2959,14 +2985,10 @@ static void acpi_nfit_scrub(struct work_struct *work)
+       mutex_lock(&acpi_desc->init_mutex);
+       query_rc = acpi_nfit_query_poison(acpi_desc);
+       tmo = __acpi_nfit_scrub(acpi_desc, query_rc);
+-      if (tmo) {
+-              queue_delayed_work(nfit_wq, &acpi_desc->dwork, tmo * HZ);
+-              acpi_desc->scrub_tmo = tmo;
+-      } else {
+-              acpi_desc->scrub_count++;
+-              if (acpi_desc->scrub_count_state)
+-                      sysfs_notify_dirent(acpi_desc->scrub_count_state);
+-      }
++      if (tmo)
++              __sched_ars(acpi_desc, tmo);
++      else
++              notify_ars_done(acpi_desc);
+       memset(acpi_desc->ars_status, 0, acpi_desc->max_ars);
+       mutex_unlock(&acpi_desc->init_mutex);
+ }
+@@ -3047,7 +3069,7 @@ static int acpi_nfit_register_regions(struct 
acpi_nfit_desc *acpi_desc)
+                       break;
+               }
+ 
+-      queue_delayed_work(nfit_wq, &acpi_desc->dwork, 0);
++      sched_ars(acpi_desc);
+       return 0;
+ }
+ 
+@@ -3249,7 +3271,7 @@ int acpi_nfit_ars_rescan(struct acpi_nfit_desc 
*acpi_desc, unsigned long flags)
+               }
+       }
+       if (scheduled) {
+-              queue_delayed_work(nfit_wq, &acpi_desc->dwork, 0);
++              sched_ars(acpi_desc);
+               dev_dbg(dev, "ars_scan triggered\n");
+       }
+       mutex_unlock(&acpi_desc->init_mutex);
+diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h
+index 7d15856a739f..a97ff42fe311 100644
+--- a/drivers/acpi/nfit/nfit.h
++++ b/drivers/acpi/nfit/nfit.h
+@@ -203,6 +203,7 @@ struct acpi_nfit_desc {
+       unsigned int max_ars;
+       unsigned int scrub_count;
+       unsigned int scrub_mode;
++      unsigned int scrub_busy:1;
+       unsigned int cancel:1;
+       unsigned long dimm_cmd_force_en;
+       unsigned long bus_cmd_force_en;
+diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
+index 738fb22978dd..b2b9eba1d214 100644
+--- a/drivers/ata/ahci.c
++++ b/drivers/ata/ahci.c
+@@ -400,6 +400,7 @@ static const struct pci_device_id ahci_pci_tbl[] = {
+       { PCI_VDEVICE(INTEL, 0x0f23), board_ahci_mobile }, /* Bay Trail AHCI */
+       { PCI_VDEVICE(INTEL, 0x22a3), board_ahci_mobile }, /* Cherry Tr. AHCI */
+       { PCI_VDEVICE(INTEL, 0x5ae3), board_ahci_mobile }, /* ApolloLake AHCI */
++      { PCI_VDEVICE(INTEL, 0x34d3), board_ahci_mobile }, /* Ice Lake LP AHCI 
*/
+ 
+       /* JMicron 360/1/3/5/6, match class to avoid IDE function */
+       { PCI_VENDOR_ID_JMICRON, PCI_ANY_ID, PCI_ANY_ID, PCI_ANY_ID,
+@@ -1280,6 +1281,59 @@ static bool ahci_broken_suspend(struct pci_dev *pdev)
+       return strcmp(buf, dmi->driver_data) < 0;
+ }
+ 
++static bool ahci_broken_lpm(struct pci_dev *pdev)
++{
++      static const struct dmi_system_id sysids[] = {
++              /* Various Lenovo 50 series have LPM issues with older BIOSen */
++              {
++                      .matches = {
++                              DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
++                              DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad X250"),
++                      },
++                      .driver_data = "20180406", /* 1.31 */
++              },
++              {
++                      .matches = {
++                              DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
++                              DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L450"),
++                      },
++                      .driver_data = "20180420", /* 1.28 */
++              },
++              {
++                      .matches = {
++                              DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
++                              DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad 
T450s"),
++                      },
++                      .driver_data = "20180315", /* 1.33 */
++              },
++              {
++                      .matches = {
++                              DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
++                              DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W541"),
++                      },
++                      /*
++                       * Note date based on release notes, 2.35 has been
++                       * reported to be good, but I've been unable to get
++                       * a hold of the reporter to get the DMI BIOS date.
++                       * TODO: fix this.
++                       */
++                      .driver_data = "20180310", /* 2.35 */
++              },
++              { }     /* terminate list */
++      };
++      const struct dmi_system_id *dmi = dmi_first_match(sysids);
++      int year, month, date;
++      char buf[9];
++
++      if (!dmi)
++              return false;
++
++      dmi_get_date(DMI_BIOS_DATE, &year, &month, &date);
++      snprintf(buf, sizeof(buf), "%04d%02d%02d", year, month, date);
++
++      return strcmp(buf, dmi->driver_data) < 0;
++}
++
+ static bool ahci_broken_online(struct pci_dev *pdev)
+ {
+ #define ENCODE_BUSDEVFN(bus, slot, func)                      \
+@@ -1694,6 +1748,12 @@ static int ahci_init_one(struct pci_dev *pdev, const 
struct pci_device_id *ent)
+                       "quirky BIOS, skipping spindown on poweroff\n");
+       }
+ 
++      if (ahci_broken_lpm(pdev)) {
++              pi.flags |= ATA_FLAG_NO_LPM;
++              dev_warn(&pdev->dev,
++                       "BIOS update required for Link Power Management 
support\n");
++      }
++
+       if (ahci_broken_suspend(pdev)) {
+               hpriv->flags |= AHCI_HFLAG_NO_SUSPEND;
+               dev_warn(&pdev->dev,
+diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
+index 9bfd2f7e4542..55cbaab4bc20 100644
+--- a/drivers/ata/libata-core.c
++++ b/drivers/ata/libata-core.c
+@@ -2502,6 +2502,9 @@ int ata_dev_configure(struct ata_device *dev)
+           (id[ATA_ID_SATA_CAPABILITY] & 0xe) == 0x2)
+               dev->horkage |= ATA_HORKAGE_NOLPM;
+ 
++      if (ap->flags & ATA_FLAG_NO_LPM)
++              dev->horkage |= ATA_HORKAGE_NOLPM;
++
+       if (dev->horkage & ATA_HORKAGE_NOLPM) {
+               ata_dev_warn(dev, "LPM support broken, forcing max_power\n");
+               dev->link->ap->target_lpm_policy = ATA_LPM_MAX_POWER;
+diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
+index 89a9d4a2efc8..c0ac1ea3e7a3 100644
+--- a/drivers/ata/libata-scsi.c
++++ b/drivers/ata/libata-scsi.c
+@@ -3802,10 +3802,20 @@ static unsigned int ata_scsi_zbc_out_xlat(struct 
ata_queued_cmd *qc)
+                */
+               goto invalid_param_len;
+       }
+-      if (block > dev->n_sectors)
+-              goto out_of_range;
+ 
+       all = cdb[14] & 0x1;
++      if (all) {
++              /*
++               * Ignore the block address (zone ID) as defined by ZBC.
++               */
++              block = 0;
++      } else if (block >= dev->n_sectors) {
++              /*
++               * Block must be a valid zone ID (a zone start LBA).
++               */
++              fp = 2;
++              goto invalid_fld;
++      }
+ 
+       if (ata_ncq_enabled(qc->dev) &&
+           ata_fpdma_zac_mgmt_out_supported(qc->dev)) {
+@@ -3834,10 +3844,6 @@ static unsigned int ata_scsi_zbc_out_xlat(struct 
ata_queued_cmd *qc)
+  invalid_fld:
+       ata_scsi_set_invalid_field(qc->dev, scmd, fp, 0xff);
+       return 1;
+- out_of_range:
+-      /* "Logical Block Address out of range" */
+-      ata_scsi_set_sense(qc->dev, scmd, ILLEGAL_REQUEST, 0x21, 0x00);
+-      return 1;
+ invalid_param_len:
+       /* "Parameter list length error" */
+       ata_scsi_set_sense(qc->dev, scmd, ILLEGAL_REQUEST, 0x1a, 0x0);
+diff --git a/drivers/block/loop.c b/drivers/block/loop.c
+index 55cf554bc914..1a2777bc5a57 100644
+--- a/drivers/block/loop.c
++++ b/drivers/block/loop.c
+@@ -644,6 +644,36 @@ static void loop_reread_partitions(struct loop_device *lo,
+                       __func__, lo->lo_number, lo->lo_file_name, rc);
+ }
+ 
++static inline int is_loop_device(struct file *file)
++{
++      struct inode *i = file->f_mapping->host;
++
++      return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR;
++}
++
++static int loop_validate_file(struct file *file, struct block_device *bdev)
++{
++      struct inode    *inode = file->f_mapping->host;
++      struct file     *f = file;
++
++      /* Avoid recursion */
++      while (is_loop_device(f)) {
++              struct loop_device *l;
++
++              if (f->f_mapping->host->i_bdev == bdev)
++                      return -EBADF;
++
++              l = f->f_mapping->host->i_bdev->bd_disk->private_data;
++              if (l->lo_state == Lo_unbound) {
++                      return -EINVAL;
++              }
++              f = l->lo_backing_file;
++      }
++      if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
++              return -EINVAL;
++      return 0;
++}
++
+ /*
+  * loop_change_fd switched the backing store of a loopback device to
+  * a new file. This is useful for operating system installers to free up
+@@ -673,14 +703,15 @@ static int loop_change_fd(struct loop_device *lo, struct 
block_device *bdev,
+       if (!file)
+               goto out;
+ 
++      error = loop_validate_file(file, bdev);
++      if (error)
++              goto out_putf;
++
+       inode = file->f_mapping->host;
+       old_file = lo->lo_backing_file;
+ 
+       error = -EINVAL;
+ 
+-      if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
+-              goto out_putf;
+-
+       /* size of the new backing store needs to be the same */
+       if (get_loop_size(lo, file) != get_loop_size(lo, old_file))
+               goto out_putf;
+@@ -706,13 +737,6 @@ static int loop_change_fd(struct loop_device *lo, struct 
block_device *bdev,
+       return error;
+ }
+ 
+-static inline int is_loop_device(struct file *file)
+-{
+-      struct inode *i = file->f_mapping->host;
+-
+-      return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR;
+-}
+-
+ /* loop sysfs attributes */
+ 
+ static ssize_t loop_attr_show(struct device *dev, char *page,
+@@ -809,16 +833,17 @@ static struct attribute_group loop_attribute_group = {
+       .attrs= loop_attrs,
+ };
+ 
+-static int loop_sysfs_init(struct loop_device *lo)
++static void loop_sysfs_init(struct loop_device *lo)
+ {
+-      return sysfs_create_group(&disk_to_dev(lo->lo_disk)->kobj,
+-                                &loop_attribute_group);
++      lo->sysfs_inited = !sysfs_create_group(&disk_to_dev(lo->lo_disk)->kobj,
++                                              &loop_attribute_group);
+ }
+ 
+ static void loop_sysfs_exit(struct loop_device *lo)
+ {
+-      sysfs_remove_group(&disk_to_dev(lo->lo_disk)->kobj,
+-                         &loop_attribute_group);
++      if (lo->sysfs_inited)
++              sysfs_remove_group(&disk_to_dev(lo->lo_disk)->kobj,
++                                 &loop_attribute_group);
+ }
+ 
+ static void loop_config_discard(struct loop_device *lo)
+@@ -877,7 +902,7 @@ static int loop_prepare_queue(struct loop_device *lo)
+ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
+                      struct block_device *bdev, unsigned int arg)
+ {
+-      struct file     *file, *f;
++      struct file     *file;
+       struct inode    *inode;
+       struct address_space *mapping;
+       int             lo_flags = 0;
+@@ -896,29 +921,13 @@ static int loop_set_fd(struct loop_device *lo, fmode_t 
mode,
+       if (lo->lo_state != Lo_unbound)
+               goto out_putf;
+ 
+-      /* Avoid recursion */
+-      f = file;
+-      while (is_loop_device(f)) {
+-              struct loop_device *l;
+-
+-              if (f->f_mapping->host->i_bdev == bdev)
+-                      goto out_putf;
+-
+-              l = f->f_mapping->host->i_bdev->bd_disk->private_data;
+-              if (l->lo_state == Lo_unbound) {
+-                      error = -EINVAL;
+-                      goto out_putf;
+-              }
+-              f = l->lo_backing_file;
+-      }
++      error = loop_validate_file(file, bdev);
++      if (error)
++              goto out_putf;
+ 
+       mapping = file->f_mapping;
+       inode = mapping->host;
+ 
+-      error = -EINVAL;
+-      if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
+-              goto out_putf;
+-
+       if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) ||
+           !file->f_op->write_iter)
+               lo_flags |= LO_FLAGS_READ_ONLY;
+diff --git a/drivers/block/loop.h b/drivers/block/loop.h
+index b78de9879f4f..4d42c7af7de7 100644
+--- a/drivers/block/loop.h
++++ b/drivers/block/loop.h
+@@ -58,6 +58,7 @@ struct loop_device {
+       struct kthread_worker   worker;
+       struct task_struct      *worker_task;
+       bool                    use_dio;
++      bool                    sysfs_inited;
+ 
+       struct request_queue    *lo_queue;
+       struct blk_mq_tag_set   tag_set;
+diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c 
b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
+index ab50090d066c..ff1a9ffbf17f 100644
+--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
++++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
+@@ -693,8 +693,11 @@ static struct platform_driver etnaviv_platform_driver = {
+       },
+ };
+ 
++static struct platform_device *etnaviv_drm;
++
+ static int __init etnaviv_init(void)
+ {
++      struct platform_device *pdev;
+       int ret;
+       struct device_node *np;
+ 
+@@ -706,7 +709,7 @@ static int __init etnaviv_init(void)
+ 
+       ret = platform_driver_register(&etnaviv_platform_driver);
+       if (ret != 0)
+-              platform_driver_unregister(&etnaviv_gpu_driver);
++              goto unregister_gpu_driver;
+ 
+       /*
+        * If the DT contains at least one available GPU device, instantiate
+@@ -715,20 +718,33 @@ static int __init etnaviv_init(void)
+       for_each_compatible_node(np, NULL, "vivante,gc") {
+               if (!of_device_is_available(np))
+                       continue;
+-
+-              platform_device_register_simple("etnaviv", -1, NULL, 0);
++              pdev = platform_device_register_simple("etnaviv", -1,
++                                                     NULL, 0);
++              if (IS_ERR(pdev)) {
++                      ret = PTR_ERR(pdev);
++                      of_node_put(np);
++                      goto unregister_platform_driver;
++              }
++              etnaviv_drm = pdev;
+               of_node_put(np);
+               break;
+       }
+ 
++      return 0;
++
++unregister_platform_driver:
++      platform_driver_unregister(&etnaviv_platform_driver);
++unregister_gpu_driver:
++      platform_driver_unregister(&etnaviv_gpu_driver);
+       return ret;
+ }
+ module_init(etnaviv_init);
+ 
+ static void __exit etnaviv_exit(void)
+ {
+-      platform_driver_unregister(&etnaviv_gpu_driver);
++      platform_device_unregister(etnaviv_drm);
+       platform_driver_unregister(&etnaviv_platform_driver);
++      platform_driver_unregister(&etnaviv_gpu_driver);
+ }
+ module_exit(etnaviv_exit);
+ 
+diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h 
b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
+index 3c3005501846..feb3c6fab382 100644
+--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
++++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
+@@ -142,6 +142,9 @@ struct etnaviv_gpu {
+       struct work_struct sync_point_work;
+       int sync_point_event;
+ 
++      /* hang detection */
++      u32 hangcheck_dma_addr;
++
+       void __iomem *mmio;
+       int irq;
+ 
+diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c 
b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+index 6cf0775dbcd7..506b05a67dfe 100644
+--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
++++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+@@ -21,6 +21,7 @@
+ #include "etnaviv_gem.h"
+ #include "etnaviv_gpu.h"
+ #include "etnaviv_sched.h"
++#include "state.xml.h"
+ 
+ static int etnaviv_job_hang_limit = 0;
+ module_param_named(job_hang_limit, etnaviv_job_hang_limit, int , 0444);
+@@ -96,6 +97,29 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job 
*sched_job)
+ {
+       struct etnaviv_gem_submit *submit = to_etnaviv_submit(sched_job);
+       struct etnaviv_gpu *gpu = submit->gpu;
++      u32 dma_addr;
++      int change;
++
++      /*
++       * If the GPU managed to complete this jobs fence, the timout is
++       * spurious. Bail out.
++       */
++      if (fence_completed(gpu, submit->out_fence->seqno))
++              return;
++
++      /*
++       * If the GPU is still making forward progress on the front-end (which
++       * should never loop) we shift out the timeout to give it a chance to
++       * finish the job.
++       */
++      dma_addr = gpu_read(gpu, VIVS_FE_DMA_ADDRESS);
++      change = dma_addr - gpu->hangcheck_dma_addr;
++      if (change < 0 || change > 16) {
++              gpu->hangcheck_dma_addr = dma_addr;
++              schedule_delayed_work(&sched_job->work_tdr,
++                                    sched_job->sched->timeout);
++              return;
++      }
+ 
+       /* block scheduler */
+       kthread_park(gpu->sched.thread);
+diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c
+index 60292d243e24..ec2d11af6c78 100644
+--- a/drivers/i2c/busses/i2c-tegra.c
++++ b/drivers/i2c/busses/i2c-tegra.c
+@@ -547,6 +547,14 @@ static int tegra_i2c_disable_packet_mode(struct 
tegra_i2c_dev *i2c_dev)
+ {
+       u32 cnfg;
+ 
++      /*
++       * NACK interrupt is generated before the I2C controller generates
++       * the STOP condition on the bus. So wait for 2 clock periods
++       * before disabling the controller so that the STOP condition has
++       * been delivered properly.
++       */
++      udelay(DIV_ROUND_UP(2 * 1000000, i2c_dev->bus_clk_rate));
++
+       cnfg = i2c_readl(i2c_dev, I2C_CNFG);
+       if (cnfg & I2C_CNFG_PACKET_MODE_EN)
+               i2c_writel(i2c_dev, cnfg & ~I2C_CNFG_PACKET_MODE_EN, I2C_CNFG);
+@@ -708,15 +716,6 @@ static int tegra_i2c_xfer_msg(struct tegra_i2c_dev 
*i2c_dev,
+       if (likely(i2c_dev->msg_err == I2C_ERR_NONE))
+               return 0;
+ 
+-      /*
+-       * NACK interrupt is generated before the I2C controller generates
+-       * the STOP condition on the bus. So wait for 2 clock periods
+-       * before resetting the controller so that the STOP condition has
+-       * been delivered properly.
+-       */
+-      if (i2c_dev->msg_err == I2C_ERR_NO_ACK)
+-              udelay(DIV_ROUND_UP(2 * 1000000, i2c_dev->bus_clk_rate));
+-
+       tegra_i2c_init(i2c_dev);
+       if (i2c_dev->msg_err == I2C_ERR_NO_ACK) {
+               if (msg->flags & I2C_M_IGNORE_NAK)
+diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
+index 1ba40bb2b966..1b6e80123fba 100644
+--- a/drivers/i2c/i2c-core-base.c
++++ b/drivers/i2c/i2c-core-base.c
+@@ -198,7 +198,16 @@ int i2c_generic_scl_recovery(struct i2c_adapter *adap)
+ 
+               val = !val;
+               bri->set_scl(adap, val);
+-              ndelay(RECOVERY_NDELAY);
++
++              /*
++               * If we can set SDA, we will always create STOP here to ensure
++               * the additional pulses will do no harm. This is achieved by
++               * letting SDA follow SCL half a cycle later.
++               */
++              ndelay(RECOVERY_NDELAY / 2);
++              if (bri->set_sda)
++                      bri->set_sda(adap, val);
++              ndelay(RECOVERY_NDELAY / 2);
+       }
+ 
+       /* check if recovery actually succeeded */
+diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
+index 2a972ed6851b..b03af54367c0 100644
+--- a/drivers/infiniband/Kconfig
++++ b/drivers/infiniband/Kconfig
+@@ -35,6 +35,17 @@ config INFINIBAND_USER_ACCESS
+         libibverbs, libibcm and a hardware driver library from
+         rdma-core <https://github.com/linux-rdma/rdma-core>.
+ 
++config INFINIBAND_USER_ACCESS_UCM
++      bool "Userspace CM (UCM, DEPRECATED)"
++      depends on BROKEN
++      depends on INFINIBAND_USER_ACCESS
++      help
++        The UCM module has known security flaws, which no one is
++        interested to fix. The user-space part of this code was
++        dropped from the upstream a long time ago.
++
++        This option is DEPRECATED and planned to be removed.
++
+ config INFINIBAND_EXP_LEGACY_VERBS_NEW_UAPI
+       bool "Allow experimental legacy verbs in new ioctl uAPI  (EXPERIMENTAL)"
+       depends on INFINIBAND_USER_ACCESS
+diff --git a/drivers/infiniband/core/Makefile 
b/drivers/infiniband/core/Makefile
+index dda9e856e3fa..e1acbf5f87f1 100644
+--- a/drivers/infiniband/core/Makefile
++++ b/drivers/infiniband/core/Makefile
+@@ -5,8 +5,8 @@ user_access-$(CONFIG_INFINIBAND_ADDR_TRANS)    := rdma_ucm.o
+ obj-$(CONFIG_INFINIBAND) +=           ib_core.o ib_cm.o iw_cm.o \
+                                       $(infiniband-y)
+ obj-$(CONFIG_INFINIBAND_USER_MAD) +=  ib_umad.o
+-obj-$(CONFIG_INFINIBAND_USER_ACCESS) +=       ib_uverbs.o ib_ucm.o \
+-                                      $(user_access-y)
++obj-$(CONFIG_INFINIBAND_USER_ACCESS) += ib_uverbs.o $(user_access-y)
++obj-$(CONFIG_INFINIBAND_USER_ACCESS_UCM) += ib_ucm.o $(user_access-y)
+ 
+ ib_core-y :=                  packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
+                               device.o fmr_pool.o cache.o netlink.o \
+diff --git a/drivers/infiniband/hw/cxgb4/mem.c 
b/drivers/infiniband/hw/cxgb4/mem.c
+index 1445918e3239..7b76e6f81aeb 100644
+--- a/drivers/infiniband/hw/cxgb4/mem.c
++++ b/drivers/infiniband/hw/cxgb4/mem.c
+@@ -774,7 +774,7 @@ static int c4iw_set_page(struct ib_mr *ibmr, u64 addr)
+ {
+       struct c4iw_mr *mhp = to_c4iw_mr(ibmr);
+ 
+-      if (unlikely(mhp->mpl_len == mhp->max_mpl_len))
++      if (unlikely(mhp->mpl_len == mhp->attr.pbl_size))
+               return -ENOMEM;
+ 
+       mhp->mpl[mhp->mpl_len++] = addr;
+diff --git a/drivers/infiniband/hw/hfi1/rc.c b/drivers/infiniband/hw/hfi1/rc.c
+index da58046a02ea..295d3c40a994 100644
+--- a/drivers/infiniband/hw/hfi1/rc.c
++++ b/drivers/infiniband/hw/hfi1/rc.c
+@@ -271,7 +271,7 @@ int hfi1_make_rc_req(struct rvt_qp *qp, struct 
hfi1_pkt_state *ps)
+ 
+       lockdep_assert_held(&qp->s_lock);
+       ps->s_txreq = get_txreq(ps->dev, qp);
+-      if (IS_ERR(ps->s_txreq))
++      if (!ps->s_txreq)
+               goto bail_no_tx;
+ 
+       if (priv->hdr_type == HFI1_PKT_TYPE_9B) {
+diff --git a/drivers/infiniband/hw/hfi1/uc.c b/drivers/infiniband/hw/hfi1/uc.c
+index 9d7a3110c14c..d140aaccdf14 100644
+--- a/drivers/infiniband/hw/hfi1/uc.c
++++ b/drivers/infiniband/hw/hfi1/uc.c
+@@ -1,5 +1,5 @@
+ /*
+- * Copyright(c) 2015, 2016 Intel Corporation.
++ * Copyright(c) 2015 - 2018 Intel Corporation.
+  *
+  * This file is provided under a dual BSD/GPLv2 license.  When using or
+  * redistributing this file, you may do so under either license.
+@@ -72,7 +72,7 @@ int hfi1_make_uc_req(struct rvt_qp *qp, struct 
hfi1_pkt_state *ps)
+       int middle = 0;
+ 
+       ps->s_txreq = get_txreq(ps->dev, qp);
+-      if (IS_ERR(ps->s_txreq))
++      if (!ps->s_txreq)
+               goto bail_no_tx;
+ 
+       if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_SEND_OK)) {
+diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c
+index 69c17a5ef038..3ae10530f754 100644
+--- a/drivers/infiniband/hw/hfi1/ud.c
++++ b/drivers/infiniband/hw/hfi1/ud.c
+@@ -1,5 +1,5 @@
+ /*
+- * Copyright(c) 2015, 2016 Intel Corporation.
++ * Copyright(c) 2015 - 2018 Intel Corporation.
+  *
+  * This file is provided under a dual BSD/GPLv2 license.  When using or
+  * redistributing this file, you may do so under either license.
+@@ -482,7 +482,7 @@ int hfi1_make_ud_req(struct rvt_qp *qp, struct 
hfi1_pkt_state *ps)
+       u32 lid;
+ 
+       ps->s_txreq = get_txreq(ps->dev, qp);
+-      if (IS_ERR(ps->s_txreq))
++      if (!ps->s_txreq)
+               goto bail_no_tx;
+ 
+       if (!(ib_rvt_state_ops[qp->state] & RVT_PROCESS_NEXT_SEND_OK)) {
+diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.c 
b/drivers/infiniband/hw/hfi1/verbs_txreq.c
+index 873e48ea923f..c4ab2d5b4502 100644
+--- a/drivers/infiniband/hw/hfi1/verbs_txreq.c
++++ b/drivers/infiniband/hw/hfi1/verbs_txreq.c
+@@ -1,5 +1,5 @@
+ /*
+- * Copyright(c) 2016 - 2017 Intel Corporation.
++ * Copyright(c) 2016 - 2018 Intel Corporation.
+  *
+  * This file is provided under a dual BSD/GPLv2 license.  When using or
+  * redistributing this file, you may do so under either license.
+@@ -94,7 +94,7 @@ struct verbs_txreq *__get_txreq(struct hfi1_ibdev *dev,
+                               struct rvt_qp *qp)
+       __must_hold(&qp->s_lock)
+ {
+-      struct verbs_txreq *tx = ERR_PTR(-EBUSY);
++      struct verbs_txreq *tx = NULL;
+ 
+       write_seqlock(&dev->txwait_lock);
+       if (ib_rvt_state_ops[qp->state] & RVT_PROCESS_RECV_OK) {
+diff --git a/drivers/infiniband/hw/hfi1/verbs_txreq.h 
b/drivers/infiniband/hw/hfi1/verbs_txreq.h
+index 729244c3086c..1c19bbc764b2 100644
+--- a/drivers/infiniband/hw/hfi1/verbs_txreq.h
++++ b/drivers/infiniband/hw/hfi1/verbs_txreq.h
+@@ -1,5 +1,5 @@
+ /*
+- * Copyright(c) 2016 Intel Corporation.
++ * Copyright(c) 2016 - 2018 Intel Corporation.
+  *
+  * This file is provided under a dual BSD/GPLv2 license.  When using or
+  * redistributing this file, you may do so under either license.
+@@ -83,7 +83,7 @@ static inline struct verbs_txreq *get_txreq(struct 
hfi1_ibdev *dev,
+       if (unlikely(!tx)) {
+               /* call slow path to get the lock */
+               tx = __get_txreq(dev, qp);
+-              if (IS_ERR(tx))
++              if (!tx)
+                       return tx;
+       }
+       tx->qp = qp;
+diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c
+index e05c3245930a..fa840666bdd1 100644
+--- a/drivers/misc/ibmasm/ibmasmfs.c
++++ b/drivers/misc/ibmasm/ibmasmfs.c
+@@ -507,35 +507,14 @@ static int remote_settings_file_close(struct inode 
*inode, struct file *file)
+ static ssize_t remote_settings_file_read(struct file *file, char __user *buf, 
size_t count, loff_t *offset)
+ {
+       void __iomem *address = (void __iomem *)file->private_data;
+-      unsigned char *page;
+-      int retval;
+       int len = 0;
+       unsigned int value;
+-
+-      if (*offset < 0)
+-              return -EINVAL;
+-      if (count == 0 || count > 1024)
+-              return 0;
+-      if (*offset != 0)
+-              return 0;
+-
+-      page = (unsigned char *)__get_free_page(GFP_KERNEL);
+-      if (!page)
+-              return -ENOMEM;
++      char lbuf[20];
+ 
+       value = readl(address);
+-      len = sprintf(page, "%d\n", value);
+-
+-      if (copy_to_user(buf, page, len)) {
+-              retval = -EFAULT;
+-              goto exit;
+-      }
+-      *offset += len;
+-      retval = len;
++      len = snprintf(lbuf, sizeof(lbuf), "%d\n", value);
+ 
+-exit:
+-      free_page((unsigned long)page);
+-      return retval;
++      return simple_read_from_buffer(buf, count, offset, lbuf, len);
+ }
+ 
+ static ssize_t remote_settings_file_write(struct file *file, const char 
__user *ubuff, size_t count, loff_t *offset)
+diff --git a/drivers/misc/mei/interrupt.c b/drivers/misc/mei/interrupt.c
+index b0b8f18a85e3..6649f0d56d2f 100644
+--- a/drivers/misc/mei/interrupt.c
++++ b/drivers/misc/mei/interrupt.c
+@@ -310,8 +310,11 @@ int mei_irq_read_handler(struct mei_device *dev,
+       if (&cl->link == &dev->file_list) {
+               /* A message for not connected fixed address clients
+                * should be silently discarded
++               * On power down client may be force cleaned,
++               * silently discard such messages
+                */
+-              if (hdr_is_fixed(mei_hdr)) {
++              if (hdr_is_fixed(mei_hdr) ||
++                  dev->dev_state == MEI_DEV_POWER_DOWN) {
+                       mei_irq_discard_msg(dev, mei_hdr);
+                       ret = 0;
+                       goto reset_slots;
+diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c
+index efd733472a35..56c6f79a5c5a 100644
+--- a/drivers/misc/vmw_balloon.c
++++ b/drivers/misc/vmw_balloon.c
+@@ -467,7 +467,7 @@ static int vmballoon_send_batched_lock(struct vmballoon *b,
+               unsigned int num_pages, bool is_2m_pages, unsigned int *target)
+ {
+       unsigned long status;
+-      unsigned long pfn = page_to_pfn(b->page);
++      unsigned long pfn = PHYS_PFN(virt_to_phys(b->batch_page));
+ 
+       STATS_INC(b->stats.lock[is_2m_pages]);
+ 
+@@ -515,7 +515,7 @@ static bool vmballoon_send_batched_unlock(struct vmballoon 
*b,
+               unsigned int num_pages, bool is_2m_pages, unsigned int *target)
+ {
+       unsigned long status;
+-      unsigned long pfn = page_to_pfn(b->page);
++      unsigned long pfn = PHYS_PFN(virt_to_phys(b->batch_page));
+ 
+       STATS_INC(b->stats.unlock[is_2m_pages]);
+ 
+diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
+index 29a1afa81f66..3ee8f57fd612 100644
+--- a/drivers/mmc/host/dw_mmc.c
++++ b/drivers/mmc/host/dw_mmc.c
+@@ -1065,8 +1065,8 @@ static void dw_mci_ctrl_thld(struct dw_mci *host, struct 
mmc_data *data)
+        * It's used when HS400 mode is enabled.
+        */
+       if (data->flags & MMC_DATA_WRITE &&
+-              !(host->timing != MMC_TIMING_MMC_HS400))
+-              return;
++              host->timing != MMC_TIMING_MMC_HS400)
++              goto disable;
+ 
+       if (data->flags & MMC_DATA_WRITE)
+               enable = SDMMC_CARD_WR_THR_EN;
+@@ -1074,7 +1074,8 @@ static void dw_mci_ctrl_thld(struct dw_mci *host, struct 
mmc_data *data)
+               enable = SDMMC_CARD_RD_THR_EN;
+ 
+       if (host->timing != MMC_TIMING_MMC_HS200 &&
+-          host->timing != MMC_TIMING_UHS_SDR104)
++          host->timing != MMC_TIMING_UHS_SDR104 &&
++          host->timing != MMC_TIMING_MMC_HS400)
+               goto disable;
+ 
+       blksz_depth = blksz / (1 << host->data_shift);
+diff --git a/drivers/mmc/host/renesas_sdhi_internal_dmac.c 
b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
+index eb027cdc8f24..8d19b5903fd1 100644
+--- a/drivers/mmc/host/renesas_sdhi_internal_dmac.c
++++ b/drivers/mmc/host/renesas_sdhi_internal_dmac.c
+@@ -139,8 +139,7 @@ renesas_sdhi_internal_dmac_abort_dma(struct tmio_mmc_host 
*host) {
+       renesas_sdhi_internal_dmac_dm_write(host, DM_CM_RST,
+                                           RST_RESERVED_BITS | val);
+ 
+-      if (host->data && host->data->flags & MMC_DATA_READ)
+-              clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags);
++      clear_bit(SDHI_INTERNAL_DMAC_RX_IN_USE, &global_flags);
+ 
+       renesas_sdhi_internal_dmac_enable_dma(host, true);
+ }
+diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c 
b/drivers/mmc/host/sdhci-esdhc-imx.c
+index cd2b5f643a15..6891be4ff9f1 100644
+--- a/drivers/mmc/host/sdhci-esdhc-imx.c
++++ b/drivers/mmc/host/sdhci-esdhc-imx.c
+@@ -306,6 +306,15 @@ static u32 esdhc_readl_le(struct sdhci_host *host, int 
reg)
+ 
+                       if (imx_data->socdata->flags & ESDHC_FLAG_HS400)
+                               val |= SDHCI_SUPPORT_HS400;
++
++                      /*
++                       * Do not advertise faster UHS modes if there are no
++                       * pinctrl states for 100MHz/200MHz.
++                       */
++                      if (IS_ERR_OR_NULL(imx_data->pins_100mhz) ||
++                          IS_ERR_OR_NULL(imx_data->pins_200mhz))
++                              val &= ~(SDHCI_SUPPORT_SDR50 | 
SDHCI_SUPPORT_DDR50
++                                       | SDHCI_SUPPORT_SDR104 | 
SDHCI_SUPPORT_HS400);
+               }
+       }
+ 
+@@ -1136,18 +1145,6 @@ sdhci_esdhc_imx_probe_dt(struct platform_device *pdev,
+                                               ESDHC_PINCTRL_STATE_100MHZ);
+               imx_data->pins_200mhz = pinctrl_lookup_state(imx_data->pinctrl,
+                                               ESDHC_PINCTRL_STATE_200MHZ);
+-              if (IS_ERR(imx_data->pins_100mhz) ||
+-                              IS_ERR(imx_data->pins_200mhz)) {
+-                      dev_warn(mmc_dev(host->mmc),
+-                              "could not get ultra high speed state, work on 
normal mode\n");
+-                      /*
+-                       * fall back to not supporting uhs by specifying no
+-                       * 1.8v quirk
+-                       */
+-                      host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
+-              }
+-      } else {
+-              host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
+       }
+ 
+       /* call to generic mmc_of_parse to support additional capabilities */
+diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c 
b/drivers/mtd/spi-nor/cadence-quadspi.c
+index 5872f31eaa60..5cf9ef6cf259 100644
+--- a/drivers/mtd/spi-nor/cadence-quadspi.c
++++ b/drivers/mtd/spi-nor/cadence-quadspi.c
+@@ -920,10 +920,12 @@ static ssize_t cqspi_write(struct spi_nor *nor, loff_t 
to,
+       if (ret)
+               return ret;
+ 
+-      if (f_pdata->use_direct_mode)
++      if (f_pdata->use_direct_mode) {
+               memcpy_toio(cqspi->ahb_base + to, buf, len);
+-      else
++              ret = cqspi_wait_idle(cqspi);
++      } else {
+               ret = cqspi_indirect_write_execute(nor, to, buf, len);
++      }
+       if (ret)
+               return ret;
+ 
+diff --git a/drivers/staging/rtl8723bs/core/rtw_ap.c 
b/drivers/staging/rtl8723bs/core/rtw_ap.c
+index 0b530ea7fd81..4b39b7ddf506 100644
+--- a/drivers/staging/rtl8723bs/core/rtw_ap.c
++++ b/drivers/staging/rtl8723bs/core/rtw_ap.c
+@@ -1059,7 +1059,7 @@ int rtw_check_beacon_data(struct adapter *padapter, u8 
*pbuf,  int len)
+               return _FAIL;
+ 
+ 
+-      if (len > MAX_IE_SZ)
++      if (len < 0 || len > MAX_IE_SZ)
+               return _FAIL;
+ 
+       pbss_network->IELength = len;
+diff --git a/drivers/staging/rtlwifi/rtl8822be/hw.c 
b/drivers/staging/rtlwifi/rtl8822be/hw.c
+index 74386003044f..c6db2bd20594 100644
+--- a/drivers/staging/rtlwifi/rtl8822be/hw.c
++++ b/drivers/staging/rtlwifi/rtl8822be/hw.c
+@@ -814,7 +814,7 @@ static void _rtl8822be_enable_aspm_back_door(struct 
ieee80211_hw *hw)
+               return;
+ 
+       pci_read_config_byte(rtlpci->pdev, 0x70f, &tmp);
+-      pci_write_config_byte(rtlpci->pdev, 0x70f, tmp | BIT(7));
++      pci_write_config_byte(rtlpci->pdev, 0x70f, tmp | ASPM_L1_LATENCY << 3);
+ 
+       pci_read_config_byte(rtlpci->pdev, 0x719, &tmp);
+       pci_write_config_byte(rtlpci->pdev, 0x719, tmp | BIT(3) | BIT(4));
+diff --git a/drivers/staging/rtlwifi/wifi.h b/drivers/staging/rtlwifi/wifi.h
+index a23bb1719e35..0ab1e2d50535 100644
+--- a/drivers/staging/rtlwifi/wifi.h
++++ b/drivers/staging/rtlwifi/wifi.h
+@@ -99,6 +99,7 @@
+ #define RTL_USB_MAX_RX_COUNT                  100
+ #define QBSS_LOAD_SIZE                                5
+ #define MAX_WMMELE_LENGTH                     64
++#define ASPM_L1_LATENCY                               7
+ 
+ #define TOTAL_CAM_ENTRY                               32
+ 
+diff --git a/drivers/thunderbolt/domain.c b/drivers/thunderbolt/domain.c
+index 6281266b8ec0..a923ebdeb73c 100644
+--- a/drivers/thunderbolt/domain.c
++++ b/drivers/thunderbolt/domain.c
+@@ -213,6 +213,10 @@ static ssize_t boot_acl_store(struct device *dev, struct 
device_attribute *attr,
+               goto err_free_acl;
+       }
+       ret = tb->cm_ops->set_boot_acl(tb, acl, tb->nboot_acl);
++      if (!ret) {
++              /* Notify userspace about the change */
++              kobject_uevent(&tb->dev.kobj, KOBJ_CHANGE);
++      }
+       mutex_unlock(&tb->lock);
+ 
+ err_free_acl:
+diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
+index c55def2f1320..097057d2eacf 100644
+--- a/drivers/usb/core/quirks.c
++++ b/drivers/usb/core/quirks.c
+@@ -378,6 +378,10 @@ static const struct usb_device_id usb_quirk_list[] = {
+       /* Corsair K70 RGB */
+       { USB_DEVICE(0x1b1c, 0x1b13), .driver_info = USB_QUIRK_DELAY_INIT },
+ 
++      /* Corsair Strafe */
++      { USB_DEVICE(0x1b1c, 0x1b15), .driver_info = USB_QUIRK_DELAY_INIT |
++        USB_QUIRK_DELAY_CTRL_MSG },
++
+       /* Corsair Strafe RGB */
+       { USB_DEVICE(0x1b1c, 0x1b20), .driver_info = USB_QUIRK_DELAY_INIT |
+         USB_QUIRK_DELAY_CTRL_MSG },
+diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
+index 99e7547f234f..0b424a4b58ec 100644
+--- a/drivers/usb/host/xhci-mem.c
++++ b/drivers/usb/host/xhci-mem.c
+@@ -591,7 +591,7 @@ struct xhci_ring *xhci_stream_id_to_ring(
+       if (!ep->stream_info)
+               return NULL;
+ 
+-      if (stream_id > ep->stream_info->num_streams)
++      if (stream_id >= ep->stream_info->num_streams)
+               return NULL;
+       return ep->stream_info->stream_rings[stream_id];
+ }
+diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
+index 8abb6cbbd98a..3be40eaa1ac9 100644
+--- a/drivers/usb/misc/yurex.c
++++ b/drivers/usb/misc/yurex.c
+@@ -396,8 +396,7 @@ static ssize_t yurex_read(struct file *file, char __user 
*buffer, size_t count,
+                         loff_t *ppos)
+ {
+       struct usb_yurex *dev;
+-      int retval = 0;
+-      int bytes_read = 0;
++      int len = 0;
+       char in_buffer[20];
+       unsigned long flags;
+ 
+@@ -405,26 +404,16 @@ static ssize_t yurex_read(struct file *file, char __user 
*buffer, size_t count,
+ 
+       mutex_lock(&dev->io_mutex);
+       if (!dev->interface) {          /* already disconnected */
+-              retval = -ENODEV;
+-              goto exit;
++              mutex_unlock(&dev->io_mutex);
++              return -ENODEV;
+       }
+ 
+       spin_lock_irqsave(&dev->lock, flags);
+-      bytes_read = snprintf(in_buffer, 20, "%lld\n", dev->bbu);
++      len = snprintf(in_buffer, 20, "%lld\n", dev->bbu);
+       spin_unlock_irqrestore(&dev->lock, flags);
+-
+-      if (*ppos < bytes_read) {
+-              if (copy_to_user(buffer, in_buffer + *ppos, bytes_read - *ppos))
+-                      retval = -EFAULT;
+-              else {
+-                      retval = bytes_read - *ppos;
+-                      *ppos += bytes_read;
+-              }
+-      }
+-
+-exit:
+       mutex_unlock(&dev->io_mutex);
+-      return retval;
++
++      return simple_read_from_buffer(buffer, count, ppos, in_buffer, len);
+ }
+ 
+ static ssize_t yurex_write(struct file *file, const char __user *user_buffer,
+diff --git a/drivers/usb/serial/ch341.c b/drivers/usb/serial/ch341.c
+index bdd7a5ad3bf1..3bb1fff02bed 100644
+--- a/drivers/usb/serial/ch341.c
++++ b/drivers/usb/serial/ch341.c
+@@ -128,7 +128,7 @@ static int ch341_control_in(struct usb_device *dev,
+       r = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), request,
+                           USB_TYPE_VENDOR | USB_RECIP_DEVICE | USB_DIR_IN,
+                           value, index, buf, bufsize, DEFAULT_TIMEOUT);
+-      if (r < bufsize) {
++      if (r < (int)bufsize) {
+               if (r >= 0) {
+                       dev_err(&dev->dev,
+                               "short control message received (%d < %u)\n",
+diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
+index ee0cc1d90b51..626a29d9aa58 100644
+--- a/drivers/usb/serial/cp210x.c
++++ b/drivers/usb/serial/cp210x.c
+@@ -149,6 +149,7 @@ static const struct usb_device_id id_table[] = {
+       { USB_DEVICE(0x10C4, 0x8977) }, /* CEL MeshWorks DevKit Device */
+       { USB_DEVICE(0x10C4, 0x8998) }, /* KCF Technologies PRN */
+       { USB_DEVICE(0x10C4, 0x89A4) }, /* CESINEL FTBC Flexible Thyristor 
Bridge Controller */
++      { USB_DEVICE(0x10C4, 0x89FB) }, /* Qivicon ZigBee USB Radio Stick */
+       { USB_DEVICE(0x10C4, 0x8A2A) }, /* HubZ dual ZigBee and Z-Wave dongle */
+       { USB_DEVICE(0x10C4, 0x8A5E) }, /* CEL EM3588 ZigBee USB Stick Long 
Range */
+       { USB_DEVICE(0x10C4, 0x8B34) }, /* Qivicon ZigBee USB Radio Stick */
+diff --git a/drivers/usb/serial/keyspan_pda.c 
b/drivers/usb/serial/keyspan_pda.c
+index 5169624d8b11..38d43c4b7ce5 100644
+--- a/drivers/usb/serial/keyspan_pda.c
++++ b/drivers/usb/serial/keyspan_pda.c
+@@ -369,8 +369,10 @@ static int keyspan_pda_get_modem_info(struct usb_serial 
*serial,
+                            3, /* get pins */
+                            USB_TYPE_VENDOR|USB_RECIP_INTERFACE|USB_DIR_IN,
+                            0, 0, data, 1, 2000);
+-      if (rc >= 0)
++      if (rc == 1)
+               *value = *data;
++      else if (rc >= 0)
++              rc = -EIO;
+ 
+       kfree(data);
+       return rc;
+diff --git a/drivers/usb/serial/mos7840.c b/drivers/usb/serial/mos7840.c
+index fdceb46d9fc6..b580b4c7fa48 100644
+--- a/drivers/usb/serial/mos7840.c
++++ b/drivers/usb/serial/mos7840.c
+@@ -468,6 +468,9 @@ static void mos7840_control_callback(struct urb *urb)
+       }
+ 
+       dev_dbg(dev, "%s urb buffer size is %d\n", __func__, 
urb->actual_length);
++      if (urb->actual_length < 1)
++              goto out;
++
+       dev_dbg(dev, "%s mos7840_port->MsrLsr is %d port %d\n", __func__,
+               mos7840_port->MsrLsr, mos7840_port->port_num);
+       data = urb->transfer_buffer;
+diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
+index 4ad6f669fe34..39d3a724a4b4 100644
+--- a/fs/binfmt_elf.c
++++ b/fs/binfmt_elf.c
+@@ -1259,9 +1259,8 @@ static int load_elf_library(struct file *file)
+               goto out_free_ph;
+       }
+ 
+-      len = ELF_PAGESTART(eppnt->p_filesz + eppnt->p_vaddr +
+-                          ELF_MIN_ALIGN - 1);
+-      bss = eppnt->p_memsz + eppnt->p_vaddr;
++      len = ELF_PAGEALIGN(eppnt->p_filesz + eppnt->p_vaddr);
++      bss = ELF_PAGEALIGN(eppnt->p_memsz + eppnt->p_vaddr);
+       if (bss > len) {
+               error = vm_brk(len, bss - len);
+               if (error)
+diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
+index 1df7f10476d6..20149b8771d9 100644
+--- a/fs/f2fs/f2fs.h
++++ b/fs/f2fs/f2fs.h
+@@ -1586,18 +1586,6 @@ static inline bool __exist_node_summaries(struct 
f2fs_sb_info *sbi)
+                       is_set_ckpt_flags(sbi, CP_FASTBOOT_FLAG));
+ }
+ 
+-/*
+- * Check whether the given nid is within node id range.
+- */
+-static inline int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
+-{
+-      if (unlikely(nid < F2FS_ROOT_INO(sbi)))
+-              return -EINVAL;
+-      if (unlikely(nid >= NM_I(sbi)->max_nid))
+-              return -EINVAL;
+-      return 0;
+-}
+-
+ /*
+  * Check whether the inode has blocks or not
+  */
+@@ -2720,6 +2708,7 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr 
*name_info,
+ struct dnode_of_data;
+ struct node_info;
+ 
++int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid);
+ bool available_free_memory(struct f2fs_sb_info *sbi, int type);
+ int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid);
+ bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid);
+diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
+index f8ef04c9f69d..3d91bea4ec90 100644
+--- a/fs/f2fs/inode.c
++++ b/fs/f2fs/inode.c
+@@ -185,6 +185,21 @@ void f2fs_inode_chksum_set(struct f2fs_sb_info *sbi, 
struct page *page)
+       ri->i_inode_checksum = cpu_to_le32(f2fs_inode_chksum(sbi, page));
+ }
+ 
++static bool sanity_check_inode(struct inode *inode)
++{
++      struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
++
++      if (f2fs_sb_has_flexible_inline_xattr(sbi->sb)
++                      && !f2fs_has_extra_attr(inode)) {
++              set_sbi_flag(sbi, SBI_NEED_FSCK);
++              f2fs_msg(sbi->sb, KERN_WARNING,
++                      "%s: corrupted inode ino=%lx, run fsck to fix.",
++                      __func__, inode->i_ino);
++              return false;
++      }
++      return true;
++}
++
+ static int do_read_inode(struct inode *inode)
+ {
+       struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+@@ -194,12 +209,8 @@ static int do_read_inode(struct inode *inode)
+       projid_t i_projid;
+ 
+       /* Check if ino is within scope */
+-      if (check_nid_range(sbi, inode->i_ino)) {
+-              f2fs_msg(inode->i_sb, KERN_ERR, "bad inode number: %lu",
+-                       (unsigned long) inode->i_ino);
+-              WARN_ON(1);
++      if (check_nid_range(sbi, inode->i_ino))
+               return -EINVAL;
+-      }
+ 
+       node_page = get_node_page(sbi, inode->i_ino);
+       if (IS_ERR(node_page))
+@@ -239,7 +250,6 @@ static int do_read_inode(struct inode *inode)
+                                       le16_to_cpu(ri->i_extra_isize) : 0;
+ 
+       if (f2fs_sb_has_flexible_inline_xattr(sbi->sb)) {
+-              f2fs_bug_on(sbi, !f2fs_has_extra_attr(inode));
+               fi->i_inline_xattr_size = le16_to_cpu(ri->i_inline_xattr_size);
+       } else if (f2fs_has_inline_xattr(inode) ||
+                               f2fs_has_inline_dentry(inode)) {
+@@ -317,6 +327,10 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned 
long ino)
+       ret = do_read_inode(inode);
+       if (ret)
+               goto bad_inode;
++      if (!sanity_check_inode(inode)) {
++              ret = -EINVAL;
++              goto bad_inode;
++      }
+ make_now:
+       if (ino == F2FS_NODE_INO(sbi)) {
+               inode->i_mapping->a_ops = &f2fs_node_aops;
+@@ -588,8 +602,11 @@ void f2fs_evict_inode(struct inode *inode)
+               alloc_nid_failed(sbi, inode->i_ino);
+               clear_inode_flag(inode, FI_FREE_NID);
+       } else {
+-              f2fs_bug_on(sbi, err &&
+-                      !exist_written_data(sbi, inode->i_ino, ORPHAN_INO));
++              /*
++               * If xattr nid is corrupted, we can reach out error condition,
++               * err & !exist_written_data(sbi, inode->i_ino, ORPHAN_INO)).
++               * In that case, check_nid_range() is enough to give a clue.
++               */
+       }
+ out_clear:
+       fscrypt_put_encryption_info(inode);
+diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
+index f202398e20ea..de48222f48e3 100644
+--- a/fs/f2fs/node.c
++++ b/fs/f2fs/node.c
+@@ -29,6 +29,21 @@ static struct kmem_cache *nat_entry_slab;
+ static struct kmem_cache *free_nid_slab;
+ static struct kmem_cache *nat_entry_set_slab;
+ 
++/*
++ * Check whether the given nid is within node id range.
++ */
++int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
++{
++      if (unlikely(nid < F2FS_ROOT_INO(sbi) || nid >= NM_I(sbi)->max_nid)) {
++              set_sbi_flag(sbi, SBI_NEED_FSCK);
++              f2fs_msg(sbi->sb, KERN_WARNING,
++                              "%s: out-of-range nid=%x, run fsck to fix.",
++                              __func__, nid);
++              return -EINVAL;
++      }
++      return 0;
++}
++
+ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
+ {
+       struct f2fs_nm_info *nm_i = NM_I(sbi);
+@@ -1158,7 +1173,8 @@ void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
+ 
+       if (!nid)
+               return;
+-      f2fs_bug_on(sbi, check_nid_range(sbi, nid));
++      if (check_nid_range(sbi, nid))
++              return;
+ 
+       rcu_read_lock();
+       apage = radix_tree_lookup(&NODE_MAPPING(sbi)->i_pages, nid);
+@@ -1182,7 +1198,8 @@ static struct page *__get_node_page(struct f2fs_sb_info 
*sbi, pgoff_t nid,
+ 
+       if (!nid)
+               return ERR_PTR(-ENOENT);
+-      f2fs_bug_on(sbi, check_nid_range(sbi, nid));
++      if (check_nid_range(sbi, nid))
++              return ERR_PTR(-EINVAL);
+ repeat:
+       page = f2fs_grab_cache_page(NODE_MAPPING(sbi), nid, false);
+       if (!page)
+diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
+index be8d1b16b8d1..cffaf842f4e7 100644
+--- a/fs/f2fs/segment.c
++++ b/fs/f2fs/segment.c
+@@ -3600,6 +3600,7 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
+       unsigned int i, start, end;
+       unsigned int readed, start_blk = 0;
+       int err = 0;
++      block_t total_node_blocks = 0;
+ 
+       do {
+               readed = ra_meta_pages(sbi, start_blk, BIO_MAX_PAGES,
+@@ -3622,6 +3623,8 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
+                       if (err)
+                               return err;
+                       seg_info_from_raw_sit(se, &sit);
++                      if (IS_NODESEG(se->type))
++                              total_node_blocks += se->valid_blocks;
+ 
+                       /* build discard map only one time */
+                       if (f2fs_discard_en(sbi)) {
+@@ -3650,15 +3653,28 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
+               unsigned int old_valid_blocks;
+ 
+               start = le32_to_cpu(segno_in_journal(journal, i));
++              if (start >= MAIN_SEGS(sbi)) {
++                      f2fs_msg(sbi->sb, KERN_ERR,
++                                      "Wrong journal entry on segno %u",
++                                      start);
++                      set_sbi_flag(sbi, SBI_NEED_FSCK);
++                      err = -EINVAL;
++                      break;
++              }
++
+               se = &sit_i->sentries[start];
+               sit = sit_in_journal(journal, i);
+ 
+               old_valid_blocks = se->valid_blocks;
++              if (IS_NODESEG(se->type))
++                      total_node_blocks -= old_valid_blocks;
+ 
+               err = check_block_count(sbi, start, &sit);
+               if (err)
+                       break;
+               seg_info_from_raw_sit(se, &sit);
++              if (IS_NODESEG(se->type))
++                      total_node_blocks += se->valid_blocks;
+ 
+               if (f2fs_discard_en(sbi)) {
+                       if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) {
+@@ -3677,6 +3693,15 @@ static int build_sit_entries(struct f2fs_sb_info *sbi)
+                               se->valid_blocks - old_valid_blocks;
+       }
+       up_read(&curseg->journal_rwsem);
++
++      if (!err && total_node_blocks != valid_node_count(sbi)) {
++              f2fs_msg(sbi->sb, KERN_ERR,
++                      "SIT is corrupted node# %u vs %u",
++                      total_node_blocks, valid_node_count(sbi));
++              set_sbi_flag(sbi, SBI_NEED_FSCK);
++              err = -EINVAL;
++      }
++
+       return err;
+ }
+ 
+diff --git a/fs/inode.c b/fs/inode.c
+index 3b55391072f3..6c6fef8c7c27 100644
+--- a/fs/inode.c
++++ b/fs/inode.c
+@@ -2013,8 +2013,14 @@ void inode_init_owner(struct inode *inode, const struct 
inode *dir,
+       inode->i_uid = current_fsuid();
+       if (dir && dir->i_mode & S_ISGID) {
+               inode->i_gid = dir->i_gid;
++
++              /* Directories are special, and always inherit S_ISGID */
+               if (S_ISDIR(mode))
+                       mode |= S_ISGID;
++              else if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP) &&
++                       !in_group_p(inode->i_gid) &&
++                       !capable_wrt_inode_uidgid(dir, CAP_FSETID))
++                      mode &= ~S_ISGID;
+       } else
+               inode->i_gid = current_fsgid();
+       inode->i_mode = mode;
+diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
+index c486ad4b43f0..b0abfe02beab 100644
+--- a/fs/proc/task_mmu.c
++++ b/fs/proc/task_mmu.c
+@@ -831,7 +831,8 @@ static int show_smap(struct seq_file *m, void *v, int 
is_pid)
+               SEQ_PUT_DEC(" kB\nSwap:           ", mss->swap);
+               SEQ_PUT_DEC(" kB\nSwapPss:        ",
+                                               mss->swap_pss >> PSS_SHIFT);
+-              SEQ_PUT_DEC(" kB\nLocked:         ", mss->pss >> PSS_SHIFT);
++              SEQ_PUT_DEC(" kB\nLocked:         ",
++                                              mss->pss_locked >> PSS_SHIFT);
+               seq_puts(m, " kB\n");
+       }
+       if (!rollup_mode) {
+diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c 
b/fs/xfs/libxfs/xfs_ialloc_btree.c
+index 367e9a0726e6..ead8c4842c29 100644
+--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
++++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
+@@ -296,7 +296,7 @@ xfs_inobt_verify(
+       case cpu_to_be32(XFS_FIBT_MAGIC):
+               break;
+       default:
+-              return NULL;
++              return __this_address;
+       }
+ 
+       /* level verification */
+diff --git a/include/linux/libata.h b/include/linux/libata.h
+index 1795fecdea17..6fed495af95c 100644
+--- a/include/linux/libata.h
++++ b/include/linux/libata.h
+@@ -211,6 +211,7 @@ enum {
+       ATA_FLAG_SLAVE_POSS     = (1 << 0), /* host supports slave dev */
+                                           /* (doesn't imply presence) */
+       ATA_FLAG_SATA           = (1 << 1),
++      ATA_FLAG_NO_LPM         = (1 << 2), /* host not happy with LPM */
+       ATA_FLAG_NO_LOG_PAGE    = (1 << 5), /* do not issue log page read */
+       ATA_FLAG_NO_ATAPI       = (1 << 6), /* No ATAPI support */
+       ATA_FLAG_PIO_DMA        = (1 << 7), /* PIO cmds via DMA */
+diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
+index 1904e814f282..56212edd6f23 100644
+--- a/kernel/bpf/verifier.c
++++ b/kernel/bpf/verifier.c
+@@ -1610,6 +1610,30 @@ static int get_callee_stack_depth(struct 
bpf_verifier_env *env,
+ }
+ #endif
+ 
++static int check_ctx_reg(struct bpf_verifier_env *env,
++                       const struct bpf_reg_state *reg, int regno)
++{
++      /* Access to ctx or passing it to a helper is only allowed in
++       * its original, unmodified form.
++       */
++
++      if (reg->off) {
++              verbose(env, "dereference of modified ctx ptr R%d off=%d 
disallowed\n",
++                      regno, reg->off);
++              return -EACCES;
++      }
++
++      if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
++              char tn_buf[48];
++
++              tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
++              verbose(env, "variable ctx access var_off=%s disallowed\n", 
tn_buf);
++              return -EACCES;
++      }
++
++      return 0;
++}
++
+ /* truncate register to smaller size (in bytes)
+  * must be called with size < BPF_REG_SIZE
+  */
+@@ -1679,24 +1703,11 @@ static int check_mem_access(struct bpf_verifier_env 
*env, int insn_idx, u32 regn
+                       verbose(env, "R%d leaks addr into ctx\n", value_regno);
+                       return -EACCES;
+               }
+-              /* ctx accesses must be at a fixed offset, so that we can
+-               * determine what type of data were returned.
+-               */
+-              if (reg->off) {
+-                      verbose(env,
+-                              "dereference of modified ctx ptr R%d off=%d+%d, 
ctx+const is allowed, ctx+const+const is not\n",
+-                              regno, reg->off, off - reg->off);
+-                      return -EACCES;
+-              }
+-              if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
+-                      char tn_buf[48];
+ 
+-                      tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+-                      verbose(env,
+-                              "variable ctx access var_off=%s off=%d size=%d",
+-                              tn_buf, off, size);
+-                      return -EACCES;
+-              }
++              err = check_ctx_reg(env, reg, regno);
++              if (err < 0)
++                      return err;
++
+               err = check_ctx_access(env, insn_idx, off, size, t, &reg_type);
+               if (!err && t == BPF_READ && value_regno >= 0) {
+                       /* ctx access returns either a scalar, or a
+@@ -1977,6 +1988,9 @@ static int check_func_arg(struct bpf_verifier_env *env, 
u32 regno,
+               expected_type = PTR_TO_CTX;
+               if (type != expected_type)
+                       goto err_type;
++              err = check_ctx_reg(env, reg, regno);
++              if (err < 0)
++                      return err;
+       } else if (arg_type_is_mem_ptr(arg_type)) {
+               expected_type = PTR_TO_STACK;
+               /* One exception here. In case function allows for NULL to be
+diff --git a/kernel/power/user.c b/kernel/power/user.c
+index 75c959de4b29..abd225550271 100644
+--- a/kernel/power/user.c
++++ b/kernel/power/user.c
+@@ -186,6 +186,11 @@ static ssize_t snapshot_write(struct file *filp, const 
char __user *buf,
+               res = PAGE_SIZE - pg_offp;
+       }
+ 
++      if (!data_of(data->handle)) {
++              res = -EINVAL;
++              goto unlock;
++      }
++
+       res = simple_write_to_buffer(data_of(data->handle), res, &pg_offp,
+                       buf, count);
+       if (res > 0)
+diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
+index bcd93031d042..4e67d0020337 100644
+--- a/kernel/trace/trace.c
++++ b/kernel/trace/trace.c
+@@ -3363,8 +3363,8 @@ static void print_func_help_header(struct trace_buffer 
*buf, struct seq_file *m,
+ 
+       print_event_info(buf, m);
+ 
+-      seq_printf(m, "#           TASK-PID   CPU#   %s  TIMESTAMP  
FUNCTION\n", tgid ? "TGID     " : "");
+-      seq_printf(m, "#              | |       |    %s     |         |\n",     
 tgid ? "  |      " : "");
++      seq_printf(m, "#           TASK-PID   %s  CPU#   TIMESTAMP  
FUNCTION\n", tgid ? "TGID     " : "");
++      seq_printf(m, "#              | |     %s    |       |         |\n",     
 tgid ? "  |      " : "");
+ }
+ 
+ static void print_func_help_header_irq(struct trace_buffer *buf, struct 
seq_file *m,
+@@ -3384,9 +3384,9 @@ static void print_func_help_header_irq(struct 
trace_buffer *buf, struct seq_file
+                  tgid ? tgid_space : space);
+       seq_printf(m, "#                          %s||| /     delay\n",
+                  tgid ? tgid_space : space);
+-      seq_printf(m, "#           TASK-PID   CPU#%s||||    TIMESTAMP  
FUNCTION\n",
++      seq_printf(m, "#           TASK-PID %sCPU#  ||||    TIMESTAMP  
FUNCTION\n",
+                  tgid ? "   TGID   " : space);
+-      seq_printf(m, "#              | |       | %s||||       |         |\n",
++      seq_printf(m, "#              | |   %s  |   ||||       |         |\n",
+                  tgid ? "     |    " : space);
+ }
+ 
+diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
+index 02aed76e0978..eebc7c92f6d0 100644
+--- a/kernel/trace/trace_kprobe.c
++++ b/kernel/trace/trace_kprobe.c
+@@ -1451,8 +1451,10 @@ create_local_trace_kprobe(char *func, void *addr, 
unsigned long offs,
+       }
+ 
+       ret = __register_trace_kprobe(tk);
+-      if (ret < 0)
++      if (ret < 0) {
++              kfree(tk->tp.call.print_fmt);
+               goto error;
++      }
+ 
+       return &tk->tp.call;
+ error:
+@@ -1472,6 +1474,8 @@ void destroy_local_trace_kprobe(struct trace_event_call 
*event_call)
+       }
+ 
+       __unregister_trace_kprobe(tk);
++
++      kfree(tk->tp.call.print_fmt);
+       free_trace_kprobe(tk);
+ }
+ #endif /* CONFIG_PERF_EVENTS */
+diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
+index 90db994ac900..1c8e30fda46a 100644
+--- a/kernel/trace/trace_output.c
++++ b/kernel/trace/trace_output.c
+@@ -594,8 +594,7 @@ int trace_print_context(struct trace_iterator *iter)
+ 
+       trace_find_cmdline(entry->pid, comm);
+ 
+-      trace_seq_printf(s, "%16s-%-5d [%03d] ",
+-                             comm, entry->pid, iter->cpu);
++      trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
+ 
+       if (tr->trace_flags & TRACE_ITER_RECORD_TGID) {
+               unsigned int tgid = trace_find_tgid(entry->pid);
+@@ -606,6 +605,8 @@ int trace_print_context(struct trace_iterator *iter)
+                       trace_seq_printf(s, "(%5d) ", tgid);
+       }
+ 
++      trace_seq_printf(s, "[%03d] ", iter->cpu);
++
+       if (tr->trace_flags & TRACE_ITER_IRQ_INFO)
+               trace_print_lat_fmt(s, entry);
+ 
+diff --git a/mm/gup.c b/mm/gup.c
+index 3d8472d48a0b..e608e6650d60 100644
+--- a/mm/gup.c
++++ b/mm/gup.c
+@@ -1222,8 +1222,6 @@ int __mm_populate(unsigned long start, unsigned long 
len, int ignore_errors)
+       int locked = 0;
+       long ret = 0;
+ 
+-      VM_BUG_ON(start & ~PAGE_MASK);
+-      VM_BUG_ON(len != PAGE_ALIGN(len));
+       end = start + len;
+ 
+       for (nstart = start; nstart < end; nstart = nend) {
+diff --git a/mm/mmap.c b/mm/mmap.c
+index fc41c0543d7f..540cfab8c2c4 100644
+--- a/mm/mmap.c
++++ b/mm/mmap.c
+@@ -186,8 +186,8 @@ static struct vm_area_struct *remove_vma(struct 
vm_area_struct *vma)
+       return next;
+ }
+ 
+-static int do_brk(unsigned long addr, unsigned long len, struct list_head 
*uf);
+-
++static int do_brk_flags(unsigned long addr, unsigned long request, unsigned 
long flags,
++              struct list_head *uf);
+ SYSCALL_DEFINE1(brk, unsigned long, brk)
+ {
+       unsigned long retval;
+@@ -245,7 +245,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
+               goto out;
+ 
+       /* Ok, looks good - let it rip. */
+-      if (do_brk(oldbrk, newbrk-oldbrk, &uf) < 0)
++      if (do_brk_flags(oldbrk, newbrk-oldbrk, 0, &uf) < 0)
+               goto out;
+ 
+ set_brk:
+@@ -2929,21 +2929,14 @@ static inline void verify_mm_writelocked(struct 
mm_struct *mm)
+  *  anonymous maps.  eventually we may be able to do some
+  *  brk-specific accounting here.
+  */
+-static int do_brk_flags(unsigned long addr, unsigned long request, unsigned 
long flags, struct list_head *uf)
++static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long 
flags, struct list_head *uf)
+ {
+       struct mm_struct *mm = current->mm;
+       struct vm_area_struct *vma, *prev;
+-      unsigned long len;
+       struct rb_node **rb_link, *rb_parent;
+       pgoff_t pgoff = addr >> PAGE_SHIFT;
+       int error;
+ 
+-      len = PAGE_ALIGN(request);
+-      if (len < request)
+-              return -ENOMEM;
+-      if (!len)
+-              return 0;
+-
+       /* Until we need other flags, refuse anything except VM_EXEC. */
+       if ((flags & (~VM_EXEC)) != 0)
+               return -EINVAL;
+@@ -3015,18 +3008,20 @@ static int do_brk_flags(unsigned long addr, unsigned 
long request, unsigned long
+       return 0;
+ }
+ 
+-static int do_brk(unsigned long addr, unsigned long len, struct list_head *uf)
+-{
+-      return do_brk_flags(addr, len, 0, uf);
+-}
+-
+-int vm_brk_flags(unsigned long addr, unsigned long len, unsigned long flags)
++int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long 
flags)
+ {
+       struct mm_struct *mm = current->mm;
++      unsigned long len;
+       int ret;
+       bool populate;
+       LIST_HEAD(uf);
+ 
++      len = PAGE_ALIGN(request);
++      if (len < request)
++              return -ENOMEM;
++      if (!len)
++              return 0;
++
+       if (down_write_killable(&mm->mmap_sem))
+               return -EINTR;
+ 
+diff --git a/mm/page_alloc.c b/mm/page_alloc.c
+index d2d0eb9536a3..322cb12a142f 100644
+--- a/mm/page_alloc.c
++++ b/mm/page_alloc.c
+@@ -6841,6 +6841,7 @@ void __init free_area_init_nodes(unsigned long 
*max_zone_pfn)
+       /* Initialise every node */
+       mminit_verify_pageflags_layout();
+       setup_nr_node_ids();
++      zero_resv_unavail();
+       for_each_online_node(nid) {
+               pg_data_t *pgdat = NODE_DATA(nid);
+               free_area_init_node(nid, NULL,
+@@ -6851,7 +6852,6 @@ void __init free_area_init_nodes(unsigned long 
*max_zone_pfn)
+                       node_set_state(nid, N_MEMORY);
+               check_for_memory(pgdat, nid);
+       }
+-      zero_resv_unavail();
+ }
+ 
+ static int __init cmdline_parse_core(char *p, unsigned long *core,
+@@ -7027,9 +7027,9 @@ void __init set_dma_reserve(unsigned long 
new_dma_reserve)
+ 
+ void __init free_area_init(unsigned long *zones_size)
+ {
++      zero_resv_unavail();
+       free_area_init_node(0, zones_size,
+                       __pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
+-      zero_resv_unavail();
+ }
+ 
+ static int page_alloc_cpu_dead(unsigned int cpu)
+diff --git a/mm/rmap.c b/mm/rmap.c
+index 8d5337fed37b..09a799c9aebd 100644
+--- a/mm/rmap.c
++++ b/mm/rmap.c
+@@ -64,6 +64,7 @@
+ #include <linux/backing-dev.h>
+ #include <linux/page_idle.h>
+ #include <linux/memremap.h>
++#include <linux/userfaultfd_k.h>
+ 
+ #include <asm/tlbflush.h>
+ 
+@@ -1481,11 +1482,16 @@ static bool try_to_unmap_one(struct page *page, struct 
vm_area_struct *vma,
+                               set_pte_at(mm, address, pvmw.pte, pteval);
+                       }
+ 
+-              } else if (pte_unused(pteval)) {
++              } else if (pte_unused(pteval) && !userfaultfd_armed(vma)) {
+                       /*
+                        * The guest indicated that the page content is of no
+                        * interest anymore. Simply discard the pte, vmscan
+                        * will take care of the rest.
++                       * A future reference will then fault in a new zero
++                       * page. When userfaultfd is active, we must not drop
++                       * this page though, as its main user (postcopy
++                       * migration) will not expect userfaults on already
++                       * copied pages.
+                        */
+                       dec_mm_counter(mm, mm_counter(page));
+                       /* We have to invalidate as we cleared the pte */
+diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
+index 6ba639f6c51d..499123afcab5 100644
+--- a/net/bridge/netfilter/ebtables.c
++++ b/net/bridge/netfilter/ebtables.c
+@@ -694,6 +694,8 @@ ebt_check_entry(struct ebt_entry *e, struct net *net,
+       }
+       i = 0;
+ 
++      memset(&mtpar, 0, sizeof(mtpar));
++      memset(&tgpar, 0, sizeof(tgpar));
+       mtpar.net       = tgpar.net       = net;
+       mtpar.table     = tgpar.table     = name;
+       mtpar.entryinfo = tgpar.entryinfo = e;
+diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
+index e85f35b89c49..f6130704f052 100644
+--- a/net/ipv4/netfilter/ip_tables.c
++++ b/net/ipv4/netfilter/ip_tables.c
+@@ -531,6 +531,7 @@ find_check_entry(struct ipt_entry *e, struct net *net, 
const char *name,
+               return -ENOMEM;
+ 
+       j = 0;
++      memset(&mtpar, 0, sizeof(mtpar));
+       mtpar.net       = net;
+       mtpar.table     = name;
+       mtpar.entryinfo = &e->ip;
+diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
+index 97f79dc943d7..685c2168f524 100644
+--- a/net/ipv6/netfilter/ip6_tables.c
++++ b/net/ipv6/netfilter/ip6_tables.c
+@@ -551,6 +551,7 @@ find_check_entry(struct ip6t_entry *e, struct net *net, 
const char *name,
+               return -ENOMEM;
+ 
+       j = 0;
++      memset(&mtpar, 0, sizeof(mtpar));
+       mtpar.net       = net;
+       mtpar.table     = name;
+       mtpar.entryinfo = &e->ipv6;
+diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
+index 74a04638ef03..93b3e4b86870 100644
+--- a/net/netfilter/nfnetlink_queue.c
++++ b/net/netfilter/nfnetlink_queue.c
+@@ -1223,6 +1223,9 @@ static int nfqnl_recv_unsupp(struct net *net, struct 
sock *ctnl,
+ static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = {
+       [NFQA_CFG_CMD]          = { .len = sizeof(struct nfqnl_msg_config_cmd) 
},
+       [NFQA_CFG_PARAMS]       = { .len = sizeof(struct 
nfqnl_msg_config_params) },
++      [NFQA_CFG_QUEUE_MAXLEN] = { .type = NLA_U32 },
++      [NFQA_CFG_MASK]         = { .type = NLA_U32 },
++      [NFQA_CFG_FLAGS]        = { .type = NLA_U32 },
+ };
+ 
+ static const struct nf_queue_handler nfqh = {
+diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
+index ed39a77f9253..76d82eebeef2 100644
+--- a/sound/pci/hda/patch_hdmi.c
++++ b/sound/pci/hda/patch_hdmi.c
+@@ -33,6 +33,7 @@
+ #include <linux/delay.h>
+ #include <linux/slab.h>
+ #include <linux/module.h>
++#include <linux/pm_runtime.h>
+ #include <sound/core.h>
+ #include <sound/jack.h>
+ #include <sound/asoundef.h>
+@@ -764,8 +765,10 @@ static void check_presence_and_report(struct hda_codec 
*codec, hda_nid_t nid,
+ 
+       if (pin_idx < 0)
+               return;
++      mutex_lock(&spec->pcm_lock);
+       if (hdmi_present_sense(get_pin(spec, pin_idx), 1))
+               snd_hda_jack_report_sync(codec);
++      mutex_unlock(&spec->pcm_lock);
+ }
+ 
+ static void jack_callback(struct hda_codec *codec,
+@@ -1628,21 +1631,23 @@ static void sync_eld_via_acomp(struct hda_codec *codec,
+ static bool hdmi_present_sense(struct hdmi_spec_per_pin *per_pin, int repoll)
+ {
+       struct hda_codec *codec = per_pin->codec;
+-      struct hdmi_spec *spec = codec->spec;
+       int ret;
+ 
+       /* no temporary power up/down needed for component notifier */
+-      if (!codec_has_acomp(codec))
+-              snd_hda_power_up_pm(codec);
++      if (!codec_has_acomp(codec)) {
++              ret = snd_hda_power_up_pm(codec);
++              if (ret < 0 && pm_runtime_suspended(hda_codec_dev(codec))) {
++                      snd_hda_power_down_pm(codec);
++                      return false;
++              }
++      }
+ 
+-      mutex_lock(&spec->pcm_lock);
+       if (codec_has_acomp(codec)) {
+               sync_eld_via_acomp(codec, per_pin);
+               ret = false; /* don't call snd_hda_jack_report_sync() */
+       } else {
+               ret = hdmi_present_sense_via_verbs(per_pin, repoll);
+       }
+-      mutex_unlock(&spec->pcm_lock);
+ 
+       if (!codec_has_acomp(codec))
+               snd_hda_power_down_pm(codec);
+@@ -1654,12 +1659,16 @@ static void hdmi_repoll_eld(struct work_struct *work)
+ {
+       struct hdmi_spec_per_pin *per_pin =
+       container_of(to_delayed_work(work), struct hdmi_spec_per_pin, work);
++      struct hda_codec *codec = per_pin->codec;
++      struct hdmi_spec *spec = codec->spec;
+ 
+       if (per_pin->repoll_count++ > 6)
+               per_pin->repoll_count = 0;
+ 
++      mutex_lock(&spec->pcm_lock);
+       if (hdmi_present_sense(per_pin, per_pin->repoll_count))
+               snd_hda_jack_report_sync(per_pin->codec);
++      mutex_unlock(&spec->pcm_lock);
+ }
+ 
+ static void intel_haswell_fixup_connect_list(struct hda_codec *codec,
+diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
+index cb9a977bf188..066efe783fe8 100644
+--- a/sound/pci/hda/patch_realtek.c
++++ b/sound/pci/hda/patch_realtek.c
+@@ -6586,7 +6586,6 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+       SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", 
ALC294_FIXUP_LENOVO_MIC_LOCATION),
+       SND_PCI_QUIRK(0x17aa, 0x312a, "ThinkCentre Station", 
ALC294_FIXUP_LENOVO_MIC_LOCATION),
+       SND_PCI_QUIRK(0x17aa, 0x312f, "ThinkCentre Station", 
ALC294_FIXUP_LENOVO_MIC_LOCATION),
+-      SND_PCI_QUIRK(0x17aa, 0x3136, "ThinkCentre Station", 
ALC294_FIXUP_LENOVO_MIC_LOCATION),
+       SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", 
ALC294_FIXUP_LENOVO_MIC_LOCATION),
+       SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", 
ALC269_FIXUP_DMIC_THINKPAD_ACPI),
+       SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
+@@ -6770,6 +6769,11 @@ static const struct snd_hda_pin_quirk 
alc269_pin_fixup_tbl[] = {
+               {0x1a, 0x02a11040},
+               {0x1b, 0x01014020},
+               {0x21, 0x0221101f}),
++      SND_HDA_PIN_QUIRK(0x10ec0235, 0x17aa, "Lenovo", 
ALC294_FIXUP_LENOVO_MIC_LOCATION,
++              {0x14, 0x90170110},
++              {0x19, 0x02a11020},
++              {0x1a, 0x02a11030},
++              {0x21, 0x0221101f}),
+       SND_HDA_PIN_QUIRK(0x10ec0236, 0x1028, "Dell", 
ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+               {0x12, 0x90a60140},
+               {0x14, 0x90170110},
+diff --git a/tools/build/Build.include b/tools/build/Build.include
+index a4bbb984941d..d9048f145f97 100644
+--- a/tools/build/Build.include
++++ b/tools/build/Build.include
+@@ -63,8 +63,8 @@ dep-cmd = $(if $(wildcard $(fixdep)),
+            $(fixdep) $(depfile) $@ '$(make-cmd)' > $(dot-target).tmp;         
  \
+            rm -f $(depfile);                                                  
  \
+            mv -f $(dot-target).tmp $(dot-target).cmd,                         
  \
+-           printf '\# cannot find fixdep (%s)\n' $(fixdep) > 
$(dot-target).cmd; \
+-           printf '\# using basic dep data\n\n' >> $(dot-target).cmd;         
  \
++           printf '$(pound) cannot find fixdep (%s)\n' $(fixdep) > 
$(dot-target).cmd; \
++           printf '$(pound) using basic dep data\n\n' >> $(dot-target).cmd;   
        \
+            cat $(depfile) >> $(dot-target).cmd;                               
  \
+            printf '\n%s\n' 'cmd_$@ := $(make-cmd)' >> $(dot-target).cmd)
+ 
+diff --git a/tools/testing/selftests/bpf/test_verifier.c 
b/tools/testing/selftests/bpf/test_verifier.c
+index fd7de7eb329e..30025d7e75e4 100644
+--- a/tools/testing/selftests/bpf/test_verifier.c
++++ b/tools/testing/selftests/bpf/test_verifier.c
+@@ -8190,7 +8190,7 @@ static struct bpf_test tests[] = {
+                                   offsetof(struct __sk_buff, mark)),
+                       BPF_EXIT_INSN(),
+               },
+-              .errstr = "dereference of modified ctx ptr R1 off=68+8, 
ctx+const is allowed, ctx+const+const is not",
++              .errstr = "dereference of modified ctx ptr",
+               .result = REJECT,
+               .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+       },
+@@ -11423,6 +11423,62 @@ static struct bpf_test tests[] = {
+               .errstr = "BPF_XADD stores into R2 packet",
+               .prog_type = BPF_PROG_TYPE_XDP,
+       },
++      {
++              "pass unmodified ctx pointer to helper",
++              .insns = {
++                      BPF_MOV64_IMM(BPF_REG_2, 0),
++                      BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
++                                   BPF_FUNC_csum_update),
++                      BPF_MOV64_IMM(BPF_REG_0, 0),
++                      BPF_EXIT_INSN(),
++              },
++              .prog_type = BPF_PROG_TYPE_SCHED_CLS,
++              .result = ACCEPT,
++      },
++      {
++              "pass modified ctx pointer to helper, 1",
++              .insns = {
++                      BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -612),
++                      BPF_MOV64_IMM(BPF_REG_2, 0),
++                      BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
++                                   BPF_FUNC_csum_update),
++                      BPF_MOV64_IMM(BPF_REG_0, 0),
++                      BPF_EXIT_INSN(),
++              },
++              .prog_type = BPF_PROG_TYPE_SCHED_CLS,
++              .result = REJECT,
++              .errstr = "dereference of modified ctx ptr",
++      },
++      {
++              "pass modified ctx pointer to helper, 2",
++              .insns = {
++                      BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -612),
++                      BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
++                                   BPF_FUNC_get_socket_cookie),
++                      BPF_MOV64_IMM(BPF_REG_0, 0),
++                      BPF_EXIT_INSN(),
++              },
++              .result_unpriv = REJECT,
++              .result = REJECT,
++              .errstr_unpriv = "dereference of modified ctx ptr",
++              .errstr = "dereference of modified ctx ptr",
++      },
++      {
++              "pass modified ctx pointer to helper, 3",
++              .insns = {
++                      BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1, 0),
++                      BPF_ALU64_IMM(BPF_AND, BPF_REG_3, 4),
++                      BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_3),
++                      BPF_MOV64_IMM(BPF_REG_2, 0),
++                      BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
++                                   BPF_FUNC_csum_update),
++                      BPF_MOV64_IMM(BPF_REG_0, 0),
++                      BPF_EXIT_INSN(),
++              },
++              .prog_type = BPF_PROG_TYPE_SCHED_CLS,
++              .result = REJECT,
++              .errstr = "variable ctx access var_off=(0x0; 0x4)",
++      },
+ };
+ 
+ static int probe_filter_length(const struct bpf_insn *fp)

Reply via email to