lkml.org 
[lkml]   [2018]   [Jan]   [3]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
SubjectRe: Linux 4.14.11
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 05496622b4ef..520fdec15bbb 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2685,6 +2685,8 @@
steal time is computed, but won't influence scheduler
behaviour

+ nopti [X86-64] Disable kernel page table isolation
+
nolapic [X86-32,APIC] Do not enable or use the local APIC.

nolapic_timer [X86-32,APIC] Do not use the local APIC timer.
@@ -3253,6 +3255,12 @@
pt. [PARIDE]
See Documentation/blockdev/paride.txt.

+ pti= [X86_64]
+ Control user/kernel address space isolation:
+ on - enable
+ off - disable
+ auto - default setting
+
pty.legacy_count=
[KNL] Number of legacy pty's. Overwrites compiled-in
default number.
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index 51101708a03a..ad41b3813f0a 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -12,6 +12,7 @@ ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
... unused hole ...
ffffec0000000000 - fffffbffffffffff (=44 bits) kasan shadow memory (16TB)
... unused hole ...
+fffffe0000000000 - fffffe7fffffffff (=39 bits) LDT remap for PTI
fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping
ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
... unused hole ...
@@ -29,8 +30,8 @@ Virtual memory map with 5 level page tables:
hole caused by [56:63] sign extension
ff00000000000000 - ff0fffffffffffff (=52 bits) guard hole, reserved for hypervisor
ff10000000000000 - ff8fffffffffffff (=55 bits) direct mapping of all phys. memory
-ff90000000000000 - ff91ffffffffffff (=49 bits) hole
-ff92000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space
+ff90000000000000 - ff9fffffffffffff (=52 bits) LDT remap for PTI
+ffa0000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space (12800 TB)
ffd2000000000000 - ffd3ffffffffffff (=49 bits) hole
ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB)
... unused hole ...
diff --git a/Makefile b/Makefile
index 9edfb78836a9..655887067dc7 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 4
PATCHLEVEL = 14
-SUBLEVEL = 10
+SUBLEVEL = 11
EXTRAVERSION =
NAME = Petit Gorille

@@ -802,6 +802,9 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-sign)
# disable invalid "can't wrap" optimizations for signed / pointers
KBUILD_CFLAGS += $(call cc-option,-fno-strict-overflow)

+# Make sure -fstack-check isn't enabled (like gentoo apparently did)
+KBUILD_CFLAGS += $(call cc-option,-fno-stack-check,)
+
# conserve stack if available
KBUILD_CFLAGS += $(call cc-option,-fconserve-stack)

diff --git a/arch/sparc/lib/hweight.S b/arch/sparc/lib/hweight.S
index e5547b22cd18..0ddbbb031822 100644
--- a/arch/sparc/lib/hweight.S
+++ b/arch/sparc/lib/hweight.S
@@ -44,8 +44,8 @@ EXPORT_SYMBOL(__arch_hweight32)
.previous

ENTRY(__arch_hweight64)
- sethi %hi(__sw_hweight16), %g1
- jmpl %g1 + %lo(__sw_hweight16), %g0
+ sethi %hi(__sw_hweight64), %g1
+ jmpl %g1 + %lo(__sw_hweight64), %g0
nop
ENDPROC(__arch_hweight64)
EXPORT_SYMBOL(__arch_hweight64)
diff --git a/arch/x86/boot/compressed/pagetable.c b/arch/x86/boot/compressed/pagetable.c
index 972319ff5b01..e691ff734cb5 100644
--- a/arch/x86/boot/compressed/pagetable.c
+++ b/arch/x86/boot/compressed/pagetable.c
@@ -23,6 +23,9 @@
*/
#undef CONFIG_AMD_MEM_ENCRYPT

+/* No PAGE_TABLE_ISOLATION support needed either: */
+#undef CONFIG_PAGE_TABLE_ISOLATION
+
#include "misc.h"

/* These actually do the work of building the kernel identity maps. */
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 3fd8bc560fae..45a63e00a6af 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -1,6 +1,11 @@
/* SPDX-License-Identifier: GPL-2.0 */
#include <linux/jump_label.h>
#include <asm/unwind_hints.h>
+#include <asm/cpufeatures.h>
+#include <asm/page_types.h>
+#include <asm/percpu.h>
+#include <asm/asm-offsets.h>
+#include <asm/processor-flags.h>

/*

@@ -187,6 +192,146 @@ For 32-bit we have the following conventions - kernel is built with
#endif
.endm

+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+
+/*
+ * PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two
+ * halves:
+ */
+#define PTI_SWITCH_PGTABLES_MASK (1<<PAGE_SHIFT)
+#define PTI_SWITCH_MASK (PTI_SWITCH_PGTABLES_MASK|(1<<X86_CR3_PTI_SWITCH_BIT))
+
+.macro SET_NOFLUSH_BIT reg:req
+ bts $X86_CR3_PCID_NOFLUSH_BIT, \reg
+.endm
+
+.macro ADJUST_KERNEL_CR3 reg:req
+ ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID
+ /* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */
+ andq $(~PTI_SWITCH_MASK), \reg
+.endm
+
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+ mov %cr3, \scratch_reg
+ ADJUST_KERNEL_CR3 \scratch_reg
+ mov \scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+#define THIS_CPU_user_pcid_flush_mask \
+ PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask
+
+.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+ mov %cr3, \scratch_reg
+
+ ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
+
+ /*
+ * Test if the ASID needs a flush.
+ */
+ movq \scratch_reg, \scratch_reg2
+ andq $(0x7FF), \scratch_reg /* mask ASID */
+ bt \scratch_reg, THIS_CPU_user_pcid_flush_mask
+ jnc .Lnoflush_\@
+
+ /* Flush needed, clear the bit */
+ btr \scratch_reg, THIS_CPU_user_pcid_flush_mask
+ movq \scratch_reg2, \scratch_reg
+ jmp .Lwrcr3_\@
+
+.Lnoflush_\@:
+ movq \scratch_reg2, \scratch_reg
+ SET_NOFLUSH_BIT \scratch_reg
+
+.Lwrcr3_\@:
+ /* Flip the PGD and ASID to the user version */
+ orq $(PTI_SWITCH_MASK), \scratch_reg
+ mov \scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
+ pushq %rax
+ SWITCH_TO_USER_CR3_NOSTACK scratch_reg=\scratch_reg scratch_reg2=%rax
+ popq %rax
+.endm
+
+.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
+ ALTERNATIVE "jmp .Ldone_\@", "", X86_FEATURE_PTI
+ movq %cr3, \scratch_reg
+ movq \scratch_reg, \save_reg
+ /*
+ * Is the "switch mask" all zero? That means that both of
+ * these are zero:
+ *
+ * 1. The user/kernel PCID bit, and
+ * 2. The user/kernel "bit" that points CR3 to the
+ * bottom half of the 8k PGD
+ *
+ * That indicates a kernel CR3 value, not a user CR3.
+ */
+ testq $(PTI_SWITCH_MASK), \scratch_reg
+ jz .Ldone_\@
+
+ ADJUST_KERNEL_CR3 \scratch_reg
+ movq \scratch_reg, %cr3
+
+.Ldone_\@:
+.endm
+
+.macro RESTORE_CR3 scratch_reg:req save_reg:req
+ ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+
+ ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
+
+ /*
+ * KERNEL pages can always resume with NOFLUSH as we do
+ * explicit flushes.
+ */
+ bt $X86_CR3_PTI_SWITCH_BIT, \save_reg
+ jnc .Lnoflush_\@
+
+ /*
+ * Check if there's a pending flush for the user ASID we're
+ * about to set.
+ */
+ movq \save_reg, \scratch_reg
+ andq $(0x7FF), \scratch_reg
+ bt \scratch_reg, THIS_CPU_user_pcid_flush_mask
+ jnc .Lnoflush_\@
+
+ btr \scratch_reg, THIS_CPU_user_pcid_flush_mask
+ jmp .Lwrcr3_\@
+
+.Lnoflush_\@:
+ SET_NOFLUSH_BIT \save_reg
+
+.Lwrcr3_\@:
+ /*
+ * The CR3 write could be avoided when not changing its value,
+ * but would require a CR3 read *and* a scratch register.
+ */
+ movq \save_reg, %cr3
+.Lend_\@:
+.endm
+
+#else /* CONFIG_PAGE_TABLE_ISOLATION=n: */
+
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+.endm
+.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
+.endm
+.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
+.endm
+.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
+.endm
+.macro RESTORE_CR3 scratch_reg:req save_reg:req
+.endm
+
+#endif
+
#endif /* CONFIG_X86_64 */

/*
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 22c891c3b78d..dd696b966e58 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -23,7 +23,6 @@
#include <asm/segment.h>
#include <asm/cache.h>
#include <asm/errno.h>
-#include "calling.h"
#include <asm/asm-offsets.h>
#include <asm/msr.h>
#include <asm/unistd.h>
@@ -40,6 +39,8 @@
#include <asm/frame.h>
#include <linux/err.h>

+#include "calling.h"
+
.code64
.section .entry.text, "ax"

@@ -164,6 +165,9 @@ ENTRY(entry_SYSCALL_64_trampoline)
/* Stash the user RSP. */
movq %rsp, RSP_SCRATCH

+ /* Note: using %rsp as a scratch reg. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
/* Load the top of the task stack into RSP */
movq CPU_ENTRY_AREA_tss + TSS_sp1 + CPU_ENTRY_AREA, %rsp

@@ -203,6 +207,10 @@ ENTRY(entry_SYSCALL_64)
*/

swapgs
+ /*
+ * This path is not taken when PAGE_TABLE_ISOLATION is disabled so it
+ * is not required to switch CR3.
+ */
movq %rsp, PER_CPU_VAR(rsp_scratch)
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp

@@ -399,6 +407,7 @@ syscall_return_via_sysret:
* We are on the trampoline stack. All regs except RDI are live.
* We can do future final exit work right here.
*/
+ SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi

popq %rdi
popq %rsp
@@ -736,6 +745,8 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode)
* We can do future final exit work right here.
*/

+ SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+
/* Restore RDI. */
popq %rdi
SWAPGS
@@ -818,7 +829,9 @@ native_irq_return_ldt:
*/

pushq %rdi /* Stash user RDI */
- SWAPGS
+ SWAPGS /* to kernel GS */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi /* to kernel CR3 */
+
movq PER_CPU_VAR(espfix_waddr), %rdi
movq %rax, (0*8)(%rdi) /* user RAX */
movq (1*8)(%rsp), %rax /* user RIP */
@@ -834,7 +847,6 @@ native_irq_return_ldt:
/* Now RAX == RSP. */

andl $0xffff0000, %eax /* RAX = (RSP & 0xffff0000) */
- popq %rdi /* Restore user RDI */

/*
* espfix_stack[31:16] == 0. The page tables are set up such that
@@ -845,7 +857,11 @@ native_irq_return_ldt:
* still points to an RO alias of the ESPFIX stack.
*/
orq PER_CPU_VAR(espfix_stack), %rax
- SWAPGS
+
+ SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+ SWAPGS /* to user GS */
+ popq %rdi /* Restore user RDI */
+
movq %rax, %rsp
UNWIND_HINT_IRET_REGS offset=8

@@ -945,6 +961,8 @@ ENTRY(switch_to_thread_stack)
UNWIND_HINT_FUNC

pushq %rdi
+ /* Need to switch before accessing the thread stack. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
movq %rsp, %rdi
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI
@@ -1244,7 +1262,11 @@ ENTRY(paranoid_entry)
js 1f /* negative -> in kernel */
SWAPGS
xorl %ebx, %ebx
-1: ret
+
+1:
+ SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14
+
+ ret
END(paranoid_entry)

/*
@@ -1266,6 +1288,7 @@ ENTRY(paranoid_exit)
testl %ebx, %ebx /* swapgs needed? */
jnz .Lparanoid_exit_no_swapgs
TRACE_IRQS_IRETQ
+ RESTORE_CR3 scratch_reg=%rbx save_reg=%r14
SWAPGS_UNSAFE_STACK
jmp .Lparanoid_exit_restore
.Lparanoid_exit_no_swapgs:
@@ -1293,6 +1316,8 @@ ENTRY(error_entry)
* from user mode due to an IRET fault.
*/
SWAPGS
+ /* We have user CR3. Change to kernel CR3. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax

.Lerror_entry_from_usermode_after_swapgs:
/* Put us onto the real thread stack. */
@@ -1339,6 +1364,7 @@ ENTRY(error_entry)
* .Lgs_change's error handler with kernel gsbase.
*/
SWAPGS
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
jmp .Lerror_entry_done

.Lbstep_iret:
@@ -1348,10 +1374,11 @@ ENTRY(error_entry)

.Lerror_bad_iret:
/*
- * We came from an IRET to user mode, so we have user gsbase.
- * Switch to kernel gsbase:
+ * We came from an IRET to user mode, so we have user
+ * gsbase and CR3. Switch to kernel gsbase and CR3:
*/
SWAPGS
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax

/*
* Pretend that the exception came from user mode: set up pt_regs
@@ -1383,6 +1410,10 @@ END(error_exit)
/*
* Runs on exception stack. Xen PV does not go through this path at all,
* so we can use real assembly here.
+ *
+ * Registers:
+ * %r14: Used to save/restore the CR3 of the interrupted context
+ * when PAGE_TABLE_ISOLATION is in use. Do not clobber.
*/
ENTRY(nmi)
UNWIND_HINT_IRET_REGS
@@ -1446,6 +1477,7 @@ ENTRY(nmi)

swapgs
cld
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
movq %rsp, %rdx
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
UNWIND_HINT_IRET_REGS base=%rdx offset=8
@@ -1698,6 +1730,8 @@ end_repeat_nmi:
movq $-1, %rsi
call do_nmi

+ RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
+
testl %ebx, %ebx /* swapgs needed? */
jnz nmi_restore
nmi_swapgs:
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 95ad40eb7eff..40f17009ec20 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -49,6 +49,10 @@
ENTRY(entry_SYSENTER_compat)
/* Interrupts are off on entry. */
SWAPGS
+
+ /* We are about to clobber %rsp anyway, clobbering here is OK */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp

/*
@@ -215,6 +219,12 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe)
pushq $0 /* pt_regs->r14 = 0 */
pushq $0 /* pt_regs->r15 = 0 */

+ /*
+ * We just saved %rdi so it is safe to clobber. It is not
+ * preserved during the C calls inside TRACE_IRQS_OFF anyway.
+ */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+
/*
* User mode is traced as though IRQs are on, and SYSENTER
* turned them off.
@@ -256,10 +266,22 @@ sysret32_from_system_call:
* when the system call started, which is already known to user
* code. We zero R8-R10 to avoid info leaks.
*/
+ movq RSP-ORIG_RAX(%rsp), %rsp
+
+ /*
+ * The original userspace %rsp (RSP-ORIG_RAX(%rsp)) is stored
+ * on the process stack which is not mapped to userspace and
+ * not readable after we SWITCH_TO_USER_CR3. Delay the CR3
+ * switch until after after the last reference to the process
+ * stack.
+ *
+ * %r8/%r9 are zeroed before the sysret, thus safe to clobber.
+ */
+ SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9
+
xorq %r8, %r8
xorq %r9, %r9
xorq %r10, %r10
- movq RSP-ORIG_RAX(%rsp), %rsp
swapgs
sysretl
END(entry_SYSCALL_compat)
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 1faf40f2dda9..577fa8adb785 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -344,14 +344,14 @@ int in_gate_area_no_mm(unsigned long addr)
* vsyscalls but leave the page not present. If so, we skip calling
* this.
*/
-static void __init set_vsyscall_pgtable_user_bits(void)
+void __init set_vsyscall_pgtable_user_bits(pgd_t *root)
{
pgd_t *pgd;
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;

- pgd = pgd_offset_k(VSYSCALL_ADDR);
+ pgd = pgd_offset_pgd(root, VSYSCALL_ADDR);
set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
p4d = p4d_offset(pgd, VSYSCALL_ADDR);
#if CONFIG_PGTABLE_LEVELS >= 5
@@ -373,7 +373,7 @@ void __init map_vsyscall(void)
vsyscall_mode == NATIVE
? PAGE_KERNEL_VSYSCALL
: PAGE_KERNEL_VVAR);
- set_vsyscall_pgtable_user_bits();
+ set_vsyscall_pgtable_user_bits(swapper_pg_dir);
}

BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 3674a4b6f8bd..8f0aace08b87 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -3,16 +3,18 @@
#include <linux/types.h>
#include <linux/slab.h>

+#include <asm/cpu_entry_area.h>
#include <asm/perf_event.h>
#include <asm/insn.h>

#include "../perf_event.h"

+/* Waste a full page so it can be mapped into the cpu_entry_area */
+DEFINE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
+
/* The size of a BTS record in bytes: */
#define BTS_RECORD_SIZE 24

-#define BTS_BUFFER_SIZE (PAGE_SIZE << 4)
-#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4)
#define PEBS_FIXUP_SIZE PAGE_SIZE

/*
@@ -279,17 +281,52 @@ void fini_debug_store_on_cpu(int cpu)

static DEFINE_PER_CPU(void *, insn_buffer);

-static int alloc_pebs_buffer(int cpu)
+static void ds_update_cea(void *cea, void *addr, size_t size, pgprot_t prot)
{
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+ phys_addr_t pa;
+ size_t msz = 0;
+
+ pa = virt_to_phys(addr);
+ for (; msz < size; msz += PAGE_SIZE, pa += PAGE_SIZE, cea += PAGE_SIZE)
+ cea_set_pte(cea, pa, prot);
+}
+
+static void ds_clear_cea(void *cea, size_t size)
+{
+ size_t msz = 0;
+
+ for (; msz < size; msz += PAGE_SIZE, cea += PAGE_SIZE)
+ cea_set_pte(cea, 0, PAGE_NONE);
+}
+
+static void *dsalloc_pages(size_t size, gfp_t flags, int cpu)
+{
+ unsigned int order = get_order(size);
int node = cpu_to_node(cpu);
- int max;
- void *buffer, *ibuffer;
+ struct page *page;
+
+ page = __alloc_pages_node(node, flags | __GFP_ZERO, order);
+ return page ? page_address(page) : NULL;
+}
+
+static void dsfree_pages(const void *buffer, size_t size)
+{
+ if (buffer)
+ free_pages((unsigned long)buffer, get_order(size));
+}
+
+static int alloc_pebs_buffer(int cpu)
+{
+ struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+ struct debug_store *ds = hwev->ds;
+ size_t bsiz = x86_pmu.pebs_buffer_size;
+ int max, node = cpu_to_node(cpu);
+ void *buffer, *ibuffer, *cea;

if (!x86_pmu.pebs)
return 0;

- buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
+ buffer = dsalloc_pages(bsiz, GFP_KERNEL, cpu);
if (unlikely(!buffer))
return -ENOMEM;

@@ -300,25 +337,27 @@ static int alloc_pebs_buffer(int cpu)
if (x86_pmu.intel_cap.pebs_format < 2) {
ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node);
if (!ibuffer) {
- kfree(buffer);
+ dsfree_pages(buffer, bsiz);
return -ENOMEM;
}
per_cpu(insn_buffer, cpu) = ibuffer;
}
-
- max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size;
-
- ds->pebs_buffer_base = (u64)(unsigned long)buffer;
+ hwev->ds_pebs_vaddr = buffer;
+ /* Update the cpu entry area mapping */
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
+ ds->pebs_buffer_base = (unsigned long) cea;
+ ds_update_cea(cea, buffer, bsiz, PAGE_KERNEL);
ds->pebs_index = ds->pebs_buffer_base;
- ds->pebs_absolute_maximum = ds->pebs_buffer_base +
- max * x86_pmu.pebs_record_size;
-
+ max = x86_pmu.pebs_record_size * (bsiz / x86_pmu.pebs_record_size);
+ ds->pebs_absolute_maximum = ds->pebs_buffer_base + max;
return 0;
}

static void release_pebs_buffer(int cpu)
{
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+ struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+ struct debug_store *ds = hwev->ds;
+ void *cea;

if (!ds || !x86_pmu.pebs)
return;
@@ -326,73 +365,70 @@ static void release_pebs_buffer(int cpu)
kfree(per_cpu(insn_buffer, cpu));
per_cpu(insn_buffer, cpu) = NULL;

- kfree((void *)(unsigned long)ds->pebs_buffer_base);
+ /* Clear the fixmap */
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
+ ds_clear_cea(cea, x86_pmu.pebs_buffer_size);
ds->pebs_buffer_base = 0;
+ dsfree_pages(hwev->ds_pebs_vaddr, x86_pmu.pebs_buffer_size);
+ hwev->ds_pebs_vaddr = NULL;
}

static int alloc_bts_buffer(int cpu)
{
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
- int node = cpu_to_node(cpu);
- int max, thresh;
- void *buffer;
+ struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+ struct debug_store *ds = hwev->ds;
+ void *buffer, *cea;
+ int max;

if (!x86_pmu.bts)
return 0;

- buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
+ buffer = dsalloc_pages(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, cpu);
if (unlikely(!buffer)) {
WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__);
return -ENOMEM;
}
-
- max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
- thresh = max / 16;
-
- ds->bts_buffer_base = (u64)(unsigned long)buffer;
+ hwev->ds_bts_vaddr = buffer;
+ /* Update the fixmap */
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer;
+ ds->bts_buffer_base = (unsigned long) cea;
+ ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL);
ds->bts_index = ds->bts_buffer_base;
- ds->bts_absolute_maximum = ds->bts_buffer_base +
- max * BTS_RECORD_SIZE;
- ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
- thresh * BTS_RECORD_SIZE;
-
+ max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE);
+ ds->bts_absolute_maximum = ds->bts_buffer_base + max;
+ ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16);
return 0;
}

static void release_bts_buffer(int cpu)
{
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+ struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+ struct debug_store *ds = hwev->ds;
+ void *cea;

if (!ds || !x86_pmu.bts)
return;

- kfree((void *)(unsigned long)ds->bts_buffer_base);
+ /* Clear the fixmap */
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer;
+ ds_clear_cea(cea, BTS_BUFFER_SIZE);
ds->bts_buffer_base = 0;
+ dsfree_pages(hwev->ds_bts_vaddr, BTS_BUFFER_SIZE);
+ hwev->ds_bts_vaddr = NULL;
}

static int alloc_ds_buffer(int cpu)
{
- int node = cpu_to_node(cpu);
- struct debug_store *ds;
-
- ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node);
- if (unlikely(!ds))
- return -ENOMEM;
+ struct debug_store *ds = &get_cpu_entry_area(cpu)->cpu_debug_store;

+ memset(ds, 0, sizeof(*ds));
per_cpu(cpu_hw_events, cpu).ds = ds;
-
return 0;
}

static void release_ds_buffer(int cpu)
{
- struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-
- if (!ds)
- return;
-
per_cpu(cpu_hw_events, cpu).ds = NULL;
- kfree(ds);
}

void release_ds_buffers(void)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index f7aaadf9331f..8e4ea143ed96 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -14,6 +14,8 @@

#include <linux/perf_event.h>

+#include <asm/intel_ds.h>
+
/* To enable MSR tracing please use the generic trace points. */

/*
@@ -77,8 +79,6 @@ struct amd_nb {
struct event_constraint event_constraints[X86_PMC_IDX_MAX];
};

-/* The maximal number of PEBS events: */
-#define MAX_PEBS_EVENTS 8
#define PEBS_COUNTER_MASK ((1ULL << MAX_PEBS_EVENTS) - 1)

/*
@@ -95,23 +95,6 @@ struct amd_nb {
PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \
PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)

-/*
- * A debug store configuration.
- *
- * We only support architectures that use 64bit fields.
- */
-struct debug_store {
- u64 bts_buffer_base;
- u64 bts_index;
- u64 bts_absolute_maximum;
- u64 bts_interrupt_threshold;
- u64 pebs_buffer_base;
- u64 pebs_index;
- u64 pebs_absolute_maximum;
- u64 pebs_interrupt_threshold;
- u64 pebs_event_reset[MAX_PEBS_EVENTS];
-};
-
#define PEBS_REGS \
(PERF_REG_X86_AX | \
PERF_REG_X86_BX | \
@@ -216,6 +199,8 @@ struct cpu_hw_events {
* Intel DebugStore bits
*/
struct debug_store *ds;
+ void *ds_pebs_vaddr;
+ void *ds_bts_vaddr;
u64 pebs_enabled;
int n_pebs;
int n_large_pebs;
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index 2fbc69a0916e..4a7884b8dca5 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -5,6 +5,7 @@

#include <linux/percpu-defs.h>
#include <asm/processor.h>
+#include <asm/intel_ds.h>

/*
* cpu_entry_area is a percpu region that contains things needed by the CPU
@@ -40,6 +41,18 @@ struct cpu_entry_area {
*/
char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ];
#endif
+#ifdef CONFIG_CPU_SUP_INTEL
+ /*
+ * Per CPU debug store for Intel performance monitoring. Wastes a
+ * full page at the moment.
+ */
+ struct debug_store cpu_debug_store;
+ /*
+ * The actual PEBS/BTS buffers must be mapped to user space
+ * Reserve enough fixmap PTEs.
+ */
+ struct debug_store_buffers cpu_debug_buffers;
+#endif
};

#define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area))
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 800104c8a3ed..07cdd1715705 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -197,11 +197,12 @@
#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */
#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */
#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_INVPCID_SINGLE ( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */

#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */
#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */
#define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */
-
+#define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */
#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */
#define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */
#define X86_FEATURE_AVX512_4VNNIW ( 7*32+16) /* AVX-512 Neural Network Instructions */
@@ -340,5 +341,6 @@
#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* SWAPGS without input dep on GS */
#define X86_BUG_MONITOR X86_BUG(12) /* IPI required to wake up remote CPU */
#define X86_BUG_AMD_E400 X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+#define X86_BUG_CPU_INSECURE X86_BUG(14) /* CPU is insecure and needs kernel page table isolation */

#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index bc359dd2f7f6..85e23bb7b34e 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -21,6 +21,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in

desc->type = (info->read_exec_only ^ 1) << 1;
desc->type |= info->contents << 2;
+ /* Set the ACCESS bit so it can be mapped RO */
+ desc->type |= 1;

desc->s = 1;
desc->dpl = 0x3;
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index c10c9128f54e..e428e16dd822 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -44,6 +44,12 @@
# define DISABLE_LA57 (1<<(X86_FEATURE_LA57 & 31))
#endif

+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define DISABLE_PTI 0
+#else
+# define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31))
+#endif
+
/*
* Make sure to add features to the correct mask
*/
@@ -54,7 +60,7 @@
#define DISABLED_MASK4 (DISABLE_PCID)
#define DISABLED_MASK5 0
#define DISABLED_MASK6 0
-#define DISABLED_MASK7 0
+#define DISABLED_MASK7 (DISABLE_PTI)
#define DISABLED_MASK8 0
#define DISABLED_MASK9 (DISABLE_MPX)
#define DISABLED_MASK10 0
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
new file mode 100644
index 000000000000..62a9f4966b42
--- /dev/null
+++ b/arch/x86/include/asm/intel_ds.h
@@ -0,0 +1,36 @@
+#ifndef _ASM_INTEL_DS_H
+#define _ASM_INTEL_DS_H
+
+#include <linux/percpu-defs.h>
+
+#define BTS_BUFFER_SIZE (PAGE_SIZE << 4)
+#define PEBS_BUFFER_SIZE (PAGE_SIZE << 4)
+
+/* The maximal number of PEBS events: */
+#define MAX_PEBS_EVENTS 8
+
+/*
+ * A debug store configuration.
+ *
+ * We only support architectures that use 64bit fields.
+ */
+struct debug_store {
+ u64 bts_buffer_base;
+ u64 bts_index;
+ u64 bts_absolute_maximum;
+ u64 bts_interrupt_threshold;
+ u64 pebs_buffer_base;
+ u64 pebs_index;
+ u64 pebs_absolute_maximum;
+ u64 pebs_interrupt_threshold;
+ u64 pebs_event_reset[MAX_PEBS_EVENTS];
+} __aligned(PAGE_SIZE);
+
+DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
+
+struct debug_store_buffers {
+ char bts_buffer[BTS_BUFFER_SIZE];
+ char pebs_buffer[PEBS_BUFFER_SIZE];
+};
+
+#endif
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 5ede7cae1d67..c931b88982a0 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -50,10 +50,33 @@ struct ldt_struct {
* call gates. On native, we could merge the ldt_struct and LDT
* allocations, but it's not worth trying to optimize.
*/
- struct desc_struct *entries;
- unsigned int nr_entries;
+ struct desc_struct *entries;
+ unsigned int nr_entries;
+
+ /*
+ * If PTI is in use, then the entries array is not mapped while we're
+ * in user mode. The whole array will be aliased at the addressed
+ * given by ldt_slot_va(slot). We use two slots so that we can allocate
+ * and map, and enable a new LDT without invalidating the mapping
+ * of an older, still-in-use LDT.
+ *
+ * slot will be -1 if this LDT doesn't have an alias mapping.
+ */
+ int slot;
};

+/* This is a multiple of PAGE_SIZE. */
+#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE)
+
+static inline void *ldt_slot_va(int slot)
+{
+#ifdef CONFIG_X86_64
+ return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot);
+#else
+ BUG();
+#endif
+}
+
/*
* Used for LDT copy/destruction.
*/
@@ -64,6 +87,7 @@ static inline void init_new_context_ldt(struct mm_struct *mm)
}
int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm);
void destroy_context_ldt(struct mm_struct *mm);
+void ldt_arch_exit_mmap(struct mm_struct *mm);
#else /* CONFIG_MODIFY_LDT_SYSCALL */
static inline void init_new_context_ldt(struct mm_struct *mm) { }
static inline int ldt_dup_context(struct mm_struct *oldmm,
@@ -71,7 +95,8 @@ static inline int ldt_dup_context(struct mm_struct *oldmm,
{
return 0;
}
-static inline void destroy_context_ldt(struct mm_struct *mm) {}
+static inline void destroy_context_ldt(struct mm_struct *mm) { }
+static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { }
#endif

static inline void load_mm_ldt(struct mm_struct *mm)
@@ -96,10 +121,31 @@ static inline void load_mm_ldt(struct mm_struct *mm)
* that we can see.
*/

- if (unlikely(ldt))
- set_ldt(ldt->entries, ldt->nr_entries);
- else
+ if (unlikely(ldt)) {
+ if (static_cpu_has(X86_FEATURE_PTI)) {
+ if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) {
+ /*
+ * Whoops -- either the new LDT isn't mapped
+ * (if slot == -1) or is mapped into a bogus
+ * slot (if slot > 1).
+ */
+ clear_LDT();
+ return;
+ }
+
+ /*
+ * If page table isolation is enabled, ldt->entries
+ * will not be mapped in the userspace pagetables.
+ * Tell the CPU to access the LDT through the alias
+ * at ldt_slot_va(ldt->slot).
+ */
+ set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries);
+ } else {
+ set_ldt(ldt->entries, ldt->nr_entries);
+ }
+ } else {
clear_LDT();
+ }
#else
clear_LDT();
#endif
@@ -194,6 +240,7 @@ static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
static inline void arch_exit_mmap(struct mm_struct *mm)
{
paravirt_arch_exit_mmap(mm);
+ ldt_arch_exit_mmap(mm);
}

#ifdef CONFIG_X86_64
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index 4b5e1eafada7..aff42e1da6ee 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -30,6 +30,17 @@ static inline void paravirt_release_p4d(unsigned long pfn) {}
*/
extern gfp_t __userpte_alloc_gfp;

+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Instead of one PGD, we acquire two PGDs. Being order-1, it is
+ * both 8k in size and 8k-aligned. That lets us just flip bit 12
+ * in a pointer to swap between the two 4k halves.
+ */
+#define PGD_ALLOCATION_ORDER 1
+#else
+#define PGD_ALLOCATION_ORDER 0
+#endif
+
/*
* Allocate and free page tables.
*/
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index f02de8bc1f72..211368922cad 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -28,6 +28,7 @@ extern pgd_t early_top_pgt[PTRS_PER_PGD];
int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);

void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user);
void ptdump_walk_pgd_level_checkwx(void);

#ifdef CONFIG_DEBUG_WX
@@ -846,7 +847,12 @@ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)

static inline int p4d_bad(p4d_t p4d)
{
- return (p4d_flags(p4d) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
+ unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER;
+
+ if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+ ignore_flags |= _PAGE_NX;
+
+ return (p4d_flags(p4d) & ~ignore_flags) != 0;
}
#endif /* CONFIG_PGTABLE_LEVELS > 3 */

@@ -880,7 +886,12 @@ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)

static inline int pgd_bad(pgd_t pgd)
{
- return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
+ unsigned long ignore_flags = _PAGE_USER;
+
+ if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+ ignore_flags |= _PAGE_NX;
+
+ return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE;
}

static inline int pgd_none(pgd_t pgd)
@@ -909,7 +920,11 @@ static inline int pgd_none(pgd_t pgd)
* pgd_offset() returns a (pgd_t *)
* pgd_index() is used get the offset into the pgd page's array of pgd_t's;
*/
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
+#define pgd_offset_pgd(pgd, address) (pgd + pgd_index((address)))
+/*
+ * a shortcut to get a pgd_t in a given mm
+ */
+#define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address))
/*
* a shortcut which implies the use of the kernel's pgd, instead
* of a process's
@@ -1111,7 +1126,14 @@ static inline int pud_write(pud_t pud)
*/
static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
{
- memcpy(dst, src, count * sizeof(pgd_t));
+ memcpy(dst, src, count * sizeof(pgd_t));
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+ /* Clone the user space pgd as well */
+ memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src),
+ count * sizeof(pgd_t));
+#endif
}

#define PTE_SHIFT ilog2(PTRS_PER_PTE)
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index e9f05331e732..81462e9a34f6 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -131,9 +131,97 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp)
#endif
}

+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
+ * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and
+ * the user one is in the last 4k. To switch between them, you
+ * just need to flip the 12th bit in their addresses.
+ */
+#define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT
+
+/*
+ * This generates better code than the inline assembly in
+ * __set_bit().
+ */
+static inline void *ptr_set_bit(void *ptr, int bit)
+{
+ unsigned long __ptr = (unsigned long)ptr;
+
+ __ptr |= BIT(bit);
+ return (void *)__ptr;
+}
+static inline void *ptr_clear_bit(void *ptr, int bit)
+{
+ unsigned long __ptr = (unsigned long)ptr;
+
+ __ptr &= ~BIT(bit);
+ return (void *)__ptr;
+}
+
+static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
+{
+ return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
+{
+ return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
+{
+ return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
+{
+ return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
+/*
+ * Page table pages are page-aligned. The lower half of the top
+ * level is used for userspace and the top half for the kernel.
+ *
+ * Returns true for parts of the PGD that map userspace and
+ * false for the parts that map the kernel.
+ */
+static inline bool pgdp_maps_userspace(void *__ptr)
+{
+ unsigned long ptr = (unsigned long)__ptr;
+
+ return (ptr & ~PAGE_MASK) < (PAGE_SIZE / 2);
+}
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd);
+
+/*
+ * Take a PGD location (pgdp) and a pgd value that needs to be set there.
+ * Populates the user and returns the resulting PGD that must be set in
+ * the kernel copy of the page tables.
+ */
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return pgd;
+ return __pti_set_user_pgd(pgdp, pgd);
+}
+#else
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ return pgd;
+}
+#endif
+
static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
{
+#if defined(CONFIG_PAGE_TABLE_ISOLATION) && !defined(CONFIG_X86_5LEVEL)
+ p4dp->pgd = pti_set_user_pgd(&p4dp->pgd, p4d.pgd);
+#else
*p4dp = p4d;
+#endif
}

static inline void native_p4d_clear(p4d_t *p4d)
@@ -147,7 +235,11 @@ static inline void native_p4d_clear(p4d_t *p4d)

static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ *pgdp = pti_set_user_pgd(pgdp, pgd);
+#else
*pgdp = pgd;
+#endif
}

static inline void native_pgd_clear(pgd_t *pgd)
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 3d27831bc58d..b97a539bcdee 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -79,13 +79,17 @@ typedef struct { pteval_t pte; } pte_t;
#define MAXMEM _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)

#ifdef CONFIG_X86_5LEVEL
-# define VMALLOC_SIZE_TB _AC(16384, UL)
-# define __VMALLOC_BASE _AC(0xff92000000000000, UL)
+# define VMALLOC_SIZE_TB _AC(12800, UL)
+# define __VMALLOC_BASE _AC(0xffa0000000000000, UL)
# define __VMEMMAP_BASE _AC(0xffd4000000000000, UL)
+# define LDT_PGD_ENTRY _AC(-112, UL)
+# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT)
#else
# define VMALLOC_SIZE_TB _AC(32, UL)
# define __VMALLOC_BASE _AC(0xffffc90000000000, UL)
# define __VMEMMAP_BASE _AC(0xffffea0000000000, UL)
+# define LDT_PGD_ENTRY _AC(-4, UL)
+# define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT)
#endif

#ifdef CONFIG_RANDOMIZE_MEMORY
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index 43212a43ee69..6a60fea90b9d 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -38,6 +38,11 @@
#define CR3_ADDR_MASK __sme_clr(0x7FFFFFFFFFFFF000ull)
#define CR3_PCID_MASK 0xFFFull
#define CR3_NOFLUSH BIT_ULL(63)
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define X86_CR3_PTI_SWITCH_BIT 11
+#endif
+
#else
/*
* CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 9e482d8b0b97..9c18da64daa9 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -851,13 +851,22 @@ static inline void spin_lock_prefetch(const void *x)

#else
/*
- * User space process size. 47bits minus one guard page. The guard
- * page is necessary on Intel CPUs: if a SYSCALL instruction is at
- * the highest possible canonical userspace address, then that
- * syscall will enter the kernel with a non-canonical return
- * address, and SYSRET will explode dangerously. We avoid this
- * particular problem by preventing anything from being mapped
- * at the maximum canonical address.
+ * User space process size. This is the first address outside the user range.
+ * There are a few constraints that determine this:
+ *
+ * On Intel CPUs, if a SYSCALL instruction is at the highest canonical
+ * address, then that syscall will enter the kernel with a
+ * non-canonical return address, and SYSRET will explode dangerously.
+ * We avoid this particular problem by preventing anything executable
+ * from being mapped at the maximum canonical address.
+ *
+ * On AMD CPUs in the Ryzen family, there's a nasty bug in which the
+ * CPUs malfunction if they execute code from the highest canonical page.
+ * They'll speculate right off the end of the canonical space, and
+ * bad things happen. This is worked around in the same way as the
+ * Intel problem.
+ *
+ * With page table isolation enabled, we map the LDT in ... [stay tuned]
*/
#define TASK_SIZE_MAX ((1UL << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE)

diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h
new file mode 100644
index 000000000000..0b5ef05b2d2d
--- /dev/null
+++ b/arch/x86/include/asm/pti.h
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _ASM_X86_PTI_H
+#define _ASM_X86_PTI_H
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+extern void pti_init(void);
+extern void pti_check_boottime_disable(void);
+#else
+static inline void pti_check_boottime_disable(void) { }
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_PTI_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 171b429f43a2..f9b48ce152eb 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -10,38 +10,90 @@
#include <asm/special_insns.h>
#include <asm/smp.h>
#include <asm/invpcid.h>
+#include <asm/pti.h>
+#include <asm/processor-flags.h>

-static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
-{
- /*
- * Bump the generation count. This also serves as a full barrier
- * that synchronizes with switch_mm(): callers are required to order
- * their read of mm_cpumask after their writes to the paging
- * structures.
- */
- return atomic64_inc_return(&mm->context.tlb_gen);
-}
+/*
+ * The x86 feature is called PCID (Process Context IDentifier). It is similar
+ * to what is traditionally called ASID on the RISC processors.
+ *
+ * We don't use the traditional ASID implementation, where each process/mm gets
+ * its own ASID and flush/restart when we run out of ASID space.
+ *
+ * Instead we have a small per-cpu array of ASIDs and cache the last few mm's
+ * that came by on this CPU, allowing cheaper switch_mm between processes on
+ * this CPU.
+ *
+ * We end up with different spaces for different things. To avoid confusion we
+ * use different names for each of them:
+ *
+ * ASID - [0, TLB_NR_DYN_ASIDS-1]
+ * the canonical identifier for an mm
+ *
+ * kPCID - [1, TLB_NR_DYN_ASIDS]
+ * the value we write into the PCID part of CR3; corresponds to the
+ * ASID+1, because PCID 0 is special.
+ *
+ * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS]
+ * for KPTI each mm has two address spaces and thus needs two
+ * PCID values, but we can still do with a single ASID denomination
+ * for each mm. Corresponds to kPCID + 2048.
+ *
+ */

/* There are 12 bits of space for ASIDS in CR3 */
#define CR3_HW_ASID_BITS 12
+
/*
* When enabled, PAGE_TABLE_ISOLATION consumes a single bit for
* user/kernel switches
*/
-#define PTI_CONSUMED_ASID_BITS 0
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define PTI_CONSUMED_PCID_BITS 1
+#else
+# define PTI_CONSUMED_PCID_BITS 0
+#endif
+
+#define CR3_AVAIL_PCID_BITS (X86_CR3_PCID_BITS - PTI_CONSUMED_PCID_BITS)

-#define CR3_AVAIL_ASID_BITS (CR3_HW_ASID_BITS - PTI_CONSUMED_ASID_BITS)
/*
* ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid. -1 below to account
- * for them being zero-based. Another -1 is because ASID 0 is reserved for
+ * for them being zero-based. Another -1 is because PCID 0 is reserved for
* use by non-PCID-aware users.
*/
-#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_ASID_BITS) - 2)
+#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_PCID_BITS) - 2)
+
+/*
+ * 6 because 6 should be plenty and struct tlb_state will fit in two cache
+ * lines.
+ */
+#define TLB_NR_DYN_ASIDS 6

+/*
+ * Given @asid, compute kPCID
+ */
static inline u16 kern_pcid(u16 asid)
{
VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ /*
+ * Make sure that the dynamic ASID space does not confict with the
+ * bit we are using to switch between user and kernel ASIDs.
+ */
+ BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_SWITCH_BIT));
+
/*
+ * The ASID being passed in here should have respected the
+ * MAX_ASID_AVAILABLE and thus never have the switch bit set.
+ */
+ VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_SWITCH_BIT));
+#endif
+ /*
+ * The dynamically-assigned ASIDs that get passed in are small
+ * (<TLB_NR_DYN_ASIDS). They never have the high switch bit set,
+ * so do not bother to clear it.
+ *
* If PCID is on, ASID-aware code paths put the ASID+1 into the
* PCID bits. This serves two purposes. It prevents a nasty
* situation in which PCID-unaware code saves CR3, loads some other
@@ -53,6 +105,18 @@ static inline u16 kern_pcid(u16 asid)
return asid + 1;
}

+/*
+ * Given @asid, compute uPCID
+ */
+static inline u16 user_pcid(u16 asid)
+{
+ u16 ret = kern_pcid(asid);
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ ret |= 1 << X86_CR3_PTI_SWITCH_BIT;
+#endif
+ return ret;
+}
+
struct pgd_t;
static inline unsigned long build_cr3(pgd_t *pgd, u16 asid)
{
@@ -95,12 +159,6 @@ static inline bool tlb_defer_switch_to_init_mm(void)
return !static_cpu_has(X86_FEATURE_PCID);
}

-/*
- * 6 because 6 should be plenty and struct tlb_state will fit in
- * two cache lines.
- */
-#define TLB_NR_DYN_ASIDS 6
-
struct tlb_context {
u64 ctx_id;
u64 tlb_gen;
@@ -134,6 +192,24 @@ struct tlb_state {
*/
bool is_lazy;

+ /*
+ * If set we changed the page tables in such a way that we
+ * needed an invalidation of all contexts (aka. PCIDs / ASIDs).
+ * This tells us to go invalidate all the non-loaded ctxs[]
+ * on the next context switch.
+ *
+ * The current ctx was kept up-to-date as it ran and does not
+ * need to be invalidated.
+ */
+ bool invalidate_other;
+
+ /*
+ * Mask that contains TLB_NR_DYN_ASIDS+1 bits to indicate
+ * the corresponding user PCID needs a flush next time we
+ * switch to it; see SWITCH_TO_USER_CR3.
+ */
+ unsigned short user_pcid_flush_mask;
+
/*
* Access to this CR4 shadow and to H/W CR4 is protected by
* disabling interrupts when modifying either one.
@@ -211,6 +287,14 @@ static inline unsigned long cr4_read_shadow(void)
return this_cpu_read(cpu_tlbstate.cr4);
}

+/*
+ * Mark all other ASIDs as invalid, preserves the current.
+ */
+static inline void invalidate_other_asid(void)
+{
+ this_cpu_write(cpu_tlbstate.invalidate_other, true);
+}
+
/*
* Save some of cr4 feature set we're using (e.g. Pentium 4MB
* enable and PPro Global page enable), so that any CPU's that boot
@@ -230,19 +314,48 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask)

extern void initialize_tlbstate_and_flush(void);

+/*
+ * Given an ASID, flush the corresponding user ASID. We can delay this
+ * until the next time we switch to it.
+ *
+ * See SWITCH_TO_USER_CR3.
+ */
+static inline void invalidate_user_asid(u16 asid)
+{
+ /* There is no user ASID if address space separation is off */
+ if (!IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+ return;
+
+ /*
+ * We only have a single ASID if PCID is off and the CR3
+ * write will have flushed it.
+ */
+ if (!cpu_feature_enabled(X86_FEATURE_PCID))
+ return;
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ __set_bit(kern_pcid(asid),
+ (unsigned long *)this_cpu_ptr(&cpu_tlbstate.user_pcid_flush_mask));
+}
+
/*
* flush the entire current user mapping
*/
static inline void __native_flush_tlb(void)
{
/*
- * If current->mm == NULL then we borrow a mm which may change during a
- * task switch and therefore we must not be preempted while we write CR3
- * back:
+ * Preemption or interrupts must be disabled to protect the access
+ * to the per CPU variable and to prevent being preempted between
+ * read_cr3() and write_cr3().
*/
- preempt_disable();
+ WARN_ON_ONCE(preemptible());
+
+ invalidate_user_asid(this_cpu_read(cpu_tlbstate.loaded_mm_asid));
+
+ /* If current->mm == NULL then the read_cr3() "borrows" an mm */
native_write_cr3(__native_read_cr3());
- preempt_enable();
}

/*
@@ -256,6 +369,8 @@ static inline void __native_flush_tlb_global(void)
/*
* Using INVPCID is considerably faster than a pair of writes
* to CR4 sandwiched inside an IRQ flag save/restore.
+ *
+ * Note, this works with CR4.PCIDE=0 or 1.
*/
invpcid_flush_all();
return;
@@ -282,7 +397,21 @@ static inline void __native_flush_tlb_global(void)
*/
static inline void __native_flush_tlb_single(unsigned long addr)
{
+ u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+
asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ /*
+ * Some platforms #GP if we call invpcid(type=1/2) before CR4.PCIDE=1.
+ * Just use invalidate_user_asid() in case we are called early.
+ */
+ if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE))
+ invalidate_user_asid(loaded_mm_asid);
+ else
+ invpcid_flush_one(user_pcid(loaded_mm_asid), addr);
}

/*
@@ -298,14 +427,6 @@ static inline void __flush_tlb_all(void)
*/
__flush_tlb();
}
-
- /*
- * Note: if we somehow had PCID but not PGE, then this wouldn't work --
- * we'd end up flushing kernel translations for the current ASID but
- * we might fail to flush kernel translations for other cached ASIDs.
- *
- * To avoid this issue, we force PCID off if PGE is off.
- */
}

/*
@@ -315,6 +436,16 @@ static inline void __flush_tlb_one(unsigned long addr)
{
count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
__flush_tlb_single(addr);
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ /*
+ * __flush_tlb_single() will have cleared the TLB entry for this ASID,
+ * but since kernel space is replicated across all, we must also
+ * invalidate all others.
+ */
+ invalidate_other_asid();
}

#define TLB_FLUSH_ALL -1UL
@@ -375,6 +506,17 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
void native_flush_tlb_others(const struct cpumask *cpumask,
const struct flush_tlb_info *info);

+static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
+{
+ /*
+ * Bump the generation count. This also serves as a full barrier
+ * that synchronizes with switch_mm(): callers are required to order
+ * their read of mm_cpumask after their writes to the paging
+ * structures.
+ */
+ return atomic64_inc_return(&mm->context.tlb_gen);
+}
+
static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
struct mm_struct *mm)
{
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index d9a7c659009c..b986b2ca688a 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -7,6 +7,7 @@

#ifdef CONFIG_X86_VSYSCALL_EMULATION
extern void map_vsyscall(void);
+extern void set_vsyscall_pgtable_user_bits(pgd_t *root);

/*
* Called on instruction fetch fault in vsyscall page.
diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index 53b4ca55ebb6..97abdaab9535 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -78,7 +78,12 @@
#define X86_CR3_PWT _BITUL(X86_CR3_PWT_BIT)
#define X86_CR3_PCD_BIT 4 /* Page Cache Disable */
#define X86_CR3_PCD _BITUL(X86_CR3_PCD_BIT)
-#define X86_CR3_PCID_MASK _AC(0x00000fff,UL) /* PCID Mask */
+
+#define X86_CR3_PCID_BITS 12
+#define X86_CR3_PCID_MASK (_AC((1UL << X86_CR3_PCID_BITS) - 1, UL))
+
+#define X86_CR3_PCID_NOFLUSH_BIT 63 /* Preserve old PCID */
+#define X86_CR3_PCID_NOFLUSH _BITULL(X86_CR3_PCID_NOFLUSH_BIT)

/*
* Intel CPU features in CR4
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 676b7cf4b62b..76417a9aab73 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -17,6 +17,7 @@
#include <asm/sigframe.h>
#include <asm/bootparam.h>
#include <asm/suspend.h>
+#include <asm/tlbflush.h>

#ifdef CONFIG_XEN
#include <xen/interface/xen.h>
@@ -94,6 +95,9 @@ void common(void) {
BLANK();
DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));

+ /* TLB state for the entry code */
+ OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask);
+
/* Layout info for cpu_entry_area */
OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss);
OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8ddcfa4d4165..f2a94dfb434e 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -898,6 +898,10 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
}

setup_force_cpu_cap(X86_FEATURE_ALWAYS);
+
+ /* Assume for now that ALL x86 CPUs are insecure */
+ setup_force_cpu_bug(X86_BUG_CPU_INSECURE);
+
fpu__init_system(c);

#ifdef CONFIG_X86_32
@@ -1335,7 +1339,10 @@ void syscall_init(void)
(entry_SYSCALL_64_trampoline - _entry_trampoline);

wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
- wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline);
+ if (static_cpu_has(X86_FEATURE_PTI))
+ wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline);
+ else
+ wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);

#ifdef CONFIG_IA32_EMULATION
wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat);
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 36b17e0febe8..5fa110699ed2 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -297,11 +297,13 @@ int __die(const char *str, struct pt_regs *regs, long err)
unsigned long sp;
#endif
printk(KERN_DEFAULT
- "%s: %04lx [#%d]%s%s%s%s\n", str, err & 0xffff, ++die_counter,
+ "%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter,
IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
- IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "");
+ IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "",
+ IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ?
+ (boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : "");

if (notify_die(DIE_OOPS, str, regs, err,
current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 7dca675fe78d..04a625f0fcda 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -341,6 +341,27 @@ GLOBAL(early_recursion_flag)
.balign PAGE_SIZE; \
GLOBAL(name)

+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Each PGD needs to be 8k long and 8k aligned. We do not
+ * ever go out to userspace with these, so we do not
+ * strictly *need* the second page, but this allows us to
+ * have a single set_pgd() implementation that does not
+ * need to worry about whether it has 4k or 8k to work
+ * with.
+ *
+ * This ensures PGDs are 8k long:
+ */
+#define PTI_USER_PGD_FILL 512
+/* This ensures they are 8k-aligned: */
+#define NEXT_PGD_PAGE(name) \
+ .balign 2 * PAGE_SIZE; \
+GLOBAL(name)
+#else
+#define NEXT_PGD_PAGE(name) NEXT_PAGE(name)
+#define PTI_USER_PGD_FILL 0
+#endif
+
/* Automate the creation of 1 to 1 mapping pmd entries */
#define PMDS(START, PERM, COUNT) \
i = 0 ; \
@@ -350,13 +371,14 @@ GLOBAL(name)
.endr

__INITDATA
-NEXT_PAGE(early_top_pgt)
+NEXT_PGD_PAGE(early_top_pgt)
.fill 511,8,0
#ifdef CONFIG_X86_5LEVEL
.quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
#else
.quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
#endif
+ .fill PTI_USER_PGD_FILL,8,0

NEXT_PAGE(early_dynamic_pgts)
.fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0
@@ -364,13 +386,14 @@ NEXT_PAGE(early_dynamic_pgts)
.data

#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH)
-NEXT_PAGE(init_top_pgt)
+NEXT_PGD_PAGE(init_top_pgt)
.quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
.org init_top_pgt + PGD_PAGE_OFFSET*8, 0
.quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
.org init_top_pgt + PGD_START_KERNEL*8, 0
/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
.quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
+ .fill PTI_USER_PGD_FILL,8,0

NEXT_PAGE(level3_ident_pgt)
.quad level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
@@ -381,8 +404,9 @@ NEXT_PAGE(level2_ident_pgt)
*/
PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
#else
-NEXT_PAGE(init_top_pgt)
+NEXT_PGD_PAGE(init_top_pgt)
.fill 512,8,0
+ .fill PTI_USER_PGD_FILL,8,0
#endif

#ifdef CONFIG_X86_5LEVEL
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index a6b5d62f45a7..26d713ecad34 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -24,6 +24,7 @@
#include <linux/uaccess.h>

#include <asm/ldt.h>
+#include <asm/tlb.h>
#include <asm/desc.h>
#include <asm/mmu_context.h>
#include <asm/syscalls.h>
@@ -51,13 +52,11 @@ static void refresh_ldt_segments(void)
static void flush_ldt(void *__mm)
{
struct mm_struct *mm = __mm;
- mm_context_t *pc;

if (this_cpu_read(cpu_tlbstate.loaded_mm) != mm)
return;

- pc = &mm->context;
- set_ldt(pc->ldt->entries, pc->ldt->nr_entries);
+ load_mm_ldt(mm);

refresh_ldt_segments();
}
@@ -94,10 +93,126 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
return NULL;
}

+ /* The new LDT isn't aliased for PTI yet. */
+ new_ldt->slot = -1;
+
new_ldt->nr_entries = num_entries;
return new_ldt;
}

+/*
+ * If PTI is enabled, this maps the LDT into the kernelmode and
+ * usermode tables for the given mm.
+ *
+ * There is no corresponding unmap function. Even if the LDT is freed, we
+ * leave the PTEs around until the slot is reused or the mm is destroyed.
+ * This is harmless: the LDT is always in ordinary memory, and no one will
+ * access the freed slot.
+ *
+ * If we wanted to unmap freed LDTs, we'd also need to do a flush to make
+ * it useful, and the flush would slow down modify_ldt().
+ */
+static int
+map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ bool is_vmalloc, had_top_level_entry;
+ unsigned long va;
+ spinlock_t *ptl;
+ pgd_t *pgd;
+ int i;
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return 0;
+
+ /*
+ * Any given ldt_struct should have map_ldt_struct() called at most
+ * once.
+ */
+ WARN_ON(ldt->slot != -1);
+
+ /*
+ * Did we already have the top level entry allocated? We can't
+ * use pgd_none() for this because it doens't do anything on
+ * 4-level page table kernels.
+ */
+ pgd = pgd_offset(mm, LDT_BASE_ADDR);
+ had_top_level_entry = (pgd->pgd != 0);
+
+ is_vmalloc = is_vmalloc_addr(ldt->entries);
+
+ for (i = 0; i * PAGE_SIZE < ldt->nr_entries * LDT_ENTRY_SIZE; i++) {
+ unsigned long offset = i << PAGE_SHIFT;
+ const void *src = (char *)ldt->entries + offset;
+ unsigned long pfn;
+ pte_t pte, *ptep;
+
+ va = (unsigned long)ldt_slot_va(slot) + offset;
+ pfn = is_vmalloc ? vmalloc_to_pfn(src) :
+ page_to_pfn(virt_to_page(src));
+ /*
+ * Treat the PTI LDT range as a *userspace* range.
+ * get_locked_pte() will allocate all needed pagetables
+ * and account for them in this mm.
+ */
+ ptep = get_locked_pte(mm, va, &ptl);
+ if (!ptep)
+ return -ENOMEM;
+ /*
+ * Map it RO so the easy to find address is not a primary
+ * target via some kernel interface which misses a
+ * permission check.
+ */
+ pte = pfn_pte(pfn, __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL));
+ set_pte_at(mm, va, ptep, pte);
+ pte_unmap_unlock(ptep, ptl);
+ }
+
+ if (mm->context.ldt) {
+ /*
+ * We already had an LDT. The top-level entry should already
+ * have been allocated and synchronized with the usermode
+ * tables.
+ */
+ WARN_ON(!had_top_level_entry);
+ if (static_cpu_has(X86_FEATURE_PTI))
+ WARN_ON(!kernel_to_user_pgdp(pgd)->pgd);
+ } else {
+ /*
+ * This is the first time we're mapping an LDT for this process.
+ * Sync the pgd to the usermode tables.
+ */
+ WARN_ON(had_top_level_entry);
+ if (static_cpu_has(X86_FEATURE_PTI)) {
+ WARN_ON(kernel_to_user_pgdp(pgd)->pgd);
+ set_pgd(kernel_to_user_pgdp(pgd), *pgd);
+ }
+ }
+
+ va = (unsigned long)ldt_slot_va(slot);
+ flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, 0);
+
+ ldt->slot = slot;
+#endif
+ return 0;
+}
+
+static void free_ldt_pgtables(struct mm_struct *mm)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ struct mmu_gather tlb;
+ unsigned long start = LDT_BASE_ADDR;
+ unsigned long end = start + (1UL << PGDIR_SHIFT);
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ tlb_gather_mmu(&tlb, mm, start, end);
+ free_pgd_range(&tlb, start, end, start, end);
+ tlb_finish_mmu(&tlb, start, end);
+#endif
+}
+
/* After calling this, the LDT is immutable. */
static void finalize_ldt_struct(struct ldt_struct *ldt)
{
@@ -156,6 +271,12 @@ int ldt_dup_context(struct mm_struct *old_mm, struct mm_struct *mm)
new_ldt->nr_entries * LDT_ENTRY_SIZE);
finalize_ldt_struct(new_ldt);

+ retval = map_ldt_struct(mm, new_ldt, 0);
+ if (retval) {
+ free_ldt_pgtables(mm);
+ free_ldt_struct(new_ldt);
+ goto out_unlock;
+ }
mm->context.ldt = new_ldt;

out_unlock:
@@ -174,6 +295,11 @@ void destroy_context_ldt(struct mm_struct *mm)
mm->context.ldt = NULL;
}

+void ldt_arch_exit_mmap(struct mm_struct *mm)
+{
+ free_ldt_pgtables(mm);
+}
+
static int read_ldt(void __user *ptr, unsigned long bytecount)
{
struct mm_struct *mm = current->mm;
@@ -287,6 +413,25 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
new_ldt->entries[ldt_info.entry_number] = ldt;
finalize_ldt_struct(new_ldt);

+ /*
+ * If we are using PTI, map the new LDT into the userspace pagetables.
+ * If there is already an LDT, use the other slot so that other CPUs
+ * will continue to use the old LDT until install_ldt() switches
+ * them over to the new LDT.
+ */
+ error = map_ldt_struct(mm, new_ldt, old_ldt ? !old_ldt->slot : 0);
+ if (error) {
+ /*
+ * This only can fail for the first LDT setup. If an LDT is
+ * already installed then the PTE page is already
+ * populated. Mop up a half populated page table.
+ */
+ if (!WARN_ON_ONCE(old_ldt))
+ free_ldt_pgtables(mm);
+ free_ldt_struct(new_ldt);
+ goto out_unlock;
+ }
+
install_ldt(mm, new_ldt);
free_ldt_struct(old_ldt);
error = 0;
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 00bc751c861c..edfede768688 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -48,8 +48,6 @@ static void load_segments(void)
"\tmovl $"STR(__KERNEL_DS)",%%eax\n"
"\tmovl %%eax,%%ds\n"
"\tmovl %%eax,%%es\n"
- "\tmovl %%eax,%%fs\n"
- "\tmovl %%eax,%%gs\n"
"\tmovl %%eax,%%ss\n"
: : : "eax", "memory");
#undef STR
@@ -232,8 +230,8 @@ void machine_kexec(struct kimage *image)
* The gdt & idt are now invalid.
* If you want to load them you must set up your own idt & gdt.
*/
- set_gdt(phys_to_virt(0), 0);
idt_invalidate(phys_to_virt(0));
+ set_gdt(phys_to_virt(0), 0);

/* now call it */
image->start = relocate_kernel_ptr((unsigned long)image->head,
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 12bf07d44dfe..2651ca2112c4 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -128,25 +128,16 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
spin_lock_irqsave(&rtc_lock, flags);
CMOS_WRITE(0xa, 0xf);
spin_unlock_irqrestore(&rtc_lock, flags);
- local_flush_tlb();
- pr_debug("1.\n");
*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_HIGH)) =
start_eip >> 4;
- pr_debug("2.\n");
*((volatile unsigned short *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) =
start_eip & 0xf;
- pr_debug("3.\n");
}

static inline void smpboot_restore_warm_reset_vector(void)
{
unsigned long flags;

- /*
- * Install writable page 0 entry to set BIOS data area.
- */
- local_flush_tlb();
-
/*
* Paranoid: Set warm reset code and vector here back
* to default values.
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 9a9c9b076955..a5b802a12212 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -93,17 +93,10 @@ static void set_tls_desc(struct task_struct *p, int idx,
cpu = get_cpu();

while (n-- > 0) {
- if (LDT_empty(info) || LDT_zero(info)) {
+ if (LDT_empty(info) || LDT_zero(info))
memset(desc, 0, sizeof(*desc));
- } else {
+ else
fill_ldt(desc, info);
-
- /*
- * Always set the accessed bit so that the CPU
- * doesn't try to write to the (read-only) GDT.
- */
- desc->type |= 1;
- }
++info;
++desc;
}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 7c16fe0b60c2..b33e860d32fe 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -361,7 +361,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
*
* No need for ist_enter here because we don't use RCU.
*/
- if (((long)regs->sp >> PGDIR_SHIFT) == ESPFIX_PGD_ENTRY &&
+ if (((long)regs->sp >> P4D_SHIFT) == ESPFIX_PGD_ENTRY &&
regs->cs == __KERNEL_CS &&
regs->ip == (unsigned long)native_irq_return_iret)
{
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index d2a8b5a24a44..1e413a9326aa 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -61,11 +61,17 @@ jiffies_64 = jiffies;
. = ALIGN(HPAGE_SIZE); \
__end_rodata_hpage_align = .;

+#define ALIGN_ENTRY_TEXT_BEGIN . = ALIGN(PMD_SIZE);
+#define ALIGN_ENTRY_TEXT_END . = ALIGN(PMD_SIZE);
+
#else

#define X64_ALIGN_RODATA_BEGIN
#define X64_ALIGN_RODATA_END

+#define ALIGN_ENTRY_TEXT_BEGIN
+#define ALIGN_ENTRY_TEXT_END
+
#endif

PHDRS {
@@ -102,8 +108,10 @@ SECTIONS
CPUIDLE_TEXT
LOCK_TEXT
KPROBES_TEXT
+ ALIGN_ENTRY_TEXT_BEGIN
ENTRY_TEXT
IRQENTRY_TEXT
+ ALIGN_ENTRY_TEXT_END
SOFTIRQENTRY_TEXT
*(.fixup)
*(.gnu.warning)
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 2e0017af8f9b..52906808e277 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -43,9 +43,10 @@ obj-$(CONFIG_AMD_NUMA) += amdtopology.o
obj-$(CONFIG_ACPI_NUMA) += srat.o
obj-$(CONFIG_NUMA_EMU) += numa_emulation.o

-obj-$(CONFIG_X86_INTEL_MPX) += mpx.o
-obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o
-obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o
+obj-$(CONFIG_X86_INTEL_MPX) += mpx.o
+obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o
+obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o
+obj-$(CONFIG_PAGE_TABLE_ISOLATION) += pti.o

obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_boot.o
diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
index fe814fd5e014..b9283cc27622 100644
--- a/arch/x86/mm/cpu_entry_area.c
+++ b/arch/x86/mm/cpu_entry_area.c
@@ -38,6 +38,32 @@ cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot)
cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot);
}

+static void percpu_setup_debug_store(int cpu)
+{
+#ifdef CONFIG_CPU_SUP_INTEL
+ int npages;
+ void *cea;
+
+ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+ return;
+
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_store;
+ npages = sizeof(struct debug_store) / PAGE_SIZE;
+ BUILD_BUG_ON(sizeof(struct debug_store) % PAGE_SIZE != 0);
+ cea_map_percpu_pages(cea, &per_cpu(cpu_debug_store, cpu), npages,
+ PAGE_KERNEL);
+
+ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers;
+ /*
+ * Force the population of PMDs for not yet allocated per cpu
+ * memory like debug store buffers.
+ */
+ npages = sizeof(struct debug_store_buffers) / PAGE_SIZE;
+ for (; npages; npages--, cea += PAGE_SIZE)
+ cea_set_pte(cea, 0, PAGE_NONE);
+#endif
+}
+
/* Setup the fixmap mappings only once per-processor */
static void __init setup_cpu_entry_area(int cpu)
{
@@ -109,6 +135,7 @@ static void __init setup_cpu_entry_area(int cpu)
cea_set_pte(&get_cpu_entry_area(cpu)->entry_trampoline,
__pa_symbol(_entry_trampoline), PAGE_KERNEL_RX);
#endif
+ percpu_setup_debug_store(cpu);
}

static __init void setup_cpu_entry_area_ptes(void)
diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c
index bfcffdf6c577..421f2664ffa0 100644
--- a/arch/x86/mm/debug_pagetables.c
+++ b/arch/x86/mm/debug_pagetables.c
@@ -5,7 +5,7 @@

static int ptdump_show(struct seq_file *m, void *v)
{
- ptdump_walk_pgd_level(m, NULL);
+ ptdump_walk_pgd_level_debugfs(m, NULL, false);
return 0;
}

@@ -22,21 +22,89 @@ static const struct file_operations ptdump_fops = {
.release = single_release,
};

-static struct dentry *pe;
+static int ptdump_show_curknl(struct seq_file *m, void *v)
+{
+ if (current->mm->pgd) {
+ down_read(&current->mm->mmap_sem);
+ ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, false);
+ up_read(&current->mm->mmap_sem);
+ }
+ return 0;
+}
+
+static int ptdump_open_curknl(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, ptdump_show_curknl, NULL);
+}
+
+static const struct file_operations ptdump_curknl_fops = {
+ .owner = THIS_MODULE,
+ .open = ptdump_open_curknl,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+static struct dentry *pe_curusr;
+
+static int ptdump_show_curusr(struct seq_file *m, void *v)
+{
+ if (current->mm->pgd) {
+ down_read(&current->mm->mmap_sem);
+ ptdump_walk_pgd_level_debugfs(m, current->mm->pgd, true);
+ up_read(&current->mm->mmap_sem);
+ }
+ return 0;
+}
+
+static int ptdump_open_curusr(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, ptdump_show_curusr, NULL);
+}
+
+static const struct file_operations ptdump_curusr_fops = {
+ .owner = THIS_MODULE,
+ .open = ptdump_open_curusr,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+#endif
+
+static struct dentry *dir, *pe_knl, *pe_curknl;

static int __init pt_dump_debug_init(void)
{
- pe = debugfs_create_file("kernel_page_tables", S_IRUSR, NULL, NULL,
- &ptdump_fops);
- if (!pe)
+ dir = debugfs_create_dir("page_tables", NULL);
+ if (!dir)
return -ENOMEM;

+ pe_knl = debugfs_create_file("kernel", 0400, dir, NULL,
+ &ptdump_fops);
+ if (!pe_knl)
+ goto err;
+
+ pe_curknl = debugfs_create_file("current_kernel", 0400,
+ dir, NULL, &ptdump_curknl_fops);
+ if (!pe_curknl)
+ goto err;
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ pe_curusr = debugfs_create_file("current_user", 0400,
+ dir, NULL, &ptdump_curusr_fops);
+ if (!pe_curusr)
+ goto err;
+#endif
return 0;
+err:
+ debugfs_remove_recursive(dir);
+ return -ENOMEM;
}

static void __exit pt_dump_debug_exit(void)
{
- debugfs_remove_recursive(pe);
+ debugfs_remove_recursive(dir);
}

module_init(pt_dump_debug_init);
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 43dedbfb7257..f56902c1f04b 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -52,11 +52,17 @@ enum address_markers_idx {
USER_SPACE_NR = 0,
KERNEL_SPACE_NR,
LOW_KERNEL_NR,
+#if defined(CONFIG_MODIFY_LDT_SYSCALL) && defined(CONFIG_X86_5LEVEL)
+ LDT_NR,
+#endif
VMALLOC_START_NR,
VMEMMAP_START_NR,
#ifdef CONFIG_KASAN
KASAN_SHADOW_START_NR,
KASAN_SHADOW_END_NR,
+#endif
+#if defined(CONFIG_MODIFY_LDT_SYSCALL) && !defined(CONFIG_X86_5LEVEL)
+ LDT_NR,
#endif
CPU_ENTRY_AREA_NR,
#ifdef CONFIG_X86_ESPFIX64
@@ -81,6 +87,9 @@ static struct addr_marker address_markers[] = {
#ifdef CONFIG_KASAN
[KASAN_SHADOW_START_NR] = { KASAN_SHADOW_START, "KASAN shadow" },
[KASAN_SHADOW_END_NR] = { KASAN_SHADOW_END, "KASAN shadow end" },
+#endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+ [LDT_NR] = { LDT_BASE_ADDR, "LDT remap" },
#endif
[CPU_ENTRY_AREA_NR] = { CPU_ENTRY_AREA_BASE,"CPU entry Area" },
#ifdef CONFIG_X86_ESPFIX64
@@ -467,7 +476,7 @@ static inline bool is_hypervisor_range(int idx)
}

static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
- bool checkwx)
+ bool checkwx, bool dmesg)
{
#ifdef CONFIG_X86_64
pgd_t *start = (pgd_t *) &init_top_pgt;
@@ -480,7 +489,7 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,

if (pgd) {
start = pgd;
- st.to_dmesg = true;
+ st.to_dmesg = dmesg;
}

st.check_wx = checkwx;
@@ -518,13 +527,37 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,

void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
{
- ptdump_walk_pgd_level_core(m, pgd, false);
+ ptdump_walk_pgd_level_core(m, pgd, false, true);
+}
+
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ if (user && static_cpu_has(X86_FEATURE_PTI))
+ pgd = kernel_to_user_pgdp(pgd);
+#endif
+ ptdump_walk_pgd_level_core(m, pgd, false, false);
+}
+EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs);
+
+static void ptdump_walk_user_pgd_level_checkwx(void)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+ pgd_t *pgd = (pgd_t *) &init_top_pgt;
+
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ pr_info("x86/mm: Checking user space page tables\n");
+ pgd = kernel_to_user_pgdp(pgd);
+ ptdump_walk_pgd_level_core(NULL, pgd, true, false);
+#endif
}
-EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level);

void ptdump_walk_pgd_level_checkwx(void)
{
- ptdump_walk_pgd_level_core(NULL, NULL, true);
+ ptdump_walk_pgd_level_core(NULL, NULL, true, false);
+ ptdump_walk_user_pgd_level_checkwx();
}

static int __init pt_dump_init(void)
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index a22c2b95e513..80259ad8c386 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -20,6 +20,7 @@
#include <asm/kaslr.h>
#include <asm/hypervisor.h>
#include <asm/cpufeature.h>
+#include <asm/pti.h>

/*
* We need to define the tracepoints somewhere, and tlb.c
@@ -161,6 +162,12 @@ struct map_range {

static int page_size_mask;

+static void enable_global_pages(void)
+{
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ __supported_pte_mask |= _PAGE_GLOBAL;
+}
+
static void __init probe_page_size_mask(void)
{
/*
@@ -179,11 +186,11 @@ static void __init probe_page_size_mask(void)
cr4_set_bits_and_update_boot(X86_CR4_PSE);

/* Enable PGE if available */
+ __supported_pte_mask &= ~_PAGE_GLOBAL;
if (boot_cpu_has(X86_FEATURE_PGE)) {
cr4_set_bits_and_update_boot(X86_CR4_PGE);
- __supported_pte_mask |= _PAGE_GLOBAL;
- } else
- __supported_pte_mask &= ~_PAGE_GLOBAL;
+ enable_global_pages();
+ }

/* Enable 1 GB linear kernel mappings if available: */
if (direct_gbpages && boot_cpu_has(X86_FEATURE_GBPAGES)) {
@@ -196,34 +203,44 @@ static void __init probe_page_size_mask(void)

static void setup_pcid(void)
{
-#ifdef CONFIG_X86_64
- if (boot_cpu_has(X86_FEATURE_PCID)) {
- if (boot_cpu_has(X86_FEATURE_PGE)) {
- /*
- * This can't be cr4_set_bits_and_update_boot() --
- * the trampoline code can't handle CR4.PCIDE and
- * it wouldn't do any good anyway. Despite the name,
- * cr4_set_bits_and_update_boot() doesn't actually
- * cause the bits in question to remain set all the
- * way through the secondary boot asm.
- *
- * Instead, we brute-force it and set CR4.PCIDE
- * manually in start_secondary().
- */
- cr4_set_bits(X86_CR4_PCIDE);
- } else {
- /*
- * flush_tlb_all(), as currently implemented, won't
- * work if PCID is on but PGE is not. Since that
- * combination doesn't exist on real hardware, there's
- * no reason to try to fully support it, but it's
- * polite to avoid corrupting data if we're on
- * an improperly configured VM.
- */
- setup_clear_cpu_cap(X86_FEATURE_PCID);
- }
+ if (!IS_ENABLED(CONFIG_X86_64))
+ return;
+
+ if (!boot_cpu_has(X86_FEATURE_PCID))
+ return;
+
+ if (boot_cpu_has(X86_FEATURE_PGE)) {
+ /*
+ * This can't be cr4_set_bits_and_update_boot() -- the
+ * trampoline code can't handle CR4.PCIDE and it wouldn't
+ * do any good anyway. Despite the name,
+ * cr4_set_bits_and_update_boot() doesn't actually cause
+ * the bits in question to remain set all the way through
+ * the secondary boot asm.
+ *
+ * Instead, we brute-force it and set CR4.PCIDE manually in
+ * start_secondary().
+ */
+ cr4_set_bits(X86_CR4_PCIDE);
+
+ /*
+ * INVPCID's single-context modes (2/3) only work if we set
+ * X86_CR4_PCIDE, *and* we INVPCID support. It's unusable
+ * on systems that have X86_CR4_PCIDE clear, or that have
+ * no INVPCID support at all.
+ */
+ if (boot_cpu_has(X86_FEATURE_INVPCID))
+ setup_force_cpu_cap(X86_FEATURE_INVPCID_SINGLE);
+ } else {
+ /*
+ * flush_tlb_all(), as currently implemented, won't work if
+ * PCID is on but PGE is not. Since that combination
+ * doesn't exist on real hardware, there's no reason to try
+ * to fully support it, but it's polite to avoid corrupting
+ * data if we're on an improperly configured VM.
+ */
+ setup_clear_cpu_cap(X86_FEATURE_PCID);
}
-#endif
}

#ifdef CONFIG_X86_32
@@ -624,6 +641,7 @@ void __init init_mem_mapping(void)
{
unsigned long end;

+ pti_check_boottime_disable();
probe_page_size_mask();
setup_pcid();

@@ -847,7 +865,7 @@ void __init zone_sizes_init(void)
free_area_init_nodes(max_zone_pfns);
}

-DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
+__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
.loaded_mm = &init_mm,
.next_asid = 1,
.cr4 = ~0UL, /* fail hard if we screw up cr4 shadow initialization */
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 17ebc5a978cc..9b7bcbd33cc2 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -355,14 +355,15 @@ static inline void _pgd_free(pgd_t *pgd)
kmem_cache_free(pgd_cache, pgd);
}
#else
+
static inline pgd_t *_pgd_alloc(void)
{
- return (pgd_t *)__get_free_page(PGALLOC_GFP);
+ return (pgd_t *)__get_free_pages(PGALLOC_GFP, PGD_ALLOCATION_ORDER);
}

static inline void _pgd_free(pgd_t *pgd)
{
- free_page((unsigned long)pgd);
+ free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
}
#endif /* CONFIG_X86_PAE */

diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
new file mode 100644
index 000000000000..bce8aea65606
--- /dev/null
+++ b/arch/x86/mm/pti.c
@@ -0,0 +1,387 @@
+/*
+ * Copyright(c) 2017 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * This code is based in part on work published here:
+ *
+ * https://github.com/IAIK/KAISER
+ *
+ * The original work was written by and and signed off by for the Linux
+ * kernel by:
+ *
+ * Signed-off-by: Richard Fellner <richard.fellner@student.tugraz.at>
+ * Signed-off-by: Moritz Lipp <moritz.lipp@iaik.tugraz.at>
+ * Signed-off-by: Daniel Gruss <daniel.gruss@iaik.tugraz.at>
+ * Signed-off-by: Michael Schwarz <michael.schwarz@iaik.tugraz.at>
+ *
+ * Major changes to the original code by: Dave Hansen <dave.hansen@intel.com>
+ * Mostly rewritten by Thomas Gleixner <tglx@linutronix.de> and
+ * Andy Lutomirsky <luto@amacapital.net>
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/bug.h>
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+
+#include <asm/cpufeature.h>
+#include <asm/hypervisor.h>
+#include <asm/vsyscall.h>
+#include <asm/cmdline.h>
+#include <asm/pti.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/desc.h>
+
+#undef pr_fmt
+#define pr_fmt(fmt) "Kernel/User page tables isolation: " fmt
+
+/* Backporting helper */
+#ifndef __GFP_NOTRACK
+#define __GFP_NOTRACK 0
+#endif
+
+static void __init pti_print_if_insecure(const char *reason)
+{
+ if (boot_cpu_has_bug(X86_BUG_CPU_INSECURE))
+ pr_info("%s\n", reason);
+}
+
+static void __init pti_print_if_secure(const char *reason)
+{
+ if (!boot_cpu_has_bug(X86_BUG_CPU_INSECURE))
+ pr_info("%s\n", reason);
+}
+
+void __init pti_check_boottime_disable(void)
+{
+ char arg[5];
+ int ret;
+
+ if (hypervisor_is_type(X86_HYPER_XEN_PV)) {
+ pti_print_if_insecure("disabled on XEN PV.");
+ return;
+ }
+
+ ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg));
+ if (ret > 0) {
+ if (ret == 3 && !strncmp(arg, "off", 3)) {
+ pti_print_if_insecure("disabled on command line.");
+ return;
+ }
+ if (ret == 2 && !strncmp(arg, "on", 2)) {
+ pti_print_if_secure("force enabled on command line.");
+ goto enable;
+ }
+ if (ret == 4 && !strncmp(arg, "auto", 4))
+ goto autosel;
+ }
+
+ if (cmdline_find_option_bool(boot_command_line, "nopti")) {
+ pti_print_if_insecure("disabled on command line.");
+ return;
+ }
+
+autosel:
+ if (!boot_cpu_has_bug(X86_BUG_CPU_INSECURE))
+ return;
+enable:
+ setup_force_cpu_cap(X86_FEATURE_PTI);
+}
+
+pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ /*
+ * Changes to the high (kernel) portion of the kernelmode page
+ * tables are not automatically propagated to the usermode tables.
+ *
+ * Users should keep in mind that, unlike the kernelmode tables,
+ * there is no vmalloc_fault equivalent for the usermode tables.
+ * Top-level entries added to init_mm's usermode pgd after boot
+ * will not be automatically propagated to other mms.
+ */
+ if (!pgdp_maps_userspace(pgdp))
+ return pgd;
+
+ /*
+ * The user page tables get the full PGD, accessible from
+ * userspace:
+ */
+ kernel_to_user_pgdp(pgdp)->pgd = pgd.pgd;
+
+ /*
+ * If this is normal user memory, make it NX in the kernel
+ * pagetables so that, if we somehow screw up and return to
+ * usermode with the kernel CR3 loaded, we'll get a page fault
+ * instead of allowing user code to execute with the wrong CR3.
+ *
+ * As exceptions, we don't set NX if:
+ * - _PAGE_USER is not set. This could be an executable
+ * EFI runtime mapping or something similar, and the kernel
+ * may execute from it
+ * - we don't have NX support
+ * - we're clearing the PGD (i.e. the new pgd is not present).
+ */
+ if ((pgd.pgd & (_PAGE_USER|_PAGE_PRESENT)) == (_PAGE_USER|_PAGE_PRESENT) &&
+ (__supported_pte_mask & _PAGE_NX))
+ pgd.pgd |= _PAGE_NX;
+
+ /* return the copy of the PGD we want the kernel to use: */
+ return pgd;
+}
+
+/*
+ * Walk the user copy of the page tables (optionally) trying to allocate
+ * page table pages on the way down.
+ *
+ * Returns a pointer to a P4D on success, or NULL on failure.
+ */
+static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
+{
+ pgd_t *pgd = kernel_to_user_pgdp(pgd_offset_k(address));
+ gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+
+ if (address < PAGE_OFFSET) {
+ WARN_ONCE(1, "attempt to walk user address\n");
+ return NULL;
+ }
+
+ if (pgd_none(*pgd)) {
+ unsigned long new_p4d_page = __get_free_page(gfp);
+ if (!new_p4d_page)
+ return NULL;
+
+ if (pgd_none(*pgd)) {
+ set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page)));
+ new_p4d_page = 0;
+ }
+ if (new_p4d_page)
+ free_page(new_p4d_page);
+ }
+ BUILD_BUG_ON(pgd_large(*pgd) != 0);
+
+ return p4d_offset(pgd, address);
+}
+
+/*
+ * Walk the user copy of the page tables (optionally) trying to allocate
+ * page table pages on the way down.
+ *
+ * Returns a pointer to a PMD on success, or NULL on failure.
+ */
+static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
+{
+ gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+ p4d_t *p4d = pti_user_pagetable_walk_p4d(address);
+ pud_t *pud;
+
+ BUILD_BUG_ON(p4d_large(*p4d) != 0);
+ if (p4d_none(*p4d)) {
+ unsigned long new_pud_page = __get_free_page(gfp);
+ if (!new_pud_page)
+ return NULL;
+
+ if (p4d_none(*p4d)) {
+ set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page)));
+ new_pud_page = 0;
+ }
+ if (new_pud_page)
+ free_page(new_pud_page);
+ }
+
+ pud = pud_offset(p4d, address);
+ /* The user page tables do not use large mappings: */
+ if (pud_large(*pud)) {
+ WARN_ON(1);
+ return NULL;
+ }
+ if (pud_none(*pud)) {
+ unsigned long new_pmd_page = __get_free_page(gfp);
+ if (!new_pmd_page)
+ return NULL;
+
+ if (pud_none(*pud)) {
+ set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
+ new_pmd_page = 0;
+ }
+ if (new_pmd_page)
+ free_page(new_pmd_page);
+ }
+
+ return pmd_offset(pud, address);
+}
+
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
+/*
+ * Walk the shadow copy of the page tables (optionally) trying to allocate
+ * page table pages on the way down. Does not support large pages.
+ *
+ * Note: this is only used when mapping *new* kernel data into the
+ * user/shadow page tables. It is never used for userspace data.
+ *
+ * Returns a pointer to a PTE on success, or NULL on failure.
+ */
+static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address)
+{
+ gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+ pmd_t *pmd = pti_user_pagetable_walk_pmd(address);
+ pte_t *pte;
+
+ /* We can't do anything sensible if we hit a large mapping. */
+ if (pmd_large(*pmd)) {
+ WARN_ON(1);
+ return NULL;
+ }
+
+ if (pmd_none(*pmd)) {
+ unsigned long new_pte_page = __get_free_page(gfp);
+ if (!new_pte_page)
+ return NULL;
+
+ if (pmd_none(*pmd)) {
+ set_pmd(pmd, __pmd(_KERNPG_TABLE | __pa(new_pte_page)));
+ new_pte_page = 0;
+ }
+ if (new_pte_page)
+ free_page(new_pte_page);
+ }
+
+ pte = pte_offset_kernel(pmd, address);
+ if (pte_flags(*pte) & _PAGE_USER) {
+ WARN_ONCE(1, "attempt to walk to user pte\n");
+ return NULL;
+ }
+ return pte;
+}
+
+static void __init pti_setup_vsyscall(void)
+{
+ pte_t *pte, *target_pte;
+ unsigned int level;
+
+ pte = lookup_address(VSYSCALL_ADDR, &level);
+ if (!pte || WARN_ON(level != PG_LEVEL_4K) || pte_none(*pte))
+ return;
+
+ target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR);
+ if (WARN_ON(!target_pte))
+ return;
+
+ *target_pte = *pte;
+ set_vsyscall_pgtable_user_bits(kernel_to_user_pgdp(swapper_pg_dir));
+}
+#else
+static void __init pti_setup_vsyscall(void) { }
+#endif
+
+static void __init
+pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear)
+{
+ unsigned long addr;
+
+ /*
+ * Clone the populated PMDs which cover start to end. These PMD areas
+ * can have holes.
+ */
+ for (addr = start; addr < end; addr += PMD_SIZE) {
+ pmd_t *pmd, *target_pmd;
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+
+ pgd = pgd_offset_k(addr);
+ if (WARN_ON(pgd_none(*pgd)))
+ return;
+ p4d = p4d_offset(pgd, addr);
+ if (WARN_ON(p4d_none(*p4d)))
+ return;
+ pud = pud_offset(p4d, addr);
+ if (pud_none(*pud))
+ continue;
+ pmd = pmd_offset(pud, addr);
+ if (pmd_none(*pmd))
+ continue;
+
+ target_pmd = pti_user_pagetable_walk_pmd(addr);
+ if (WARN_ON(!target_pmd))
+ return;
+
+ /*
+ * Copy the PMD. That is, the kernelmode and usermode
+ * tables will share the last-level page tables of this
+ * address range
+ */
+ *target_pmd = pmd_clear_flags(*pmd, clear);
+ }
+}
+
+/*
+ * Clone a single p4d (i.e. a top-level entry on 4-level systems and a
+ * next-level entry on 5-level systems.
+ */
+static void __init pti_clone_p4d(unsigned long addr)
+{
+ p4d_t *kernel_p4d, *user_p4d;
+ pgd_t *kernel_pgd;
+
+ user_p4d = pti_user_pagetable_walk_p4d(addr);
+ kernel_pgd = pgd_offset_k(addr);
+ kernel_p4d = p4d_offset(kernel_pgd, addr);
+ *user_p4d = *kernel_p4d;
+}
+
+/*
+ * Clone the CPU_ENTRY_AREA into the user space visible page table.
+ */
+static void __init pti_clone_user_shared(void)
+{
+ pti_clone_p4d(CPU_ENTRY_AREA_BASE);
+}
+
+/*
+ * Clone the ESPFIX P4D into the user space visinble page table
+ */
+static void __init pti_setup_espfix64(void)
+{
+#ifdef CONFIG_X86_ESPFIX64
+ pti_clone_p4d(ESPFIX_BASE_ADDR);
+#endif
+}
+
+/*
+ * Clone the populated PMDs of the entry and irqentry text and force it RO.
+ */
+static void __init pti_clone_entry_text(void)
+{
+ pti_clone_pmds((unsigned long) __entry_text_start,
+ (unsigned long) __irqentry_text_end, _PAGE_RW);
+}
+
+/*
+ * Initialize kernel page table isolation
+ */
+void __init pti_init(void)
+{
+ if (!static_cpu_has(X86_FEATURE_PTI))
+ return;
+
+ pr_info("enabled\n");
+
+ pti_clone_user_shared();
+ pti_clone_entry_text();
+ pti_setup_espfix64();
+ pti_setup_vsyscall();
+}
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 0a1be3adc97e..a1561957dccb 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -28,6 +28,38 @@
* Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
*/

+/*
+ * We get here when we do something requiring a TLB invalidation
+ * but could not go invalidate all of the contexts. We do the
+ * necessary invalidation by clearing out the 'ctx_id' which
+ * forces a TLB flush when the context is loaded.
+ */
+void clear_asid_other(void)
+{
+ u16 asid;
+
+ /*
+ * This is only expected to be set if we have disabled
+ * kernel _PAGE_GLOBAL pages.
+ */
+ if (!static_cpu_has(X86_FEATURE_PTI)) {
+ WARN_ON_ONCE(1);
+ return;
+ }
+
+ for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) {
+ /* Do not need to flush the current asid */
+ if (asid == this_cpu_read(cpu_tlbstate.loaded_mm_asid))
+ continue;
+ /*
+ * Make sure the next time we go to switch to
+ * this asid, we do a flush:
+ */
+ this_cpu_write(cpu_tlbstate.ctxs[asid].ctx_id, 0);
+ }
+ this_cpu_write(cpu_tlbstate.invalidate_other, false);
+}
+
atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);


@@ -42,6 +74,9 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
return;
}

+ if (this_cpu_read(cpu_tlbstate.invalidate_other))
+ clear_asid_other();
+
for (asid = 0; asid < TLB_NR_DYN_ASIDS; asid++) {
if (this_cpu_read(cpu_tlbstate.ctxs[asid].ctx_id) !=
next->context.ctx_id)
@@ -65,6 +100,25 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
*need_flush = true;
}

+static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, bool need_flush)
+{
+ unsigned long new_mm_cr3;
+
+ if (need_flush) {
+ invalidate_user_asid(new_asid);
+ new_mm_cr3 = build_cr3(pgdir, new_asid);
+ } else {
+ new_mm_cr3 = build_cr3_noflush(pgdir, new_asid);
+ }
+
+ /*
+ * Caution: many callers of this function expect
+ * that load_cr3() is serializing and orders TLB
+ * fills with respect to the mm_cpumask writes.
+ */
+ write_cr3(new_mm_cr3);
+}
+
void leave_mm(int cpu)
{
struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
@@ -195,7 +249,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
if (need_flush) {
this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
- write_cr3(build_cr3(next->pgd, new_asid));
+ load_new_mm_cr3(next->pgd, new_asid, true);

/*
* NB: This gets called via leave_mm() in the idle path
@@ -208,7 +262,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
} else {
/* The new ASID is already up to date. */
- write_cr3(build_cr3_noflush(next->pgd, new_asid));
+ load_new_mm_cr3(next->pgd, new_asid, false);

/* See above wrt _rcuidle. */
trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 20fb31579b69..39c4b35ac7a4 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -195,6 +195,9 @@ static pgd_t *efi_pgd;
* because we want to avoid inserting EFI region mappings (EFI_VA_END
* to EFI_VA_START) into the standard kernel page tables. Everything
* else can be shared, see efi_sync_low_kernel_mappings().
+ *
+ * We don't want the pgd on the pgd_list and cannot use pgd_alloc() for the
+ * allocation.
*/
int __init efi_alloc_page_tables(void)
{
@@ -207,7 +210,7 @@ int __init efi_alloc_page_tables(void)
return 0;

gfp_mask = GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO;
- efi_pgd = (pgd_t *)__get_free_page(gfp_mask);
+ efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER);
if (!efi_pgd)
return -ENOMEM;

diff --git a/block/blk-map.c b/block/blk-map.c
index d5251edcc0dd..368daa02714e 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -12,22 +12,29 @@
#include "blk.h"

/*
- * Append a bio to a passthrough request. Only works can be merged into
- * the request based on the driver constraints.
+ * Append a bio to a passthrough request. Only works if the bio can be merged
+ * into the request based on the driver constraints.
*/
-int blk_rq_append_bio(struct request *rq, struct bio *bio)
+int blk_rq_append_bio(struct request *rq, struct bio **bio)
{
- blk_queue_bounce(rq->q, &bio);
+ struct bio *orig_bio = *bio;
+
+ blk_queue_bounce(rq->q, bio);

if (!rq->bio) {
- blk_rq_bio_prep(rq->q, rq, bio);
+ blk_rq_bio_prep(rq->q, rq, *bio);
} else {
- if (!ll_back_merge_fn(rq->q, rq, bio))
+ if (!ll_back_merge_fn(rq->q, rq, *bio)) {
+ if (orig_bio != *bio) {
+ bio_put(*bio);
+ *bio = orig_bio;
+ }
return -EINVAL;
+ }

- rq->biotail->bi_next = bio;
- rq->biotail = bio;
- rq->__data_len += bio->bi_iter.bi_size;
+ rq->biotail->bi_next = *bio;
+ rq->biotail = *bio;
+ rq->__data_len += (*bio)->bi_iter.bi_size;
}

return 0;
@@ -80,14 +87,12 @@ static int __blk_rq_map_user_iov(struct request *rq,
* We link the bounce buffer in and could have to traverse it
* later so we have to get a ref to prevent it from being freed
*/
- ret = blk_rq_append_bio(rq, bio);
- bio_get(bio);
+ ret = blk_rq_append_bio(rq, &bio);
if (ret) {
- bio_endio(bio);
__blk_rq_unmap_user(orig_bio);
- bio_put(bio);
return ret;
}
+ bio_get(bio);

return 0;
}
@@ -220,7 +225,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
int reading = rq_data_dir(rq) == READ;
unsigned long addr = (unsigned long) kbuf;
int do_copy = 0;
- struct bio *bio;
+ struct bio *bio, *orig_bio;
int ret;

if (len > (queue_max_hw_sectors(q) << 9))
@@ -243,10 +248,11 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf,
if (do_copy)
rq->rq_flags |= RQF_COPY_USER;

- ret = blk_rq_append_bio(rq, bio);
+ orig_bio = bio;
+ ret = blk_rq_append_bio(rq, &bio);
if (unlikely(ret)) {
/* request is too big */
- bio_put(bio);
+ bio_put(orig_bio);
return ret;
}

diff --git a/block/bounce.c b/block/bounce.c
index fceb1a96480b..1d05c422c932 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -200,6 +200,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
unsigned i = 0;
bool bounce = false;
int sectors = 0;
+ bool passthrough = bio_is_passthrough(*bio_orig);

bio_for_each_segment(from, *bio_orig, iter) {
if (i++ < BIO_MAX_PAGES)
@@ -210,13 +211,14 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
if (!bounce)
return;

- if (sectors < bio_sectors(*bio_orig)) {
+ if (!passthrough && sectors < bio_sectors(*bio_orig)) {
bio = bio_split(*bio_orig, sectors, GFP_NOIO, bounce_bio_split);
bio_chain(bio, *bio_orig);
generic_make_request(*bio_orig);
*bio_orig = bio;
}
- bio = bio_clone_bioset(*bio_orig, GFP_NOIO, bounce_bio_set);
+ bio = bio_clone_bioset(*bio_orig, GFP_NOIO, passthrough ? NULL :
+ bounce_bio_set);

bio_for_each_segment_all(to, bio, i) {
struct page *page = to->bv_page;
diff --git a/drivers/android/binder.c b/drivers/android/binder.c
index 88b4bbe58100..a340766b51fe 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -482,7 +482,8 @@ enum binder_deferred_state {
* @tsk task_struct for group_leader of process
* (invariant after initialized)
* @files files_struct for process
- * (invariant after initialized)
+ * (protected by @files_lock)
+ * @files_lock mutex to protect @files
* @deferred_work_node: element for binder_deferred_list
* (protected by binder_deferred_lock)
* @deferred_work: bitmap of deferred work to perform
@@ -530,6 +531,7 @@ struct binder_proc {
int pid;
struct task_struct *tsk;
struct files_struct *files;
+ struct mutex files_lock;
struct hlist_node deferred_work_node;
int deferred_work;
bool is_dead;
@@ -877,20 +879,26 @@ static void binder_inc_node_tmpref_ilocked(struct binder_node *node);

static int task_get_unused_fd_flags(struct binder_proc *proc, int flags)
{
- struct files_struct *files = proc->files;
unsigned long rlim_cur;
unsigned long irqs;
+ int ret;

- if (files == NULL)
- return -ESRCH;
-
- if (!lock_task_sighand(proc->tsk, &irqs))
- return -EMFILE;
-
+ mutex_lock(&proc->files_lock);
+ if (proc->files == NULL) {
+ ret = -ESRCH;
+ goto err;
+ }
+ if (!lock_task_sighand(proc->tsk, &irqs)) {
+ ret = -EMFILE;
+ goto err;
+ }
rlim_cur = task_rlimit(proc->tsk, RLIMIT_NOFILE);
unlock_task_sighand(proc->tsk, &irqs);

- return __alloc_fd(files, 0, rlim_cur, flags);
+ ret = __alloc_fd(proc->files, 0, rlim_cur, flags);
+err:
+ mutex_unlock(&proc->files_lock);
+ return ret;
}

/*
@@ -899,8 +907,10 @@ static int task_get_unused_fd_flags(struct binder_proc *proc, int flags)
static void task_fd_install(
struct binder_proc *proc, unsigned int fd, struct file *file)
{
+ mutex_lock(&proc->files_lock);
if (proc->files)
__fd_install(proc->files, fd, file);
+ mutex_unlock(&proc->files_lock);
}

/*
@@ -910,9 +920,11 @@ static long task_close_fd(struct binder_proc *proc, unsigned int fd)
{
int retval;

- if (proc->files == NULL)
- return -ESRCH;
-
+ mutex_lock(&proc->files_lock);
+ if (proc->files == NULL) {
+ retval = -ESRCH;
+ goto err;
+ }
retval = __close_fd(proc->files, fd);
/* can't restart close syscall because file table entry was cleared */
if (unlikely(retval == -ERESTARTSYS ||
@@ -920,7 +932,8 @@ static long task_close_fd(struct binder_proc *proc, unsigned int fd)
retval == -ERESTARTNOHAND ||
retval == -ERESTART_RESTARTBLOCK))
retval = -EINTR;
-
+err:
+ mutex_unlock(&proc->files_lock);
return retval;
}

@@ -4627,7 +4640,9 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma)
ret = binder_alloc_mmap_handler(&proc->alloc, vma);
if (ret)
return ret;
+ mutex_lock(&proc->files_lock);
proc->files = get_files_struct(current);
+ mutex_unlock(&proc->files_lock);
return 0;

err_bad_arg:
@@ -4651,6 +4666,7 @@ static int binder_open(struct inode *nodp, struct file *filp)
spin_lock_init(&proc->outer_lock);
get_task_struct(current->group_leader);
proc->tsk = current->group_leader;
+ mutex_init(&proc->files_lock);
INIT_LIST_HEAD(&proc->todo);
proc->default_priority = task_nice(current);
binder_dev = container_of(filp->private_data, struct binder_device,
@@ -4903,9 +4919,11 @@ static void binder_deferred_func(struct work_struct *work)

files = NULL;
if (defer & BINDER_DEFERRED_PUT_FILES) {
+ mutex_lock(&proc->files_lock);
files = proc->files;
if (files)
proc->files = NULL;
+ mutex_unlock(&proc->files_lock);
}

if (defer & BINDER_DEFERRED_FLUSH)
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
index eb3af2739537..07532d83be0b 100644
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -186,6 +186,11 @@ static void cache_associativity(struct cacheinfo *this_leaf)
this_leaf->ways_of_associativity = (size / nr_sets) / line_size;
}

+static bool cache_node_is_unified(struct cacheinfo *this_leaf)
+{
+ return of_property_read_bool(this_leaf->of_node, "cache-unified");
+}
+
static void cache_of_override_properties(unsigned int cpu)
{
int index;
@@ -194,6 +199,14 @@ static void cache_of_override_properties(unsigned int cpu)

for (index = 0; index < cache_leaves(cpu); index++) {
this_leaf = this_cpu_ci->info_list + index;
+ /*
+ * init_cache_level must setup the cache level correctly
+ * overriding the architecturally specified levels, so
+ * if type is NONE at this stage, it should be unified
+ */
+ if (this_leaf->type == CACHE_TYPE_NOCACHE &&
+ cache_node_is_unified(this_leaf))
+ this_leaf->type = CACHE_TYPE_UNIFIED;
cache_size(this_leaf);
cache_get_line_size(this_leaf);
cache_nr_sets(this_leaf);
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index eb4528c87c0b..d6f3d9ee1350 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -1074,7 +1074,7 @@ void acpi_gpiochip_add(struct gpio_chip *chip)
}

if (!chip->names)
- devprop_gpiochip_set_names(chip);
+ devprop_gpiochip_set_names(chip, dev_fwnode(chip->parent));

acpi_gpiochip_request_regions(acpi_gpio);
acpi_gpiochip_scan_gpios(acpi_gpio);
diff --git a/drivers/gpio/gpiolib-devprop.c b/drivers/gpio/gpiolib-devprop.c
index 27f383bda7d9..f748aa3e77f7 100644
--- a/drivers/gpio/gpiolib-devprop.c
+++ b/drivers/gpio/gpiolib-devprop.c
@@ -19,30 +19,27 @@
/**
* devprop_gpiochip_set_names - Set GPIO line names using device properties
* @chip: GPIO chip whose lines should be named, if possible
+ * @fwnode: Property Node containing the gpio-line-names property
*
* Looks for device property "gpio-line-names" and if it exists assigns
* GPIO line names for the chip. The memory allocated for the assigned
* names belong to the underlying firmware node and should not be released
* by the caller.
*/
-void devprop_gpiochip_set_names(struct gpio_chip *chip)
+void devprop_gpiochip_set_names(struct gpio_chip *chip,
+ const struct fwnode_handle *fwnode)
{
struct gpio_device *gdev = chip->gpiodev;
const char **names;
int ret, i;

- if (!chip->parent) {
- dev_warn(&gdev->dev, "GPIO chip parent is NULL\n");
- return;
- }
-
- ret = device_property_read_string_array(chip->parent, "gpio-line-names",
+ ret = fwnode_property_read_string_array(fwnode, "gpio-line-names",
NULL, 0);
if (ret < 0)
return;

if (ret != gdev->ngpio) {
- dev_warn(chip->parent,
+ dev_warn(&gdev->dev,
"names %d do not match number of GPIOs %d\n", ret,
gdev->ngpio);
return;
@@ -52,10 +49,10 @@ void devprop_gpiochip_set_names(struct gpio_chip *chip)
if (!names)
return;

- ret = device_property_read_string_array(chip->parent, "gpio-line-names",
+ ret = fwnode_property_read_string_array(fwnode, "gpio-line-names",
names, gdev->ngpio);
if (ret < 0) {
- dev_warn(chip->parent, "failed to read GPIO line names\n");
+ dev_warn(&gdev->dev, "failed to read GPIO line names\n");
kfree(names);
return;
}
diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index bfcd20699ec8..ba38f530e403 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -493,7 +493,8 @@ int of_gpiochip_add(struct gpio_chip *chip)

/* If the chip defines names itself, these take precedence */
if (!chip->names)
- devprop_gpiochip_set_names(chip);
+ devprop_gpiochip_set_names(chip,
+ of_fwnode_handle(chip->of_node));

of_node_get(chip->of_node);

diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h
index d003ccb12781..3d4d0634c9dd 100644
--- a/drivers/gpio/gpiolib.h
+++ b/drivers/gpio/gpiolib.h
@@ -224,7 +224,8 @@ static inline int gpio_chip_hwgpio(const struct gpio_desc *desc)
return desc - &desc->gdev->descs[0];
}

-void devprop_gpiochip_set_names(struct gpio_chip *chip);
+void devprop_gpiochip_set_names(struct gpio_chip *chip,
+ const struct fwnode_handle *fwnode);

/* With descriptor prefix */

diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c
index feafdb961c48..59b2f96d986a 100644
--- a/drivers/infiniband/core/security.c
+++ b/drivers/infiniband/core/security.c
@@ -386,6 +386,9 @@ int ib_open_shared_qp_security(struct ib_qp *qp, struct ib_device *dev)
if (ret)
return ret;

+ if (!qp->qp_sec)
+ return 0;
+
mutex_lock(&real_qp->qp_sec->mutex);
ret = check_qp_port_pkey_settings(real_qp->qp_sec->ports_pkeys,
qp->qp_sec);
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index d8f540054392..93c1a57dbff1 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -2085,8 +2085,8 @@ int ib_uverbs_ex_modify_qp(struct ib_uverbs_file *file,
return -EOPNOTSUPP;

if (ucore->inlen > sizeof(cmd)) {
- if (ib_is_udata_cleared(ucore, sizeof(cmd),
- ucore->inlen - sizeof(cmd)))
+ if (!ib_is_udata_cleared(ucore, sizeof(cmd),
+ ucore->inlen - sizeof(cmd)))
return -EOPNOTSUPP;
}

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index de57d6c11a25..9032f77cc38d 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/drivers/infiniband/core/verbs.c
@@ -1400,7 +1400,8 @@ int ib_close_qp(struct ib_qp *qp)
spin_unlock_irqrestore(&real_qp->device->event_handler_lock, flags);

atomic_dec(&real_qp->usecnt);
- ib_close_shared_qp_security(qp->qp_sec);
+ if (qp->qp_sec)
+ ib_close_shared_qp_security(qp->qp_sec);
kfree(qp);

return 0;
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index eae8ea81c6e2..514c1000ded1 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -586,10 +586,10 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe,
ret = -EAGAIN;
goto skip_cqe;
}
- if (unlikely((CQE_WRID_MSN(hw_cqe) != (wq->rq.msn)))) {
+ if (unlikely(!CQE_STATUS(hw_cqe) &&
+ CQE_WRID_MSN(hw_cqe) != wq->rq.msn)) {
t4_set_wq_in_error(wq);
- hw_cqe->header |= htonl(CQE_STATUS_V(T4_ERR_MSN));
- goto proc_cqe;
+ hw_cqe->header |= cpu_to_be32(CQE_STATUS_V(T4_ERR_MSN));
}
goto proc_cqe;
}
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 6ff44dc606eb..3409eee16092 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1129,7 +1129,6 @@ struct hfi1_devdata {
u16 pcie_lnkctl;
u16 pcie_devctl2;
u32 pci_msix0;
- u32 pci_lnkctl3;
u32 pci_tph2;

/*
diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 09e50fd2a08f..8c7e7a60b715 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -411,15 +411,12 @@ int restore_pci_variables(struct hfi1_devdata *dd)
if (ret)
goto error;

- ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_SPCIE1,
- dd->pci_lnkctl3);
- if (ret)
- goto error;
-
- ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_TPH2, dd->pci_tph2);
- if (ret)
- goto error;
-
+ if (pci_find_ext_capability(dd->pcidev, PCI_EXT_CAP_ID_TPH)) {
+ ret = pci_write_config_dword(dd->pcidev, PCIE_CFG_TPH2,
+ dd->pci_tph2);
+ if (ret)
+ goto error;
+ }
return 0;

error:
@@ -469,15 +466,12 @@ int save_pci_variables(struct hfi1_devdata *dd)
if (ret)
goto error;

- ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_SPCIE1,
- &dd->pci_lnkctl3);
- if (ret)
- goto error;
-
- ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_TPH2, &dd->pci_tph2);
- if (ret)
- goto error;
-
+ if (pci_find_ext_capability(dd->pcidev, PCI_EXT_CAP_ID_TPH)) {
+ ret = pci_read_config_dword(dd->pcidev, PCIE_CFG_TPH2,
+ &dd->pci_tph2);
+ if (ret)
+ goto error;
+ }
return 0;

error:
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 5aff1e33d984..30d479f87cb8 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1415,6 +1415,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
}

INIT_LIST_HEAD(&context->vma_private_list);
+ mutex_init(&context->vma_private_list_mutex);
INIT_LIST_HEAD(&context->db_page_list);
mutex_init(&context->db_page_mutex);

@@ -1576,7 +1577,9 @@ static void mlx5_ib_vma_close(struct vm_area_struct *area)
* mlx5_ib_disassociate_ucontext().
*/
mlx5_ib_vma_priv_data->vma = NULL;
+ mutex_lock(mlx5_ib_vma_priv_data->vma_private_list_mutex);
list_del(&mlx5_ib_vma_priv_data->list);
+ mutex_unlock(mlx5_ib_vma_priv_data->vma_private_list_mutex);
kfree(mlx5_ib_vma_priv_data);
}

@@ -1596,10 +1599,13 @@ static int mlx5_ib_set_vma_data(struct vm_area_struct *vma,
return -ENOMEM;

vma_prv->vma = vma;
+ vma_prv->vma_private_list_mutex = &ctx->vma_private_list_mutex;
vma->vm_private_data = vma_prv;
vma->vm_ops = &mlx5_ib_vm_ops;

+ mutex_lock(&ctx->vma_private_list_mutex);
list_add(&vma_prv->list, vma_head);
+ mutex_unlock(&ctx->vma_private_list_mutex);

return 0;
}
@@ -1642,6 +1648,7 @@ static void mlx5_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
* mlx5_ib_vma_close.
*/
down_write(&owning_mm->mmap_sem);
+ mutex_lock(&context->vma_private_list_mutex);
list_for_each_entry_safe(vma_private, n, &context->vma_private_list,
list) {
vma = vma_private->vma;
@@ -1656,6 +1663,7 @@ static void mlx5_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
list_del(&vma_private->list);
kfree(vma_private);
}
+ mutex_unlock(&context->vma_private_list_mutex);
up_write(&owning_mm->mmap_sem);
mmput(owning_mm);
put_task_struct(owning_process);
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 189e80cd6b2f..754103372faa 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -115,6 +115,8 @@ enum {
struct mlx5_ib_vma_private_data {
struct list_head list;
struct vm_area_struct *vma;
+ /* protect vma_private_list add/del */
+ struct mutex *vma_private_list_mutex;
};

struct mlx5_ib_ucontext {
@@ -129,6 +131,8 @@ struct mlx5_ib_ucontext {
/* Transport Domain number */
u32 tdn;
struct list_head vma_private_list;
+ /* protect vma_private_list add/del */
+ struct mutex vma_private_list_mutex;

unsigned long upd_xlt_page;
/* protect ODP/KSM */
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index d7b53d53c116..72d6ffbfd638 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -167,7 +167,7 @@ static void bcm_sf2_gphy_enable_set(struct dsa_switch *ds, bool enable)
reg = reg_readl(priv, REG_SPHY_CNTRL);
if (enable) {
reg |= PHY_RESET;
- reg &= ~(EXT_PWR_DOWN | IDDQ_BIAS | CK25_DIS);
+ reg &= ~(EXT_PWR_DOWN | IDDQ_BIAS | IDDQ_GLOBAL_PWR | CK25_DIS);
reg_writel(priv, reg, REG_SPHY_CNTRL);
udelay(21);
reg = reg_readl(priv, REG_SPHY_CNTRL);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index dc5de275352a..aa764c5e3c6b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1875,7 +1875,7 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
* here forever if we consistently cannot allocate
* buffers.
*/
- else if (rc == -ENOMEM)
+ else if (rc == -ENOMEM && budget)
rx_pkts++;
else if (rc == -EBUSY) /* partial completion */
break;
@@ -1961,7 +1961,7 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget)
cpu_to_le32(RX_CMPL_ERRORS_CRC_ERROR);

rc = bnxt_rx_pkt(bp, bnapi, &raw_cons, &event);
- if (likely(rc == -EIO))
+ if (likely(rc == -EIO) && budget)
rx_pkts++;
else if (rc == -EBUSY) /* partial completion */
break;
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 656e6af70f0a..aef3fcf2f5b9 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -14227,7 +14227,9 @@ static int tg3_change_mtu(struct net_device *dev, int new_mtu)
/* Reset PHY, otherwise the read DMA engine will be in a mode that
* breaks all requests to 256 bytes.
*/
- if (tg3_asic_rev(tp) == ASIC_REV_57766)
+ if (tg3_asic_rev(tp) == ASIC_REV_57766 ||
+ tg3_asic_rev(tp) == ASIC_REV_5717 ||
+ tg3_asic_rev(tp) == ASIC_REV_5719)
reset_phy = true;

err = tg3_restart_hw(tp, reset_phy);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 3dc2d771a222..faf7cdc97ebf 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -818,6 +818,12 @@ static void fec_enet_bd_init(struct net_device *dev)
for (i = 0; i < txq->bd.ring_size; i++) {
/* Initialize the BD for every fragment in the page. */
bdp->cbd_sc = cpu_to_fec16(0);
+ if (bdp->cbd_bufaddr &&
+ !IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
+ dma_unmap_single(&fep->pdev->dev,
+ fec32_to_cpu(bdp->cbd_bufaddr),
+ fec16_to_cpu(bdp->cbd_datlen),
+ DMA_TO_DEVICE);
if (txq->tx_skbuff[i]) {
dev_kfree_skb_any(txq->tx_skbuff[i]);
txq->tx_skbuff[i] = NULL;
diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c
index c9798210fa0f..0495487f7b42 100644
--- a/drivers/net/ethernet/marvell/mvmdio.c
+++ b/drivers/net/ethernet/marvell/mvmdio.c
@@ -344,7 +344,8 @@ static int orion_mdio_probe(struct platform_device *pdev)
dev->regs + MVMDIO_ERR_INT_MASK);

} else if (dev->err_interrupt == -EPROBE_DEFER) {
- return -EPROBE_DEFER;
+ ret = -EPROBE_DEFER;
+ goto out_mdio;
}

if (pdev->dev.of_node)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 1fffdebbc9e8..e9a1fbcc4adf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -362,7 +362,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
case MLX5_CMD_OP_QUERY_VPORT_COUNTER:
case MLX5_CMD_OP_ALLOC_Q_COUNTER:
case MLX5_CMD_OP_QUERY_Q_COUNTER:
- case MLX5_CMD_OP_SET_RATE_LIMIT:
+ case MLX5_CMD_OP_SET_PP_RATE_LIMIT:
case MLX5_CMD_OP_QUERY_RATE_LIMIT:
case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT:
case MLX5_CMD_OP_QUERY_SCHEDULING_ELEMENT:
@@ -505,7 +505,7 @@ const char *mlx5_command_str(int command)
MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER);
MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER);
MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER);
- MLX5_COMMAND_STR_CASE(SET_RATE_LIMIT);
+ MLX5_COMMAND_STR_CASE(SET_PP_RATE_LIMIT);
MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT);
MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT);
MLX5_COMMAND_STR_CASE(DESTROY_SCHEDULING_ELEMENT);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 13b5ef9d8703..5fa071620104 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -590,6 +590,7 @@ struct mlx5e_channel {
struct mlx5_core_dev *mdev;
struct mlx5e_tstamp *tstamp;
int ix;
+ int cpu;
};

struct mlx5e_channels {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index cc11bbbd0309..3cdb932cae76 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -71,11 +71,6 @@ struct mlx5e_channel_param {
struct mlx5e_cq_param icosq_cq;
};

-static int mlx5e_get_node(struct mlx5e_priv *priv, int ix)
-{
- return pci_irq_get_node(priv->mdev->pdev, MLX5_EQ_VEC_COMP_BASE + ix);
-}
-
static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
{
return MLX5_CAP_GEN(mdev, striding_rq) &&
@@ -452,17 +447,16 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
int wq_sz = mlx5_wq_ll_get_size(&rq->wq);
int mtt_sz = mlx5e_get_wqe_mtt_sz();
int mtt_alloc = mtt_sz + MLX5_UMR_ALIGN - 1;
- int node = mlx5e_get_node(c->priv, c->ix);
int i;

rq->mpwqe.info = kzalloc_node(wq_sz * sizeof(*rq->mpwqe.info),
- GFP_KERNEL, node);
+ GFP_KERNEL, cpu_to_node(c->cpu));
if (!rq->mpwqe.info)
goto err_out;

/* We allocate more than mtt_sz as we will align the pointer */
- rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz,
- GFP_KERNEL, node);
+ rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz, GFP_KERNEL,
+ cpu_to_node(c->cpu));
if (unlikely(!rq->mpwqe.mtt_no_align))
goto err_free_wqe_info;

@@ -570,7 +564,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
int err;
int i;

- rqp->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+ rqp->wq.db_numa_node = cpu_to_node(c->cpu);

err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->wq,
&rq->wq_ctrl);
@@ -636,8 +630,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
default: /* MLX5_WQ_TYPE_LINKED_LIST */
rq->wqe.frag_info =
kzalloc_node(wq_sz * sizeof(*rq->wqe.frag_info),
- GFP_KERNEL,
- mlx5e_get_node(c->priv, c->ix));
+ GFP_KERNEL, cpu_to_node(c->cpu));
if (!rq->wqe.frag_info) {
err = -ENOMEM;
goto err_rq_wq_destroy;
@@ -1007,13 +1000,13 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
sq->uar_map = mdev->mlx5e_res.bfreg.map;
sq->min_inline_mode = params->tx_min_inline_mode;

- param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+ param->wq.db_numa_node = cpu_to_node(c->cpu);
err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
if (err)
return err;
sq->wq.db = &sq->wq.db[MLX5_SND_DBR];

- err = mlx5e_alloc_xdpsq_db(sq, mlx5e_get_node(c->priv, c->ix));
+ err = mlx5e_alloc_xdpsq_db(sq, cpu_to_node(c->cpu));
if (err)
goto err_sq_wq_destroy;

@@ -1060,13 +1053,13 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
sq->channel = c;
sq->uar_map = mdev->mlx5e_res.bfreg.map;

- param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+ param->wq.db_numa_node = cpu_to_node(c->cpu);
err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
if (err)
return err;
sq->wq.db = &sq->wq.db[MLX5_SND_DBR];

- err = mlx5e_alloc_icosq_db(sq, mlx5e_get_node(c->priv, c->ix));
+ err = mlx5e_alloc_icosq_db(sq, cpu_to_node(c->cpu));
if (err)
goto err_sq_wq_destroy;

@@ -1132,13 +1125,13 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
if (MLX5_IPSEC_DEV(c->priv->mdev))
set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);

- param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+ param->wq.db_numa_node = cpu_to_node(c->cpu);
err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
if (err)
return err;
sq->wq.db = &sq->wq.db[MLX5_SND_DBR];

- err = mlx5e_alloc_txqsq_db(sq, mlx5e_get_node(c->priv, c->ix));
+ err = mlx5e_alloc_txqsq_db(sq, cpu_to_node(c->cpu));
if (err)
goto err_sq_wq_destroy;

@@ -1510,8 +1503,8 @@ static int mlx5e_alloc_cq(struct mlx5e_channel *c,
struct mlx5_core_dev *mdev = c->priv->mdev;
int err;

- param->wq.buf_numa_node = mlx5e_get_node(c->priv, c->ix);
- param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
+ param->wq.buf_numa_node = cpu_to_node(c->cpu);
+ param->wq.db_numa_node = cpu_to_node(c->cpu);
param->eq_ix = c->ix;

err = mlx5e_alloc_cq_common(mdev, param, cq);
@@ -1610,6 +1603,11 @@ static void mlx5e_close_cq(struct mlx5e_cq *cq)
mlx5e_free_cq(cq);
}

+static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
+{
+ return cpumask_first(priv->mdev->priv.irq_info[ix].mask);
+}
+
static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
struct mlx5e_params *params,
struct mlx5e_channel_param *cparam)
@@ -1758,12 +1756,13 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
{
struct mlx5e_cq_moder icocq_moder = {0, 0};
struct net_device *netdev = priv->netdev;
+ int cpu = mlx5e_get_cpu(priv, ix);
struct mlx5e_channel *c;
unsigned int irq;
int err;
int eqn;

- c = kzalloc_node(sizeof(*c), GFP_KERNEL, mlx5e_get_node(priv, ix));
+ c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
if (!c)
return -ENOMEM;

@@ -1771,6 +1770,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
c->mdev = priv->mdev;
c->tstamp = &priv->tstamp;
c->ix = ix;
+ c->cpu = cpu;
c->pdev = &priv->mdev->pdev->dev;
c->netdev = priv->netdev;
c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
@@ -1859,8 +1859,7 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c)
for (tc = 0; tc < c->num_tc; tc++)
mlx5e_activate_txqsq(&c->sq[tc]);
mlx5e_activate_rq(&c->rq);
- netif_set_xps_queue(c->netdev,
- mlx5_get_vector_affinity(c->priv->mdev, c->ix), c->ix);
+ netif_set_xps_queue(c->netdev, get_cpu_mask(c->cpu), c->ix);
}

static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
@@ -3554,6 +3553,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
struct sk_buff *skb,
netdev_features_t features)
{
+ unsigned int offset = 0;
struct udphdr *udph;
u8 proto;
u16 port;
@@ -3563,7 +3563,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
proto = ip_hdr(skb)->protocol;
break;
case htons(ETH_P_IPV6):
- proto = ipv6_hdr(skb)->nexthdr;
+ proto = ipv6_find_hdr(skb, &offset, -1, NULL, NULL);
break;
default:
goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c
index 3c11d6e2160a..14962969c5ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.c
@@ -66,6 +66,9 @@ static int mlx5_fpga_mem_read_i2c(struct mlx5_fpga_device *fdev, size_t size,
u8 actual_size;
int err;

+ if (!size)
+ return -EINVAL;
+
if (!fdev->mdev)
return -ENOTCONN;

@@ -95,6 +98,9 @@ static int mlx5_fpga_mem_write_i2c(struct mlx5_fpga_device *fdev, size_t size,
u8 actual_size;
int err;

+ if (!size)
+ return -EINVAL;
+
if (!fdev->mdev)
return -ENOTCONN;

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 06562c9a6b9c..8bfc37e4ec87 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -316,9 +316,6 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev)
{
struct mlx5_priv *priv = &dev->priv;
struct mlx5_eq_table *table = &priv->eq_table;
- struct irq_affinity irqdesc = {
- .pre_vectors = MLX5_EQ_VEC_COMP_BASE,
- };
int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq);
int nvec;

@@ -332,10 +329,9 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev)
if (!priv->irq_info)
goto err_free_msix;

- nvec = pci_alloc_irq_vectors_affinity(dev->pdev,
+ nvec = pci_alloc_irq_vectors(dev->pdev,
MLX5_EQ_VEC_COMP_BASE + 1, nvec,
- PCI_IRQ_MSIX | PCI_IRQ_AFFINITY,
- &irqdesc);
+ PCI_IRQ_MSIX);
if (nvec < 0)
return nvec;

@@ -621,6 +617,63 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev)
return (u64)timer_l | (u64)timer_h1 << 32;
}

+static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+ struct mlx5_priv *priv = &mdev->priv;
+ int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i);
+
+ if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {
+ mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
+ return -ENOMEM;
+ }
+
+ cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
+ priv->irq_info[i].mask);
+
+ if (IS_ENABLED(CONFIG_SMP) &&
+ irq_set_affinity_hint(irq, priv->irq_info[i].mask))
+ mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
+
+ return 0;
+}
+
+static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+ struct mlx5_priv *priv = &mdev->priv;
+ int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i);
+
+ irq_set_affinity_hint(irq, NULL);
+ free_cpumask_var(priv->irq_info[i].mask);
+}
+
+static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev)
+{
+ int err;
+ int i;
+
+ for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) {
+ err = mlx5_irq_set_affinity_hint(mdev, i);
+ if (err)
+ goto err_out;
+ }
+
+ return 0;
+
+err_out:
+ for (i--; i >= 0; i--)
+ mlx5_irq_clear_affinity_hint(mdev, i);
+
+ return err;
+}
+
+static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev)
+{
+ int i;
+
+ for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++)
+ mlx5_irq_clear_affinity_hint(mdev, i);
+}
+
int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
unsigned int *irqn)
{
@@ -1093,6 +1146,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
goto err_stop_eqs;
}

+ err = mlx5_irq_set_affinity_hints(dev);
+ if (err) {
+ dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n");
+ goto err_affinity_hints;
+ }
+
err = mlx5_init_fs(dev);
if (err) {
dev_err(&pdev->dev, "Failed to init flow steering\n");
@@ -1150,6 +1209,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
mlx5_cleanup_fs(dev);

err_fs:
+ mlx5_irq_clear_affinity_hints(dev);
+
+err_affinity_hints:
free_comp_eqs(dev);

err_stop_eqs:
@@ -1218,6 +1280,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,

mlx5_sriov_detach(dev);
mlx5_cleanup_fs(dev);
+ mlx5_irq_clear_affinity_hints(dev);
free_comp_eqs(dev);
mlx5_stop_eqs(dev);
mlx5_put_uars_page(dev, priv->uar);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index db9e665ab104..889130edb715 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -213,8 +213,8 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev,
err_cmd:
memset(din, 0, sizeof(din));
memset(dout, 0, sizeof(dout));
- MLX5_SET(destroy_qp_in, in, opcode, MLX5_CMD_OP_DESTROY_QP);
- MLX5_SET(destroy_qp_in, in, qpn, qp->qpn);
+ MLX5_SET(destroy_qp_in, din, opcode, MLX5_CMD_OP_DESTROY_QP);
+ MLX5_SET(destroy_qp_in, din, qpn, qp->qpn);
mlx5_cmd_exec(dev, din, sizeof(din), dout, sizeof(dout));
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rl.c b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
index e651e4c02867..d3c33e9eea72 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
@@ -125,16 +125,16 @@ static struct mlx5_rl_entry *find_rl_entry(struct mlx5_rl_table *table,
return ret_entry;
}

-static int mlx5_set_rate_limit_cmd(struct mlx5_core_dev *dev,
+static int mlx5_set_pp_rate_limit_cmd(struct mlx5_core_dev *dev,
u32 rate, u16 index)
{
- u32 in[MLX5_ST_SZ_DW(set_rate_limit_in)] = {0};
- u32 out[MLX5_ST_SZ_DW(set_rate_limit_out)] = {0};
+ u32 in[MLX5_ST_SZ_DW(set_pp_rate_limit_in)] = {0};
+ u32 out[MLX5_ST_SZ_DW(set_pp_rate_limit_out)] = {0};

- MLX5_SET(set_rate_limit_in, in, opcode,
- MLX5_CMD_OP_SET_RATE_LIMIT);
- MLX5_SET(set_rate_limit_in, in, rate_limit_index, index);
- MLX5_SET(set_rate_limit_in, in, rate_limit, rate);
+ MLX5_SET(set_pp_rate_limit_in, in, opcode,
+ MLX5_CMD_OP_SET_PP_RATE_LIMIT);
+ MLX5_SET(set_pp_rate_limit_in, in, rate_limit_index, index);
+ MLX5_SET(set_pp_rate_limit_in, in, rate_limit, rate);
return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
}

@@ -173,7 +173,7 @@ int mlx5_rl_add_rate(struct mlx5_core_dev *dev, u32 rate, u16 *index)
entry->refcount++;
} else {
/* new rate limit */
- err = mlx5_set_rate_limit_cmd(dev, rate, entry->index);
+ err = mlx5_set_pp_rate_limit_cmd(dev, rate, entry->index);
if (err) {
mlx5_core_err(dev, "Failed configuring rate: %u (%d)\n",
rate, err);
@@ -209,7 +209,7 @@ void mlx5_rl_remove_rate(struct mlx5_core_dev *dev, u32 rate)
entry->refcount--;
if (!entry->refcount) {
/* need to remove rate */
- mlx5_set_rate_limit_cmd(dev, 0, entry->index);
+ mlx5_set_pp_rate_limit_cmd(dev, 0, entry->index);
entry->rate = 0;
}

@@ -262,8 +262,8 @@ void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev)
/* Clear all configured rates */
for (i = 0; i < table->max_size; i++)
if (table->rl_entry[i].rate)
- mlx5_set_rate_limit_cmd(dev, 0,
- table->rl_entry[i].index);
+ mlx5_set_pp_rate_limit_cmd(dev, 0,
+ table->rl_entry[i].index);

kfree(dev->priv.rl_table.rl_entry);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index 07a9ba6cfc70..2f74953e4561 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -71,9 +71,9 @@ struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port)
struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
struct mlx5e_vxlan *vxlan;

- spin_lock(&vxlan_db->lock);
+ spin_lock_bh(&vxlan_db->lock);
vxlan = radix_tree_lookup(&vxlan_db->tree, port);
- spin_unlock(&vxlan_db->lock);
+ spin_unlock_bh(&vxlan_db->lock);

return vxlan;
}
@@ -88,8 +88,12 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
struct mlx5e_vxlan *vxlan;
int err;

- if (mlx5e_vxlan_lookup_port(priv, port))
+ mutex_lock(&priv->state_lock);
+ vxlan = mlx5e_vxlan_lookup_port(priv, port);
+ if (vxlan) {
+ atomic_inc(&vxlan->refcount);
goto free_work;
+ }

if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port))
goto free_work;
@@ -99,10 +103,11 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
goto err_delete_port;

vxlan->udp_port = port;
+ atomic_set(&vxlan->refcount, 1);

- spin_lock_irq(&vxlan_db->lock);
+ spin_lock_bh(&vxlan_db->lock);
err = radix_tree_insert(&vxlan_db->tree, vxlan->udp_port, vxlan);
- spin_unlock_irq(&vxlan_db->lock);
+ spin_unlock_bh(&vxlan_db->lock);
if (err)
goto err_free;

@@ -113,35 +118,39 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
err_delete_port:
mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
free_work:
+ mutex_unlock(&priv->state_lock);
kfree(vxlan_work);
}

-static void __mlx5e_vxlan_core_del_port(struct mlx5e_priv *priv, u16 port)
+static void mlx5e_vxlan_del_port(struct work_struct *work)
{
+ struct mlx5e_vxlan_work *vxlan_work =
+ container_of(work, struct mlx5e_vxlan_work, work);
+ struct mlx5e_priv *priv = vxlan_work->priv;
struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
+ u16 port = vxlan_work->port;
struct mlx5e_vxlan *vxlan;
+ bool remove = false;

- spin_lock_irq(&vxlan_db->lock);
- vxlan = radix_tree_delete(&vxlan_db->tree, port);
- spin_unlock_irq(&vxlan_db->lock);
-
+ mutex_lock(&priv->state_lock);
+ spin_lock_bh(&vxlan_db->lock);
+ vxlan = radix_tree_lookup(&vxlan_db->tree, port);
if (!vxlan)
- return;
-
- mlx5e_vxlan_core_del_port_cmd(priv->mdev, vxlan->udp_port);
-
- kfree(vxlan);
-}
+ goto out_unlock;

-static void mlx5e_vxlan_del_port(struct work_struct *work)
-{
- struct mlx5e_vxlan_work *vxlan_work =
- container_of(work, struct mlx5e_vxlan_work, work);
- struct mlx5e_priv *priv = vxlan_work->priv;
- u16 port = vxlan_work->port;
+ if (atomic_dec_and_test(&vxlan->refcount)) {
+ radix_tree_delete(&vxlan_db->tree, port);
+ remove = true;
+ }

- __mlx5e_vxlan_core_del_port(priv, port);
+out_unlock:
+ spin_unlock_bh(&vxlan_db->lock);

+ if (remove) {
+ mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
+ kfree(vxlan);
+ }
+ mutex_unlock(&priv->state_lock);
kfree(vxlan_work);
}

@@ -171,12 +180,11 @@ void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv)
struct mlx5e_vxlan *vxlan;
unsigned int port = 0;

- spin_lock_irq(&vxlan_db->lock);
+ /* Lockless since we are the only radix-tree consumers, wq is disabled */
while (radix_tree_gang_lookup(&vxlan_db->tree, (void **)&vxlan, port, 1)) {
port = vxlan->udp_port;
- spin_unlock_irq(&vxlan_db->lock);
- __mlx5e_vxlan_core_del_port(priv, (u16)port);
- spin_lock_irq(&vxlan_db->lock);
+ radix_tree_delete(&vxlan_db->tree, port);
+ mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
+ kfree(vxlan);
}
- spin_unlock_irq(&vxlan_db->lock);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
index 5def12c048e3..5ef6ae7d568a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
@@ -36,6 +36,7 @@
#include "en.h"

struct mlx5e_vxlan {
+ atomic_t refcount;
u16 udp_port;
};

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index db38880f54b4..3ead7439821c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4164,6 +4164,7 @@ static int mlxsw_sp_port_stp_set(struct mlxsw_sp_port *mlxsw_sp_port,

static int mlxsw_sp_port_ovs_join(struct mlxsw_sp_port *mlxsw_sp_port)
{
+ u16 vid = 1;
int err;

err = mlxsw_sp_port_vp_mode_set(mlxsw_sp_port, true);
@@ -4176,8 +4177,19 @@ static int mlxsw_sp_port_ovs_join(struct mlxsw_sp_port *mlxsw_sp_port)
true, false);
if (err)
goto err_port_vlan_set;
+
+ for (; vid <= VLAN_N_VID - 1; vid++) {
+ err = mlxsw_sp_port_vid_learning_set(mlxsw_sp_port,
+ vid, false);
+ if (err)
+ goto err_vid_learning_set;
+ }
+
return 0;

+err_vid_learning_set:
+ for (vid--; vid >= 1; vid--)
+ mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, vid, true);
err_port_vlan_set:
mlxsw_sp_port_stp_set(mlxsw_sp_port, false);
err_port_stp_set:
@@ -4187,6 +4199,12 @@ static int mlxsw_sp_port_ovs_join(struct mlxsw_sp_port *mlxsw_sp_port)

static void mlxsw_sp_port_ovs_leave(struct mlxsw_sp_port *mlxsw_sp_port)
{
+ u16 vid;
+
+ for (vid = VLAN_N_VID - 1; vid >= 1; vid--)
+ mlxsw_sp_port_vid_learning_set(mlxsw_sp_port,
+ vid, true);
+
mlxsw_sp_port_vlan_set(mlxsw_sp_port, 2, VLAN_N_VID - 1,
false, false);
mlxsw_sp_port_stp_set(mlxsw_sp_port, false);
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 32bf1fecf864..9b85cbd5a231 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -77,6 +77,7 @@ static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
}

if (buffer->flags & EFX_TX_BUF_SKB) {
+ EFX_WARN_ON_PARANOID(!pkts_compl || !bytes_compl);
(*pkts_compl)++;
(*bytes_compl) += buffer->skb->len;
dev_consume_skb_any((struct sk_buff *)buffer->skb);
@@ -426,12 +427,14 @@ static int efx_tx_map_data(struct efx_tx_queue *tx_queue, struct sk_buff *skb,
static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue)
{
struct efx_tx_buffer *buffer;
+ unsigned int bytes_compl = 0;
+ unsigned int pkts_compl = 0;

/* Work backwards until we hit the original insert pointer value */
while (tx_queue->insert_count != tx_queue->write_count) {
--tx_queue->insert_count;
buffer = __efx_tx_queue_get_insert_buffer(tx_queue);
- efx_dequeue_buffer(tx_queue, buffer, NULL, NULL);
+ efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl);
}
}

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 4d02b27df044..a3f456b91c99 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -2069,7 +2069,7 @@ static struct phy_driver marvell_drivers[] = {
.flags = PHY_HAS_INTERRUPT,
.probe = marvell_probe,
.config_init = &m88e1145_config_init,
- .config_aneg = &marvell_config_aneg,
+ .config_aneg = &m88e1101_config_aneg,
.read_status = &genphy_read_status,
.ack_interrupt = &marvell_ack_interrupt,
.config_intr = &marvell_config_intr,
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index fdb43dd9b5cd..6c45ff650ec7 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -622,6 +622,7 @@ static int ksz9031_read_status(struct phy_device *phydev)
phydev->link = 0;
if (phydev->drv->config_intr && phy_interrupt_is_valid(phydev))
phydev->drv->config_intr(phydev);
+ return genphy_config_aneg(phydev);
}

return 0;
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index bcb4755bcd95..4b377b978a0b 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -525,6 +525,7 @@ struct phylink *phylink_create(struct net_device *ndev, struct device_node *np,
pl->link_config.pause = MLO_PAUSE_AN;
pl->link_config.speed = SPEED_UNKNOWN;
pl->link_config.duplex = DUPLEX_UNKNOWN;
+ pl->link_config.an_enabled = true;
pl->ops = ops;
__set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state);

@@ -948,6 +949,7 @@ int phylink_ethtool_ksettings_set(struct phylink *pl,
mutex_lock(&pl->state_mutex);
/* Configure the MAC to match the new settings */
linkmode_copy(pl->link_config.advertising, our_kset.link_modes.advertising);
+ pl->link_config.interface = config.interface;
pl->link_config.speed = our_kset.base.speed;
pl->link_config.duplex = our_kset.base.duplex;
pl->link_config.an_enabled = our_kset.base.autoneg != AUTONEG_DISABLE;
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 81394a4b2803..2092febfcb42 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1204,6 +1204,7 @@ static const struct usb_device_id products[] = {
{QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */
{QMI_FIXED_INTF(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */
{QMI_FIXED_INTF(0x1199, 0x907b, 10)}, /* Sierra Wireless EM74xx */
+ {QMI_FIXED_INTF(0x1199, 0x9091, 8)}, /* Sierra Wireless EM7565 */
{QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */
{QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */
{QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index a2f4e52fadb5..9e9202b50e73 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3105,6 +3105,11 @@ static void vxlan_config_apply(struct net_device *dev,

max_mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM :
VXLAN_HEADROOM);
+ if (max_mtu < ETH_MIN_MTU)
+ max_mtu = ETH_MIN_MTU;
+
+ if (!changelink && !conf->mtu)
+ dev->mtu = max_mtu;
}

if (dev->mtu > max_mtu)
diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c
index 4307bf0013e1..63e916d4d069 100644
--- a/drivers/phy/tegra/xusb.c
+++ b/drivers/phy/tegra/xusb.c
@@ -75,14 +75,14 @@ MODULE_DEVICE_TABLE(of, tegra_xusb_padctl_of_match);
static struct device_node *
tegra_xusb_find_pad_node(struct tegra_xusb_padctl *padctl, const char *name)
{
- /*
- * of_find_node_by_name() drops a reference, so make sure to grab one.
- */
- struct device_node *np = of_node_get(padctl->dev->of_node);
+ struct device_node *pads, *np;
+
+ pads = of_get_child_by_name(padctl->dev->of_node, "pads");
+ if (!pads)
+ return NULL;

- np = of_find_node_by_name(np, "pads");
- if (np)
- np = of_find_node_by_name(np, name);
+ np = of_get_child_by_name(pads, name);
+ of_node_put(pads);

return np;
}
@@ -90,16 +90,16 @@ tegra_xusb_find_pad_node(struct tegra_xusb_padctl *padctl, const char *name)
static struct device_node *
tegra_xusb_pad_find_phy_node(struct tegra_xusb_pad *pad, unsigned int index)
{
- /*
- * of_find_node_by_name() drops a reference, so make sure to grab one.
- */
- struct device_node *np = of_node_get(pad->dev.of_node);
+ struct device_node *np, *lanes;

- np = of_find_node_by_name(np, "lanes");
- if (!np)
+ lanes = of_get_child_by_name(pad->dev.of_node, "lanes");
+ if (!lanes)
return NULL;

- return of_find_node_by_name(np, pad->soc->lanes[index].name);
+ np = of_get_child_by_name(lanes, pad->soc->lanes[index].name);
+ of_node_put(lanes);
+
+ return np;
}

static int
@@ -195,7 +195,7 @@ int tegra_xusb_pad_register(struct tegra_xusb_pad *pad,
unsigned int i;
int err;

- children = of_find_node_by_name(pad->dev.of_node, "lanes");
+ children = of_get_child_by_name(pad->dev.of_node, "lanes");
if (!children)
return -ENODEV;

@@ -444,21 +444,21 @@ static struct device_node *
tegra_xusb_find_port_node(struct tegra_xusb_padctl *padctl, const char *type,
unsigned int index)
{
- /*
- * of_find_node_by_name() drops a reference, so make sure to grab one.
- */
- struct device_node *np = of_node_get(padctl->dev->of_node);
+ struct device_node *ports, *np;
+ char *name;

- np = of_find_node_by_name(np, "ports");
- if (np) {
- char *name;
+ ports = of_get_child_by_name(padctl->dev->of_node, "ports");
+ if (!ports)
+ return NULL;

- name = kasprintf(GFP_KERNEL, "%s-%u", type, index);
- if (!name)
- return ERR_PTR(-ENOMEM);
- np = of_find_node_by_name(np, name);
- kfree(name);
+ name = kasprintf(GFP_KERNEL, "%s-%u", type, index);
+ if (!name) {
+ of_node_put(ports);
+ return ERR_PTR(-ENOMEM);
}
+ np = of_get_child_by_name(ports, name);
+ kfree(name);
+ of_node_put(ports);

return np;
}
@@ -847,7 +847,7 @@ static void tegra_xusb_remove_ports(struct tegra_xusb_padctl *padctl)

static int tegra_xusb_padctl_probe(struct platform_device *pdev)
{
- struct device_node *np = of_node_get(pdev->dev.of_node);
+ struct device_node *np = pdev->dev.of_node;
const struct tegra_xusb_padctl_soc *soc;
struct tegra_xusb_padctl *padctl;
const struct of_device_id *match;
@@ -855,7 +855,7 @@ static int tegra_xusb_padctl_probe(struct platform_device *pdev)
int err;

/* for backwards compatibility with old device trees */
- np = of_find_node_by_name(np, "pads");
+ np = of_get_child_by_name(np, "pads");
if (!np) {
dev_warn(&pdev->dev, "deprecated DT, using legacy driver\n");
return tegra_xusb_padctl_legacy_probe(pdev);
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 5340efc673a9..92dd4aef21a3 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -564,9 +564,9 @@ enum qeth_cq {
};

struct qeth_ipato {
- int enabled;
- int invert4;
- int invert6;
+ bool enabled;
+ bool invert4;
+ bool invert6;
struct list_head entries;
};

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 330e5d3dadf3..7c7a244b6684 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1479,9 +1479,9 @@ static int qeth_setup_card(struct qeth_card *card)
qeth_set_intial_options(card);
/* IP address takeover */
INIT_LIST_HEAD(&card->ipato.entries);
- card->ipato.enabled = 0;
- card->ipato.invert4 = 0;
- card->ipato.invert6 = 0;
+ card->ipato.enabled = false;
+ card->ipato.invert4 = false;
+ card->ipato.invert6 = false;
/* init QDIO stuff */
qeth_init_qdio_info(card);
INIT_DELAYED_WORK(&card->buffer_reclaim_work, qeth_buffer_reclaim_work);
@@ -5445,6 +5445,13 @@ int qeth_poll(struct napi_struct *napi, int budget)
}
EXPORT_SYMBOL_GPL(qeth_poll);

+static int qeth_setassparms_inspect_rc(struct qeth_ipa_cmd *cmd)
+{
+ if (!cmd->hdr.return_code)
+ cmd->hdr.return_code = cmd->data.setassparms.hdr.return_code;
+ return cmd->hdr.return_code;
+}
+
int qeth_setassparms_cb(struct qeth_card *card,
struct qeth_reply *reply, unsigned long data)
{
@@ -6304,7 +6311,7 @@ static int qeth_ipa_checksum_run_cmd_cb(struct qeth_card *card,
(struct qeth_checksum_cmd *)reply->param;

QETH_CARD_TEXT(card, 4, "chkdoccb");
- if (cmd->hdr.return_code)
+ if (qeth_setassparms_inspect_rc(cmd))
return 0;

memset(chksum_cb, 0, sizeof(*chksum_cb));
diff --git a/drivers/s390/net/qeth_l3.h b/drivers/s390/net/qeth_l3.h
index 194ae9b577cc..e5833837b799 100644
--- a/drivers/s390/net/qeth_l3.h
+++ b/drivers/s390/net/qeth_l3.h
@@ -82,7 +82,7 @@ void qeth_l3_del_vipa(struct qeth_card *, enum qeth_prot_versions, const u8 *);
int qeth_l3_add_rxip(struct qeth_card *, enum qeth_prot_versions, const u8 *);
void qeth_l3_del_rxip(struct qeth_card *card, enum qeth_prot_versions,
const u8 *);
-int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *, struct qeth_ipaddr *);
+void qeth_l3_update_ipato(struct qeth_card *card);
struct qeth_ipaddr *qeth_l3_get_addr_buffer(enum qeth_prot_versions);
int qeth_l3_add_ip(struct qeth_card *, struct qeth_ipaddr *);
int qeth_l3_delete_ip(struct qeth_card *, struct qeth_ipaddr *);
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 27185ab38136..36dee176f8e2 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -163,8 +163,8 @@ static void qeth_l3_convert_addr_to_bits(u8 *addr, u8 *bits, int len)
}
}

-int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
- struct qeth_ipaddr *addr)
+static bool qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
+ struct qeth_ipaddr *addr)
{
struct qeth_ipato_entry *ipatoe;
u8 addr_bits[128] = {0, };
@@ -173,6 +173,8 @@ int qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,

if (!card->ipato.enabled)
return 0;
+ if (addr->type != QETH_IP_TYPE_NORMAL)
+ return 0;

qeth_l3_convert_addr_to_bits((u8 *) &addr->u, addr_bits,
(addr->proto == QETH_PROT_IPV4)? 4:16);
@@ -289,8 +291,7 @@ int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr)
memcpy(addr, tmp_addr, sizeof(struct qeth_ipaddr));
addr->ref_counter = 1;

- if (addr->type == QETH_IP_TYPE_NORMAL &&
- qeth_l3_is_addr_covered_by_ipato(card, addr)) {
+ if (qeth_l3_is_addr_covered_by_ipato(card, addr)) {
QETH_CARD_TEXT(card, 2, "tkovaddr");
addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
}
@@ -604,6 +605,27 @@ int qeth_l3_setrouting_v6(struct qeth_card *card)
/*
* IP address takeover related functions
*/
+
+/**
+ * qeth_l3_update_ipato() - Update 'takeover' property, for all NORMAL IPs.
+ *
+ * Caller must hold ip_lock.
+ */
+void qeth_l3_update_ipato(struct qeth_card *card)
+{
+ struct qeth_ipaddr *addr;
+ unsigned int i;
+
+ hash_for_each(card->ip_htable, i, addr, hnode) {
+ if (addr->type != QETH_IP_TYPE_NORMAL)
+ continue;
+ if (qeth_l3_is_addr_covered_by_ipato(card, addr))
+ addr->set_flags |= QETH_IPA_SETIP_TAKEOVER_FLAG;
+ else
+ addr->set_flags &= ~QETH_IPA_SETIP_TAKEOVER_FLAG;
+ }
+}
+
static void qeth_l3_clear_ipato_list(struct qeth_card *card)
{
struct qeth_ipato_entry *ipatoe, *tmp;
@@ -615,6 +637,7 @@ static void qeth_l3_clear_ipato_list(struct qeth_card *card)
kfree(ipatoe);
}

+ qeth_l3_update_ipato(card);
spin_unlock_bh(&card->ip_lock);
}

@@ -639,8 +662,10 @@ int qeth_l3_add_ipato_entry(struct qeth_card *card,
}
}

- if (!rc)
+ if (!rc) {
list_add_tail(&new->entry, &card->ipato.entries);
+ qeth_l3_update_ipato(card);
+ }

spin_unlock_bh(&card->ip_lock);

@@ -663,6 +688,7 @@ void qeth_l3_del_ipato_entry(struct qeth_card *card,
(proto == QETH_PROT_IPV4)? 4:16) &&
(ipatoe->mask_bits == mask_bits)) {
list_del(&ipatoe->entry);
+ qeth_l3_update_ipato(card);
kfree(ipatoe);
}
}
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index 7a829ad77783..1295dd8ec849 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -370,8 +370,8 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
struct qeth_card *card = dev_get_drvdata(dev);
- struct qeth_ipaddr *addr;
- int i, rc = 0;
+ bool enable;
+ int rc = 0;

if (!card)
return -EINVAL;
@@ -384,25 +384,18 @@ static ssize_t qeth_l3_dev_ipato_enable_store(struct device *dev,
}

if (sysfs_streq(buf, "toggle")) {
- card->ipato.enabled = (card->ipato.enabled)? 0 : 1;
- } else if (sysfs_streq(buf, "1")) {
- card->ipato.enabled = 1;
- hash_for_each(card->ip_htable, i, addr, hnode) {
- if ((addr->type == QETH_IP_TYPE_NORMAL) &&
- qeth_l3_is_addr_covered_by_ipato(card, addr))
- addr->set_flags |=
- QETH_IPA_SETIP_TAKEOVER_FLAG;
- }
- } else if (sysfs_streq(buf, "0")) {
- card->ipato.enabled = 0;
- hash_for_each(card->ip_htable, i, addr, hnode) {
- if (addr->set_flags &
- QETH_IPA_SETIP_TAKEOVER_FLAG)
- addr->set_flags &=
- ~QETH_IPA_SETIP_TAKEOVER_FLAG;
- }
- } else
+ enable = !card->ipato.enabled;
+ } else if (kstrtobool(buf, &enable)) {
rc = -EINVAL;
+ goto out;
+ }
+
+ if (card->ipato.enabled != enable) {
+ card->ipato.enabled = enable;
+ spin_lock_bh(&card->ip_lock);
+ qeth_l3_update_ipato(card);
+ spin_unlock_bh(&card->ip_lock);
+ }
out:
mutex_unlock(&card->conf_mutex);
return rc ? rc : count;
@@ -428,20 +421,27 @@ static ssize_t qeth_l3_dev_ipato_invert4_store(struct device *dev,
const char *buf, size_t count)
{
struct qeth_card *card = dev_get_drvdata(dev);
+ bool invert;
int rc = 0;

if (!card)
return -EINVAL;

mutex_lock(&card->conf_mutex);
- if (sysfs_streq(buf, "toggle"))
- card->ipato.invert4 = (card->ipato.invert4)? 0 : 1;
- else if (sysfs_streq(buf, "1"))
- card->ipato.invert4 = 1;
- else if (sysfs_streq(buf, "0"))
- card->ipato.invert4 = 0;
- else
+ if (sysfs_streq(buf, "toggle")) {
+ invert = !card->ipato.invert4;
+ } else if (kstrtobool(buf, &invert)) {
rc = -EINVAL;
+ goto out;
+ }
+
+ if (card->ipato.invert4 != invert) {
+ card->ipato.invert4 = invert;
+ spin_lock_bh(&card->ip_lock);
+ qeth_l3_update_ipato(card);
+ spin_unlock_bh(&card->ip_lock);
+ }
+out:
mutex_unlock(&card->conf_mutex);
return rc ? rc : count;
}
@@ -607,20 +607,27 @@ static ssize_t qeth_l3_dev_ipato_invert6_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
struct qeth_card *card = dev_get_drvdata(dev);
+ bool invert;
int rc = 0;

if (!card)
return -EINVAL;

mutex_lock(&card->conf_mutex);
- if (sysfs_streq(buf, "toggle"))
- card->ipato.invert6 = (card->ipato.invert6)? 0 : 1;
- else if (sysfs_streq(buf, "1"))
- card->ipato.invert6 = 1;
- else if (sysfs_streq(buf, "0"))
- card->ipato.invert6 = 0;
- else
+ if (sysfs_streq(buf, "toggle")) {
+ invert = !card->ipato.invert6;
+ } else if (kstrtobool(buf, &invert)) {
rc = -EINVAL;
+ goto out;
+ }
+
+ if (card->ipato.invert6 != invert) {
+ card->ipato.invert6 = invert;
+ spin_lock_bh(&card->ip_lock);
+ qeth_l3_update_ipato(card);
+ spin_unlock_bh(&card->ip_lock);
+ }
+out:
mutex_unlock(&card->conf_mutex);
return rc ? rc : count;
}
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
index a4f28b7e4c65..e18877177f1b 100644
--- a/drivers/scsi/osd/osd_initiator.c
+++ b/drivers/scsi/osd/osd_initiator.c
@@ -1576,7 +1576,9 @@ static struct request *_make_request(struct request_queue *q, bool has_write,
return req;

for_each_bio(bio) {
- ret = blk_rq_append_bio(req, bio);
+ struct bio *bounce_bio = bio;
+
+ ret = blk_rq_append_bio(req, &bounce_bio);
if (ret)
return ERR_PTR(ret);
}
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index 93e2c90fa77d..83dc3292e9ab 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -348,7 +348,7 @@ static int ion_dma_buf_begin_cpu_access(struct dma_buf *dmabuf,
mutex_lock(&buffer->lock);
list_for_each_entry(a, &buffer->attachments, list) {
dma_sync_sg_for_cpu(a->dev, a->table->sgl, a->table->nents,
- DMA_BIDIRECTIONAL);
+ direction);
}
mutex_unlock(&buffer->lock);

@@ -370,7 +370,7 @@ static int ion_dma_buf_end_cpu_access(struct dma_buf *dmabuf,
mutex_lock(&buffer->lock);
list_for_each_entry(a, &buffer->attachments, list) {
dma_sync_sg_for_device(a->dev, a->table->sgl, a->table->nents,
- DMA_BIDIRECTIONAL);
+ direction);
}
mutex_unlock(&buffer->lock);

diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 7c69b4a9694d..0d99b242e82e 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -920,7 +920,7 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
" %d i: %d bio: %p, allocating another"
" bio\n", bio->bi_vcnt, i, bio);

- rc = blk_rq_append_bio(req, bio);
+ rc = blk_rq_append_bio(req, &bio);
if (rc) {
pr_err("pSCSI: failed to append bio\n");
goto fail;
@@ -938,7 +938,7 @@ pscsi_map_sg(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents,
}

if (bio) {
- rc = blk_rq_append_bio(req, bio);
+ rc = blk_rq_append_bio(req, &bio);
if (rc) {
pr_err("pSCSI: failed to append bio\n");
goto fail;
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index bdf0e6e89991..faf50df81622 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -1764,7 +1764,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
{
struct n_tty_data *ldata = tty->disc_data;

- if (!old || (old->c_lflag ^ tty->termios.c_lflag) & ICANON) {
+ if (!old || (old->c_lflag ^ tty->termios.c_lflag) & (ICANON | EXTPROC)) {
bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE);
ldata->line_start = ldata->read_tail;
if (!L_ICANON(tty) || !read_cnt(ldata)) {
@@ -2427,7 +2427,7 @@ static int n_tty_ioctl(struct tty_struct *tty, struct file *file,
return put_user(tty_chars_in_buffer(tty), (int __user *) arg);
case TIOCINQ:
down_write(&tty->termios_rwsem);
- if (L_ICANON(tty))
+ if (L_ICANON(tty) && !L_EXTPROC(tty))
retval = inq_canon(ldata);
else
retval = read_cnt(ldata);
diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index f8eba1c5412f..677fa99b7747 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -446,7 +446,7 @@ EXPORT_SYMBOL_GPL(tty_prepare_flip_string);
* Callers other than flush_to_ldisc() need to exclude the kworker
* from concurrent use of the line discipline, see paste_selection().
*
- * Returns the number of bytes not processed
+ * Returns the number of bytes processed
*/
int tty_ldisc_receive_buf(struct tty_ldisc *ld, const unsigned char *p,
char *f, int count)
diff --git a/drivers/usb/chipidea/ci_hdrc_msm.c b/drivers/usb/chipidea/ci_hdrc_msm.c
index bb626120296f..53f3bf459dd1 100644
--- a/drivers/usb/chipidea/ci_hdrc_msm.c
+++ b/drivers/usb/chipidea/ci_hdrc_msm.c
@@ -251,7 +251,7 @@ static int ci_hdrc_msm_probe(struct platform_device *pdev)
if (ret)
goto err_mux;

- ulpi_node = of_find_node_by_name(of_node_get(pdev->dev.of_node), "ulpi");
+ ulpi_node = of_get_child_by_name(pdev->dev.of_node, "ulpi");
if (ulpi_node) {
phy_node = of_get_next_available_child(ulpi_node, NULL);
ci->hsic = of_device_is_compatible(phy_node, "qcom,usb-hsic-phy");
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index 843ef46d2537..9e3355b97396 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -1007,7 +1007,7 @@ int usb_get_bos_descriptor(struct usb_device *dev)
case USB_SSP_CAP_TYPE:
ssp_cap = (struct usb_ssp_cap_descriptor *)buffer;
ssac = (le32_to_cpu(ssp_cap->bmAttributes) &
- USB_SSP_SUBLINK_SPEED_ATTRIBS) + 1;
+ USB_SSP_SUBLINK_SPEED_ATTRIBS);
if (length >= USB_DT_USB_SSP_CAP_SIZE(ssac))
dev->bos->ssp_cap = ssp_cap;
break;
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index 50010282c010..c05c4f877750 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -57,10 +57,11 @@ static const struct usb_device_id usb_quirk_list[] = {
/* Microsoft LifeCam-VX700 v2.0 */
{ USB_DEVICE(0x045e, 0x0770), .driver_info = USB_QUIRK_RESET_RESUME },

- /* Logitech HD Pro Webcams C920, C920-C and C930e */
+ /* Logitech HD Pro Webcams C920, C920-C, C925e and C930e */
{ USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },
{ USB_DEVICE(0x046d, 0x0841), .driver_info = USB_QUIRK_DELAY_INIT },
{ USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT },
+ { USB_DEVICE(0x046d, 0x085b), .driver_info = USB_QUIRK_DELAY_INIT },

/* Logitech ConferenceCam CC3000e */
{ USB_DEVICE(0x046d, 0x0847), .driver_info = USB_QUIRK_DELAY_INIT },
@@ -154,6 +155,9 @@ static const struct usb_device_id usb_quirk_list[] = {
/* Genesys Logic hub, internally used by KY-688 USB 3.1 Type-C Hub */
{ USB_DEVICE(0x05e3, 0x0612), .driver_info = USB_QUIRK_NO_LPM },

+ /* ELSA MicroLink 56K */
+ { USB_DEVICE(0x05cc, 0x2267), .driver_info = USB_QUIRK_RESET_RESUME },
+
/* Genesys Logic hub, internally used by Moshi USB to Ethernet Adapter */
{ USB_DEVICE(0x05e3, 0x0616), .driver_info = USB_QUIRK_NO_LPM },

diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 76f392954733..abb8f19ae40f 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -189,6 +189,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
xhci->quirks |= XHCI_TRUST_TX_LENGTH;
xhci->quirks |= XHCI_BROKEN_STREAMS;
}
+ if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
+ pdev->device == 0x0014)
+ xhci->quirks |= XHCI_TRUST_TX_LENGTH;
if (pdev->vendor == PCI_VENDOR_ID_RENESAS &&
pdev->device == 0x0015)
xhci->quirks |= XHCI_RESET_ON_RESUME;
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 49d1b2d4606d..d038e543c246 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1017,6 +1017,7 @@ static const struct usb_device_id id_table_combined[] = {
.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
{ USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_BT_USB_PID) },
{ USB_DEVICE(CYPRESS_VID, CYPRESS_WICED_WL_USB_PID) },
+ { USB_DEVICE(AIRBUS_DS_VID, AIRBUS_DS_P8GR) },
{ } /* Terminating entry */
};

diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 4faa09fe308c..8b4ecd2bd297 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -914,6 +914,12 @@
#define ICPDAS_I7561U_PID 0x0104
#define ICPDAS_I7563U_PID 0x0105

+/*
+ * Airbus Defence and Space
+ */
+#define AIRBUS_DS_VID 0x1e8e /* Vendor ID */
+#define AIRBUS_DS_P8GR 0x6001 /* Tetra P8GR */
+
/*
* RT Systems programming cables for various ham radios
*/
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 54e316b1892d..a9400458ccea 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -236,6 +236,8 @@ static void option_instat_callback(struct urb *urb);
/* These Quectel products use Qualcomm's vendor ID */
#define QUECTEL_PRODUCT_UC20 0x9003
#define QUECTEL_PRODUCT_UC15 0x9090
+/* These Yuga products use Qualcomm's vendor ID */
+#define YUGA_PRODUCT_CLM920_NC5 0x9625

#define QUECTEL_VENDOR_ID 0x2c7c
/* These Quectel products use Quectel's vendor ID */
@@ -283,6 +285,7 @@ static void option_instat_callback(struct urb *urb);
#define TELIT_PRODUCT_LE922_USBCFG3 0x1043
#define TELIT_PRODUCT_LE922_USBCFG5 0x1045
#define TELIT_PRODUCT_ME910 0x1100
+#define TELIT_PRODUCT_ME910_DUAL_MODEM 0x1101
#define TELIT_PRODUCT_LE920 0x1200
#define TELIT_PRODUCT_LE910 0x1201
#define TELIT_PRODUCT_LE910_USBCFG4 0x1206
@@ -648,6 +651,11 @@ static const struct option_blacklist_info telit_me910_blacklist = {
.reserved = BIT(1) | BIT(3),
};

+static const struct option_blacklist_info telit_me910_dual_modem_blacklist = {
+ .sendsetup = BIT(0),
+ .reserved = BIT(3),
+};
+
static const struct option_blacklist_info telit_le910_blacklist = {
.sendsetup = BIT(0),
.reserved = BIT(1) | BIT(2),
@@ -677,6 +685,10 @@ static const struct option_blacklist_info cinterion_rmnet2_blacklist = {
.reserved = BIT(4) | BIT(5),
};

+static const struct option_blacklist_info yuga_clm920_nc5_blacklist = {
+ .reserved = BIT(1) | BIT(4),
+};
+
static const struct usb_device_id option_ids[] = {
{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_COLT) },
{ USB_DEVICE(OPTION_VENDOR_ID, OPTION_PRODUCT_RICOLA) },
@@ -1181,6 +1193,9 @@ static const struct usb_device_id option_ids[] = {
{ USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC15)},
{ USB_DEVICE(QUALCOMM_VENDOR_ID, QUECTEL_PRODUCT_UC20),
.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
+ /* Yuga products use Qualcomm vendor ID */
+ { USB_DEVICE(QUALCOMM_VENDOR_ID, YUGA_PRODUCT_CLM920_NC5),
+ .driver_info = (kernel_ulong_t)&yuga_clm920_nc5_blacklist },
/* Quectel products using Quectel vendor ID */
{ USB_DEVICE(QUECTEL_VENDOR_ID, QUECTEL_PRODUCT_EC21),
.driver_info = (kernel_ulong_t)&net_intf4_blacklist },
@@ -1247,6 +1262,8 @@ static const struct usb_device_id option_ids[] = {
.driver_info = (kernel_ulong_t)&telit_le922_blacklist_usbcfg0 },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
.driver_info = (kernel_ulong_t)&telit_me910_blacklist },
+ { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM),
+ .driver_info = (kernel_ulong_t)&telit_me910_dual_modem_blacklist },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910),
.driver_info = (kernel_ulong_t)&telit_le910_blacklist },
{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE910_USBCFG4),
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 9f9d3a904464..55a8fb25ce2b 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -166,6 +166,8 @@ static const struct usb_device_id id_table[] = {
{DEVICE_SWI(0x1199, 0x9079)}, /* Sierra Wireless EM74xx */
{DEVICE_SWI(0x1199, 0x907a)}, /* Sierra Wireless EM74xx QDL */
{DEVICE_SWI(0x1199, 0x907b)}, /* Sierra Wireless EM74xx */
+ {DEVICE_SWI(0x1199, 0x9090)}, /* Sierra Wireless EM7565 QDL */
+ {DEVICE_SWI(0x1199, 0x9091)}, /* Sierra Wireless EM7565 */
{DEVICE_SWI(0x413c, 0x81a2)}, /* Dell Wireless 5806 Gobi(TM) 4G LTE Mobile Broadband Card */
{DEVICE_SWI(0x413c, 0x81a3)}, /* Dell Wireless 5570 HSPA+ (42Mbps) Mobile Broadband Card */
{DEVICE_SWI(0x413c, 0x81a4)}, /* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
@@ -346,6 +348,7 @@ static int qcprobe(struct usb_serial *serial, const struct usb_device_id *id)
break;
case 2:
dev_dbg(dev, "NMEA GPS interface found\n");
+ sendsetup = true;
break;
case 3:
dev_dbg(dev, "Modem port found\n");
diff --git a/drivers/usb/usbip/stub_dev.c b/drivers/usb/usbip/stub_dev.c
index c653ce533430..720408d39f11 100644
--- a/drivers/usb/usbip/stub_dev.c
+++ b/drivers/usb/usbip/stub_dev.c
@@ -163,8 +163,7 @@ static void stub_shutdown_connection(struct usbip_device *ud)
* step 1?
*/
if (ud->tcp_socket) {
- dev_dbg(&sdev->udev->dev, "shutdown tcp_socket %p\n",
- ud->tcp_socket);
+ dev_dbg(&sdev->udev->dev, "shutdown sockfd %d\n", ud->sockfd);
kernel_sock_shutdown(ud->tcp_socket, SHUT_RDWR);
}

diff --git a/drivers/usb/usbip/stub_main.c b/drivers/usb/usbip/stub_main.c
index 7170404e8979..6968c906fa29 100644
--- a/drivers/usb/usbip/stub_main.c
+++ b/drivers/usb/usbip/stub_main.c
@@ -251,11 +251,12 @@ void stub_device_cleanup_urbs(struct stub_device *sdev)
struct stub_priv *priv;
struct urb *urb;

- dev_dbg(&sdev->udev->dev, "free sdev %p\n", sdev);
+ dev_dbg(&sdev->udev->dev, "Stub device cleaning up urbs\n");

while ((priv = stub_priv_pop(sdev))) {
urb = priv->urb;
- dev_dbg(&sdev->udev->dev, "free urb %p\n", urb);
+ dev_dbg(&sdev->udev->dev, "free urb seqnum %lu\n",
+ priv->seqnum);
usb_kill_urb(urb);

kmem_cache_free(stub_priv_cache, priv);
diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c
index 283a9be77a22..5b807185f79e 100644
--- a/drivers/usb/usbip/stub_rx.c
+++ b/drivers/usb/usbip/stub_rx.c
@@ -225,9 +225,6 @@ static int stub_recv_cmd_unlink(struct stub_device *sdev,
if (priv->seqnum != pdu->u.cmd_unlink.seqnum)
continue;

- dev_info(&priv->urb->dev->dev, "unlink urb %p\n",
- priv->urb);
-
/*
* This matched urb is not completed yet (i.e., be in
* flight in usb hcd hardware/driver). Now we are
@@ -266,8 +263,8 @@ static int stub_recv_cmd_unlink(struct stub_device *sdev,
ret = usb_unlink_urb(priv->urb);
if (ret != -EINPROGRESS)
dev_err(&priv->urb->dev->dev,
- "failed to unlink a urb %p, ret %d\n",
- priv->urb, ret);
+ "failed to unlink a urb # %lu, ret %d\n",
+ priv->seqnum, ret);

return 0;
}
diff --git a/drivers/usb/usbip/stub_tx.c b/drivers/usb/usbip/stub_tx.c
index 87ff94be4235..96aa375b80d9 100644
--- a/drivers/usb/usbip/stub_tx.c
+++ b/drivers/usb/usbip/stub_tx.c
@@ -102,7 +102,7 @@ void stub_complete(struct urb *urb)
/* link a urb to the queue of tx. */
spin_lock_irqsave(&sdev->priv_lock, flags);
if (sdev->ud.tcp_socket == NULL) {
- usbip_dbg_stub_tx("ignore urb for closed connection %p", urb);
+ usbip_dbg_stub_tx("ignore urb for closed connection\n");
/* It will be freed in stub_device_cleanup_urbs(). */
} else if (priv->unlinking) {
stub_enqueue_ret_unlink(sdev, priv->seqnum, urb->status);
@@ -204,8 +204,8 @@ static int stub_send_ret_submit(struct stub_device *sdev)

/* 1. setup usbip_header */
setup_ret_submit_pdu(&pdu_header, urb);
- usbip_dbg_stub_tx("setup txdata seqnum: %d urb: %p\n",
- pdu_header.base.seqnum, urb);
+ usbip_dbg_stub_tx("setup txdata seqnum: %d\n",
+ pdu_header.base.seqnum);
usbip_header_correct_endian(&pdu_header, 1);

iov[iovnum].iov_base = &pdu_header;
diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c
index 2281f3562870..17b599b923f3 100644
--- a/drivers/usb/usbip/usbip_common.c
+++ b/drivers/usb/usbip/usbip_common.c
@@ -331,26 +331,20 @@ int usbip_recv(struct socket *sock, void *buf, int size)
struct msghdr msg = {.msg_flags = MSG_NOSIGNAL};
int total = 0;

+ if (!sock || !buf || !size)
+ return -EINVAL;
+
iov_iter_kvec(&msg.msg_iter, READ|ITER_KVEC, &iov, 1, size);

usbip_dbg_xmit("enter\n");

- if (!sock || !buf || !size) {
- pr_err("invalid arg, sock %p buff %p size %d\n", sock, buf,
- size);
- return -EINVAL;
- }
-
do {
- int sz = msg_data_left(&msg);
+ msg_data_left(&msg);
sock->sk->sk_allocation = GFP_NOIO;

result = sock_recvmsg(sock, &msg, MSG_WAITALL);
- if (result <= 0) {
- pr_debug("receive sock %p buf %p size %u ret %d total %d\n",
- sock, buf + total, sz, result, total);
+ if (result <= 0)
goto err;
- }

total += result;
} while (msg_data_left(&msg));
diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
index 1f0cf81cc145..692cfdef667e 100644
--- a/drivers/usb/usbip/vhci_hcd.c
+++ b/drivers/usb/usbip/vhci_hcd.c
@@ -670,9 +670,6 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag
struct vhci_device *vdev;
unsigned long flags;

- usbip_dbg_vhci_hc("enter, usb_hcd %p urb %p mem_flags %d\n",
- hcd, urb, mem_flags);
-
if (portnum > VHCI_HC_PORTS) {
pr_err("invalid port number %d\n", portnum);
return -ENODEV;
@@ -836,8 +833,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
struct vhci_device *vdev;
unsigned long flags;

- pr_info("dequeue a urb %p\n", urb);
-
spin_lock_irqsave(&vhci->lock, flags);

priv = urb->hcpriv;
@@ -865,7 +860,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
/* tcp connection is closed */
spin_lock(&vdev->priv_lock);

- pr_info("device %p seems to be disconnected\n", vdev);
list_del(&priv->list);
kfree(priv);
urb->hcpriv = NULL;
@@ -877,8 +871,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
* vhci_rx will receive RET_UNLINK and give back the URB.
* Otherwise, we give back it here.
*/
- pr_info("gives back urb %p\n", urb);
-
usb_hcd_unlink_urb_from_ep(hcd, urb);

spin_unlock_irqrestore(&vhci->lock, flags);
@@ -906,8 +898,6 @@ static int vhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)

unlink->unlink_seqnum = priv->seqnum;

- pr_info("device %p seems to be still connected\n", vdev);
-
/* send cmd_unlink and try to cancel the pending URB in the
* peer */
list_add_tail(&unlink->list, &vdev->unlink_tx);
@@ -989,7 +979,7 @@ static void vhci_shutdown_connection(struct usbip_device *ud)

/* need this? see stub_dev.c */
if (ud->tcp_socket) {
- pr_debug("shutdown tcp_socket %p\n", ud->tcp_socket);
+ pr_debug("shutdown tcp_socket %d\n", ud->sockfd);
kernel_sock_shutdown(ud->tcp_socket, SHUT_RDWR);
}

diff --git a/drivers/usb/usbip/vhci_rx.c b/drivers/usb/usbip/vhci_rx.c
index ef2f2d5ca6b2..1343037d00f9 100644
--- a/drivers/usb/usbip/vhci_rx.c
+++ b/drivers/usb/usbip/vhci_rx.c
@@ -37,24 +37,23 @@ struct urb *pickup_urb_and_free_priv(struct vhci_device *vdev, __u32 seqnum)
urb = priv->urb;
status = urb->status;

- usbip_dbg_vhci_rx("find urb %p vurb %p seqnum %u\n",
- urb, priv, seqnum);
+ usbip_dbg_vhci_rx("find urb seqnum %u\n", seqnum);

switch (status) {
case -ENOENT:
/* fall through */
case -ECONNRESET:
- dev_info(&urb->dev->dev,
- "urb %p was unlinked %ssynchronuously.\n", urb,
- status == -ENOENT ? "" : "a");
+ dev_dbg(&urb->dev->dev,
+ "urb seq# %u was unlinked %ssynchronuously\n",
+ seqnum, status == -ENOENT ? "" : "a");
break;
case -EINPROGRESS:
/* no info output */
break;
default:
- dev_info(&urb->dev->dev,
- "urb %p may be in a error, status %d\n", urb,
- status);
+ dev_dbg(&urb->dev->dev,
+ "urb seq# %u may be in a error, status %d\n",
+ seqnum, status);
}

list_del(&priv->list);
@@ -81,8 +80,8 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev,
spin_unlock_irqrestore(&vdev->priv_lock, flags);

if (!urb) {
- pr_err("cannot find a urb of seqnum %u\n", pdu->base.seqnum);
- pr_info("max seqnum %d\n",
+ pr_err("cannot find a urb of seqnum %u max seqnum %d\n",
+ pdu->base.seqnum,
atomic_read(&vhci_hcd->seqnum));
usbip_event_add(ud, VDEV_EVENT_ERROR_TCP);
return;
@@ -105,7 +104,7 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev,
if (usbip_dbg_flag_vhci_rx)
usbip_dump_urb(urb);

- usbip_dbg_vhci_rx("now giveback urb %p\n", urb);
+ usbip_dbg_vhci_rx("now giveback urb %u\n", pdu->base.seqnum);

spin_lock_irqsave(&vhci->lock, flags);
usb_hcd_unlink_urb_from_ep(vhci_hcd_to_hcd(vhci_hcd), urb);
@@ -172,7 +171,7 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev,
pr_info("the urb (seqnum %d) was already given back\n",
pdu->base.seqnum);
} else {
- usbip_dbg_vhci_rx("now giveback urb %p\n", urb);
+ usbip_dbg_vhci_rx("now giveback urb %d\n", pdu->base.seqnum);

/* If unlink is successful, status is -ECONNRESET */
urb->status = pdu->u.ret_unlink.status;
diff --git a/drivers/usb/usbip/vhci_tx.c b/drivers/usb/usbip/vhci_tx.c
index 3e7878fe2fd4..a9a663a578b6 100644
--- a/drivers/usb/usbip/vhci_tx.c
+++ b/drivers/usb/usbip/vhci_tx.c
@@ -83,7 +83,8 @@ static int vhci_send_cmd_submit(struct vhci_device *vdev)
memset(&msg, 0, sizeof(msg));
memset(&iov, 0, sizeof(iov));

- usbip_dbg_vhci_tx("setup txdata urb %p\n", urb);
+ usbip_dbg_vhci_tx("setup txdata urb seqnum %lu\n",
+ priv->seqnum);

/* 1. setup usbip_header */
setup_cmd_submit_pdu(&pdu_header, urb);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index fd47bd96b5d3..6362e3606aa5 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -241,14 +241,24 @@ struct request {
struct request *next_rq;
};

+static inline bool blk_op_is_scsi(unsigned int op)
+{
+ return op == REQ_OP_SCSI_IN || op == REQ_OP_SCSI_OUT;
+}
+
+static inline bool blk_op_is_private(unsigned int op)
+{
+ return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT;
+}
+
static inline bool blk_rq_is_scsi(struct request *rq)
{
- return req_op(rq) == REQ_OP_SCSI_IN || req_op(rq) == REQ_OP_SCSI_OUT;
+ return blk_op_is_scsi(req_op(rq));
}

static inline bool blk_rq_is_private(struct request *rq)
{
- return req_op(rq) == REQ_OP_DRV_IN || req_op(rq) == REQ_OP_DRV_OUT;
+ return blk_op_is_private(req_op(rq));
}

static inline bool blk_rq_is_passthrough(struct request *rq)
@@ -256,6 +266,13 @@ static inline bool blk_rq_is_passthrough(struct request *rq)
return blk_rq_is_scsi(rq) || blk_rq_is_private(rq);
}

+static inline bool bio_is_passthrough(struct bio *bio)
+{
+ unsigned op = bio_op(bio);
+
+ return blk_op_is_scsi(op) || blk_op_is_private(op);
+}
+
static inline unsigned short req_get_ioprio(struct request *req)
{
return req->ioprio;
@@ -952,7 +969,7 @@ extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
extern void blk_rq_unprep_clone(struct request *rq);
extern blk_status_t blk_insert_cloned_request(struct request_queue *q,
struct request *rq);
-extern int blk_rq_append_bio(struct request *rq, struct bio *bio);
+extern int blk_rq_append_bio(struct request *rq, struct bio **bio);
extern void blk_delay_queue(struct request_queue *, unsigned long);
extern void blk_queue_split(struct request_queue *, struct bio **);
extern void blk_recount_segments(struct request_queue *, struct bio *);
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 2477a5cb5bd5..fb83dee528a1 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -86,7 +86,7 @@ enum cpuhp_state {
CPUHP_MM_ZSWP_POOL_PREPARE,
CPUHP_KVM_PPC_BOOK3S_PREPARE,
CPUHP_ZCOMP_PREPARE,
- CPUHP_TIMERS_DEAD,
+ CPUHP_TIMERS_PREPARE,
CPUHP_MIPS_SOC_PREPARE,
CPUHP_BP_PREPARE_DYN,
CPUHP_BP_PREPARE_DYN_END = CPUHP_BP_PREPARE_DYN + 20,
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index ea04ca024f0d..067a6fa675ed 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -272,7 +272,8 @@ struct ipv6_pinfo {
* 100: prefer care-of address
*/
dontfrag:1,
- autoflowlabel:1;
+ autoflowlabel:1,
+ autoflowlabel_set:1;
__u8 min_hopcount;
__u8 tclass;
__be32 rcv_flowinfo;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 401c8972cc3a..8b3d0103c03a 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -546,6 +546,7 @@ struct mlx5_core_sriov {
};

struct mlx5_irq_info {
+ cpumask_var_t mask;
char name[MLX5_MAX_IRQ_NAME];
};

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 69772347f866..c8091f06eaa4 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -147,7 +147,7 @@ enum {
MLX5_CMD_OP_ALLOC_Q_COUNTER = 0x771,
MLX5_CMD_OP_DEALLOC_Q_COUNTER = 0x772,
MLX5_CMD_OP_QUERY_Q_COUNTER = 0x773,
- MLX5_CMD_OP_SET_RATE_LIMIT = 0x780,
+ MLX5_CMD_OP_SET_PP_RATE_LIMIT = 0x780,
MLX5_CMD_OP_QUERY_RATE_LIMIT = 0x781,
MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT = 0x782,
MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT = 0x783,
@@ -7233,7 +7233,7 @@ struct mlx5_ifc_add_vxlan_udp_dport_in_bits {
u8 vxlan_udp_port[0x10];
};

-struct mlx5_ifc_set_rate_limit_out_bits {
+struct mlx5_ifc_set_pp_rate_limit_out_bits {
u8 status[0x8];
u8 reserved_at_8[0x18];

@@ -7242,7 +7242,7 @@ struct mlx5_ifc_set_rate_limit_out_bits {
u8 reserved_at_40[0x40];
};

-struct mlx5_ifc_set_rate_limit_in_bits {
+struct mlx5_ifc_set_pp_rate_limit_in_bits {
u8 opcode[0x10];
u8 reserved_at_10[0x10];

@@ -7255,6 +7255,8 @@ struct mlx5_ifc_set_rate_limit_in_bits {
u8 reserved_at_60[0x20];

u8 rate_limit[0x20];
+
+ u8 reserved_at_a0[0x160];
};

struct mlx5_ifc_access_register_out_bits {
diff --git a/include/linux/pti.h b/include/linux/pti.h
new file mode 100644
index 000000000000..0174883a935a
--- /dev/null
+++ b/include/linux/pti.h
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _INCLUDE_PTI_H
+#define _INCLUDE_PTI_H
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#include <asm/pti.h>
+#else
+static inline void pti_init(void) { }
+#endif
+
+#endif
diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index 37b4bb2545b3..6866df4f31b5 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -101,12 +101,18 @@ static inline bool ptr_ring_full_bh(struct ptr_ring *r)

/* Note: callers invoking this in a loop must use a compiler barrier,
* for example cpu_relax(). Callers must hold producer_lock.
+ * Callers are responsible for making sure pointer that is being queued
+ * points to a valid data.
*/
static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr)
{
if (unlikely(!r->size) || r->queue[r->producer])
return -ENOSPC;

+ /* Make sure the pointer we are storing points to a valid data. */
+ /* Pairs with smp_read_barrier_depends in __ptr_ring_consume. */
+ smp_wmb();
+
r->queue[r->producer++] = ptr;
if (unlikely(r->producer >= r->size))
r->producer = 0;
@@ -275,6 +281,9 @@ static inline void *__ptr_ring_consume(struct ptr_ring *r)
if (ptr)
__ptr_ring_discard_one(r);

+ /* Make sure anyone accessing data through the pointer is up to date. */
+ /* Pairs with smp_wmb in __ptr_ring_produce. */
+ smp_read_barrier_depends();
return ptr;
}

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 4aa40ef02d32..e8418fc77a43 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -214,7 +214,8 @@ struct tcp_sock {
u8 chrono_type:2, /* current chronograph type */
rate_app_limited:1, /* rate_{delivered,interval_us} limited? */
fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
- unused:4;
+ is_sack_reneg:1, /* in recovery from loss with SACK reneg? */
+ unused:3;
u8 nonagle : 4,/* Disable Nagle algorithm? */
thin_lto : 1,/* Use linear timeouts for thin streams */
unused1 : 1,
diff --git a/include/linux/tick.h b/include/linux/tick.h
index cf413b344ddb..5cdac11dd317 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -119,6 +119,7 @@ extern void tick_nohz_idle_exit(void);
extern void tick_nohz_irq_exit(void);
extern ktime_t tick_nohz_get_sleep_length(void);
extern unsigned long tick_nohz_get_idle_calls(void);
+extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu);
extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
#else /* !CONFIG_NO_HZ_COMMON */
diff --git a/include/linux/timer.h b/include/linux/timer.h
index ac66f29c6916..e0ea1fe87572 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -246,9 +246,11 @@ unsigned long round_jiffies_up(unsigned long j);
unsigned long round_jiffies_up_relative(unsigned long j);

#ifdef CONFIG_HOTPLUG_CPU
+int timers_prepare_cpu(unsigned int cpu);
int timers_dead_cpu(unsigned int cpu);
#else
-#define timers_dead_cpu NULL
+#define timers_prepare_cpu NULL
+#define timers_dead_cpu NULL
#endif

#endif
diff --git a/include/net/ip.h b/include/net/ip.h
index 9896f46cbbf1..af8addbaa3c1 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -34,6 +34,7 @@
#include <net/flow_dissector.h>

#define IPV4_MAX_PMTU 65535U /* RFC 2675, Section 5.1 */
+#define IPV4_MIN_MTU 68 /* RFC 791 */

struct sock;

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6ced69940f5c..0a13574134b8 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1085,7 +1085,7 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb);
void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
struct rate_sample *rs);
void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
- struct rate_sample *rs);
+ bool is_sack_reneg, struct rate_sample *rs);
void tcp_rate_check_app_limited(struct sock *sk);

/* These functions determine how the current flow behaves in respect of SACK
diff --git a/init/main.c b/init/main.c
index 8a390f60ec81..b32ec72cdf3d 100644
--- a/init/main.c
+++ b/init/main.c
@@ -75,6 +75,7 @@
#include <linux/slab.h>
#include <linux/perf_event.h>
#include <linux/ptrace.h>
+#include <linux/pti.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/sched_clock.h>
@@ -506,6 +507,8 @@ static void __init mm_init(void)
ioremap_huge_init();
/* Should be run before the first non-init thread is created */
init_espfix_bsp();
+ /* Should be run after espfix64 is set up. */
+ pti_init();
}

asmlinkage __visible void __init start_kernel(void)
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 7891aecc6aec..f21bfa3172d8 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1277,9 +1277,9 @@ static struct cpuhp_step cpuhp_bp_states[] = {
* before blk_mq_queue_reinit_notify() from notify_dead(),
* otherwise a RCU stall occurs.
*/
- [CPUHP_TIMERS_DEAD] = {
+ [CPUHP_TIMERS_PREPARE] = {
.name = "timers:dead",
- .startup.single = NULL,
+ .startup.single = timers_prepare_cpu,
.teardown.single = timers_dead_cpu,
},
/* Kicks the plugged cpu into life */
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 2f52ec0f1539..d6717a3331a1 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -244,7 +244,7 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, unsigned long *util,
#ifdef CONFIG_NO_HZ_COMMON
static bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu)
{
- unsigned long idle_calls = tick_nohz_get_idle_calls();
+ unsigned long idle_calls = tick_nohz_get_idle_calls_cpu(sg_cpu->cpu);
bool ret = idle_calls == sg_cpu->saved_idle_calls;

sg_cpu->saved_idle_calls = idle_calls;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index c7a899c5ce64..dfa4a117fee3 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -674,6 +674,11 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
ts->next_tick = 0;
}

+static inline bool local_timer_softirq_pending(void)
+{
+ return local_softirq_pending() & TIMER_SOFTIRQ;
+}
+
static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
ktime_t now, int cpu)
{
@@ -690,8 +695,18 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
} while (read_seqretry(&jiffies_lock, seq));
ts->last_jiffies = basejiff;

- if (rcu_needs_cpu(basemono, &next_rcu) ||
- arch_needs_cpu() || irq_work_needs_cpu()) {
+ /*
+ * Keep the periodic tick, when RCU, architecture or irq_work
+ * requests it.
+ * Aside of that check whether the local timer softirq is
+ * pending. If so its a bad idea to call get_next_timer_interrupt()
+ * because there is an already expired timer, so it will request
+ * immeditate expiry, which rearms the hardware timer with a
+ * minimal delta which brings us back to this place
+ * immediately. Lather, rinse and repeat...
+ */
+ if (rcu_needs_cpu(basemono, &next_rcu) || arch_needs_cpu() ||
+ irq_work_needs_cpu() || local_timer_softirq_pending()) {
next_tick = basemono + TICK_NSEC;
} else {
/*
@@ -1009,6 +1024,19 @@ ktime_t tick_nohz_get_sleep_length(void)
return ts->sleep_length;
}

+/**
+ * tick_nohz_get_idle_calls_cpu - return the current idle calls counter value
+ * for a particular CPU.
+ *
+ * Called from the schedutil frequency scaling governor in scheduler context.
+ */
+unsigned long tick_nohz_get_idle_calls_cpu(int cpu)
+{
+ struct tick_sched *ts = tick_get_tick_sched(cpu);
+
+ return ts->idle_calls;
+}
+
/**
* tick_nohz_get_idle_calls - return the current idle calls counter value
*
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index f2674a056c26..73e3cdbc61f1 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -814,11 +814,10 @@ static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu)
struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu);

/*
- * If the timer is deferrable and nohz is active then we need to use
- * the deferrable base.
+ * If the timer is deferrable and NO_HZ_COMMON is set then we need
+ * to use the deferrable base.
*/
- if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
- (tflags & TIMER_DEFERRABLE))
+ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE))
base = per_cpu_ptr(&timer_bases[BASE_DEF], cpu);
return base;
}
@@ -828,11 +827,10 @@ static inline struct timer_base *get_timer_this_cpu_base(u32 tflags)
struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);

/*
- * If the timer is deferrable and nohz is active then we need to use
- * the deferrable base.
+ * If the timer is deferrable and NO_HZ_COMMON is set then we need
+ * to use the deferrable base.
*/
- if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active &&
- (tflags & TIMER_DEFERRABLE))
+ if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && (tflags & TIMER_DEFERRABLE))
base = this_cpu_ptr(&timer_bases[BASE_DEF]);
return base;
}
@@ -984,8 +982,6 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
if (!ret && pending_only)
goto out_unlock;

- debug_activate(timer, expires);
-
new_base = get_target_base(base, timer->flags);

if (base != new_base) {
@@ -1009,6 +1005,8 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
}
}

+ debug_activate(timer, expires);
+
timer->expires = expires;
/*
* If 'idx' was calculated above and the base time did not advance
@@ -1644,7 +1642,7 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
base->must_forward_clk = false;

__run_timers(base);
- if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active)
+ if (IS_ENABLED(CONFIG_NO_HZ_COMMON))
__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));
}

@@ -1803,6 +1801,21 @@ static void migrate_timer_list(struct timer_base *new_base, struct hlist_head *h
}
}

+int timers_prepare_cpu(unsigned int cpu)
+{
+ struct timer_base *base;
+ int b;
+
+ for (b = 0; b < NR_BASES; b++) {
+ base = per_cpu_ptr(&timer_bases[b], cpu);
+ base->clk = jiffies;
+ base->next_expiry = base->clk + NEXT_TIMER_MAX_DELTA;
+ base->is_idle = false;
+ base->must_forward_clk = true;
+ }
+ return 0;
+}
+
int timers_dead_cpu(unsigned int cpu)
{
struct timer_base *old_base;
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 81279c6602ff..0476a9372014 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -281,6 +281,8 @@ EXPORT_SYMBOL_GPL(ring_buffer_event_data);
/* Missed count stored at end */
#define RB_MISSED_STORED (1 << 30)

+#define RB_MISSED_FLAGS (RB_MISSED_EVENTS|RB_MISSED_STORED)
+
struct buffer_data_page {
u64 time_stamp; /* page time stamp */
local_t commit; /* write committed index */
@@ -332,7 +334,9 @@ static void rb_init_page(struct buffer_data_page *bpage)
*/
size_t ring_buffer_page_len(void *page)
{
- return local_read(&((struct buffer_data_page *)page)->commit)
+ struct buffer_data_page *bpage = page;
+
+ return (local_read(&bpage->commit) & ~RB_MISSED_FLAGS)
+ BUF_PAGE_HDR_SIZE;
}

@@ -4439,8 +4443,13 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data)
{
struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
struct buffer_data_page *bpage = data;
+ struct page *page = virt_to_page(bpage);
unsigned long flags;

+ /* If the page is still in use someplace else, we can't reuse it */
+ if (page_ref_count(page) > 1)
+ goto out;
+
local_irq_save(flags);
arch_spin_lock(&cpu_buffer->lock);

@@ -4452,6 +4461,7 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, int cpu, void *data)
arch_spin_unlock(&cpu_buffer->lock);
local_irq_restore(flags);

+ out:
free_page((unsigned long)bpage);
}
EXPORT_SYMBOL_GPL(ring_buffer_free_read_page);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 80de14973b42..76bcc80b893e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6769,7 +6769,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
.spd_release = buffer_spd_release,
};
struct buffer_ref *ref;
- int entries, size, i;
+ int entries, i;
ssize_t ret = 0;

#ifdef CONFIG_TRACER_MAX_TRACE
@@ -6823,14 +6823,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
break;
}

- /*
- * zero out any left over data, this is going to
- * user land.
- */
- size = ring_buffer_page_len(ref->page);
- if (size < PAGE_SIZE)
- memset(ref->page + size, 0, PAGE_SIZE - size);
-
page = virt_to_page(ref->page);

spd.pages[i] = page;
@@ -7588,6 +7580,7 @@ allocate_trace_buffer(struct trace_array *tr, struct trace_buffer *buf, int size
buf->data = alloc_percpu(struct trace_array_cpu);
if (!buf->data) {
ring_buffer_free(buf->buffer);
+ buf->buffer = NULL;
return -ENOMEM;
}

@@ -7611,7 +7604,9 @@ static int allocate_trace_buffers(struct trace_array *tr, int size)
allocate_snapshot ? size : 1);
if (WARN_ON(ret)) {
ring_buffer_free(tr->trace_buffer.buffer);
+ tr->trace_buffer.buffer = NULL;
free_percpu(tr->trace_buffer.data);
+ tr->trace_buffer.data = NULL;
return -ENOMEM;
}
tr->allocated_snapshot = allocate_snapshot;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index de2152730809..08190db0a2dc 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1223,19 +1223,20 @@ static int br_dev_newlink(struct net *src_net, struct net_device *dev,
struct net_bridge *br = netdev_priv(dev);
int err;

+ err = register_netdevice(dev);
+ if (err)
+ return err;
+
if (tb[IFLA_ADDRESS]) {
spin_lock_bh(&br->lock);
br_stp_change_bridge_id(br, nla_data(tb[IFLA_ADDRESS]));
spin_unlock_bh(&br->lock);
}

- err = register_netdevice(dev);
- if (err)
- return err;
-
err = br_changelink(dev, tb, data, extack);
if (err)
- unregister_netdevice(dev);
+ br_dev_delete(dev, NULL);
+
return err;
}

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 6cfdc7c84c48..0dd6359e5924 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -266,7 +266,7 @@ struct net *get_net_ns_by_id(struct net *net, int id)
spin_lock_bh(&net->nsid_lock);
peer = idr_find(&net->netns_ids, id);
if (peer)
- get_net(peer);
+ peer = maybe_get_net(peer);
spin_unlock_bh(&net->nsid_lock);
rcu_read_unlock();

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e140ba49b30a..15fa5baa8fae 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1181,12 +1181,12 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
int i, new_frags;
u32 d_off;

- if (!num_frags)
- return 0;
-
if (skb_shared(skb) || skb_unclone(skb, gfp_mask))
return -EINVAL;

+ if (!num_frags)
+ goto release;
+
new_frags = (__skb_pagelen(skb) + PAGE_SIZE - 1) >> PAGE_SHIFT;
for (i = 0; i < new_frags; i++) {
page = alloc_page(gfp_mask);
@@ -1242,6 +1242,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
__skb_fill_page_desc(skb, new_frags - 1, head, 0, d_off);
skb_shinfo(skb)->nr_frags = new_frags;

+release:
skb_zcopy_clear(skb, false);
return 0;
}
@@ -3657,8 +3658,6 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,

skb_shinfo(nskb)->tx_flags |= skb_shinfo(head_skb)->tx_flags &
SKBTX_SHARED_FRAG;
- if (skb_zerocopy_clone(nskb, head_skb, GFP_ATOMIC))
- goto err;

while (pos < offset + len) {
if (i >= nfrags) {
@@ -3684,6 +3683,8 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,

if (unlikely(skb_orphan_frags(frag_skb, GFP_ATOMIC)))
goto err;
+ if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC))
+ goto err;

*nskb_frag = *frag;
__skb_frag_ref(nskb_frag);
@@ -4296,7 +4297,7 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
struct sock *sk = skb->sk;

if (!skb_may_tx_timestamp(sk, false))
- return;
+ goto err;

/* Take a reference to prevent skb_orphan() from freeing the socket,
* but only if the socket refcount is not zero.
@@ -4305,7 +4306,11 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
*skb_hwtstamps(skb) = *hwtstamps;
__skb_complete_tx_timestamp(skb, sk, SCM_TSTAMP_SND, false);
sock_put(sk);
+ return;
}
+
+err:
+ kfree_skb(skb);
}
EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index d7adc0616599..bffa88ecc534 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1420,7 +1420,7 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev)

static bool inetdev_valid_mtu(unsigned int mtu)
{
- return mtu >= 68;
+ return mtu >= IPV4_MIN_MTU;
}

static void inetdev_send_gratuitous_arp(struct net_device *dev,
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 37819ab4cc74..d72874150905 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1274,14 +1274,19 @@ static int __net_init ip_fib_net_init(struct net *net)

static void ip_fib_net_exit(struct net *net)
{
- unsigned int i;
+ int i;

rtnl_lock();
#ifdef CONFIG_IP_MULTIPLE_TABLES
RCU_INIT_POINTER(net->ipv4.fib_main, NULL);
RCU_INIT_POINTER(net->ipv4.fib_default, NULL);
#endif
- for (i = 0; i < FIB_TABLE_HASHSZ; i++) {
+ /* Destroy the tables in reverse order to guarantee that the
+ * local table, ID 255, is destroyed before the main table, ID
+ * 254. This is necessary as the local table may contain
+ * references to data contained in the main table.
+ */
+ for (i = FIB_TABLE_HASHSZ - 1; i >= 0; i--) {
struct hlist_head *head = &net->ipv4.fib_table_hash[i];
struct hlist_node *tmp;
struct fib_table *tb;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 01ed22139ac2..aff3751df950 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -706,7 +706,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)

nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
int type = nla_type(nla);
- u32 val;
+ u32 fi_val, val;

if (!type)
continue;
@@ -723,7 +723,11 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
val = nla_get_u32(nla);
}

- if (fi->fib_metrics->metrics[type - 1] != val)
+ fi_val = fi->fib_metrics->metrics[type - 1];
+ if (type == RTAX_FEATURES)
+ fi_val &= ~DST_FEATURE_ECN_CA;
+
+ if (fi_val != val)
return false;
}

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index ab183af0b5b6..c621266e0306 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -89,6 +89,7 @@
#include <linux/rtnetlink.h>
#include <linux/times.h>
#include <linux/pkt_sched.h>
+#include <linux/byteorder/generic.h>

#include <net/net_namespace.h>
#include <net/arp.h>
@@ -321,6 +322,23 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted)
return scount;
}

+/* source address selection per RFC 3376 section 4.2.13 */
+static __be32 igmpv3_get_srcaddr(struct net_device *dev,
+ const struct flowi4 *fl4)
+{
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
+
+ if (!in_dev)
+ return htonl(INADDR_ANY);
+
+ for_ifa(in_dev) {
+ if (inet_ifa_match(fl4->saddr, ifa))
+ return fl4->saddr;
+ } endfor_ifa(in_dev);
+
+ return htonl(INADDR_ANY);
+}
+
static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
{
struct sk_buff *skb;
@@ -368,7 +386,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
pip->frag_off = htons(IP_DF);
pip->ttl = 1;
pip->daddr = fl4.daddr;
- pip->saddr = fl4.saddr;
+ pip->saddr = igmpv3_get_srcaddr(dev, &fl4);
pip->protocol = IPPROTO_IGMP;
pip->tot_len = 0; /* filled in later */
ip_select_ident(net, skb, NULL);
@@ -404,16 +422,17 @@ static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel)
}

static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc,
- int type, struct igmpv3_grec **ppgr)
+ int type, struct igmpv3_grec **ppgr, unsigned int mtu)
{
struct net_device *dev = pmc->interface->dev;
struct igmpv3_report *pih;
struct igmpv3_grec *pgr;

- if (!skb)
- skb = igmpv3_newpack(dev, dev->mtu);
- if (!skb)
- return NULL;
+ if (!skb) {
+ skb = igmpv3_newpack(dev, mtu);
+ if (!skb)
+ return NULL;
+ }
pgr = skb_put(skb, sizeof(struct igmpv3_grec));
pgr->grec_type = type;
pgr->grec_auxwords = 0;
@@ -436,12 +455,17 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
struct igmpv3_grec *pgr = NULL;
struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list;
int scount, stotal, first, isquery, truncate;
+ unsigned int mtu;

if (pmc->multiaddr == IGMP_ALL_HOSTS)
return skb;
if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
return skb;

+ mtu = READ_ONCE(dev->mtu);
+ if (mtu < IPV4_MIN_MTU)
+ return skb;
+
isquery = type == IGMPV3_MODE_IS_INCLUDE ||
type == IGMPV3_MODE_IS_EXCLUDE;
truncate = type == IGMPV3_MODE_IS_EXCLUDE ||
@@ -462,7 +486,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
if (skb)
igmpv3_sendpack(skb);
- skb = igmpv3_newpack(dev, dev->mtu);
+ skb = igmpv3_newpack(dev, mtu);
}
}
first = 1;
@@ -498,12 +522,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
pgr->grec_nsrcs = htons(scount);
if (skb)
igmpv3_sendpack(skb);
- skb = igmpv3_newpack(dev, dev->mtu);
+ skb = igmpv3_newpack(dev, mtu);
first = 1;
scount = 0;
}
if (first) {
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
first = 0;
}
if (!skb)
@@ -538,7 +562,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
igmpv3_sendpack(skb);
skb = NULL; /* add_grhead will get a new one */
}
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
}
}
if (pgr)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index e9805ad664ac..4e90082b23a6 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -349,8 +349,8 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
dev->needed_headroom = t_hlen + hlen;
mtu -= (dev->hard_header_len + t_hlen);

- if (mtu < 68)
- mtu = 68;
+ if (mtu < IPV4_MIN_MTU)
+ mtu = IPV4_MIN_MTU;

return mtu;
}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 33b70bfd1122..125c1eab3eaa 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -513,11 +513,16 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
int err;
struct ip_options_data opt_copy;
struct raw_frag_vec rfv;
+ int hdrincl;

err = -EMSGSIZE;
if (len > 0xFFFF)
goto out;

+ /* hdrincl should be READ_ONCE(inet->hdrincl)
+ * but READ_ONCE() doesn't work with bit fields
+ */
+ hdrincl = inet->hdrincl;
/*
* Check the flags.
*/
@@ -593,7 +598,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
/* Linux does not mangle headers on raw sockets,
* so that IP options + IP_HDRINCL is non-sense.
*/
- if (inet->hdrincl)
+ if (hdrincl)
goto done;
if (ipc.opt->opt.srr) {
if (!daddr)
@@ -615,12 +620,12 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)

flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE,
- inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol,
+ hdrincl ? IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk) |
- (inet->hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
+ (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
daddr, saddr, 0, 0, sk->sk_uid);

- if (!inet->hdrincl) {
+ if (!hdrincl) {
rfv.msg = msg;
rfv.hlen = 0;

@@ -645,7 +650,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
goto do_confirm;
back_from_confirm:

- if (inet->hdrincl)
+ if (hdrincl)
err = raw_send_hdrinc(sk, &fl4, msg, len,
&rt, msg->msg_flags, &ipc.sockc);

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5091402720ab..a0c72b09cefc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2356,6 +2356,7 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->snd_cwnd_cnt = 0;
tp->window_clamp = 0;
tcp_set_ca_state(sk, TCP_CA_Open);
+ tp->is_sack_reneg = 0;
tcp_clear_retrans(tp);
inet_csk_delack_init(sk);
/* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 69ee877574d0..8322f26e770e 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -110,7 +110,8 @@ struct bbr {
u32 lt_last_lost; /* LT intvl start: tp->lost */
u32 pacing_gain:10, /* current gain for setting pacing rate */
cwnd_gain:10, /* current gain for setting cwnd */
- full_bw_cnt:3, /* number of rounds without large bw gains */
+ full_bw_reached:1, /* reached full bw in Startup? */
+ full_bw_cnt:2, /* number of rounds without large bw gains */
cycle_idx:3, /* current index in pacing_gain cycle array */
has_seen_rtt:1, /* have we seen an RTT sample yet? */
unused_b:5;
@@ -180,7 +181,7 @@ static bool bbr_full_bw_reached(const struct sock *sk)
{
const struct bbr *bbr = inet_csk_ca(sk);

- return bbr->full_bw_cnt >= bbr_full_bw_cnt;
+ return bbr->full_bw_reached;
}

/* Return the windowed max recent bandwidth sample, in pkts/uS << BW_SCALE. */
@@ -717,6 +718,7 @@ static void bbr_check_full_bw_reached(struct sock *sk,
return;
}
++bbr->full_bw_cnt;
+ bbr->full_bw_reached = bbr->full_bw_cnt >= bbr_full_bw_cnt;
}

/* If pipe is probably full, drain the queue and then enter steady-state. */
@@ -850,6 +852,7 @@ static void bbr_init(struct sock *sk)
bbr->restore_cwnd = 0;
bbr->round_start = 0;
bbr->idle_restart = 0;
+ bbr->full_bw_reached = 0;
bbr->full_bw = 0;
bbr->full_bw_cnt = 0;
bbr->cycle_mstamp = 0;
@@ -871,6 +874,11 @@ static u32 bbr_sndbuf_expand(struct sock *sk)
*/
static u32 bbr_undo_cwnd(struct sock *sk)
{
+ struct bbr *bbr = inet_csk_ca(sk);
+
+ bbr->full_bw = 0; /* spurious slow-down; reset full pipe detection */
+ bbr->full_bw_cnt = 0;
+ bbr_reset_lt_bw_sampling(sk);
return tcp_sk(sk)->snd_cwnd;
}

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index c5447b9f8517..ff48ac654e5a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -521,9 +521,6 @@ static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep)
u32 new_sample = tp->rcv_rtt_est.rtt_us;
long m = sample;

- if (m == 0)
- m = 1;
-
if (new_sample != 0) {
/* If we sample in larger samples in the non-timestamp
* case, we could grossly overestimate the RTT especially
@@ -560,6 +557,8 @@ static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp)
if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq))
return;
delta_us = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcv_rtt_est.time);
+ if (!delta_us)
+ delta_us = 1;
tcp_rcv_rtt_update(tp, delta_us, 1);

new_measure:
@@ -576,8 +575,11 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
(TCP_SKB_CB(skb)->end_seq -
TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) {
u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
- u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
+ u32 delta_us;

+ if (!delta)
+ delta = 1;
+ delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
tcp_rcv_rtt_update(tp, delta_us, 0);
}
}
@@ -1975,6 +1977,8 @@ void tcp_enter_loss(struct sock *sk)
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
tp->sacked_out = 0;
tp->fackets_out = 0;
+ /* Mark SACK reneging until we recover from this loss event. */
+ tp->is_sack_reneg = 1;
}
tcp_clear_all_retrans_hints(tp);

@@ -2428,6 +2432,7 @@ static bool tcp_try_undo_recovery(struct sock *sk)
return true;
}
tcp_set_ca_state(sk, TCP_CA_Open);
+ tp->is_sack_reneg = 0;
return false;
}

@@ -2459,8 +2464,10 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPSPURIOUSRTOS);
inet_csk(sk)->icsk_retransmits = 0;
- if (frto_undo || tcp_is_sack(tp))
+ if (frto_undo || tcp_is_sack(tp)) {
tcp_set_ca_state(sk, TCP_CA_Open);
+ tp->is_sack_reneg = 0;
+ }
return true;
}
return false;
@@ -3551,6 +3558,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
struct tcp_sacktag_state sack_state;
struct rate_sample rs = { .prior_delivered = 0 };
u32 prior_snd_una = tp->snd_una;
+ bool is_sack_reneg = tp->is_sack_reneg;
u32 ack_seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
bool is_dupack = false;
@@ -3666,7 +3674,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)

delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */
lost = tp->lost - lost; /* freshly marked lost */
- tcp_rate_gen(sk, delivered, lost, sack_state.rate);
+ tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate);
tcp_cong_control(sk, ack, delivered, flag, sack_state.rate);
tcp_xmit_recovery(sk, rexmit);
return 1;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5a5ed4f14678..cab4b935e474 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -844,7 +844,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
req->ts_recent,
0,
- tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,
+ tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->saddr,
AF_INET),
inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
ip_hdr(skb)->tos);
diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c
index 3330a370d306..c61240e43923 100644
--- a/net/ipv4/tcp_rate.c
+++ b/net/ipv4/tcp_rate.c
@@ -106,7 +106,7 @@ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,

/* Update the connection delivery information and generate a rate sample. */
void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
- struct rate_sample *rs)
+ bool is_sack_reneg, struct rate_sample *rs)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 snd_us, ack_us;
@@ -124,8 +124,12 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,

rs->acked_sacked = delivered; /* freshly ACKed or SACKed */
rs->losses = lost; /* freshly marked lost */
- /* Return an invalid sample if no timing information is available. */
- if (!rs->prior_mstamp) {
+ /* Return an invalid sample if no timing information is available or
+ * in recovery from loss with SACK reneging. Rate samples taken during
+ * a SACK reneging event may overestimate bw by including packets that
+ * were SACKed before the reneg.
+ */
+ if (!rs->prior_mstamp || is_sack_reneg) {
rs->delivered = -1;
rs->interval_us = -1;
return;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 655dd8d7f064..e9af1879cd53 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -264,6 +264,7 @@ void tcp_delack_timer_handler(struct sock *sk)
icsk->icsk_ack.pingpong = 0;
icsk->icsk_ack.ato = TCP_ATO_MIN;
}
+ tcp_mstamp_refresh(tcp_sk(sk));
tcp_send_ack(sk);
__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS);
}
@@ -627,6 +628,7 @@ static void tcp_keepalive_timer (unsigned long data)
goto out;
}

+ tcp_mstamp_refresh(tp);
if (sk->sk_state == TCP_FIN_WAIT2 && sock_flag(sk, SOCK_DEAD)) {
if (tp->linger2 >= 0) {
const int tmo = tcp_fin_time(sk) - TCP_TIMEWAIT_LEN;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 2ec39404c449..c5318f5f6a14 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -231,7 +231,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
.proxy_ndp = 0,
.accept_source_route = 0, /* we do not accept RH0 by default. */
.disable_ipv6 = 0,
- .accept_dad = 1,
+ .accept_dad = 0,
.suppress_frag_ndisc = 1,
.accept_ra_mtu = 1,
.stable_secret = {
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index fe5262fd6aa5..bcbd5f3bf8bd 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -210,7 +210,6 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
np->mcast_hops = IPV6_DEFAULT_MCASTHOPS;
np->mc_loop = 1;
np->pmtudisc = IPV6_PMTUDISC_WANT;
- np->autoflowlabel = ip6_default_np_autolabel(net);
np->repflow = net->ipv6.sysctl.flowlabel_reflect;
sk->sk_ipv6only = net->ipv6.sysctl.bindv6only;

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 5d6bee070871..7a2df6646486 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1020,6 +1020,36 @@ static void ip6gre_tunnel_setup(struct net_device *dev)
eth_random_addr(dev->perm_addr);
}

+#define GRE6_FEATURES (NETIF_F_SG | \
+ NETIF_F_FRAGLIST | \
+ NETIF_F_HIGHDMA | \
+ NETIF_F_HW_CSUM)
+
+static void ip6gre_tnl_init_features(struct net_device *dev)
+{
+ struct ip6_tnl *nt = netdev_priv(dev);
+
+ dev->features |= GRE6_FEATURES;
+ dev->hw_features |= GRE6_FEATURES;
+
+ if (!(nt->parms.o_flags & TUNNEL_SEQ)) {
+ /* TCP offload with GRE SEQ is not supported, nor
+ * can we support 2 levels of outer headers requiring
+ * an update.
+ */
+ if (!(nt->parms.o_flags & TUNNEL_CSUM) ||
+ nt->encap.type == TUNNEL_ENCAP_NONE) {
+ dev->features |= NETIF_F_GSO_SOFTWARE;
+ dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+ }
+
+ /* Can use a lockless transmit, unless we generate
+ * output sequences
+ */
+ dev->features |= NETIF_F_LLTX;
+ }
+}
+
static int ip6gre_tunnel_init_common(struct net_device *dev)
{
struct ip6_tnl *tunnel;
@@ -1054,6 +1084,8 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
if (!(tunnel->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
dev->mtu -= 8;

+ ip6gre_tnl_init_features(dev);
+
return 0;
}

@@ -1302,11 +1334,6 @@ static const struct net_device_ops ip6gre_tap_netdev_ops = {
.ndo_get_iflink = ip6_tnl_get_iflink,
};

-#define GRE6_FEATURES (NETIF_F_SG | \
- NETIF_F_FRAGLIST | \
- NETIF_F_HIGHDMA | \
- NETIF_F_HW_CSUM)
-
static void ip6gre_tap_setup(struct net_device *dev)
{

@@ -1386,26 +1413,6 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
nt->net = dev_net(dev);
ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);

- dev->features |= GRE6_FEATURES;
- dev->hw_features |= GRE6_FEATURES;
-
- if (!(nt->parms.o_flags & TUNNEL_SEQ)) {
- /* TCP offload with GRE SEQ is not supported, nor
- * can we support 2 levels of outer headers requiring
- * an update.
- */
- if (!(nt->parms.o_flags & TUNNEL_CSUM) ||
- (nt->encap.type == TUNNEL_ENCAP_NONE)) {
- dev->features |= NETIF_F_GSO_SOFTWARE;
- dev->hw_features |= NETIF_F_GSO_SOFTWARE;
- }
-
- /* Can use a lockless transmit, unless we generate
- * output sequences
- */
- dev->features |= NETIF_F_LLTX;
- }
-
err = register_netdevice(dev);
if (err)
goto out;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 5110a418cc4d..f7dd51c42314 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -166,6 +166,14 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
!(IP6CB(skb)->flags & IP6SKB_REROUTED));
}

+static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np)
+{
+ if (!np->autoflowlabel_set)
+ return ip6_default_np_autolabel(net);
+ else
+ return np->autoflowlabel;
+}
+
/*
* xmit an sk_buff (used by TCP, SCTP and DCCP)
* Note : socket lock is not held for SYNACK packets, but might be modified
@@ -230,7 +238,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
hlimit = ip6_dst_hoplimit(dst);

ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel,
- np->autoflowlabel, fl6));
+ ip6_autoflowlabel(net, np), fl6));

hdr->payload_len = htons(seg_len);
hdr->nexthdr = proto;
@@ -1626,7 +1634,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,

ip6_flow_hdr(hdr, v6_cork->tclass,
ip6_make_flowlabel(net, skb, fl6->flowlabel,
- np->autoflowlabel, fl6));
+ ip6_autoflowlabel(net, np), fl6));
hdr->hop_limit = v6_cork->hop_limit;
hdr->nexthdr = proto;
hdr->saddr = fl6->saddr;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a1c24443cd9e..ef958d50746b 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -912,7 +912,7 @@ static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto,
if (t->parms.collect_md) {
tun_dst = ipv6_tun_rx_dst(skb, 0, 0, 0);
if (!tun_dst)
- return 0;
+ goto drop;
}
ret = __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate,
log_ecn_error);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index a5e466d4e093..90dbfa78a390 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -878,6 +878,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname,
break;
case IPV6_AUTOFLOWLABEL:
np->autoflowlabel = valbool;
+ np->autoflowlabel_set = 1;
retv = 0;
break;
case IPV6_RECVFRAGSIZE:
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 12b7c27ce5ce..9a38a2c641fa 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -1682,16 +1682,16 @@ static int grec_size(struct ifmcaddr6 *pmc, int type, int gdel, int sdel)
}

static struct sk_buff *add_grhead(struct sk_buff *skb, struct ifmcaddr6 *pmc,
- int type, struct mld2_grec **ppgr)
+ int type, struct mld2_grec **ppgr, unsigned int mtu)
{
- struct net_device *dev = pmc->idev->dev;
struct mld2_report *pmr;
struct mld2_grec *pgr;

- if (!skb)
- skb = mld_newpack(pmc->idev, dev->mtu);
- if (!skb)
- return NULL;
+ if (!skb) {
+ skb = mld_newpack(pmc->idev, mtu);
+ if (!skb)
+ return NULL;
+ }
pgr = skb_put(skb, sizeof(struct mld2_grec));
pgr->grec_type = type;
pgr->grec_auxwords = 0;
@@ -1714,10 +1714,15 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
struct mld2_grec *pgr = NULL;
struct ip6_sf_list *psf, *psf_next, *psf_prev, **psf_list;
int scount, stotal, first, isquery, truncate;
+ unsigned int mtu;

if (pmc->mca_flags & MAF_NOREPORT)
return skb;

+ mtu = READ_ONCE(dev->mtu);
+ if (mtu < IPV6_MIN_MTU)
+ return skb;
+
isquery = type == MLD2_MODE_IS_INCLUDE ||
type == MLD2_MODE_IS_EXCLUDE;
truncate = type == MLD2_MODE_IS_EXCLUDE ||
@@ -1738,7 +1743,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) {
if (skb)
mld_sendpack(skb);
- skb = mld_newpack(idev, dev->mtu);
+ skb = mld_newpack(idev, mtu);
}
}
first = 1;
@@ -1774,12 +1779,12 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
pgr->grec_nsrcs = htons(scount);
if (skb)
mld_sendpack(skb);
- skb = mld_newpack(idev, dev->mtu);
+ skb = mld_newpack(idev, mtu);
first = 1;
scount = 0;
}
if (first) {
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
first = 0;
}
if (!skb)
@@ -1814,7 +1819,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc,
mld_sendpack(skb);
skb = NULL; /* add_grhead will get a new one */
}
- skb = add_grhead(skb, pmc, type, &pgr);
+ skb = add_grhead(skb, pmc, type, &pgr, mtu);
}
}
if (pgr)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 598efa8cfe25..ca8d3266e92e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3700,19 +3700,13 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
if (!ipv6_addr_any(&fl6.saddr))
flags |= RT6_LOOKUP_F_HAS_SADDR;

- if (!fibmatch)
- dst = ip6_route_input_lookup(net, dev, &fl6, flags);
- else
- dst = ip6_route_lookup(net, &fl6, 0);
+ dst = ip6_route_input_lookup(net, dev, &fl6, flags);

rcu_read_unlock();
} else {
fl6.flowi6_oif = oif;

- if (!fibmatch)
- dst = ip6_route_output(net, NULL, &fl6);
- else
- dst = ip6_route_lookup(net, &fl6, 0);
+ dst = ip6_route_output(net, NULL, &fl6);
}


@@ -3729,6 +3723,15 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
goto errout;
}

+ if (fibmatch && rt->dst.from) {
+ struct rt6_info *ort = container_of(rt->dst.from,
+ struct rt6_info, dst);
+
+ dst_hold(&ort->dst);
+ ip6_rt_put(rt);
+ rt = ort;
+ }
+
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb) {
ip6_rt_put(rt);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 32ded300633d..237cc6187c5a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -988,7 +988,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale,
tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
req->ts_recent, sk->sk_bound_dev_if,
- tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->daddr),
+ tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr),
0, 0);
}

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 15c99dfa3d72..aac9d68b4636 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -254,6 +254,9 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
struct sock *sk = skb->sk;
int ret = -ENOMEM;

+ if (!net_eq(dev_net(dev), sock_net(sk)))
+ return 0;
+
dev_hold(dev);

if (is_vmalloc_addr(skb->head))
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index cfb652a4e007..dbe1079a1651 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -532,6 +532,7 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
return -EINVAL;

skb_reset_network_header(skb);
+ key->eth.type = skb->protocol;
} else {
eth = eth_hdr(skb);
ether_addr_copy(key->eth.src, eth->h_source);
@@ -545,15 +546,23 @@ static int key_extract(struct sk_buff *skb, struct sw_flow_key *key)
if (unlikely(parse_vlan(skb, key)))
return -ENOMEM;

- skb->protocol = parse_ethertype(skb);
- if (unlikely(skb->protocol == htons(0)))
+ key->eth.type = parse_ethertype(skb);
+ if (unlikely(key->eth.type == htons(0)))
return -ENOMEM;

+ /* Multiple tagged packets need to retain TPID to satisfy
+ * skb_vlan_pop(), which will later shift the ethertype into
+ * skb->protocol.
+ */
+ if (key->eth.cvlan.tci & htons(VLAN_TAG_PRESENT))
+ skb->protocol = key->eth.cvlan.tpid;
+ else
+ skb->protocol = key->eth.type;
+
skb_reset_network_header(skb);
__skb_push(skb, skb->data - skb_mac_header(skb));
}
skb_reset_mac_len(skb);
- key->eth.type = skb->protocol;

/* Network layer. */
if (key->eth.type == htons(ETH_P_IP)) {
diff --git a/net/rds/send.c b/net/rds/send.c
index b52cdc8ae428..f72466c63f0c 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1009,6 +1009,9 @@ static int rds_rdma_bytes(struct msghdr *msg, size_t *rdma_bytes)
continue;

if (cmsg->cmsg_type == RDS_CMSG_RDMA_ARGS) {
+ if (cmsg->cmsg_len <
+ CMSG_LEN(sizeof(struct rds_rdma_args)))
+ return -EINVAL;
args = CMSG_DATA(cmsg);
*rdma_bytes += args->remote_vec.bytes;
}
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index 44de4ee51ce9..a08a32fa0949 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -59,11 +59,12 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt)
struct net_device *dev = qdisc_dev(sch);
int err;

+ net_inc_ingress_queue();
+
err = tcf_block_get(&q->block, &dev->ingress_cl_list);
if (err)
return err;

- net_inc_ingress_queue();
sch->flags |= TCQ_F_CPUSTATS;

return 0;
@@ -153,6 +154,9 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt)
struct net_device *dev = qdisc_dev(sch);
int err;

+ net_inc_ingress_queue();
+ net_inc_egress_queue();
+
err = tcf_block_get(&q->ingress_block, &dev->ingress_cl_list);
if (err)
return err;
@@ -161,9 +165,6 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt)
if (err)
return err;

- net_inc_ingress_queue();
- net_inc_egress_queue();
-
sch->flags |= TCQ_F_CPUSTATS;

return 0;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index d6163f7aefb1..df806b8819aa 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3874,13 +3874,17 @@ static int sctp_setsockopt_reset_streams(struct sock *sk,
struct sctp_association *asoc;
int retval = -EINVAL;

- if (optlen < sizeof(struct sctp_reset_streams))
+ if (optlen < sizeof(*params))
return -EINVAL;

params = memdup_user(optval, optlen);
if (IS_ERR(params))
return PTR_ERR(params);

+ if (params->srs_number_streams * sizeof(__u16) >
+ optlen - sizeof(*params))
+ goto out;
+
asoc = sctp_id2assoc(sk, params->srs_assoc_id);
if (!asoc)
goto out;
@@ -4413,7 +4417,7 @@ static int sctp_init_sock(struct sock *sk)
SCTP_DBG_OBJCNT_INC(sock);

local_bh_disable();
- percpu_counter_inc(&sctp_sockets_allocated);
+ sk_sockets_allocated_inc(sk);
sock_prot_inuse_add(net, sk->sk_prot, 1);

/* Nothing can fail after this block, otherwise
@@ -4457,7 +4461,7 @@ static void sctp_destroy_sock(struct sock *sk)
}
sctp_endpoint_free(sp->ep);
local_bh_disable();
- percpu_counter_dec(&sctp_sockets_allocated);
+ sk_sockets_allocated_dec(sk);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
local_bh_enable();
}
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index d50edd6e0019..98a44ecb11e7 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -709,11 +709,11 @@ static unsigned int tipc_poll(struct file *file, struct socket *sock,

switch (sk->sk_state) {
case TIPC_ESTABLISHED:
+ case TIPC_CONNECTING:
if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk))
mask |= POLLOUT;
/* fall thru' */
case TIPC_LISTEN:
- case TIPC_CONNECTING:
if (!skb_queue_empty(&sk->sk_receive_queue))
mask |= (POLLIN | POLLRDNORM);
break;
diff --git a/security/Kconfig b/security/Kconfig
index e8e449444e65..6614b9312b45 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -54,6 +54,17 @@ config SECURITY_NETWORK
implement socket and networking access controls.
If you are unsure how to answer this question, answer N.

+config PAGE_TABLE_ISOLATION
+ bool "Remove the kernel mapping in user mode"
+ depends on X86_64 && !UML
+ default y
+ help
+ This feature reduces the number of hardware side channels by
+ ensuring that the majority of kernel addresses are not mapped
+ into userspace.
+
+ See Documentation/x86/pagetable-isolation.txt for more details.
+
config SECURITY_INFINIBAND
bool "Infiniband Security Hooks"
depends on SECURITY && INFINIBAND
diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c
index 038a180d3f81..cbe818eda336 100644
--- a/sound/hda/hdac_i915.c
+++ b/sound/hda/hdac_i915.c
@@ -325,7 +325,7 @@ static int hdac_component_master_match(struct device *dev, void *data)
*/
int snd_hdac_i915_register_notifier(const struct i915_audio_component_audio_ops *aops)
{
- if (WARN_ON(!hdac_acomp))
+ if (!hdac_acomp)
return -ENODEV;

hdac_acomp->audio_ops = aops;
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index a81aacf684b2..37e1cf8218ff 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -271,6 +271,8 @@ enum {
CXT_FIXUP_HP_SPECTRE,
CXT_FIXUP_HP_GATE_MIC,
CXT_FIXUP_MUTE_LED_GPIO,
+ CXT_FIXUP_HEADSET_MIC,
+ CXT_FIXUP_HP_MIC_NO_PRESENCE,
};

/* for hda_fixup_thinkpad_acpi() */
@@ -350,6 +352,18 @@ static void cxt_fixup_headphone_mic(struct hda_codec *codec,
}
}

+static void cxt_fixup_headset_mic(struct hda_codec *codec,
+ const struct hda_fixup *fix, int action)
+{
+ struct conexant_spec *spec = codec->spec;
+
+ switch (action) {
+ case HDA_FIXUP_ACT_PRE_PROBE:
+ spec->parse_flags |= HDA_PINCFG_HEADSET_MIC;
+ break;
+ }
+}
+
/* OPLC XO 1.5 fixup */

/* OLPC XO-1.5 supports DC input mode (e.g. for use with analog sensors)
@@ -880,6 +894,19 @@ static const struct hda_fixup cxt_fixups[] = {
.type = HDA_FIXUP_FUNC,
.v.func = cxt_fixup_mute_led_gpio,
},
+ [CXT_FIXUP_HEADSET_MIC] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = cxt_fixup_headset_mic,
+ },
+ [CXT_FIXUP_HP_MIC_NO_PRESENCE] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = (const struct hda_pintbl[]) {
+ { 0x1a, 0x02a1113c },
+ { }
+ },
+ .chained = true,
+ .chain_id = CXT_FIXUP_HEADSET_MIC,
+ },
};

static const struct snd_pci_quirk cxt5045_fixups[] = {
@@ -934,6 +961,8 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
SND_PCI_QUIRK(0x103c, 0x8115, "HP Z1 Gen3", CXT_FIXUP_HP_GATE_MIC),
SND_PCI_QUIRK(0x103c, 0x814f, "HP ZBook 15u G3", CXT_FIXUP_MUTE_LED_GPIO),
SND_PCI_QUIRK(0x103c, 0x822e, "HP ProBook 440 G4", CXT_FIXUP_MUTE_LED_GPIO),
+ SND_PCI_QUIRK(0x103c, 0x8299, "HP 800 G3 SFF", CXT_FIXUP_HP_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x103c, 0x829a, "HP 800 G3 DM", CXT_FIXUP_HP_MIC_NO_PRESENCE),
SND_PCI_QUIRK(0x1043, 0x138d, "Asus", CXT_FIXUP_HEADPHONE_MIC_PIN),
SND_PCI_QUIRK(0x152d, 0x0833, "OLPC XO-1.5", CXT_FIXUP_OLPC_XO),
SND_PCI_QUIRK(0x17aa, 0x20f2, "Lenovo T400", CXT_PINCFG_LENOVO_TP410),
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 9ac4b9076ee2..acdb196ddb44 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -324,8 +324,12 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
case 0x10ec0292:
alc_update_coef_idx(codec, 0x4, 1<<15, 0);
break;
- case 0x10ec0215:
case 0x10ec0225:
+ case 0x10ec0295:
+ case 0x10ec0299:
+ alc_update_coef_idx(codec, 0x67, 0xf000, 0x3000);
+ /* fallthrough */
+ case 0x10ec0215:
case 0x10ec0233:
case 0x10ec0236:
case 0x10ec0255:
@@ -336,10 +340,8 @@ static void alc_fill_eapd_coef(struct hda_codec *codec)
case 0x10ec0286:
case 0x10ec0288:
case 0x10ec0285:
- case 0x10ec0295:
case 0x10ec0298:
case 0x10ec0289:
- case 0x10ec0299:
alc_update_coef_idx(codec, 0x10, 1<<9, 0);
break;
case 0x10ec0275:
@@ -6305,6 +6307,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
+ SND_PCI_QUIRK(0x17aa, 0x313c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
SND_PCI_QUIRK(0x17aa, 0x3112, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
@@ -6557,6 +6560,11 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
{0x1b, 0x01011020},
{0x21, 0x02211010}),
+ SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+ {0x12, 0x90a60130},
+ {0x14, 0x90170110},
+ {0x1b, 0x01011020},
+ {0x21, 0x0221101f}),
SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
{0x12, 0x90a60160},
{0x14, 0x90170120},
diff --git a/sound/soc/codecs/da7218.c b/sound/soc/codecs/da7218.c
index b2d42ec1dcd9..56564ce90cb6 100644
--- a/sound/soc/codecs/da7218.c
+++ b/sound/soc/codecs/da7218.c
@@ -2520,7 +2520,7 @@ static struct da7218_pdata *da7218_of_to_pdata(struct snd_soc_codec *codec)
}

if (da7218->dev_id == DA7218_DEV_ID) {
- hpldet_np = of_find_node_by_name(np, "da7218_hpldet");
+ hpldet_np = of_get_child_by_name(np, "da7218_hpldet");
if (!hpldet_np)
return pdata;

diff --git a/sound/soc/codecs/msm8916-wcd-analog.c b/sound/soc/codecs/msm8916-wcd-analog.c
index 18933bf6473f..8c7063e1aa46 100644
--- a/sound/soc/codecs/msm8916-wcd-analog.c
+++ b/sound/soc/codecs/msm8916-wcd-analog.c
@@ -267,7 +267,7 @@
#define MSM8916_WCD_ANALOG_RATES (SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 |\
SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_48000)
#define MSM8916_WCD_ANALOG_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\
- SNDRV_PCM_FMTBIT_S24_LE)
+ SNDRV_PCM_FMTBIT_S32_LE)

static int btn_mask = SND_JACK_BTN_0 | SND_JACK_BTN_1 |
SND_JACK_BTN_2 | SND_JACK_BTN_3 | SND_JACK_BTN_4;
diff --git a/sound/soc/codecs/msm8916-wcd-digital.c b/sound/soc/codecs/msm8916-wcd-digital.c
index 66df8f810f0d..694db27b11fa 100644
--- a/sound/soc/codecs/msm8916-wcd-digital.c
+++ b/sound/soc/codecs/msm8916-wcd-digital.c
@@ -194,7 +194,7 @@
SNDRV_PCM_RATE_32000 | \
SNDRV_PCM_RATE_48000)
#define MSM8916_WCD_DIGITAL_FORMATS (SNDRV_PCM_FMTBIT_S16_LE |\
- SNDRV_PCM_FMTBIT_S24_LE)
+ SNDRV_PCM_FMTBIT_S32_LE)

struct msm8916_wcd_digital_priv {
struct clk *ahbclk, *mclk;
@@ -645,7 +645,7 @@ static int msm8916_wcd_digital_hw_params(struct snd_pcm_substream *substream,
RX_I2S_CTL_RX_I2S_MODE_MASK,
RX_I2S_CTL_RX_I2S_MODE_16);
break;
- case SNDRV_PCM_FORMAT_S24_LE:
+ case SNDRV_PCM_FORMAT_S32_LE:
snd_soc_update_bits(dai->codec, LPASS_CDC_CLK_TX_I2S_CTL,
TX_I2S_CTL_TX_I2S_MODE_MASK,
TX_I2S_CTL_TX_I2S_MODE_32);
diff --git a/sound/soc/codecs/tlv320aic31xx.h b/sound/soc/codecs/tlv320aic31xx.h
index 730fb2058869..1ff3edb7bbb6 100644
--- a/sound/soc/codecs/tlv320aic31xx.h
+++ b/sound/soc/codecs/tlv320aic31xx.h
@@ -116,7 +116,7 @@ struct aic31xx_pdata {
/* INT2 interrupt control */
#define AIC31XX_INT2CTRL AIC31XX_REG(0, 49)
/* GPIO1 control */
-#define AIC31XX_GPIO1 AIC31XX_REG(0, 50)
+#define AIC31XX_GPIO1 AIC31XX_REG(0, 51)

#define AIC31XX_DACPRB AIC31XX_REG(0, 60)
/* ADC Instruction Set Register */
diff --git a/sound/soc/codecs/twl4030.c b/sound/soc/codecs/twl4030.c
index c482b2e7a7d2..cfe72b9d4356 100644
--- a/sound/soc/codecs/twl4030.c
+++ b/sound/soc/codecs/twl4030.c
@@ -232,7 +232,7 @@ static struct twl4030_codec_data *twl4030_get_pdata(struct snd_soc_codec *codec)
struct twl4030_codec_data *pdata = dev_get_platdata(codec->dev);
struct device_node *twl4030_codec_node = NULL;

- twl4030_codec_node = of_find_node_by_name(codec->dev->parent->of_node,
+ twl4030_codec_node = of_get_child_by_name(codec->dev->parent->of_node,
"codec");

if (!pdata && twl4030_codec_node) {
@@ -241,9 +241,11 @@ static struct twl4030_codec_data *twl4030_get_pdata(struct snd_soc_codec *codec)
GFP_KERNEL);
if (!pdata) {
dev_err(codec->dev, "Can not allocate memory\n");
+ of_node_put(twl4030_codec_node);
return NULL;
}
twl4030_setup_pdata_of(pdata, twl4030_codec_node);
+ of_node_put(twl4030_codec_node);
}

return pdata;
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 65c059b5ffd7..66e32f5d2917 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -1733,7 +1733,7 @@ static int wm_adsp_load(struct wm_adsp *dsp)
le64_to_cpu(footer->timestamp));

while (pos < firmware->size &&
- pos - firmware->size > sizeof(*region)) {
+ sizeof(*region) < firmware->size - pos) {
region = (void *)&(firmware->data[pos]);
region_name = "Unknown";
reg = 0;
@@ -1782,8 +1782,8 @@ static int wm_adsp_load(struct wm_adsp *dsp)
regions, le32_to_cpu(region->len), offset,
region_name);

- if ((pos + le32_to_cpu(region->len) + sizeof(*region)) >
- firmware->size) {
+ if (le32_to_cpu(region->len) >
+ firmware->size - pos - sizeof(*region)) {
adsp_err(dsp,
"%s.%d: %s region len %d bytes exceeds file length %zu\n",
file, regions, region_name,
@@ -2253,7 +2253,7 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp)

blocks = 0;
while (pos < firmware->size &&
- pos - firmware->size > sizeof(*blk)) {
+ sizeof(*blk) < firmware->size - pos) {
blk = (void *)(&firmware->data[pos]);

type = le16_to_cpu(blk->type);
@@ -2327,8 +2327,8 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp)
}

if (reg) {
- if ((pos + le32_to_cpu(blk->len) + sizeof(*blk)) >
- firmware->size) {
+ if (le32_to_cpu(blk->len) >
+ firmware->size - pos - sizeof(*blk)) {
adsp_err(dsp,
"%s.%d: %s region len %d bytes exceeds file length %zu\n",
file, blocks, region_name,
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index 64598d1183f8..3ffbb498cc70 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -1452,12 +1452,6 @@ static int fsl_ssi_probe(struct platform_device *pdev)
sizeof(fsl_ssi_ac97_dai));

fsl_ac97_data = ssi_private;
-
- ret = snd_soc_set_ac97_ops_of_reset(&fsl_ssi_ac97_ops, pdev);
- if (ret) {
- dev_err(&pdev->dev, "could not set AC'97 ops\n");
- return ret;
- }
} else {
/* Initialize this copy of the CPU DAI driver structure */
memcpy(&ssi_private->cpu_dai_drv, &fsl_ssi_dai_template,
@@ -1568,6 +1562,14 @@ static int fsl_ssi_probe(struct platform_device *pdev)
return ret;
}

+ if (fsl_ssi_is_ac97(ssi_private)) {
+ ret = snd_soc_set_ac97_ops_of_reset(&fsl_ssi_ac97_ops, pdev);
+ if (ret) {
+ dev_err(&pdev->dev, "could not set AC'97 ops\n");
+ goto error_ac97_ops;
+ }
+ }
+
ret = devm_snd_soc_register_component(&pdev->dev, &fsl_ssi_component,
&ssi_private->cpu_dai_drv, 1);
if (ret) {
@@ -1651,6 +1653,10 @@ static int fsl_ssi_probe(struct platform_device *pdev)
fsl_ssi_debugfs_remove(&ssi_private->dbg_stats);

error_asoc_register:
+ if (fsl_ssi_is_ac97(ssi_private))
+ snd_soc_set_ac97_ops(NULL);
+
+error_ac97_ops:
if (ssi_private->soc->imx)
fsl_ssi_imx_clean(pdev, ssi_private);

diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c
index 0304ffb714f2..1aef72df20a1 100644
--- a/tools/testing/selftests/x86/ldt_gdt.c
+++ b/tools/testing/selftests/x86/ldt_gdt.c
@@ -122,8 +122,7 @@ static void check_valid_segment(uint16_t index, int ldt,
* NB: Different Linux versions do different things with the
* accessed bit in set_thread_area().
*/
- if (ar != expected_ar &&
- (ldt || ar != (expected_ar | AR_ACCESSED))) {
+ if (ar != expected_ar && ar != (expected_ar | AR_ACCESSED)) {
printf("[FAIL]\t%s entry %hu has AR 0x%08X but expected 0x%08X\n",
(ldt ? "LDT" : "GDT"), index, ar, expected_ar);
nerrs++;
diff --git a/tools/usb/usbip/src/utils.c b/tools/usb/usbip/src/utils.c
index 2b3d6d235015..3d7b42e77299 100644
--- a/tools/usb/usbip/src/utils.c
+++ b/tools/usb/usbip/src/utils.c
@@ -30,6 +30,7 @@ int modify_match_busid(char *busid, int add)
char command[SYSFS_BUS_ID_SIZE + 4];
char match_busid_attr_path[SYSFS_PATH_MAX];
int rc;
+ int cmd_size;

snprintf(match_busid_attr_path, sizeof(match_busid_attr_path),
"%s/%s/%s/%s/%s/%s", SYSFS_MNT_PATH, SYSFS_BUS_NAME,
@@ -37,12 +38,14 @@ int modify_match_busid(char *busid, int add)
attr_name);

if (add)
- snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s", busid);
+ cmd_size = snprintf(command, SYSFS_BUS_ID_SIZE + 4, "add %s",
+ busid);
else
- snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s", busid);
+ cmd_size = snprintf(command, SYSFS_BUS_ID_SIZE + 4, "del %s",
+ busid);

rc = write_sysfs_attribute(match_busid_attr_path, command,
- sizeof(command));
+ cmd_size);
if (rc < 0) {
dbg("failed to write match_busid: %s", strerror(errno));
return -1;
\
 
 \ /
  Last update: 2018-01-03 15:19    [W:0.179 / U:0.972 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site