Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Ingo writes:
"x86 fixes:
Misc fixes:
- fix various vDSO bugs: asm constraints and retpolines
- add vDSO test units to make sure they never re-appear
- fix UV platform TSC initialization bug
- fix build warning on Clang"
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/vdso: Fix vDSO syscall fallback asm constraint regression
x86/cpu/amd: Remove unnecessary parentheses
x86/vdso: Only enable vDSO retpolines when enabled and supported
x86/tsc: Fix UV TSC initialization
x86/platform/uv: Provide is_early_uv_system()
selftests/x86: Add clock_gettime() tests to test_vdso
x86/vdso: Fix asm constraints on vDSO syscall fallbacks
diff --git a/Documentation/fb/uvesafb.txt b/Documentation/fb/uvesafb.txt
index f6362d8..aa92419 100644
--- a/Documentation/fb/uvesafb.txt
+++ b/Documentation/fb/uvesafb.txt
@@ -15,7 +15,8 @@
arches.
v86d source code can be downloaded from the following website:
- http://dev.gentoo.org/~spock/projects/uvesafb
+
+ https://github.com/mjanusz/v86d
Please refer to the v86d documentation for detailed configuration and
installation instructions.
@@ -177,7 +178,7 @@
--
Michal Januszewski <spock@gentoo.org>
- Last updated: 2009-03-30
+ Last updated: 2017-10-10
Documentation of the uvesafb options is loosely based on vesafb.txt.
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 8313a63..960de8f 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -425,7 +425,7 @@
1 - Disabled by default, enabled when an ICMP black hole detected
2 - Always enabled, use initial MSS of tcp_base_mss.
-tcp_probe_interval - INTEGER
+tcp_probe_interval - UNSIGNED INTEGER
Controls how often to start TCP Packetization-Layer Path MTU
Discovery reprobe. The default is reprobing every 10 minutes as
per RFC4821.
diff --git a/MAINTAINERS b/MAINTAINERS
index b22e7fd..e2d9749 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1251,7 +1251,7 @@
ARM/Annapurna Labs ALPINE ARCHITECTURE
M: Tsahee Zidenberg <tsahee@annapurnalabs.com>
-M: Antoine Tenart <antoine.tenart@free-electrons.com>
+M: Antoine Tenart <antoine.tenart@bootlin.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: arch/arm/mach-alpine/
@@ -2956,7 +2956,6 @@
BROADCOM BNX2 GIGABIT ETHERNET DRIVER
M: Rasesh Mody <rasesh.mody@cavium.com>
-M: Harish Patil <harish.patil@cavium.com>
M: Dept-GELinuxNICDev@cavium.com
L: netdev@vger.kernel.org
S: Supported
@@ -2977,6 +2976,7 @@
BROADCOM BNX2X 10 GIGABIT ETHERNET DRIVER
M: Ariel Elior <ariel.elior@cavium.com>
+M: Sudarsana Kalluru <sudarsana.kalluru@cavium.com>
M: everest-linux-l2@cavium.com
L: netdev@vger.kernel.org
S: Supported
@@ -5470,7 +5470,8 @@
F: drivers/net/ethernet/agere/
ETHERNET BRIDGE
-M: Stephen Hemminger <stephen@networkplumber.org>
+M: Roopa Prabhu <roopa@cumulusnetworks.com>
+M: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
L: bridge@lists.linux-foundation.org (moderated for non-subscribers)
L: netdev@vger.kernel.org
W: http://www.linuxfoundation.org/en/Net:Bridge
@@ -8598,7 +8599,6 @@
F: arch/*/include/asm/spinlock*.h
F: include/linux/rwlock*.h
F: include/linux/mutex*.h
-F: arch/*/include/asm/mutex*.h
F: include/linux/rwsem*.h
F: arch/*/include/asm/rwsem.h
F: include/linux/seqlock.h
@@ -11979,7 +11979,7 @@
F: drivers/scsi/qla4xxx/
QLOGIC QLCNIC (1/10)Gb ETHERNET DRIVER
-M: Harish Patil <harish.patil@cavium.com>
+M: Shahed Shaikh <Shahed.Shaikh@cavium.com>
M: Manish Chopra <manish.chopra@cavium.com>
M: Dept-GELinuxNICDev@cavium.com
L: netdev@vger.kernel.org
@@ -11987,7 +11987,6 @@
F: drivers/net/ethernet/qlogic/qlcnic/
QLOGIC QLGE 10Gb ETHERNET DRIVER
-M: Harish Patil <harish.patil@cavium.com>
M: Manish Chopra <manish.chopra@cavium.com>
M: Dept-GELinuxNICDev@cavium.com
L: netdev@vger.kernel.org
@@ -15395,7 +15394,7 @@
UVESAFB DRIVER
M: Michal Januszewski <spock@gentoo.org>
L: linux-fbdev@vger.kernel.org
-W: http://dev.gentoo.org/~spock/projects/uvesafb/
+W: https://github.com/mjanusz/v86d
S: Maintained
F: Documentation/fb/uvesafb.txt
F: drivers/video/fbdev/uvesafb.*
diff --git a/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts b/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts
index b10dccd..3b1baa8 100644
--- a/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts
@@ -11,6 +11,7 @@
#include "sama5d2-pinfunc.h"
#include <dt-bindings/mfd/atmel-flexcom.h>
#include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/pinctrl/at91.h>
/ {
model = "Atmel SAMA5D2 PTC EK";
@@ -299,6 +300,7 @@
<PIN_PA30__NWE_NANDWE>,
<PIN_PB2__NRD_NANDOE>;
bias-pull-up;
+ atmel,drive-strength = <ATMEL_PIO_DRVSTR_ME>;
};
ale_cle_rdy_cs {
diff --git a/arch/arm/boot/dts/bcm63138.dtsi b/arch/arm/boot/dts/bcm63138.dtsi
index 43ee992..6df6151 100644
--- a/arch/arm/boot/dts/bcm63138.dtsi
+++ b/arch/arm/boot/dts/bcm63138.dtsi
@@ -106,21 +106,23 @@
global_timer: timer@1e200 {
compatible = "arm,cortex-a9-global-timer";
reg = <0x1e200 0x20>;
- interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
clocks = <&axi_clk>;
};
local_timer: local-timer@1e600 {
compatible = "arm,cortex-a9-twd-timer";
reg = <0x1e600 0x20>;
- interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) |
+ IRQ_TYPE_EDGE_RISING)>;
clocks = <&axi_clk>;
};
twd_watchdog: watchdog@1e620 {
compatible = "arm,cortex-a9-twd-wdt";
reg = <0x1e620 0x20>;
- interrupts = <GIC_PPI 14 IRQ_TYPE_LEVEL_HIGH>;
+ interrupts = <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) |
+ IRQ_TYPE_LEVEL_HIGH)>;
};
armpll: armpll {
@@ -158,7 +160,7 @@
serial0: serial@600 {
compatible = "brcm,bcm6345-uart";
reg = <0x600 0x1b>;
- interrupts = <GIC_SPI 32 0>;
+ interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&periph_clk>;
clock-names = "periph";
status = "disabled";
@@ -167,7 +169,7 @@
serial1: serial@620 {
compatible = "brcm,bcm6345-uart";
reg = <0x620 0x1b>;
- interrupts = <GIC_SPI 33 0>;
+ interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&periph_clk>;
clock-names = "periph";
status = "disabled";
@@ -180,7 +182,7 @@
reg = <0x2000 0x600>, <0xf0 0x10>;
reg-names = "nand", "nand-int-base";
status = "disabled";
- interrupts = <GIC_SPI 38 0>;
+ interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
interrupt-names = "nand";
};
diff --git a/arch/arm/boot/dts/stm32mp157c.dtsi b/arch/arm/boot/dts/stm32mp157c.dtsi
index 661be94..185541a 100644
--- a/arch/arm/boot/dts/stm32mp157c.dtsi
+++ b/arch/arm/boot/dts/stm32mp157c.dtsi
@@ -1078,8 +1078,8 @@
interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
clocks = <&rcc SPI6_K>;
resets = <&rcc SPI6_R>;
- dmas = <&mdma1 34 0x0 0x40008 0x0 0x0 0>,
- <&mdma1 35 0x0 0x40002 0x0 0x0 0>;
+ dmas = <&mdma1 34 0x0 0x40008 0x0 0x0>,
+ <&mdma1 35 0x0 0x40002 0x0 0x0>;
dma-names = "rx", "tx";
status = "disabled";
};
diff --git a/arch/arm/boot/dts/sun8i-r40.dtsi b/arch/arm/boot/dts/sun8i-r40.dtsi
index ffd9f00..5f547c1 100644
--- a/arch/arm/boot/dts/sun8i-r40.dtsi
+++ b/arch/arm/boot/dts/sun8i-r40.dtsi
@@ -800,8 +800,7 @@
};
hdmi_phy: hdmi-phy@1ef0000 {
- compatible = "allwinner,sun8i-r40-hdmi-phy",
- "allwinner,sun50i-a64-hdmi-phy";
+ compatible = "allwinner,sun8i-r40-hdmi-phy";
reg = <0x01ef0000 0x10000>;
clocks = <&ccu CLK_BUS_HDMI1>, <&ccu CLK_HDMI_SLOW>,
<&ccu 7>, <&ccu 16>;
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index fc91205..5bf9443 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -473,7 +473,7 @@ void pci_ioremap_set_mem_type(int mem_type)
int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr)
{
- BUG_ON(offset + SZ_64K > IO_SPACE_LIMIT);
+ BUG_ON(offset + SZ_64K - 1 > IO_SPACE_LIMIT);
return ioremap_page_range(PCI_IO_VIRT_BASE + offset,
PCI_IO_VIRT_BASE + offset + SZ_64K,
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index fbc74b5..8edf93b 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -413,3 +413,4 @@
396 common pkey_free sys_pkey_free
397 common statx sys_statx
398 common rseq sys_rseq
+399 common io_pgetevents sys_io_pgetevents
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 07256b0..a6c9fba 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -57,6 +57,45 @@ static u64 core_reg_offset_from_id(u64 id)
return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE);
}
+static int validate_core_offset(const struct kvm_one_reg *reg)
+{
+ u64 off = core_reg_offset_from_id(reg->id);
+ int size;
+
+ switch (off) {
+ case KVM_REG_ARM_CORE_REG(regs.regs[0]) ...
+ KVM_REG_ARM_CORE_REG(regs.regs[30]):
+ case KVM_REG_ARM_CORE_REG(regs.sp):
+ case KVM_REG_ARM_CORE_REG(regs.pc):
+ case KVM_REG_ARM_CORE_REG(regs.pstate):
+ case KVM_REG_ARM_CORE_REG(sp_el1):
+ case KVM_REG_ARM_CORE_REG(elr_el1):
+ case KVM_REG_ARM_CORE_REG(spsr[0]) ...
+ KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
+ size = sizeof(__u64);
+ break;
+
+ case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+ KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+ size = sizeof(__uint128_t);
+ break;
+
+ case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+ case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+ size = sizeof(__u32);
+ break;
+
+ default:
+ return -EINVAL;
+ }
+
+ if (KVM_REG_SIZE(reg->id) == size &&
+ IS_ALIGNED(off, size / sizeof(__u32)))
+ return 0;
+
+ return -EINVAL;
+}
+
static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
{
/*
@@ -76,6 +115,9 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
(off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
return -ENOENT;
+ if (validate_core_offset(reg))
+ return -EINVAL;
+
if (copy_to_user(uaddr, ((u32 *)regs) + off, KVM_REG_SIZE(reg->id)))
return -EFAULT;
@@ -98,6 +140,9 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
(off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
return -ENOENT;
+ if (validate_core_offset(reg))
+ return -EINVAL;
+
if (KVM_REG_SIZE(reg->id) > sizeof(tmp))
return -EINVAL;
@@ -107,17 +152,25 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
}
if (off == KVM_REG_ARM_CORE_REG(regs.pstate)) {
- u32 mode = (*(u32 *)valp) & PSR_AA32_MODE_MASK;
+ u64 mode = (*(u64 *)valp) & PSR_AA32_MODE_MASK;
switch (mode) {
case PSR_AA32_MODE_USR:
+ if (!system_supports_32bit_el0())
+ return -EINVAL;
+ break;
case PSR_AA32_MODE_FIQ:
case PSR_AA32_MODE_IRQ:
case PSR_AA32_MODE_SVC:
case PSR_AA32_MODE_ABT:
case PSR_AA32_MODE_UND:
+ if (!vcpu_el1_is_32bit(vcpu))
+ return -EINVAL;
+ break;
case PSR_MODE_EL0t:
case PSR_MODE_EL1t:
case PSR_MODE_EL1h:
+ if (vcpu_el1_is_32bit(vcpu))
+ return -EINVAL;
break;
default:
err = -EINVAL;
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 192b3ba..f58ea50 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -117,11 +117,14 @@ static pte_t get_clear_flush(struct mm_struct *mm,
/*
* If HW_AFDBM is enabled, then the HW could turn on
- * the dirty bit for any page in the set, so check
- * them all. All hugetlb entries are already young.
+ * the dirty or accessed bit for any page in the set,
+ * so check them all.
*/
if (pte_dirty(pte))
orig_pte = pte_mkdirty(orig_pte);
+
+ if (pte_young(pte))
+ orig_pte = pte_mkyoung(orig_pte);
}
if (valid) {
@@ -320,11 +323,40 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
return get_clear_flush(mm, addr, ptep, pgsize, ncontig);
}
+/*
+ * huge_ptep_set_access_flags will update access flags (dirty, accesssed)
+ * and write permission.
+ *
+ * For a contiguous huge pte range we need to check whether or not write
+ * permission has to change only on the first pte in the set. Then for
+ * all the contiguous ptes we need to check whether or not there is a
+ * discrepancy between dirty or young.
+ */
+static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig)
+{
+ int i;
+
+ if (pte_write(pte) != pte_write(huge_ptep_get(ptep)))
+ return 1;
+
+ for (i = 0; i < ncontig; i++) {
+ pte_t orig_pte = huge_ptep_get(ptep + i);
+
+ if (pte_dirty(pte) != pte_dirty(orig_pte))
+ return 1;
+
+ if (pte_young(pte) != pte_young(orig_pte))
+ return 1;
+ }
+
+ return 0;
+}
+
int huge_ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t pte, int dirty)
{
- int ncontig, i, changed = 0;
+ int ncontig, i;
size_t pgsize = 0;
unsigned long pfn = pte_pfn(pte), dpfn;
pgprot_t hugeprot;
@@ -336,19 +368,23 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
dpfn = pgsize >> PAGE_SHIFT;
- orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
- if (!pte_same(orig_pte, pte))
- changed = 1;
+ if (!__cont_access_flags_changed(ptep, pte, ncontig))
+ return 0;
- /* Make sure we don't lose the dirty state */
+ orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
+
+ /* Make sure we don't lose the dirty or young state */
if (pte_dirty(orig_pte))
pte = pte_mkdirty(pte);
+ if (pte_young(orig_pte))
+ pte = pte_mkyoung(pte);
+
hugeprot = pte_pgprot(pte);
for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
- return changed;
+ return 1;
}
void huge_ptep_set_wrprotect(struct mm_struct *mm,
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 933c574..998f8d0 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -646,6 +646,16 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
*/
local_irq_disable();
ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
+ /*
+ * If the PTE disappeared temporarily due to a THP
+ * collapse, just return and let the guest try again.
+ */
+ if (!ptep) {
+ local_irq_enable();
+ if (page)
+ put_page(page);
+ return RESUME_GUEST;
+ }
pte = *ptep;
local_irq_enable();
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index aee6031..b2d26d9 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -186,7 +186,7 @@ static void __init setup_bootmem(void)
BUG_ON(mem_size == 0);
set_max_mapnr(PFN_DOWN(mem_size));
- max_low_pfn = pfn_base + PFN_DOWN(mem_size);
+ max_low_pfn = memblock_end_of_DRAM();
#ifdef CONFIG_BLK_DEV_INITRD
setup_initrd();
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d7e9bce..51b953ad 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -249,6 +249,17 @@ static u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
*/
static const u64 shadow_nonpresent_or_rsvd_mask_len = 5;
+/*
+ * In some cases, we need to preserve the GFN of a non-present or reserved
+ * SPTE when we usurp the upper five bits of the physical address space to
+ * defend against L1TF, e.g. for MMIO SPTEs. To preserve the GFN, we'll
+ * shift bits of the GFN that overlap with shadow_nonpresent_or_rsvd_mask
+ * left into the reserved bits, i.e. the GFN in the SPTE will be split into
+ * high and low parts. This mask covers the lower bits of the GFN.
+ */
+static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
+
+
static void mmu_spte_set(u64 *sptep, u64 spte);
static union kvm_mmu_page_role
kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu);
@@ -357,9 +368,7 @@ static bool is_mmio_spte(u64 spte)
static gfn_t get_mmio_spte_gfn(u64 spte)
{
- u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask |
- shadow_nonpresent_or_rsvd_mask;
- u64 gpa = spte & ~mask;
+ u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask;
gpa |= (spte >> shadow_nonpresent_or_rsvd_mask_len)
& shadow_nonpresent_or_rsvd_mask;
@@ -423,6 +432,8 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
static void kvm_mmu_reset_all_pte_masks(void)
{
+ u8 low_phys_bits;
+
shadow_user_mask = 0;
shadow_accessed_mask = 0;
shadow_dirty_mask = 0;
@@ -437,12 +448,17 @@ static void kvm_mmu_reset_all_pte_masks(void)
* appropriate mask to guard against L1TF attacks. Otherwise, it is
* assumed that the CPU is not vulnerable to L1TF.
*/
+ low_phys_bits = boot_cpu_data.x86_phys_bits;
if (boot_cpu_data.x86_phys_bits <
- 52 - shadow_nonpresent_or_rsvd_mask_len)
+ 52 - shadow_nonpresent_or_rsvd_mask_len) {
shadow_nonpresent_or_rsvd_mask =
rsvd_bits(boot_cpu_data.x86_phys_bits -
shadow_nonpresent_or_rsvd_mask_len,
boot_cpu_data.x86_phys_bits - 1);
+ low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len;
+ }
+ shadow_nonpresent_or_rsvd_lower_gfn_mask =
+ GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT);
}
static int is_cpuid_PSE36(void)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 06412ba..612fd17 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -121,7 +121,6 @@ module_param_named(pml, enable_pml, bool, S_IRUGO);
#define MSR_BITMAP_MODE_X2APIC 1
#define MSR_BITMAP_MODE_X2APIC_APICV 2
-#define MSR_BITMAP_MODE_LM 4
#define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL
@@ -857,6 +856,7 @@ struct nested_vmx {
/* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */
u64 vmcs01_debugctl;
+ u64 vmcs01_guest_bndcfgs;
u16 vpid02;
u16 last_vpid;
@@ -2899,8 +2899,7 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
}
- if (is_long_mode(&vmx->vcpu))
- wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+ wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
#else
savesegment(fs, fs_sel);
savesegment(gs, gs_sel);
@@ -2951,8 +2950,7 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
vmx->loaded_cpu_state = NULL;
#ifdef CONFIG_X86_64
- if (is_long_mode(&vmx->vcpu))
- rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+ rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
#endif
if (host_state->ldt_sel || (host_state->gs_sel & 7)) {
kvm_load_ldt(host_state->ldt_sel);
@@ -2980,24 +2978,19 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
#ifdef CONFIG_X86_64
static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx)
{
- if (is_long_mode(&vmx->vcpu)) {
- preempt_disable();
- if (vmx->loaded_cpu_state)
- rdmsrl(MSR_KERNEL_GS_BASE,
- vmx->msr_guest_kernel_gs_base);
- preempt_enable();
- }
+ preempt_disable();
+ if (vmx->loaded_cpu_state)
+ rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+ preempt_enable();
return vmx->msr_guest_kernel_gs_base;
}
static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data)
{
- if (is_long_mode(&vmx->vcpu)) {
- preempt_disable();
- if (vmx->loaded_cpu_state)
- wrmsrl(MSR_KERNEL_GS_BASE, data);
- preempt_enable();
- }
+ preempt_disable();
+ if (vmx->loaded_cpu_state)
+ wrmsrl(MSR_KERNEL_GS_BASE, data);
+ preempt_enable();
vmx->msr_guest_kernel_gs_base = data;
}
#endif
@@ -3533,9 +3526,6 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT;
- if (kvm_mpx_supported())
- msrs->exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
-
/* We support free control of debug control saving. */
msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS;
@@ -3552,8 +3542,6 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
VM_ENTRY_LOAD_IA32_PAT;
msrs->entry_ctls_high |=
(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);
- if (kvm_mpx_supported())
- msrs->entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
/* We support free control of debug control loading. */
msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS;
@@ -3601,12 +3589,12 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
msrs->secondary_ctls_high);
msrs->secondary_ctls_low = 0;
msrs->secondary_ctls_high &=
- SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
SECONDARY_EXEC_DESC |
SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
SECONDARY_EXEC_APIC_REGISTER_VIRT |
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
SECONDARY_EXEC_WBINVD_EXITING;
+
/*
* We can emulate "VMCS shadowing," even if the hardware
* doesn't support it.
@@ -3663,6 +3651,10 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
msrs->secondary_ctls_high |=
SECONDARY_EXEC_UNRESTRICTED_GUEST;
+ if (flexpriority_enabled)
+ msrs->secondary_ctls_high |=
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+
/* miscellaneous data */
rdmsr(MSR_IA32_VMX_MISC,
msrs->misc_low,
@@ -5073,19 +5065,6 @@ static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
if (!msr)
return;
- /*
- * MSR_KERNEL_GS_BASE is not intercepted when the guest is in
- * 64-bit mode as a 64-bit kernel may frequently access the
- * MSR. This means we need to manually save/restore the MSR
- * when switching between guest and host state, but only if
- * the guest is in 64-bit mode. Sync our cached value if the
- * guest is transitioning to 32-bit mode and the CPU contains
- * guest state, i.e. the cache is stale.
- */
-#ifdef CONFIG_X86_64
- if (!(efer & EFER_LMA))
- (void)vmx_read_guest_kernel_gs_base(vmx);
-#endif
vcpu->arch.efer = efer;
if (efer & EFER_LMA) {
vm_entry_controls_setbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE);
@@ -6078,9 +6057,6 @@ static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
mode |= MSR_BITMAP_MODE_X2APIC_APICV;
}
- if (is_long_mode(vcpu))
- mode |= MSR_BITMAP_MODE_LM;
-
return mode;
}
@@ -6121,9 +6097,6 @@ static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu)
if (!changed)
return;
- vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW,
- !(mode & MSR_BITMAP_MODE_LM));
-
if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV))
vmx_update_msr_bitmap_x2apic(msr_bitmap, mode);
@@ -6189,6 +6162,11 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
nested_mark_vmcs12_pages_dirty(vcpu);
}
+static u8 vmx_get_rvi(void)
+{
+ return vmcs_read16(GUEST_INTR_STATUS) & 0xff;
+}
+
static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6201,7 +6179,7 @@ static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
WARN_ON_ONCE(!vmx->nested.virtual_apic_page))
return false;
- rvi = vmcs_read16(GUEST_INTR_STATUS) & 0xff;
+ rvi = vmx_get_rvi();
vapic_page = kmap(vmx->nested.virtual_apic_page);
vppr = *((u32 *)(vapic_page + APIC_PROCPRI));
@@ -10245,15 +10223,16 @@ static void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
if (!lapic_in_kernel(vcpu))
return;
+ if (!flexpriority_enabled &&
+ !cpu_has_vmx_virtualize_x2apic_mode())
+ return;
+
/* Postpone execution until vmcs01 is the current VMCS. */
if (is_guest_mode(vcpu)) {
to_vmx(vcpu)->nested.change_vmcs01_virtual_apic_mode = true;
return;
}
- if (!cpu_need_tpr_shadow(vcpu))
- return;
-
sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
@@ -10375,6 +10354,14 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
return max_irr;
}
+static u8 vmx_has_apicv_interrupt(struct kvm_vcpu *vcpu)
+{
+ u8 rvi = vmx_get_rvi();
+ u8 vppr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_PROCPRI);
+
+ return ((rvi & 0xf0) > (vppr & 0xf0));
+}
+
static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
{
if (!kvm_vcpu_apicv_active(vcpu))
@@ -11264,6 +11251,23 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
#undef cr4_fixed1_update
}
+static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ if (kvm_mpx_supported()) {
+ bool mpx_enabled = guest_cpuid_has(vcpu, X86_FEATURE_MPX);
+
+ if (mpx_enabled) {
+ vmx->nested.msrs.entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
+ vmx->nested.msrs.exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
+ } else {
+ vmx->nested.msrs.entry_ctls_high &= ~VM_ENTRY_LOAD_BNDCFGS;
+ vmx->nested.msrs.exit_ctls_high &= ~VM_EXIT_CLEAR_BNDCFGS;
+ }
+ }
+}
+
static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -11280,8 +11284,10 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
- if (nested_vmx_allowed(vcpu))
+ if (nested_vmx_allowed(vcpu)) {
nested_vmx_cr_fixed1_bits_update(vcpu);
+ nested_vmx_entry_exit_ctls_update(vcpu);
+ }
}
static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
@@ -12049,8 +12055,13 @@ static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
set_cr4_guest_host_mask(vmx);
- if (vmx_mpx_supported())
- vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
+ if (kvm_mpx_supported()) {
+ if (vmx->nested.nested_run_pending &&
+ (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
+ vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
+ else
+ vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs);
+ }
if (enable_vpid) {
if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02)
@@ -12595,15 +12606,21 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
bool from_vmentry = !!exit_qual;
u32 dummy_exit_qual;
- u32 vmcs01_cpu_exec_ctrl;
+ bool evaluate_pending_interrupts;
int r = 0;
- vmcs01_cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+ evaluate_pending_interrupts = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) &
+ (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING);
+ if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu))
+ evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu);
enter_guest_mode(vcpu);
if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
+ if (kvm_mpx_supported() &&
+ !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
+ vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);
vmx_segment_cache_clear(vmx);
@@ -12643,16 +12660,14 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
* to L1 or delivered directly to L2 (e.g. In case L1 don't
* intercept EXTERNAL_INTERRUPT).
*
- * Usually this would be handled by L0 requesting a
- * IRQ/NMI window by setting VMCS accordingly. However,
- * this setting was done on VMCS01 and now VMCS02 is active
- * instead. Thus, we force L0 to perform pending event
- * evaluation by requesting a KVM_REQ_EVENT.
+ * Usually this would be handled by the processor noticing an
+ * IRQ/NMI window request, or checking RVI during evaluation of
+ * pending virtual interrupts. However, this setting was done
+ * on VMCS01 and now VMCS02 is active instead. Thus, we force L0
+ * to perform pending event evaluation by requesting a KVM_REQ_EVENT.
*/
- if (vmcs01_cpu_exec_ctrl &
- (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING)) {
+ if (unlikely(evaluate_pending_interrupts))
kvm_make_request(KVM_REQ_EVENT, vcpu);
- }
/*
* Note no nested_vmx_succeed or nested_vmx_fail here. At this point
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index edbf00e..ca71773 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4698,7 +4698,7 @@ static void kvm_init_msr_list(void)
*/
switch (msrs_to_save[i]) {
case MSR_IA32_BNDCFGS:
- if (!kvm_x86_ops->mpx_supported())
+ if (!kvm_mpx_supported())
continue;
break;
case MSR_TSC_AUX:
diff --git a/drivers/crypto/caam/caamalg.c b/drivers/crypto/caam/caamalg.c
index d676679..ec40f99 100644
--- a/drivers/crypto/caam/caamalg.c
+++ b/drivers/crypto/caam/caamalg.c
@@ -1553,8 +1553,8 @@ static struct ablkcipher_edesc *ablkcipher_edesc_alloc(struct ablkcipher_request
edesc->src_nents = src_nents;
edesc->dst_nents = dst_nents;
edesc->sec4_sg_bytes = sec4_sg_bytes;
- edesc->sec4_sg = (void *)edesc + sizeof(struct ablkcipher_edesc) +
- desc_bytes;
+ edesc->sec4_sg = (struct sec4_sg_entry *)((u8 *)edesc->hw_desc +
+ desc_bytes);
edesc->iv_dir = DMA_TO_DEVICE;
/* Make sure IV is located in a DMAable area */
@@ -1757,8 +1757,8 @@ static struct ablkcipher_edesc *ablkcipher_giv_edesc_alloc(
edesc->src_nents = src_nents;
edesc->dst_nents = dst_nents;
edesc->sec4_sg_bytes = sec4_sg_bytes;
- edesc->sec4_sg = (void *)edesc + sizeof(struct ablkcipher_edesc) +
- desc_bytes;
+ edesc->sec4_sg = (struct sec4_sg_entry *)((u8 *)edesc->hw_desc +
+ desc_bytes);
edesc->iv_dir = DMA_FROM_DEVICE;
/* Make sure IV is located in a DMAable area */
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index 5c539af..010bbf6 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -367,7 +367,8 @@ static inline void dsgl_walk_init(struct dsgl_walk *walk,
walk->to = (struct phys_sge_pairs *)(dsgl + 1);
}
-static inline void dsgl_walk_end(struct dsgl_walk *walk, unsigned short qid)
+static inline void dsgl_walk_end(struct dsgl_walk *walk, unsigned short qid,
+ int pci_chan_id)
{
struct cpl_rx_phys_dsgl *phys_cpl;
@@ -385,6 +386,7 @@ static inline void dsgl_walk_end(struct dsgl_walk *walk, unsigned short qid)
phys_cpl->rss_hdr_int.opcode = CPL_RX_PHYS_ADDR;
phys_cpl->rss_hdr_int.qid = htons(qid);
phys_cpl->rss_hdr_int.hash_val = 0;
+ phys_cpl->rss_hdr_int.channel = pci_chan_id;
}
static inline void dsgl_walk_add_page(struct dsgl_walk *walk,
@@ -718,7 +720,7 @@ static inline void create_wreq(struct chcr_context *ctx,
FILL_WR_RX_Q_ID(ctx->dev->rx_channel_id, qid,
!!lcb, ctx->tx_qidx);
- chcr_req->ulptx.cmd_dest = FILL_ULPTX_CMD_DEST(ctx->dev->tx_channel_id,
+ chcr_req->ulptx.cmd_dest = FILL_ULPTX_CMD_DEST(ctx->tx_chan_id,
qid);
chcr_req->ulptx.len = htonl((DIV_ROUND_UP(len16, 16) -
((sizeof(chcr_req->wreq)) >> 4)));
@@ -1339,16 +1341,23 @@ static int chcr_device_init(struct chcr_context *ctx)
adap->vres.ncrypto_fc);
rxq_perchan = u_ctx->lldi.nrxq / u_ctx->lldi.nchan;
txq_perchan = ntxq / u_ctx->lldi.nchan;
- rxq_idx = ctx->dev->tx_channel_id * rxq_perchan;
- rxq_idx += id % rxq_perchan;
- txq_idx = ctx->dev->tx_channel_id * txq_perchan;
- txq_idx += id % txq_perchan;
spin_lock(&ctx->dev->lock_chcr_dev);
- ctx->rx_qidx = rxq_idx;
- ctx->tx_qidx = txq_idx;
+ ctx->tx_chan_id = ctx->dev->tx_channel_id;
ctx->dev->tx_channel_id = !ctx->dev->tx_channel_id;
ctx->dev->rx_channel_id = 0;
spin_unlock(&ctx->dev->lock_chcr_dev);
+ rxq_idx = ctx->tx_chan_id * rxq_perchan;
+ rxq_idx += id % rxq_perchan;
+ txq_idx = ctx->tx_chan_id * txq_perchan;
+ txq_idx += id % txq_perchan;
+ ctx->rx_qidx = rxq_idx;
+ ctx->tx_qidx = txq_idx;
+ /* Channel Id used by SGE to forward packet to Host.
+ * Same value should be used in cpl_fw6_pld RSS_CH field
+ * by FW. Driver programs PCI channel ID to be used in fw
+ * at the time of queue allocation with value "pi->tx_chan"
+ */
+ ctx->pci_chan_id = txq_idx / txq_perchan;
}
out:
return err;
@@ -2503,6 +2512,7 @@ void chcr_add_aead_dst_ent(struct aead_request *req,
struct crypto_aead *tfm = crypto_aead_reqtfm(req);
struct dsgl_walk dsgl_walk;
unsigned int authsize = crypto_aead_authsize(tfm);
+ struct chcr_context *ctx = a_ctx(tfm);
u32 temp;
dsgl_walk_init(&dsgl_walk, phys_cpl);
@@ -2512,7 +2522,7 @@ void chcr_add_aead_dst_ent(struct aead_request *req,
dsgl_walk_add_page(&dsgl_walk, IV, &reqctx->iv_dma);
temp = req->cryptlen + (reqctx->op ? -authsize : authsize);
dsgl_walk_add_sg(&dsgl_walk, req->dst, temp, req->assoclen);
- dsgl_walk_end(&dsgl_walk, qid);
+ dsgl_walk_end(&dsgl_walk, qid, ctx->pci_chan_id);
}
void chcr_add_cipher_src_ent(struct ablkcipher_request *req,
@@ -2544,6 +2554,8 @@ void chcr_add_cipher_dst_ent(struct ablkcipher_request *req,
unsigned short qid)
{
struct chcr_blkcipher_req_ctx *reqctx = ablkcipher_request_ctx(req);
+ struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(wrparam->req);
+ struct chcr_context *ctx = c_ctx(tfm);
struct dsgl_walk dsgl_walk;
dsgl_walk_init(&dsgl_walk, phys_cpl);
@@ -2552,7 +2564,7 @@ void chcr_add_cipher_dst_ent(struct ablkcipher_request *req,
reqctx->dstsg = dsgl_walk.last_sg;
reqctx->dst_ofst = dsgl_walk.last_sg_len;
- dsgl_walk_end(&dsgl_walk, qid);
+ dsgl_walk_end(&dsgl_walk, qid, ctx->pci_chan_id);
}
void chcr_add_hash_src_ent(struct ahash_request *req,
diff --git a/drivers/crypto/chelsio/chcr_crypto.h b/drivers/crypto/chelsio/chcr_crypto.h
index 54835cb..0d2c70c 100644
--- a/drivers/crypto/chelsio/chcr_crypto.h
+++ b/drivers/crypto/chelsio/chcr_crypto.h
@@ -255,6 +255,8 @@ struct chcr_context {
struct chcr_dev *dev;
unsigned char tx_qidx;
unsigned char rx_qidx;
+ unsigned char tx_chan_id;
+ unsigned char pci_chan_id;
struct __crypto_ctx crypto_ctx[0];
};
diff --git a/drivers/crypto/mxs-dcp.c b/drivers/crypto/mxs-dcp.c
index a10c418..56bd281 100644
--- a/drivers/crypto/mxs-dcp.c
+++ b/drivers/crypto/mxs-dcp.c
@@ -63,7 +63,7 @@ struct dcp {
struct dcp_coherent_block *coh;
struct completion completion[DCP_MAX_CHANS];
- struct mutex mutex[DCP_MAX_CHANS];
+ spinlock_t lock[DCP_MAX_CHANS];
struct task_struct *thread[DCP_MAX_CHANS];
struct crypto_queue queue[DCP_MAX_CHANS];
};
@@ -349,13 +349,20 @@ static int dcp_chan_thread_aes(void *data)
int ret;
- do {
- __set_current_state(TASK_INTERRUPTIBLE);
+ while (!kthread_should_stop()) {
+ set_current_state(TASK_INTERRUPTIBLE);
- mutex_lock(&sdcp->mutex[chan]);
+ spin_lock(&sdcp->lock[chan]);
backlog = crypto_get_backlog(&sdcp->queue[chan]);
arq = crypto_dequeue_request(&sdcp->queue[chan]);
- mutex_unlock(&sdcp->mutex[chan]);
+ spin_unlock(&sdcp->lock[chan]);
+
+ if (!backlog && !arq) {
+ schedule();
+ continue;
+ }
+
+ set_current_state(TASK_RUNNING);
if (backlog)
backlog->complete(backlog, -EINPROGRESS);
@@ -363,11 +370,8 @@ static int dcp_chan_thread_aes(void *data)
if (arq) {
ret = mxs_dcp_aes_block_crypt(arq);
arq->complete(arq, ret);
- continue;
}
-
- schedule();
- } while (!kthread_should_stop());
+ }
return 0;
}
@@ -409,9 +413,9 @@ static int mxs_dcp_aes_enqueue(struct ablkcipher_request *req, int enc, int ecb)
rctx->ecb = ecb;
actx->chan = DCP_CHAN_CRYPTO;
- mutex_lock(&sdcp->mutex[actx->chan]);
+ spin_lock(&sdcp->lock[actx->chan]);
ret = crypto_enqueue_request(&sdcp->queue[actx->chan], &req->base);
- mutex_unlock(&sdcp->mutex[actx->chan]);
+ spin_unlock(&sdcp->lock[actx->chan]);
wake_up_process(sdcp->thread[actx->chan]);
@@ -640,13 +644,20 @@ static int dcp_chan_thread_sha(void *data)
struct ahash_request *req;
int ret, fini;
- do {
- __set_current_state(TASK_INTERRUPTIBLE);
+ while (!kthread_should_stop()) {
+ set_current_state(TASK_INTERRUPTIBLE);
- mutex_lock(&sdcp->mutex[chan]);
+ spin_lock(&sdcp->lock[chan]);
backlog = crypto_get_backlog(&sdcp->queue[chan]);
arq = crypto_dequeue_request(&sdcp->queue[chan]);
- mutex_unlock(&sdcp->mutex[chan]);
+ spin_unlock(&sdcp->lock[chan]);
+
+ if (!backlog && !arq) {
+ schedule();
+ continue;
+ }
+
+ set_current_state(TASK_RUNNING);
if (backlog)
backlog->complete(backlog, -EINPROGRESS);
@@ -658,12 +669,8 @@ static int dcp_chan_thread_sha(void *data)
ret = dcp_sha_req_to_buf(arq);
fini = rctx->fini;
arq->complete(arq, ret);
- if (!fini)
- continue;
}
-
- schedule();
- } while (!kthread_should_stop());
+ }
return 0;
}
@@ -721,9 +728,9 @@ static int dcp_sha_update_fx(struct ahash_request *req, int fini)
rctx->init = 1;
}
- mutex_lock(&sdcp->mutex[actx->chan]);
+ spin_lock(&sdcp->lock[actx->chan]);
ret = crypto_enqueue_request(&sdcp->queue[actx->chan], &req->base);
- mutex_unlock(&sdcp->mutex[actx->chan]);
+ spin_unlock(&sdcp->lock[actx->chan]);
wake_up_process(sdcp->thread[actx->chan]);
mutex_unlock(&actx->mutex);
@@ -997,7 +1004,7 @@ static int mxs_dcp_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, sdcp);
for (i = 0; i < DCP_MAX_CHANS; i++) {
- mutex_init(&sdcp->mutex[i]);
+ spin_lock_init(&sdcp->lock[i]);
init_completion(&sdcp->completion[i]);
crypto_init_queue(&sdcp->queue[i], 50);
}
diff --git a/drivers/crypto/qat/qat_c3xxx/adf_drv.c b/drivers/crypto/qat/qat_c3xxx/adf_drv.c
index ba197f3..763c216 100644
--- a/drivers/crypto/qat/qat_c3xxx/adf_drv.c
+++ b/drivers/crypto/qat/qat_c3xxx/adf_drv.c
@@ -123,7 +123,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
struct adf_hw_device_data *hw_data;
char name[ADF_DEVICE_NAME_LENGTH];
unsigned int i, bar_nr;
- int ret, bar_mask;
+ unsigned long bar_mask;
+ int ret;
switch (ent->device) {
case ADF_C3XXX_PCI_DEVICE_ID:
@@ -235,8 +236,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
/* Find and map all the device's BARS */
i = 0;
bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
- for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
- ADF_PCI_MAX_BARS * 2) {
+ for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) {
struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
bar->base_addr = pci_resource_start(pdev, bar_nr);
diff --git a/drivers/crypto/qat/qat_c3xxxvf/adf_drv.c b/drivers/crypto/qat/qat_c3xxxvf/adf_drv.c
index 24ec908..613c7d5 100644
--- a/drivers/crypto/qat/qat_c3xxxvf/adf_drv.c
+++ b/drivers/crypto/qat/qat_c3xxxvf/adf_drv.c
@@ -125,7 +125,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
struct adf_hw_device_data *hw_data;
char name[ADF_DEVICE_NAME_LENGTH];
unsigned int i, bar_nr;
- int ret, bar_mask;
+ unsigned long bar_mask;
+ int ret;
switch (ent->device) {
case ADF_C3XXXIOV_PCI_DEVICE_ID:
@@ -215,8 +216,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
/* Find and map all the device's BARS */
i = 0;
bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
- for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
- ADF_PCI_MAX_BARS * 2) {
+ for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) {
struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
bar->base_addr = pci_resource_start(pdev, bar_nr);
diff --git a/drivers/crypto/qat/qat_c62x/adf_drv.c b/drivers/crypto/qat/qat_c62x/adf_drv.c
index 59a5a0d..9cb8329 100644
--- a/drivers/crypto/qat/qat_c62x/adf_drv.c
+++ b/drivers/crypto/qat/qat_c62x/adf_drv.c
@@ -123,7 +123,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
struct adf_hw_device_data *hw_data;
char name[ADF_DEVICE_NAME_LENGTH];
unsigned int i, bar_nr;
- int ret, bar_mask;
+ unsigned long bar_mask;
+ int ret;
switch (ent->device) {
case ADF_C62X_PCI_DEVICE_ID:
@@ -235,8 +236,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
/* Find and map all the device's BARS */
i = (hw_data->fuses & ADF_DEVICE_FUSECTL_MASK) ? 1 : 0;
bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
- for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
- ADF_PCI_MAX_BARS * 2) {
+ for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) {
struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
bar->base_addr = pci_resource_start(pdev, bar_nr);
diff --git a/drivers/crypto/qat/qat_c62xvf/adf_drv.c b/drivers/crypto/qat/qat_c62xvf/adf_drv.c
index b9f3e0e..278452b 100644
--- a/drivers/crypto/qat/qat_c62xvf/adf_drv.c
+++ b/drivers/crypto/qat/qat_c62xvf/adf_drv.c
@@ -125,7 +125,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
struct adf_hw_device_data *hw_data;
char name[ADF_DEVICE_NAME_LENGTH];
unsigned int i, bar_nr;
- int ret, bar_mask;
+ unsigned long bar_mask;
+ int ret;
switch (ent->device) {
case ADF_C62XIOV_PCI_DEVICE_ID:
@@ -215,8 +216,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
/* Find and map all the device's BARS */
i = 0;
bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
- for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
- ADF_PCI_MAX_BARS * 2) {
+ for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) {
struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
bar->base_addr = pci_resource_start(pdev, bar_nr);
diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
index be5c5a9..3a9708e 100644
--- a/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
+++ b/drivers/crypto/qat/qat_dh895xcc/adf_drv.c
@@ -123,7 +123,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
struct adf_hw_device_data *hw_data;
char name[ADF_DEVICE_NAME_LENGTH];
unsigned int i, bar_nr;
- int ret, bar_mask;
+ unsigned long bar_mask;
+ int ret;
switch (ent->device) {
case ADF_DH895XCC_PCI_DEVICE_ID:
@@ -237,8 +238,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
/* Find and map all the device's BARS */
i = 0;
bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
- for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
- ADF_PCI_MAX_BARS * 2) {
+ for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) {
struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
bar->base_addr = pci_resource_start(pdev, bar_nr);
diff --git a/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c b/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c
index 26ab17b..3da0f95 100644
--- a/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c
+++ b/drivers/crypto/qat/qat_dh895xccvf/adf_drv.c
@@ -125,7 +125,8 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
struct adf_hw_device_data *hw_data;
char name[ADF_DEVICE_NAME_LENGTH];
unsigned int i, bar_nr;
- int ret, bar_mask;
+ unsigned long bar_mask;
+ int ret;
switch (ent->device) {
case ADF_DH895XCCIOV_PCI_DEVICE_ID:
@@ -215,8 +216,7 @@ static int adf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
/* Find and map all the device's BARS */
i = 0;
bar_mask = pci_select_bars(pdev, IORESOURCE_MEM);
- for_each_set_bit(bar_nr, (const unsigned long *)&bar_mask,
- ADF_PCI_MAX_BARS * 2) {
+ for_each_set_bit(bar_nr, &bar_mask, ADF_PCI_MAX_BARS * 2) {
struct adf_bar *bar = &accel_pci_dev->pci_bars[i++];
bar->base_addr = pci_resource_start(pdev, bar_nr);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index ec0d62a..4f22e74 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -358,8 +358,8 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
struct queue *q,
struct qcm_process_device *qpd)
{
- int retval;
struct mqd_manager *mqd_mgr;
+ int retval;
mqd_mgr = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_COMPUTE);
if (!mqd_mgr)
@@ -387,8 +387,12 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
if (!q->properties.is_active)
return 0;
- retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue,
- &q->properties, q->process->mm);
+ if (WARN(q->process->mm != current->mm,
+ "should only run in user thread"))
+ retval = -EFAULT;
+ else
+ retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue,
+ &q->properties, current->mm);
if (retval)
goto out_uninit_mqd;
@@ -545,9 +549,15 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
retval = map_queues_cpsch(dqm);
else if (q->properties.is_active &&
(q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
- q->properties.type == KFD_QUEUE_TYPE_SDMA))
- retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue,
- &q->properties, q->process->mm);
+ q->properties.type == KFD_QUEUE_TYPE_SDMA)) {
+ if (WARN(q->process->mm != current->mm,
+ "should only run in user thread"))
+ retval = -EFAULT;
+ else
+ retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd,
+ q->pipe, q->queue,
+ &q->properties, current->mm);
+ }
out_unlock:
dqm_unlock(dqm);
@@ -653,6 +663,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm,
static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
struct qcm_process_device *qpd)
{
+ struct mm_struct *mm = NULL;
struct queue *q;
struct mqd_manager *mqd_mgr;
struct kfd_process_device *pdd;
@@ -686,6 +697,15 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
kfd_flush_tlb(pdd);
}
+ /* Take a safe reference to the mm_struct, which may otherwise
+ * disappear even while the kfd_process is still referenced.
+ */
+ mm = get_task_mm(pdd->process->lead_thread);
+ if (!mm) {
+ retval = -EFAULT;
+ goto out;
+ }
+
/* activate all active queues on the qpd */
list_for_each_entry(q, &qpd->queues_list, list) {
if (!q->properties.is_evicted)
@@ -700,14 +720,15 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
q->properties.is_evicted = false;
q->properties.is_active = true;
retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe,
- q->queue, &q->properties,
- q->process->mm);
+ q->queue, &q->properties, mm);
if (retval)
goto out;
dqm->queue_count++;
}
qpd->evicted = 0;
out:
+ if (mm)
+ mmput(mm);
dqm_unlock(dqm);
return retval;
}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 9687595..6903fe6 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -4633,12 +4633,18 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
}
spin_unlock_irqrestore(&adev->ddev->event_lock, flags);
- /* Signal HW programming completion */
- drm_atomic_helper_commit_hw_done(state);
if (wait_for_vblank)
drm_atomic_helper_wait_for_flip_done(dev, state);
+ /*
+ * FIXME:
+ * Delay hw_done() until flip_done() is signaled. This is to block
+ * another commit from freeing the CRTC state while we're still
+ * waiting on flip_done.
+ */
+ drm_atomic_helper_commit_hw_done(state);
+
drm_atomic_helper_cleanup_planes(dev, state);
/* Finally, drop a runtime PM reference for each newly disabled CRTC,
diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c
index baff50a..df31c38 100644
--- a/drivers/gpu/drm/drm_client.c
+++ b/drivers/gpu/drm/drm_client.c
@@ -63,20 +63,21 @@ static void drm_client_close(struct drm_client_dev *client)
EXPORT_SYMBOL(drm_client_close);
/**
- * drm_client_new - Create a DRM client
+ * drm_client_init - Initialise a DRM client
* @dev: DRM device
* @client: DRM client
* @name: Client name
* @funcs: DRM client functions (optional)
*
+ * This initialises the client and opens a &drm_file. Use drm_client_add() to complete the process.
* The caller needs to hold a reference on @dev before calling this function.
* The client is freed when the &drm_device is unregistered. See drm_client_release().
*
* Returns:
* Zero on success or negative error code on failure.
*/
-int drm_client_new(struct drm_device *dev, struct drm_client_dev *client,
- const char *name, const struct drm_client_funcs *funcs)
+int drm_client_init(struct drm_device *dev, struct drm_client_dev *client,
+ const char *name, const struct drm_client_funcs *funcs)
{
int ret;
@@ -95,10 +96,6 @@ int drm_client_new(struct drm_device *dev, struct drm_client_dev *client,
if (ret)
goto err_put_module;
- mutex_lock(&dev->clientlist_mutex);
- list_add(&client->list, &dev->clientlist);
- mutex_unlock(&dev->clientlist_mutex);
-
drm_dev_get(dev);
return 0;
@@ -109,13 +106,33 @@ int drm_client_new(struct drm_device *dev, struct drm_client_dev *client,
return ret;
}
-EXPORT_SYMBOL(drm_client_new);
+EXPORT_SYMBOL(drm_client_init);
+
+/**
+ * drm_client_add - Add client to the device list
+ * @client: DRM client
+ *
+ * Add the client to the &drm_device client list to activate its callbacks.
+ * @client must be initialized by a call to drm_client_init(). After
+ * drm_client_add() it is no longer permissible to call drm_client_release()
+ * directly (outside the unregister callback), instead cleanup will happen
+ * automatically on driver unload.
+ */
+void drm_client_add(struct drm_client_dev *client)
+{
+ struct drm_device *dev = client->dev;
+
+ mutex_lock(&dev->clientlist_mutex);
+ list_add(&client->list, &dev->clientlist);
+ mutex_unlock(&dev->clientlist_mutex);
+}
+EXPORT_SYMBOL(drm_client_add);
/**
* drm_client_release - Release DRM client resources
* @client: DRM client
*
- * Releases resources by closing the &drm_file that was opened by drm_client_new().
+ * Releases resources by closing the &drm_file that was opened by drm_client_init().
* It is called automatically if the &drm_client_funcs.unregister callback is _not_ set.
*
* This function should only be called from the unregister callback. An exception
diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c
index 9da36a6..9ac1f2e 100644
--- a/drivers/gpu/drm/drm_fb_cma_helper.c
+++ b/drivers/gpu/drm/drm_fb_cma_helper.c
@@ -160,7 +160,7 @@ struct drm_fbdev_cma *drm_fbdev_cma_init(struct drm_device *dev,
fb_helper = &fbdev_cma->fb_helper;
- ret = drm_client_new(dev, &fb_helper->client, "fbdev", NULL);
+ ret = drm_client_init(dev, &fb_helper->client, "fbdev", NULL);
if (ret)
goto err_free;
@@ -169,6 +169,8 @@ struct drm_fbdev_cma *drm_fbdev_cma_init(struct drm_device *dev,
if (ret)
goto err_client_put;
+ drm_client_add(&fb_helper->client);
+
return fbdev_cma;
err_client_put:
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 16ec93b7..515a7ae 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -3218,12 +3218,14 @@ int drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp)
if (!fb_helper)
return -ENOMEM;
- ret = drm_client_new(dev, &fb_helper->client, "fbdev", &drm_fbdev_client_funcs);
+ ret = drm_client_init(dev, &fb_helper->client, "fbdev", &drm_fbdev_client_funcs);
if (ret) {
kfree(fb_helper);
return ret;
}
+ drm_client_add(&fb_helper->client);
+
fb_helper->preferred_bpp = preferred_bpp;
drm_fbdev_client_hotplug(&fb_helper->client);
diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c
index b54fb78..b82da96 100644
--- a/drivers/gpu/drm/drm_lease.c
+++ b/drivers/gpu/drm/drm_lease.c
@@ -566,14 +566,14 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
lessee_priv->is_master = 1;
lessee_priv->authenticated = 1;
- /* Hook up the fd */
- fd_install(fd, lessee_file);
-
/* Pass fd back to userspace */
DRM_DEBUG_LEASE("Returning fd %d id %d\n", fd, lessee->lessee_id);
cl->fd = fd;
cl->lessee_id = lessee->lessee_id;
+ /* Hook up the fd */
+ fd_install(fd, lessee_file);
+
DRM_DEBUG_LEASE("drm_mode_create_lease_ioctl succeeded\n");
return 0;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_iommu.h b/drivers/gpu/drm/exynos/exynos_drm_iommu.h
index 87f6b56..797d9ee 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_iommu.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_iommu.h
@@ -55,37 +55,12 @@ static inline void __exynos_iommu_detach(struct exynos_drm_private *priv,
static inline int __exynos_iommu_create_mapping(struct exynos_drm_private *priv,
unsigned long start, unsigned long size)
{
- struct iommu_domain *domain;
- int ret;
-
- domain = iommu_domain_alloc(priv->dma_dev->bus);
- if (!domain)
- return -ENOMEM;
-
- ret = iommu_get_dma_cookie(domain);
- if (ret)
- goto free_domain;
-
- ret = iommu_dma_init_domain(domain, start, size, NULL);
- if (ret)
- goto put_cookie;
-
- priv->mapping = domain;
+ priv->mapping = iommu_get_domain_for_dev(priv->dma_dev);
return 0;
-
-put_cookie:
- iommu_put_dma_cookie(domain);
-free_domain:
- iommu_domain_free(domain);
- return ret;
}
static inline void __exynos_iommu_release_mapping(struct exynos_drm_private *priv)
{
- struct iommu_domain *domain = priv->mapping;
-
- iommu_put_dma_cookie(domain);
- iommu_domain_free(domain);
priv->mapping = NULL;
}
@@ -94,7 +69,9 @@ static inline int __exynos_iommu_attach(struct exynos_drm_private *priv,
{
struct iommu_domain *domain = priv->mapping;
- return iommu_attach_device(domain, dev);
+ if (dev != priv->dma_dev)
+ return iommu_attach_device(domain, dev);
+ return 0;
}
static inline void __exynos_iommu_detach(struct exynos_drm_private *priv,
@@ -102,7 +79,8 @@ static inline void __exynos_iommu_detach(struct exynos_drm_private *priv,
{
struct iommu_domain *domain = priv->mapping;
- iommu_detach_device(domain, dev);
+ if (dev != priv->dma_dev)
+ iommu_detach_device(domain, dev);
}
#else
#error Unsupported architecture and IOMMU/DMA-mapping glue code
diff --git a/drivers/gpu/drm/i2c/tda9950.c b/drivers/gpu/drm/i2c/tda9950.c
index 5d2f0d5..250b5e0 100644
--- a/drivers/gpu/drm/i2c/tda9950.c
+++ b/drivers/gpu/drm/i2c/tda9950.c
@@ -191,7 +191,8 @@ static irqreturn_t tda9950_irq(int irq, void *data)
break;
}
/* TDA9950 executes all retries for us */
- tx_status |= CEC_TX_STATUS_MAX_RETRIES;
+ if (tx_status != CEC_TX_STATUS_OK)
+ tx_status |= CEC_TX_STATUS_MAX_RETRIES;
cec_transmit_done(priv->adap, tx_status, arb_lost_cnt,
nack_cnt, 0, err_cnt);
break;
@@ -310,7 +311,7 @@ static void tda9950_release(struct tda9950_priv *priv)
/* Wait up to .5s for it to signal non-busy */
do {
csr = tda9950_read(client, REG_CSR);
- if (!(csr & CSR_BUSY) || --timeout)
+ if (!(csr & CSR_BUSY) || !--timeout)
break;
msleep(10);
} while (1);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index f7f2aa7..a262a64 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -232,6 +232,20 @@ static bool compress_init(struct compress *c)
return true;
}
+static void *compress_next_page(struct drm_i915_error_object *dst)
+{
+ unsigned long page;
+
+ if (dst->page_count >= dst->num_pages)
+ return ERR_PTR(-ENOSPC);
+
+ page = __get_free_page(GFP_ATOMIC | __GFP_NOWARN);
+ if (!page)
+ return ERR_PTR(-ENOMEM);
+
+ return dst->pages[dst->page_count++] = (void *)page;
+}
+
static int compress_page(struct compress *c,
void *src,
struct drm_i915_error_object *dst)
@@ -245,19 +259,14 @@ static int compress_page(struct compress *c,
do {
if (zstream->avail_out == 0) {
- unsigned long page;
+ zstream->next_out = compress_next_page(dst);
+ if (IS_ERR(zstream->next_out))
+ return PTR_ERR(zstream->next_out);
- page = __get_free_page(GFP_ATOMIC | __GFP_NOWARN);
- if (!page)
- return -ENOMEM;
-
- dst->pages[dst->page_count++] = (void *)page;
-
- zstream->next_out = (void *)page;
zstream->avail_out = PAGE_SIZE;
}
- if (zlib_deflate(zstream, Z_SYNC_FLUSH) != Z_OK)
+ if (zlib_deflate(zstream, Z_NO_FLUSH) != Z_OK)
return -EIO;
} while (zstream->avail_in);
@@ -268,19 +277,42 @@ static int compress_page(struct compress *c,
return 0;
}
+static int compress_flush(struct compress *c,
+ struct drm_i915_error_object *dst)
+{
+ struct z_stream_s *zstream = &c->zstream;
+
+ do {
+ switch (zlib_deflate(zstream, Z_FINISH)) {
+ case Z_OK: /* more space requested */
+ zstream->next_out = compress_next_page(dst);
+ if (IS_ERR(zstream->next_out))
+ return PTR_ERR(zstream->next_out);
+
+ zstream->avail_out = PAGE_SIZE;
+ break;
+
+ case Z_STREAM_END:
+ goto end;
+
+ default: /* any error */
+ return -EIO;
+ }
+ } while (1);
+
+end:
+ memset(zstream->next_out, 0, zstream->avail_out);
+ dst->unused = zstream->avail_out;
+ return 0;
+}
+
static void compress_fini(struct compress *c,
struct drm_i915_error_object *dst)
{
struct z_stream_s *zstream = &c->zstream;
- if (dst) {
- zlib_deflate(zstream, Z_FINISH);
- dst->unused = zstream->avail_out;
- }
-
zlib_deflateEnd(zstream);
kfree(zstream->workspace);
-
if (c->tmp)
free_page((unsigned long)c->tmp);
}
@@ -319,6 +351,12 @@ static int compress_page(struct compress *c,
return 0;
}
+static int compress_flush(struct compress *c,
+ struct drm_i915_error_object *dst)
+{
+ return 0;
+}
+
static void compress_fini(struct compress *c,
struct drm_i915_error_object *dst)
{
@@ -917,6 +955,7 @@ i915_error_object_create(struct drm_i915_private *i915,
unsigned long num_pages;
struct sgt_iter iter;
dma_addr_t dma;
+ int ret;
if (!vma)
return NULL;
@@ -930,6 +969,7 @@ i915_error_object_create(struct drm_i915_private *i915,
dst->gtt_offset = vma->node.start;
dst->gtt_size = vma->node.size;
+ dst->num_pages = num_pages;
dst->page_count = 0;
dst->unused = 0;
@@ -938,28 +978,26 @@ i915_error_object_create(struct drm_i915_private *i915,
return NULL;
}
+ ret = -EINVAL;
for_each_sgt_dma(dma, iter, vma->pages) {
void __iomem *s;
- int ret;
ggtt->vm.insert_page(&ggtt->vm, dma, slot, I915_CACHE_NONE, 0);
s = io_mapping_map_atomic_wc(&ggtt->iomap, slot);
ret = compress_page(&compress, (void __force *)s, dst);
io_mapping_unmap_atomic(s);
-
if (ret)
- goto unwind;
+ break;
}
- goto out;
-unwind:
- while (dst->page_count--)
- free_page((unsigned long)dst->pages[dst->page_count]);
- kfree(dst);
- dst = NULL;
+ if (ret || compress_flush(&compress, dst)) {
+ while (dst->page_count--)
+ free_page((unsigned long)dst->pages[dst->page_count]);
+ kfree(dst);
+ dst = NULL;
+ }
-out:
compress_fini(&compress, dst);
ggtt->vm.clear_range(&ggtt->vm, slot, PAGE_SIZE);
return dst;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index f893a4e..8710fb1 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -135,6 +135,7 @@ struct i915_gpu_state {
struct drm_i915_error_object {
u64 gtt_offset;
u64 gtt_size;
+ int num_pages;
int page_count;
int unused;
u32 *pages[0];
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 90628a4..2987796 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -3091,36 +3091,27 @@ gen11_gt_irq_handler(struct drm_i915_private * const i915,
spin_unlock(&i915->irq_lock);
}
-static void
-gen11_gu_misc_irq_ack(struct drm_i915_private *dev_priv, const u32 master_ctl,
- u32 *iir)
+static u32
+gen11_gu_misc_irq_ack(struct drm_i915_private *dev_priv, const u32 master_ctl)
{
void __iomem * const regs = dev_priv->regs;
+ u32 iir;
if (!(master_ctl & GEN11_GU_MISC_IRQ))
- return;
+ return 0;
- *iir = raw_reg_read(regs, GEN11_GU_MISC_IIR);
- if (likely(*iir))
- raw_reg_write(regs, GEN11_GU_MISC_IIR, *iir);
+ iir = raw_reg_read(regs, GEN11_GU_MISC_IIR);
+ if (likely(iir))
+ raw_reg_write(regs, GEN11_GU_MISC_IIR, iir);
+
+ return iir;
}
static void
-gen11_gu_misc_irq_handler(struct drm_i915_private *dev_priv,
- const u32 master_ctl, const u32 iir)
+gen11_gu_misc_irq_handler(struct drm_i915_private *dev_priv, const u32 iir)
{
- if (!(master_ctl & GEN11_GU_MISC_IRQ))
- return;
-
- if (unlikely(!iir)) {
- DRM_ERROR("GU_MISC iir blank!\n");
- return;
- }
-
if (iir & GEN11_GU_MISC_GSE)
intel_opregion_asle_intr(dev_priv);
- else
- DRM_ERROR("Unexpected GU_MISC interrupt 0x%x\n", iir);
}
static irqreturn_t gen11_irq_handler(int irq, void *arg)
@@ -3157,12 +3148,12 @@ static irqreturn_t gen11_irq_handler(int irq, void *arg)
enable_rpm_wakeref_asserts(i915);
}
- gen11_gu_misc_irq_ack(i915, master_ctl, &gu_misc_iir);
+ gu_misc_iir = gen11_gu_misc_irq_ack(i915, master_ctl);
/* Acknowledge and enable interrupts. */
raw_reg_write(regs, GEN11_GFX_MSTR_IRQ, GEN11_MASTER_IRQ | master_ctl);
- gen11_gu_misc_irq_handler(i915, master_ctl, gu_misc_iir);
+ gen11_gu_misc_irq_handler(i915, gu_misc_iir);
return IRQ_HANDLED;
}
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 6a4d138..1df3ce1 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -592,7 +592,6 @@ static const struct intel_device_info intel_cannonlake_info = {
GEN10_FEATURES, \
GEN(11), \
.ddb_size = 2048, \
- .has_csr = 0, \
.has_logical_ring_elsq = 1
static const struct intel_device_info intel_icelake_11_info = {
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 5146ee0..bc49909 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -976,7 +976,6 @@
#define USB_DEVICE_ID_SIS817_TOUCH 0x0817
#define USB_DEVICE_ID_SIS_TS 0x1013
#define USB_DEVICE_ID_SIS1030_TOUCH 0x1030
-#define USB_DEVICE_ID_SIS10FB_TOUCH 0x10fb
#define USB_VENDOR_ID_SKYCABLE 0x1223
#define USB_DEVICE_ID_SKYCABLE_WIRELESS_PRESENTER 0x3F07
diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c
index f307665..4e3592e 100644
--- a/drivers/hid/i2c-hid/i2c-hid.c
+++ b/drivers/hid/i2c-hid/i2c-hid.c
@@ -47,7 +47,7 @@
/* quirks to control the device */
#define I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV BIT(0)
#define I2C_HID_QUIRK_NO_IRQ_AFTER_RESET BIT(1)
-#define I2C_HID_QUIRK_RESEND_REPORT_DESCR BIT(2)
+#define I2C_HID_QUIRK_NO_RUNTIME_PM BIT(2)
/* flags */
#define I2C_HID_STARTED 0
@@ -169,9 +169,8 @@ static const struct i2c_hid_quirks {
{ USB_VENDOR_ID_WEIDA, USB_DEVICE_ID_WEIDA_8755,
I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV },
{ I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288,
- I2C_HID_QUIRK_NO_IRQ_AFTER_RESET },
- { USB_VENDOR_ID_SIS_TOUCH, USB_DEVICE_ID_SIS10FB_TOUCH,
- I2C_HID_QUIRK_RESEND_REPORT_DESCR },
+ I2C_HID_QUIRK_NO_IRQ_AFTER_RESET |
+ I2C_HID_QUIRK_NO_RUNTIME_PM },
{ 0, 0 }
};
@@ -1105,7 +1104,9 @@ static int i2c_hid_probe(struct i2c_client *client,
goto err_mem_free;
}
- pm_runtime_put(&client->dev);
+ if (!(ihid->quirks & I2C_HID_QUIRK_NO_RUNTIME_PM))
+ pm_runtime_put(&client->dev);
+
return 0;
err_mem_free:
@@ -1130,7 +1131,8 @@ static int i2c_hid_remove(struct i2c_client *client)
struct i2c_hid *ihid = i2c_get_clientdata(client);
struct hid_device *hid;
- pm_runtime_get_sync(&client->dev);
+ if (!(ihid->quirks & I2C_HID_QUIRK_NO_RUNTIME_PM))
+ pm_runtime_get_sync(&client->dev);
pm_runtime_disable(&client->dev);
pm_runtime_set_suspended(&client->dev);
pm_runtime_put_noidle(&client->dev);
@@ -1236,22 +1238,13 @@ static int i2c_hid_resume(struct device *dev)
/* Instead of resetting device, simply powers the device on. This
* solves "incomplete reports" on Raydium devices 2386:3118 and
- * 2386:4B33
+ * 2386:4B33 and fixes various SIS touchscreens no longer sending
+ * data after a suspend/resume.
*/
ret = i2c_hid_set_power(client, I2C_HID_PWR_ON);
if (ret)
return ret;
- /* Some devices need to re-send report descr cmd
- * after resume, after this it will be back normal.
- * otherwise it issues too many incomplete reports.
- */
- if (ihid->quirks & I2C_HID_QUIRK_RESEND_REPORT_DESCR) {
- ret = i2c_hid_command(client, &hid_report_descr_cmd, NULL, 0);
- if (ret)
- return ret;
- }
-
if (hid->driver && hid->driver->reset_resume) {
ret = hid->driver->reset_resume(hid);
return ret;
diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
index da13371..08a8327 100644
--- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h
+++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h
@@ -29,6 +29,7 @@
#define CNL_Ax_DEVICE_ID 0x9DFC
#define GLK_Ax_DEVICE_ID 0x31A2
#define CNL_H_DEVICE_ID 0xA37C
+#define ICL_MOBILE_DEVICE_ID 0x34FC
#define SPT_H_DEVICE_ID 0xA135
#define REVISION_ID_CHT_A0 0x6
diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
index a1125a5..256b301 100644
--- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c
+++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c
@@ -38,6 +38,7 @@ static const struct pci_device_id ish_pci_tbl[] = {
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, CNL_Ax_DEVICE_ID)},
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, GLK_Ax_DEVICE_ID)},
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, CNL_H_DEVICE_ID)},
+ {PCI_DEVICE(PCI_VENDOR_ID_INTEL, ICL_MOBILE_DEVICE_ID)},
{PCI_DEVICE(PCI_VENDOR_ID_INTEL, SPT_H_DEVICE_ID)},
{0, }
};
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 73e47d9..bee0dfb 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -3069,7 +3069,7 @@ static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom,
return 0;
offset_mask = pte_pgsize - 1;
- __pte = *pte & PM_ADDR_MASK;
+ __pte = __sme_clr(*pte & PM_ADDR_MASK);
return (__pte & ~offset_mask) | (iova & offset_mask);
}
diff --git a/drivers/media/v4l2-core/v4l2-event.c b/drivers/media/v4l2-core/v4l2-event.c
index 127fe6e..a3ef1f5 100644
--- a/drivers/media/v4l2-core/v4l2-event.c
+++ b/drivers/media/v4l2-core/v4l2-event.c
@@ -115,14 +115,6 @@ static void __v4l2_event_queue_fh(struct v4l2_fh *fh, const struct v4l2_event *e
if (sev == NULL)
return;
- /*
- * If the event has been added to the fh->subscribed list, but its
- * add op has not completed yet elems will be 0, treat this as
- * not being subscribed.
- */
- if (!sev->elems)
- return;
-
/* Increase event sequence number on fh. */
fh->sequence++;
@@ -208,6 +200,7 @@ int v4l2_event_subscribe(struct v4l2_fh *fh,
struct v4l2_subscribed_event *sev, *found_ev;
unsigned long flags;
unsigned i;
+ int ret = 0;
if (sub->type == V4L2_EVENT_ALL)
return -EINVAL;
@@ -225,31 +218,36 @@ int v4l2_event_subscribe(struct v4l2_fh *fh,
sev->flags = sub->flags;
sev->fh = fh;
sev->ops = ops;
+ sev->elems = elems;
+
+ mutex_lock(&fh->subscribe_lock);
spin_lock_irqsave(&fh->vdev->fh_lock, flags);
found_ev = v4l2_event_subscribed(fh, sub->type, sub->id);
- if (!found_ev)
- list_add(&sev->list, &fh->subscribed);
spin_unlock_irqrestore(&fh->vdev->fh_lock, flags);
if (found_ev) {
+ /* Already listening */
kvfree(sev);
- return 0; /* Already listening */
+ goto out_unlock;
}
if (sev->ops && sev->ops->add) {
- int ret = sev->ops->add(sev, elems);
+ ret = sev->ops->add(sev, elems);
if (ret) {
- sev->ops = NULL;
- v4l2_event_unsubscribe(fh, sub);
- return ret;
+ kvfree(sev);
+ goto out_unlock;
}
}
- /* Mark as ready for use */
- sev->elems = elems;
+ spin_lock_irqsave(&fh->vdev->fh_lock, flags);
+ list_add(&sev->list, &fh->subscribed);
+ spin_unlock_irqrestore(&fh->vdev->fh_lock, flags);
- return 0;
+out_unlock:
+ mutex_unlock(&fh->subscribe_lock);
+
+ return ret;
}
EXPORT_SYMBOL_GPL(v4l2_event_subscribe);
@@ -288,6 +286,8 @@ int v4l2_event_unsubscribe(struct v4l2_fh *fh,
return 0;
}
+ mutex_lock(&fh->subscribe_lock);
+
spin_lock_irqsave(&fh->vdev->fh_lock, flags);
sev = v4l2_event_subscribed(fh, sub->type, sub->id);
@@ -305,6 +305,8 @@ int v4l2_event_unsubscribe(struct v4l2_fh *fh,
if (sev && sev->ops && sev->ops->del)
sev->ops->del(sev);
+ mutex_unlock(&fh->subscribe_lock);
+
kvfree(sev);
return 0;
diff --git a/drivers/media/v4l2-core/v4l2-fh.c b/drivers/media/v4l2-core/v4l2-fh.c
index 3895999..c91a7bd 100644
--- a/drivers/media/v4l2-core/v4l2-fh.c
+++ b/drivers/media/v4l2-core/v4l2-fh.c
@@ -45,6 +45,7 @@ void v4l2_fh_init(struct v4l2_fh *fh, struct video_device *vdev)
INIT_LIST_HEAD(&fh->available);
INIT_LIST_HEAD(&fh->subscribed);
fh->sequence = -1;
+ mutex_init(&fh->subscribe_lock);
}
EXPORT_SYMBOL_GPL(v4l2_fh_init);
@@ -90,6 +91,7 @@ void v4l2_fh_exit(struct v4l2_fh *fh)
return;
v4l_disable_media_source(fh->vdev);
v4l2_event_unsubscribe_all(fh);
+ mutex_destroy(&fh->subscribe_lock);
fh->vdev = NULL;
}
EXPORT_SYMBOL_GPL(v4l2_fh_exit);
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index abf9e88..f57f5de 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -235,7 +235,7 @@ int mmc_of_parse(struct mmc_host *host)
host->caps |= MMC_CAP_NEEDS_POLL;
ret = mmc_gpiod_request_cd(host, "cd", 0, true,
- cd_debounce_delay_ms,
+ cd_debounce_delay_ms * 1000,
&cd_gpio_invert);
if (!ret)
dev_info(host->parent, "Got CD GPIO\n");
diff --git a/drivers/mmc/core/slot-gpio.c b/drivers/mmc/core/slot-gpio.c
index 2a83368..86803a3 100644
--- a/drivers/mmc/core/slot-gpio.c
+++ b/drivers/mmc/core/slot-gpio.c
@@ -271,7 +271,7 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
if (debounce) {
ret = gpiod_set_debounce(desc, debounce);
if (ret < 0)
- ctx->cd_debounce_delay_ms = debounce;
+ ctx->cd_debounce_delay_ms = debounce / 1000;
}
if (gpio_invert)
diff --git a/drivers/mmc/host/renesas_sdhi_sys_dmac.c b/drivers/mmc/host/renesas_sdhi_sys_dmac.c
index 890f192..5389c48 100644
--- a/drivers/mmc/host/renesas_sdhi_sys_dmac.c
+++ b/drivers/mmc/host/renesas_sdhi_sys_dmac.c
@@ -498,7 +498,8 @@ static const struct soc_device_attribute gen3_soc_whitelist[] = {
static int renesas_sdhi_sys_dmac_probe(struct platform_device *pdev)
{
- if (of_device_get_match_data(&pdev->dev) == &of_rcar_gen3_compatible &&
+ if ((of_device_get_match_data(&pdev->dev) == &of_rcar_gen3_compatible ||
+ of_device_get_match_data(&pdev->dev) == &of_rcar_r8a7795_compatible) &&
!soc_device_match(gen3_soc_whitelist))
return -ENODEV;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 0d87e11..ee28ec9 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -210,6 +210,7 @@ static void bond_get_stats(struct net_device *bond_dev,
static void bond_slave_arr_handler(struct work_struct *work);
static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act,
int mod);
+static void bond_netdev_notify_work(struct work_struct *work);
/*---------------------------- General routines -----------------------------*/
@@ -1170,9 +1171,27 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
}
}
- /* don't change skb->dev for link-local packets */
- if (is_link_local_ether_addr(eth_hdr(skb)->h_dest))
+ /* Link-local multicast packets should be passed to the
+ * stack on the link they arrive as well as pass them to the
+ * bond-master device. These packets are mostly usable when
+ * stack receives it with the link on which they arrive
+ * (e.g. LLDP) they also must be available on master. Some of
+ * the use cases include (but are not limited to): LLDP agents
+ * that must be able to operate both on enslaved interfaces as
+ * well as on bonds themselves; linux bridges that must be able
+ * to process/pass BPDUs from attached bonds when any kind of
+ * STP version is enabled on the network.
+ */
+ if (is_link_local_ether_addr(eth_hdr(skb)->h_dest)) {
+ struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+
+ if (nskb) {
+ nskb->dev = bond->dev;
+ nskb->queue_mapping = 0;
+ netif_rx(nskb);
+ }
return RX_HANDLER_PASS;
+ }
if (bond_should_deliver_exact_match(skb, slave, bond))
return RX_HANDLER_EXACT;
@@ -1269,6 +1288,8 @@ static struct slave *bond_alloc_slave(struct bonding *bond)
return NULL;
}
}
+ INIT_DELAYED_WORK(&slave->notify_work, bond_netdev_notify_work);
+
return slave;
}
@@ -1276,6 +1297,7 @@ static void bond_free_slave(struct slave *slave)
{
struct bonding *bond = bond_get_bond_by_slave(slave);
+ cancel_delayed_work_sync(&slave->notify_work);
if (BOND_MODE(bond) == BOND_MODE_8023AD)
kfree(SLAVE_AD_INFO(slave));
@@ -1297,39 +1319,26 @@ static void bond_fill_ifslave(struct slave *slave, struct ifslave *info)
info->link_failure_count = slave->link_failure_count;
}
-static void bond_netdev_notify(struct net_device *dev,
- struct netdev_bonding_info *info)
-{
- rtnl_lock();
- netdev_bonding_info_change(dev, info);
- rtnl_unlock();
-}
-
static void bond_netdev_notify_work(struct work_struct *_work)
{
- struct netdev_notify_work *w =
- container_of(_work, struct netdev_notify_work, work.work);
+ struct slave *slave = container_of(_work, struct slave,
+ notify_work.work);
- bond_netdev_notify(w->dev, &w->bonding_info);
- dev_put(w->dev);
- kfree(w);
+ if (rtnl_trylock()) {
+ struct netdev_bonding_info binfo;
+
+ bond_fill_ifslave(slave, &binfo.slave);
+ bond_fill_ifbond(slave->bond, &binfo.master);
+ netdev_bonding_info_change(slave->dev, &binfo);
+ rtnl_unlock();
+ } else {
+ queue_delayed_work(slave->bond->wq, &slave->notify_work, 1);
+ }
}
void bond_queue_slave_event(struct slave *slave)
{
- struct bonding *bond = slave->bond;
- struct netdev_notify_work *nnw = kzalloc(sizeof(*nnw), GFP_ATOMIC);
-
- if (!nnw)
- return;
-
- dev_hold(slave->dev);
- nnw->dev = slave->dev;
- bond_fill_ifslave(slave, &nnw->bonding_info.slave);
- bond_fill_ifbond(bond, &nnw->bonding_info.master);
- INIT_DELAYED_WORK(&nnw->work, bond_netdev_notify_work);
-
- queue_delayed_work(slave->bond->wq, &nnw->work, 0);
+ queue_delayed_work(slave->bond->wq, &slave->notify_work, 0);
}
void bond_lower_state_changed(struct slave *slave)
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 29b5774..25621a2 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2185,25 +2185,6 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
}
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void ena_netpoll(struct net_device *netdev)
-{
- struct ena_adapter *adapter = netdev_priv(netdev);
- int i;
-
- /* Dont schedule NAPI if the driver is in the middle of reset
- * or netdev is down.
- */
-
- if (!test_bit(ENA_FLAG_DEV_UP, &adapter->flags) ||
- test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))
- return;
-
- for (i = 0; i < adapter->num_queues; i++)
- napi_schedule(&adapter->ena_napi[i].napi);
-}
-#endif /* CONFIG_NET_POLL_CONTROLLER */
-
static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb,
struct net_device *sb_dev,
select_queue_fallback_t fallback)
@@ -2369,9 +2350,6 @@ static const struct net_device_ops ena_netdev_ops = {
.ndo_change_mtu = ena_change_mtu,
.ndo_set_mac_address = NULL,
.ndo_validate_addr = eth_validate_addr,
-#ifdef CONFIG_NET_POLL_CONTROLLER
- .ndo_poll_controller = ena_netpoll,
-#endif /* CONFIG_NET_POLL_CONTROLLER */
};
static int ena_device_validate_params(struct ena_adapter *adapter,
diff --git a/drivers/net/ethernet/amd/declance.c b/drivers/net/ethernet/amd/declance.c
index 116997a..00332a1 100644
--- a/drivers/net/ethernet/amd/declance.c
+++ b/drivers/net/ethernet/amd/declance.c
@@ -1031,6 +1031,7 @@ static int dec_lance_probe(struct device *bdev, const int type)
int i, ret;
unsigned long esar_base;
unsigned char *esar;
+ const char *desc;
if (dec_lance_debug && version_printed++ == 0)
printk(version);
@@ -1216,19 +1217,20 @@ static int dec_lance_probe(struct device *bdev, const int type)
*/
switch (type) {
case ASIC_LANCE:
- printk("%s: IOASIC onboard LANCE", name);
+ desc = "IOASIC onboard LANCE";
break;
case PMAD_LANCE:
- printk("%s: PMAD-AA", name);
+ desc = "PMAD-AA";
break;
case PMAX_LANCE:
- printk("%s: PMAX onboard LANCE", name);
+ desc = "PMAX onboard LANCE";
break;
}
for (i = 0; i < 6; i++)
dev->dev_addr[i] = esar[i * 4];
- printk(", addr = %pM, irq = %d\n", dev->dev_addr, dev->irq);
+ printk("%s: %s, addr = %pM, irq = %d\n",
+ name, desc, dev->dev_addr, dev->irq);
dev->netdev_ops = &lance_netdev_ops;
dev->watchdog_timeo = 5*HZ;
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 1470457..c57238f 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1069,9 +1069,6 @@ static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv)
{
u32 reg;
- /* Stop monitoring MPD interrupt */
- intrl2_0_mask_set(priv, INTRL2_0_MPD | INTRL2_0_BRCM_MATCH_TAG);
-
/* Disable RXCHK, active filters and Broadcom tag matching */
reg = rxchk_readl(priv, RXCHK_CONTROL);
reg &= ~(RXCHK_BRCM_TAG_MATCH_MASK <<
@@ -1081,6 +1078,17 @@ static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv)
/* Clear the MagicPacket detection logic */
mpd_enable_set(priv, false);
+ reg = intrl2_0_readl(priv, INTRL2_CPU_STATUS);
+ if (reg & INTRL2_0_MPD)
+ netdev_info(priv->netdev, "Wake-on-LAN (MPD) interrupt!\n");
+
+ if (reg & INTRL2_0_BRCM_MATCH_TAG) {
+ reg = rxchk_readl(priv, RXCHK_BRCM_TAG_MATCH_STATUS) &
+ RXCHK_BRCM_TAG_MATCH_MASK;
+ netdev_info(priv->netdev,
+ "Wake-on-LAN (filters 0x%02x) interrupt!\n", reg);
+ }
+
netif_dbg(priv, wol, priv->netdev, "resumed from WOL\n");
}
@@ -1105,7 +1113,6 @@ static irqreturn_t bcm_sysport_rx_isr(int irq, void *dev_id)
struct bcm_sysport_priv *priv = netdev_priv(dev);
struct bcm_sysport_tx_ring *txr;
unsigned int ring, ring_bit;
- u32 reg;
priv->irq0_stat = intrl2_0_readl(priv, INTRL2_CPU_STATUS) &
~intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS);
@@ -1131,16 +1138,6 @@ static irqreturn_t bcm_sysport_rx_isr(int irq, void *dev_id)
if (priv->irq0_stat & INTRL2_0_TX_RING_FULL)
bcm_sysport_tx_reclaim_all(priv);
- if (priv->irq0_stat & INTRL2_0_MPD)
- netdev_info(priv->netdev, "Wake-on-LAN (MPD) interrupt!\n");
-
- if (priv->irq0_stat & INTRL2_0_BRCM_MATCH_TAG) {
- reg = rxchk_readl(priv, RXCHK_BRCM_TAG_MATCH_STATUS) &
- RXCHK_BRCM_TAG_MATCH_MASK;
- netdev_info(priv->netdev,
- "Wake-on-LAN (filters 0x%02x) interrupt!\n", reg);
- }
-
if (!priv->is_lite)
goto out;
@@ -2641,9 +2638,6 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv)
/* UniMAC receive needs to be turned on */
umac_enable_set(priv, CMD_RX_EN, 1);
- /* Enable the interrupt wake-up source */
- intrl2_0_mask_clear(priv, INTRL2_0_MPD | INTRL2_0_BRCM_MATCH_TAG);
-
netif_dbg(priv, wol, ndev, "entered WOL mode\n");
return 0;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 61957b0..0478e56 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1884,8 +1884,11 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
if (TX_CMP_TYPE(txcmp) == CMP_TYPE_TX_L2_CMP) {
tx_pkts++;
/* return full budget so NAPI will complete. */
- if (unlikely(tx_pkts > bp->tx_wake_thresh))
+ if (unlikely(tx_pkts > bp->tx_wake_thresh)) {
rx_pkts = budget;
+ raw_cons = NEXT_RAW_CMP(raw_cons);
+ break;
+ }
} else if ((TX_CMP_TYPE(txcmp) & 0x30) == 0x10) {
if (likely(budget))
rc = bnxt_rx_pkt(bp, bnapi, &raw_cons, &event);
@@ -1913,7 +1916,7 @@ static int bnxt_poll_work(struct bnxt *bp, struct bnxt_napi *bnapi, int budget)
}
raw_cons = NEXT_RAW_CMP(raw_cons);
- if (rx_pkts == budget)
+ if (rx_pkts && rx_pkts == budget)
break;
}
@@ -2027,8 +2030,12 @@ static int bnxt_poll(struct napi_struct *napi, int budget)
while (1) {
work_done += bnxt_poll_work(bp, bnapi, budget - work_done);
- if (work_done >= budget)
+ if (work_done >= budget) {
+ if (!budget)
+ BNXT_CP_DB_REARM(cpr->cp_doorbell,
+ cpr->cp_raw_cons);
break;
+ }
if (!bnxt_has_work(bp, cpr)) {
if (napi_complete_done(napi, work_done))
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index f1a86b4..58b9744 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -2160,6 +2160,7 @@ static void macb_configure_dma(struct macb *bp)
else
dmacfg &= ~GEM_BIT(TXCOEN);
+ dmacfg &= ~GEM_BIT(ADDR64);
#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
if (bp->hw_dma_cap & HW_DMA_CAP_64B)
dmacfg |= GEM_BIT(ADDR64);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 2708297..bf9b9fd 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1158,7 +1158,7 @@ static void fec_enet_timeout_work(struct work_struct *work)
napi_disable(&fep->napi);
netif_tx_lock_bh(ndev);
fec_restart(ndev);
- netif_wake_queue(ndev);
+ netif_tx_wake_all_queues(ndev);
netif_tx_unlock_bh(ndev);
napi_enable(&fep->napi);
}
@@ -1273,7 +1273,7 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
/* Since we have freed up a buffer, the ring is no longer full
*/
- if (netif_queue_stopped(ndev)) {
+ if (netif_tx_queue_stopped(nq)) {
entries_free = fec_enet_get_free_txdesc_num(txq);
if (entries_free >= txq->tx_wake_threshold)
netif_tx_wake_queue(nq);
@@ -1746,7 +1746,7 @@ static void fec_enet_adjust_link(struct net_device *ndev)
napi_disable(&fep->napi);
netif_tx_lock_bh(ndev);
fec_restart(ndev);
- netif_wake_queue(ndev);
+ netif_tx_wake_all_queues(ndev);
netif_tx_unlock_bh(ndev);
napi_enable(&fep->napi);
}
@@ -2247,7 +2247,7 @@ static int fec_enet_set_pauseparam(struct net_device *ndev,
napi_disable(&fep->napi);
netif_tx_lock_bh(ndev);
fec_restart(ndev);
- netif_wake_queue(ndev);
+ netif_tx_wake_all_queues(ndev);
netif_tx_unlock_bh(ndev);
napi_enable(&fep->napi);
}
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c
index a051e58..79d03f8 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.c
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.c
@@ -84,7 +84,7 @@ static void hnae_unmap_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb)
if (cb->type == DESC_TYPE_SKB)
dma_unmap_single(ring_to_dev(ring), cb->dma, cb->length,
ring_to_dma_dir(ring));
- else
+ else if (cb->length)
dma_unmap_page(ring_to_dev(ring), cb->dma, cb->length,
ring_to_dma_dir(ring));
}
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index f56855e..28e9078 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -40,9 +40,9 @@
#define SKB_TMP_LEN(SKB) \
(((SKB)->transport_header - (SKB)->mac_header) + tcp_hdrlen(SKB))
-static void fill_v2_desc(struct hnae_ring *ring, void *priv,
- int size, dma_addr_t dma, int frag_end,
- int buf_num, enum hns_desc_type type, int mtu)
+static void fill_v2_desc_hw(struct hnae_ring *ring, void *priv, int size,
+ int send_sz, dma_addr_t dma, int frag_end,
+ int buf_num, enum hns_desc_type type, int mtu)
{
struct hnae_desc *desc = &ring->desc[ring->next_to_use];
struct hnae_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use];
@@ -64,7 +64,7 @@ static void fill_v2_desc(struct hnae_ring *ring, void *priv,
desc_cb->type = type;
desc->addr = cpu_to_le64(dma);
- desc->tx.send_size = cpu_to_le16((u16)size);
+ desc->tx.send_size = cpu_to_le16((u16)send_sz);
/* config bd buffer end */
hnae_set_bit(rrcfv, HNSV2_TXD_VLD_B, 1);
@@ -133,6 +133,14 @@ static void fill_v2_desc(struct hnae_ring *ring, void *priv,
ring_ptr_move_fw(ring, next_to_use);
}
+static void fill_v2_desc(struct hnae_ring *ring, void *priv,
+ int size, dma_addr_t dma, int frag_end,
+ int buf_num, enum hns_desc_type type, int mtu)
+{
+ fill_v2_desc_hw(ring, priv, size, size, dma, frag_end,
+ buf_num, type, mtu);
+}
+
static const struct acpi_device_id hns_enet_acpi_match[] = {
{ "HISI00C1", 0 },
{ "HISI00C2", 0 },
@@ -289,15 +297,15 @@ static void fill_tso_desc(struct hnae_ring *ring, void *priv,
/* when the frag size is bigger than hardware, split this frag */
for (k = 0; k < frag_buf_num; k++)
- fill_v2_desc(ring, priv,
- (k == frag_buf_num - 1) ?
+ fill_v2_desc_hw(ring, priv, k == 0 ? size : 0,
+ (k == frag_buf_num - 1) ?
sizeoflast : BD_MAX_SEND_SIZE,
- dma + BD_MAX_SEND_SIZE * k,
- frag_end && (k == frag_buf_num - 1) ? 1 : 0,
- buf_num,
- (type == DESC_TYPE_SKB && !k) ?
+ dma + BD_MAX_SEND_SIZE * k,
+ frag_end && (k == frag_buf_num - 1) ? 1 : 0,
+ buf_num,
+ (type == DESC_TYPE_SKB && !k) ?
DESC_TYPE_SKB : DESC_TYPE_PAGE,
- mtu);
+ mtu);
}
netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev,
@@ -1495,21 +1503,6 @@ static int hns_nic_do_ioctl(struct net_device *netdev, struct ifreq *ifr,
return phy_mii_ioctl(phy_dev, ifr, cmd);
}
-/* use only for netconsole to poll with the device without interrupt */
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void hns_nic_poll_controller(struct net_device *ndev)
-{
- struct hns_nic_priv *priv = netdev_priv(ndev);
- unsigned long flags;
- int i;
-
- local_irq_save(flags);
- for (i = 0; i < priv->ae_handle->q_num * 2; i++)
- napi_schedule(&priv->ring_data[i].napi);
- local_irq_restore(flags);
-}
-#endif
-
static netdev_tx_t hns_nic_net_xmit(struct sk_buff *skb,
struct net_device *ndev)
{
@@ -1962,9 +1955,6 @@ static const struct net_device_ops hns_nic_netdev_ops = {
.ndo_set_features = hns_nic_set_features,
.ndo_fix_features = hns_nic_fix_features,
.ndo_get_stats64 = hns_nic_get_stats64,
-#ifdef CONFIG_NET_POLL_CONTROLLER
- .ndo_poll_controller = hns_nic_poll_controller,
-#endif
.ndo_set_rx_mode = hns_nic_set_rx_mode,
.ndo_select_queue = hns_nic_select_queue,
};
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index 09e9da1..4a8f829 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -789,23 +789,6 @@ static void hinic_get_stats64(struct net_device *netdev,
stats->tx_errors = nic_tx_stats->tx_dropped;
}
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void hinic_netpoll(struct net_device *netdev)
-{
- struct hinic_dev *nic_dev = netdev_priv(netdev);
- int i, num_qps;
-
- num_qps = hinic_hwdev_num_qps(nic_dev->hwdev);
- for (i = 0; i < num_qps; i++) {
- struct hinic_txq *txq = &nic_dev->txqs[i];
- struct hinic_rxq *rxq = &nic_dev->rxqs[i];
-
- napi_schedule(&txq->napi);
- napi_schedule(&rxq->napi);
- }
-}
-#endif
-
static const struct net_device_ops hinic_netdev_ops = {
.ndo_open = hinic_open,
.ndo_stop = hinic_close,
@@ -818,9 +801,6 @@ static const struct net_device_ops hinic_netdev_ops = {
.ndo_start_xmit = hinic_xmit_frame,
.ndo_tx_timeout = hinic_tx_timeout,
.ndo_get_stats64 = hinic_get_stats64,
-#ifdef CONFIG_NET_POLL_CONTROLLER
- .ndo_poll_controller = hinic_netpoll,
-#endif
};
static void netdev_features_init(struct net_device *netdev)
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index ba580bf..03f64f4 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -921,17 +921,6 @@ static int ehea_poll(struct napi_struct *napi, int budget)
return rx;
}
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void ehea_netpoll(struct net_device *dev)
-{
- struct ehea_port *port = netdev_priv(dev);
- int i;
-
- for (i = 0; i < port->num_def_qps; i++)
- napi_schedule(&port->port_res[i].napi);
-}
-#endif
-
static irqreturn_t ehea_recv_irq_handler(int irq, void *param)
{
struct ehea_port_res *pr = param;
@@ -2953,9 +2942,6 @@ static const struct net_device_ops ehea_netdev_ops = {
.ndo_open = ehea_open,
.ndo_stop = ehea_stop,
.ndo_start_xmit = ehea_start_xmit,
-#ifdef CONFIG_NET_POLL_CONTROLLER
- .ndo_poll_controller = ehea_netpoll,
-#endif
.ndo_get_stats64 = ehea_get_stats64,
.ndo_set_mac_address = ehea_set_mac_addr,
.ndo_validate_addr = eth_validate_addr,
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 4f0daf6..699ef94 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2207,19 +2207,6 @@ static int ibmvnic_poll(struct napi_struct *napi, int budget)
return frames_processed;
}
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void ibmvnic_netpoll_controller(struct net_device *dev)
-{
- struct ibmvnic_adapter *adapter = netdev_priv(dev);
- int i;
-
- replenish_pools(netdev_priv(dev));
- for (i = 0; i < adapter->req_rx_queues; i++)
- ibmvnic_interrupt_rx(adapter->rx_scrq[i]->irq,
- adapter->rx_scrq[i]);
-}
-#endif
-
static int wait_for_reset(struct ibmvnic_adapter *adapter)
{
int rc, ret;
@@ -2292,9 +2279,6 @@ static const struct net_device_ops ibmvnic_netdev_ops = {
.ndo_set_mac_address = ibmvnic_set_mac,
.ndo_validate_addr = eth_validate_addr,
.ndo_tx_timeout = ibmvnic_tx_timeout,
-#ifdef CONFIG_NET_POLL_CONTROLLER
- .ndo_poll_controller = ibmvnic_netpoll_controller,
-#endif
.ndo_change_mtu = ibmvnic_change_mtu,
.ndo_features_check = ibmvnic_features_check,
};
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index f27d73a..6cdd58d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -3196,11 +3196,13 @@ int ixgbe_poll(struct napi_struct *napi, int budget)
return budget;
/* all work done, exit the polling mode */
- napi_complete_done(napi, work_done);
- if (adapter->rx_itr_setting & 1)
- ixgbe_set_itr(q_vector);
- if (!test_bit(__IXGBE_DOWN, &adapter->state))
- ixgbe_irq_enable_queues(adapter, BIT_ULL(q_vector->v_idx));
+ if (likely(napi_complete_done(napi, work_done))) {
+ if (adapter->rx_itr_setting & 1)
+ ixgbe_set_itr(q_vector);
+ if (!test_bit(__IXGBE_DOWN, &adapter->state))
+ ixgbe_irq_enable_queues(adapter,
+ BIT_ULL(q_vector->v_idx));
+ }
return min(work_done, budget - 1);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index db2cfcd..0f189f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -54,6 +54,7 @@
#include "en_stats.h"
#include "en/fs.h"
+extern const struct net_device_ops mlx5e_netdev_ops;
struct page_pool;
#define MLX5E_METADATA_ETHER_TYPE (0x8CE4)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index bbf69e8..1431232 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -16,6 +16,8 @@ struct mlx5e_tc_table {
DECLARE_HASHTABLE(mod_hdr_tbl, 8);
DECLARE_HASHTABLE(hairpin_tbl, 8);
+
+ struct notifier_block netdevice_nb;
};
struct mlx5e_flow_table {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 54118b7..f291d1b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4315,7 +4315,7 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp)
}
}
-static const struct net_device_ops mlx5e_netdev_ops = {
+const struct net_device_ops mlx5e_netdev_ops = {
.ndo_open = mlx5e_open,
.ndo_stop = mlx5e_close,
.ndo_start_xmit = mlx5e_xmit,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 9fed540..8579672 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1368,6 +1368,9 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
*match_level = MLX5_MATCH_L2;
}
+ } else {
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c, svlan_tag, 1);
+ MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1);
}
if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CVLAN)) {
@@ -2946,14 +2949,71 @@ int mlx5e_stats_flower(struct mlx5e_priv *priv,
return 0;
}
+static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv,
+ struct mlx5e_priv *peer_priv)
+{
+ struct mlx5_core_dev *peer_mdev = peer_priv->mdev;
+ struct mlx5e_hairpin_entry *hpe;
+ u16 peer_vhca_id;
+ int bkt;
+
+ if (!same_hw_devs(priv, peer_priv))
+ return;
+
+ peer_vhca_id = MLX5_CAP_GEN(peer_mdev, vhca_id);
+
+ hash_for_each(priv->fs.tc.hairpin_tbl, bkt, hpe, hairpin_hlist) {
+ if (hpe->peer_vhca_id == peer_vhca_id)
+ hpe->hp->pair->peer_gone = true;
+ }
+}
+
+static int mlx5e_tc_netdev_event(struct notifier_block *this,
+ unsigned long event, void *ptr)
+{
+ struct net_device *ndev = netdev_notifier_info_to_dev(ptr);
+ struct mlx5e_flow_steering *fs;
+ struct mlx5e_priv *peer_priv;
+ struct mlx5e_tc_table *tc;
+ struct mlx5e_priv *priv;
+
+ if (ndev->netdev_ops != &mlx5e_netdev_ops ||
+ event != NETDEV_UNREGISTER ||
+ ndev->reg_state == NETREG_REGISTERED)
+ return NOTIFY_DONE;
+
+ tc = container_of(this, struct mlx5e_tc_table, netdevice_nb);
+ fs = container_of(tc, struct mlx5e_flow_steering, tc);
+ priv = container_of(fs, struct mlx5e_priv, fs);
+ peer_priv = netdev_priv(ndev);
+ if (priv == peer_priv ||
+ !(priv->netdev->features & NETIF_F_HW_TC))
+ return NOTIFY_DONE;
+
+ mlx5e_tc_hairpin_update_dead_peer(priv, peer_priv);
+
+ return NOTIFY_DONE;
+}
+
int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
{
struct mlx5e_tc_table *tc = &priv->fs.tc;
+ int err;
hash_init(tc->mod_hdr_tbl);
hash_init(tc->hairpin_tbl);
- return rhashtable_init(&tc->ht, &tc_ht_params);
+ err = rhashtable_init(&tc->ht, &tc_ht_params);
+ if (err)
+ return err;
+
+ tc->netdevice_nb.notifier_call = mlx5e_tc_netdev_event;
+ if (register_netdevice_notifier(&tc->netdevice_nb)) {
+ tc->netdevice_nb.notifier_call = NULL;
+ mlx5_core_warn(priv->mdev, "Failed to register netdev notifier\n");
+ }
+
+ return err;
}
static void _mlx5e_tc_del_flow(void *ptr, void *arg)
@@ -2969,6 +3029,9 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv)
{
struct mlx5e_tc_table *tc = &priv->fs.tc;
+ if (tc->netdevice_nb.notifier_call)
+ unregister_netdevice_notifier(&tc->netdevice_nb);
+
rhashtable_free_and_destroy(&tc->ht, _mlx5e_tc_del_flow, NULL);
if (!IS_ERR_OR_NULL(tc->t)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 2b252cd..ea7dedc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -2000,7 +2000,7 @@ static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw)
u32 max_guarantee = 0;
int i;
- for (i = 0; i <= esw->total_vports; i++) {
+ for (i = 0; i < esw->total_vports; i++) {
evport = &esw->vports[i];
if (!evport->enabled || evport->info.min_rate < max_guarantee)
continue;
@@ -2020,7 +2020,7 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider)
int err;
int i;
- for (i = 0; i <= esw->total_vports; i++) {
+ for (i = 0; i < esw->total_vports; i++) {
evport = &esw->vports[i];
if (!evport->enabled)
continue;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
index d2f7607..a1ee9a8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
@@ -475,7 +475,8 @@ static void mlx5_hairpin_destroy_queues(struct mlx5_hairpin *hp)
for (i = 0; i < hp->num_channels; i++) {
mlx5_core_destroy_rq(hp->func_mdev, hp->rqn[i]);
- mlx5_core_destroy_sq(hp->peer_mdev, hp->sqn[i]);
+ if (!hp->peer_gone)
+ mlx5_core_destroy_sq(hp->peer_mdev, hp->sqn[i]);
}
}
@@ -567,6 +568,8 @@ static void mlx5_hairpin_unpair_queues(struct mlx5_hairpin *hp)
MLX5_RQC_STATE_RST, 0, 0);
/* unset peer SQs */
+ if (hp->peer_gone)
+ return;
for (i = 0; i < hp->num_channels; i++)
mlx5_hairpin_modify_sq(hp->peer_mdev, hp->sqn[i], MLX5_SQC_STATE_RDY,
MLX5_SQC_STATE_RST, 0, 0);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 8ed38fd..c6d29fd 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -2077,14 +2077,17 @@ nfp_ctrl_rx_one(struct nfp_net *nn, struct nfp_net_dp *dp,
return true;
}
-static void nfp_ctrl_rx(struct nfp_net_r_vector *r_vec)
+static bool nfp_ctrl_rx(struct nfp_net_r_vector *r_vec)
{
struct nfp_net_rx_ring *rx_ring = r_vec->rx_ring;
struct nfp_net *nn = r_vec->nfp_net;
struct nfp_net_dp *dp = &nn->dp;
+ unsigned int budget = 512;
- while (nfp_ctrl_rx_one(nn, dp, r_vec, rx_ring))
+ while (nfp_ctrl_rx_one(nn, dp, r_vec, rx_ring) && budget--)
continue;
+
+ return budget;
}
static void nfp_ctrl_poll(unsigned long arg)
@@ -2096,9 +2099,13 @@ static void nfp_ctrl_poll(unsigned long arg)
__nfp_ctrl_tx_queued(r_vec);
spin_unlock_bh(&r_vec->lock);
- nfp_ctrl_rx(r_vec);
-
- nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry);
+ if (nfp_ctrl_rx(r_vec)) {
+ nfp_net_irq_unmask(r_vec->nfp_net, r_vec->irq_entry);
+ } else {
+ tasklet_schedule(&r_vec->tasklet);
+ nn_dp_warn(&r_vec->nfp_net->dp,
+ "control message budget exceeded!\n");
+ }
}
/* Setup and Configuration
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index 69aa7fc..59c70be 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -72,9 +72,6 @@ static void netxen_schedule_work(struct netxen_adapter *adapter,
work_func_t func, int delay);
static void netxen_cancel_fw_work(struct netxen_adapter *adapter);
static int netxen_nic_poll(struct napi_struct *napi, int budget);
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void netxen_nic_poll_controller(struct net_device *netdev);
-#endif
static void netxen_create_sysfs_entries(struct netxen_adapter *adapter);
static void netxen_remove_sysfs_entries(struct netxen_adapter *adapter);
@@ -581,9 +578,6 @@ static const struct net_device_ops netxen_netdev_ops = {
.ndo_tx_timeout = netxen_tx_timeout,
.ndo_fix_features = netxen_fix_features,
.ndo_set_features = netxen_set_features,
-#ifdef CONFIG_NET_POLL_CONTROLLER
- .ndo_poll_controller = netxen_nic_poll_controller,
-#endif
};
static inline bool netxen_function_zero(struct pci_dev *pdev)
@@ -2402,23 +2396,6 @@ static int netxen_nic_poll(struct napi_struct *napi, int budget)
return work_done;
}
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void netxen_nic_poll_controller(struct net_device *netdev)
-{
- int ring;
- struct nx_host_sds_ring *sds_ring;
- struct netxen_adapter *adapter = netdev_priv(netdev);
- struct netxen_recv_context *recv_ctx = &adapter->recv_ctx;
-
- disable_irq(adapter->irq);
- for (ring = 0; ring < adapter->max_sds_rings; ring++) {
- sds_ring = &recv_ctx->sds_rings[ring];
- netxen_intr(adapter->irq, sds_ring);
- }
- enable_irq(adapter->irq);
-}
-#endif
-
static int
nx_incr_dev_ref_cnt(struct netxen_adapter *adapter)
{
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index 9b3ef00e..a713826 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -11987,6 +11987,7 @@ struct public_global {
u32 running_bundle_id;
s32 external_temperature;
u32 mdump_reason;
+ u64 reserved;
u32 data_ptr;
u32 data_size;
};
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index 17f3dfa..e860bdf 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -1710,7 +1710,7 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn,
cm_info->local_ip[0] = ntohl(iph->daddr);
cm_info->remote_ip[0] = ntohl(iph->saddr);
- cm_info->ip_version = TCP_IPV4;
+ cm_info->ip_version = QED_TCP_IPV4;
ip_hlen = (iph->ihl) * sizeof(u32);
*payload_len = ntohs(iph->tot_len) - ip_hlen;
@@ -1730,7 +1730,7 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn,
cm_info->remote_ip[i] =
ntohl(ip6h->saddr.in6_u.u6_addr32[i]);
}
- cm_info->ip_version = TCP_IPV6;
+ cm_info->ip_version = QED_TCP_IPV6;
ip_hlen = sizeof(*ip6h);
*payload_len = ntohs(ip6h->payload_len);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index be941cf..c71391b 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
@@ -228,7 +228,7 @@ static int qed_rdma_alloc(struct qed_hwfn *p_hwfn,
num_cons, "Toggle");
if (rc) {
DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
- "Failed to allocate toogle bits, rc = %d\n", rc);
+ "Failed to allocate toggle bits, rc = %d\n", rc);
goto free_cq_map;
}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index 7d7a64c..f9167d1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -140,23 +140,16 @@ static void qed_rdma_copy_gids(struct qed_rdma_qp *qp, __le32 *src_gid,
static enum roce_flavor qed_roce_mode_to_flavor(enum roce_mode roce_mode)
{
- enum roce_flavor flavor;
-
switch (roce_mode) {
case ROCE_V1:
- flavor = PLAIN_ROCE;
- break;
+ return PLAIN_ROCE;
case ROCE_V2_IPV4:
- flavor = RROCE_IPV4;
- break;
+ return RROCE_IPV4;
case ROCE_V2_IPV6:
- flavor = ROCE_V2_IPV6;
- break;
+ return RROCE_IPV6;
default:
- flavor = MAX_ROCE_MODE;
- break;
+ return MAX_ROCE_FLAVOR;
}
- return flavor;
}
static void qed_roce_free_cid_pair(struct qed_hwfn *p_hwfn, u16 cid)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
index 8de644b4..77b6248 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
@@ -154,7 +154,7 @@ qed_set_pf_update_tunn_mode(struct qed_tunnel_info *p_tun,
static void qed_set_tunn_cls_info(struct qed_tunnel_info *p_tun,
struct qed_tunnel_info *p_src)
{
- enum tunnel_clss type;
+ int type;
p_tun->b_update_rx_cls = p_src->b_update_rx_cls;
p_tun->b_update_tx_cls = p_src->b_update_tx_cls;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index 3d42696..be118d0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -413,7 +413,6 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn)
}
if (!p_iov->b_pre_fp_hsi &&
- ETH_HSI_VER_MINOR &&
(resp->pfdev_info.minor_fp_hsi < ETH_HSI_VER_MINOR)) {
DP_INFO(p_hwfn,
"PF is using older fastpath HSI; %02x.%02x is configured\n",
@@ -572,7 +571,7 @@ int qed_vf_hw_prepare(struct qed_hwfn *p_hwfn)
static void
__qed_vf_prep_tunn_req_tlv(struct vfpf_update_tunn_param_tlv *p_req,
struct qed_tunn_update_type *p_src,
- enum qed_tunn_clss mask, u8 *p_cls)
+ enum qed_tunn_mode mask, u8 *p_cls)
{
if (p_src->b_update_mode) {
p_req->tun_mode_update_mask |= BIT(mask);
@@ -587,7 +586,7 @@ __qed_vf_prep_tunn_req_tlv(struct vfpf_update_tunn_param_tlv *p_req,
static void
qed_vf_prep_tunn_req_tlv(struct vfpf_update_tunn_param_tlv *p_req,
struct qed_tunn_update_type *p_src,
- enum qed_tunn_clss mask,
+ enum qed_tunn_mode mask,
u8 *p_cls, struct qed_tunn_update_udp_port *p_port,
u8 *p_update_port, u16 *p_udp_port)
{
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 8131292..0c443ea 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -1800,7 +1800,8 @@ struct qlcnic_hardware_ops {
int (*config_loopback) (struct qlcnic_adapter *, u8);
int (*clear_loopback) (struct qlcnic_adapter *, u8);
int (*config_promisc_mode) (struct qlcnic_adapter *, u32);
- void (*change_l2_filter) (struct qlcnic_adapter *, u64 *, u16);
+ void (*change_l2_filter)(struct qlcnic_adapter *adapter, u64 *addr,
+ u16 vlan, struct qlcnic_host_tx_ring *tx_ring);
int (*get_board_info) (struct qlcnic_adapter *);
void (*set_mac_filter_count) (struct qlcnic_adapter *);
void (*free_mac_list) (struct qlcnic_adapter *);
@@ -2064,9 +2065,10 @@ static inline int qlcnic_nic_set_promisc(struct qlcnic_adapter *adapter,
}
static inline void qlcnic_change_filter(struct qlcnic_adapter *adapter,
- u64 *addr, u16 id)
+ u64 *addr, u16 vlan,
+ struct qlcnic_host_tx_ring *tx_ring)
{
- adapter->ahw->hw_ops->change_l2_filter(adapter, addr, id);
+ adapter->ahw->hw_ops->change_l2_filter(adapter, addr, vlan, tx_ring);
}
static inline int qlcnic_get_board_info(struct qlcnic_adapter *adapter)
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
index 569d54e..a79d84f 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c
@@ -2135,7 +2135,8 @@ int qlcnic_83xx_sre_macaddr_change(struct qlcnic_adapter *adapter, u8 *addr,
}
void qlcnic_83xx_change_l2_filter(struct qlcnic_adapter *adapter, u64 *addr,
- u16 vlan_id)
+ u16 vlan_id,
+ struct qlcnic_host_tx_ring *tx_ring)
{
u8 mac[ETH_ALEN];
memcpy(&mac, addr, ETH_ALEN);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
index b75a812..73fe2f6 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h
@@ -550,7 +550,8 @@ int qlcnic_83xx_wrt_reg_indirect(struct qlcnic_adapter *, ulong, u32);
int qlcnic_83xx_nic_set_promisc(struct qlcnic_adapter *, u32);
int qlcnic_83xx_config_hw_lro(struct qlcnic_adapter *, int);
int qlcnic_83xx_config_rss(struct qlcnic_adapter *, int);
-void qlcnic_83xx_change_l2_filter(struct qlcnic_adapter *, u64 *, u16);
+void qlcnic_83xx_change_l2_filter(struct qlcnic_adapter *adapter, u64 *addr,
+ u16 vlan, struct qlcnic_host_tx_ring *ring);
int qlcnic_83xx_get_pci_info(struct qlcnic_adapter *, struct qlcnic_pci_info *);
int qlcnic_83xx_set_nic_info(struct qlcnic_adapter *, struct qlcnic_info *);
void qlcnic_83xx_initialize_nic(struct qlcnic_adapter *, int);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h
index 4bb33af..56a3bd9 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.h
@@ -173,7 +173,8 @@ int qlcnic_82xx_napi_add(struct qlcnic_adapter *adapter,
struct net_device *netdev);
void qlcnic_82xx_get_beacon_state(struct qlcnic_adapter *);
void qlcnic_82xx_change_filter(struct qlcnic_adapter *adapter,
- u64 *uaddr, u16 vlan_id);
+ u64 *uaddr, u16 vlan_id,
+ struct qlcnic_host_tx_ring *tx_ring);
int qlcnic_82xx_config_intr_coalesce(struct qlcnic_adapter *,
struct ethtool_coalesce *);
int qlcnic_82xx_set_rx_coalesce(struct qlcnic_adapter *);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index 84dd830..9647578 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -268,13 +268,12 @@ static void qlcnic_add_lb_filter(struct qlcnic_adapter *adapter,
}
void qlcnic_82xx_change_filter(struct qlcnic_adapter *adapter, u64 *uaddr,
- u16 vlan_id)
+ u16 vlan_id, struct qlcnic_host_tx_ring *tx_ring)
{
struct cmd_desc_type0 *hwdesc;
struct qlcnic_nic_req *req;
struct qlcnic_mac_req *mac_req;
struct qlcnic_vlan_req *vlan_req;
- struct qlcnic_host_tx_ring *tx_ring = adapter->tx_ring;
u32 producer;
u64 word;
@@ -301,7 +300,8 @@ void qlcnic_82xx_change_filter(struct qlcnic_adapter *adapter, u64 *uaddr,
static void qlcnic_send_filter(struct qlcnic_adapter *adapter,
struct cmd_desc_type0 *first_desc,
- struct sk_buff *skb)
+ struct sk_buff *skb,
+ struct qlcnic_host_tx_ring *tx_ring)
{
struct vlan_ethhdr *vh = (struct vlan_ethhdr *)(skb->data);
struct ethhdr *phdr = (struct ethhdr *)(skb->data);
@@ -335,7 +335,7 @@ static void qlcnic_send_filter(struct qlcnic_adapter *adapter,
tmp_fil->vlan_id == vlan_id) {
if (jiffies > (QLCNIC_READD_AGE * HZ + tmp_fil->ftime))
qlcnic_change_filter(adapter, &src_addr,
- vlan_id);
+ vlan_id, tx_ring);
tmp_fil->ftime = jiffies;
return;
}
@@ -350,7 +350,7 @@ static void qlcnic_send_filter(struct qlcnic_adapter *adapter,
if (!fil)
return;
- qlcnic_change_filter(adapter, &src_addr, vlan_id);
+ qlcnic_change_filter(adapter, &src_addr, vlan_id, tx_ring);
fil->ftime = jiffies;
fil->vlan_id = vlan_id;
memcpy(fil->faddr, &src_addr, ETH_ALEN);
@@ -766,7 +766,7 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
}
if (adapter->drv_mac_learn)
- qlcnic_send_filter(adapter, first_desc, skb);
+ qlcnic_send_filter(adapter, first_desc, skb, tx_ring);
tx_ring->tx_stats.tx_bytes += skb->len;
tx_ring->tx_stats.xmit_called++;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 2d38d1a..dbd4801 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -59,9 +59,6 @@ static int qlcnic_close(struct net_device *netdev);
static void qlcnic_tx_timeout(struct net_device *netdev);
static void qlcnic_attach_work(struct work_struct *work);
static void qlcnic_fwinit_work(struct work_struct *work);
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void qlcnic_poll_controller(struct net_device *netdev);
-#endif
static void qlcnic_idc_debug_info(struct qlcnic_adapter *adapter, u8 encoding);
static int qlcnic_can_start_firmware(struct qlcnic_adapter *adapter);
@@ -545,9 +542,6 @@ static const struct net_device_ops qlcnic_netdev_ops = {
.ndo_udp_tunnel_add = qlcnic_add_vxlan_port,
.ndo_udp_tunnel_del = qlcnic_del_vxlan_port,
.ndo_features_check = qlcnic_features_check,
-#ifdef CONFIG_NET_POLL_CONTROLLER
- .ndo_poll_controller = qlcnic_poll_controller,
-#endif
#ifdef CONFIG_QLCNIC_SRIOV
.ndo_set_vf_mac = qlcnic_sriov_set_vf_mac,
.ndo_set_vf_rate = qlcnic_sriov_set_vf_tx_rate,
@@ -3200,45 +3194,6 @@ static irqreturn_t qlcnic_msix_tx_intr(int irq, void *data)
return IRQ_HANDLED;
}
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void qlcnic_poll_controller(struct net_device *netdev)
-{
- struct qlcnic_adapter *adapter = netdev_priv(netdev);
- struct qlcnic_host_sds_ring *sds_ring;
- struct qlcnic_recv_context *recv_ctx;
- struct qlcnic_host_tx_ring *tx_ring;
- int ring;
-
- if (!test_bit(__QLCNIC_DEV_UP, &adapter->state))
- return;
-
- recv_ctx = adapter->recv_ctx;
-
- for (ring = 0; ring < adapter->drv_sds_rings; ring++) {
- sds_ring = &recv_ctx->sds_rings[ring];
- qlcnic_disable_sds_intr(adapter, sds_ring);
- napi_schedule(&sds_ring->napi);
- }
-
- if (adapter->flags & QLCNIC_MSIX_ENABLED) {
- /* Only Multi-Tx queue capable devices need to
- * schedule NAPI for TX rings
- */
- if ((qlcnic_83xx_check(adapter) &&
- (adapter->flags & QLCNIC_TX_INTR_SHARED)) ||
- (qlcnic_82xx_check(adapter) &&
- !qlcnic_check_multi_tx(adapter)))
- return;
-
- for (ring = 0; ring < adapter->drv_tx_rings; ring++) {
- tx_ring = &adapter->tx_ring[ring];
- qlcnic_disable_tx_intr(adapter, tx_ring);
- napi_schedule(&tx_ring->napi);
- }
- }
-}
-#endif
-
static void
qlcnic_idc_debug_info(struct qlcnic_adapter *adapter, u8 encoding)
{
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
index 7fd86d4..11167ab 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_handlers.c
@@ -113,7 +113,7 @@ rmnet_map_ingress_handler(struct sk_buff *skb,
struct sk_buff *skbn;
if (skb->dev->type == ARPHRD_ETHER) {
- if (pskb_expand_head(skb, ETH_HLEN, 0, GFP_KERNEL)) {
+ if (pskb_expand_head(skb, ETH_HLEN, 0, GFP_ATOMIC)) {
kfree_skb(skb);
return;
}
@@ -147,7 +147,7 @@ static int rmnet_map_egress_handler(struct sk_buff *skb,
}
if (skb_headroom(skb) < required_headroom) {
- if (pskb_expand_head(skb, required_headroom, 0, GFP_KERNEL))
+ if (pskb_expand_head(skb, required_headroom, 0, GFP_ATOMIC))
return -ENOMEM;
}
@@ -189,6 +189,9 @@ rx_handler_result_t rmnet_rx_handler(struct sk_buff **pskb)
if (!skb)
goto done;
+ if (skb->pkt_type == PACKET_LOOPBACK)
+ return RX_HANDLER_PASS;
+
dev = skb->dev;
port = rmnet_get_port(dev);
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index ab30aae..9a5e296 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -4072,13 +4072,12 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
genphy_soft_reset(dev->phydev);
- /* It was reported that chip version 33 ends up with 10MBit/Half on a
+ /* It was reported that several chips end up with 10MBit/Half on a
* 1GBit link after resuming from S3. For whatever reason the PHY on
- * this chip doesn't properly start a renegotiation when soft-reset.
+ * these chips doesn't properly start a renegotiation when soft-reset.
* Explicitly requesting a renegotiation fixes this.
*/
- if (tp->mac_version == RTL_GIGA_MAC_VER_33 &&
- dev->phydev->autoneg == AUTONEG_ENABLE)
+ if (dev->phydev->autoneg == AUTONEG_ENABLE)
phy_restart_aneg(dev->phydev);
}
@@ -4536,9 +4535,14 @@ static void rtl8169_hw_reset(struct rtl8169_private *tp)
static void rtl_set_tx_config_registers(struct rtl8169_private *tp)
{
- /* Set DMA burst size and Interframe Gap Time */
- RTL_W32(tp, TxConfig, (TX_DMA_BURST << TxDMAShift) |
- (InterFrameGap << TxInterFrameGapShift));
+ u32 val = TX_DMA_BURST << TxDMAShift |
+ InterFrameGap << TxInterFrameGapShift;
+
+ if (tp->mac_version >= RTL_GIGA_MAC_VER_34 &&
+ tp->mac_version != RTL_GIGA_MAC_VER_39)
+ val |= TXCFG_AUTO_FIFO;
+
+ RTL_W32(tp, TxConfig, val);
}
static void rtl_set_rx_max_size(struct rtl8169_private *tp)
@@ -5033,7 +5037,6 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp)
rtl_disable_clock_request(tp);
- RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO);
RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB);
/* Adjust EEE LED frequency */
@@ -5067,7 +5070,6 @@ static void rtl_hw_start_8168f(struct rtl8169_private *tp)
rtl_disable_clock_request(tp);
- RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO);
RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB);
RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN);
RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN);
@@ -5112,8 +5114,6 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp)
static void rtl_hw_start_8168g(struct rtl8169_private *tp)
{
- RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO);
-
rtl_eri_write(tp, 0xc8, ERIAR_MASK_0101, 0x080002, ERIAR_EXGMAC);
rtl_eri_write(tp, 0xcc, ERIAR_MASK_0001, 0x38, ERIAR_EXGMAC);
rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x48, ERIAR_EXGMAC);
@@ -5211,8 +5211,6 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
rtl_hw_aspm_clkreq_enable(tp, false);
rtl_ephy_init(tp, e_info_8168h_1, ARRAY_SIZE(e_info_8168h_1));
- RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO);
-
rtl_eri_write(tp, 0xc8, ERIAR_MASK_0101, 0x00080002, ERIAR_EXGMAC);
rtl_eri_write(tp, 0xcc, ERIAR_MASK_0001, 0x38, ERIAR_EXGMAC);
rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x48, ERIAR_EXGMAC);
@@ -5295,8 +5293,6 @@ static void rtl_hw_start_8168ep(struct rtl8169_private *tp)
{
rtl8168ep_stop_cmac(tp);
- RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO);
-
rtl_eri_write(tp, 0xc8, ERIAR_MASK_0101, 0x00080002, ERIAR_EXGMAC);
rtl_eri_write(tp, 0xcc, ERIAR_MASK_0001, 0x2f, ERIAR_EXGMAC);
rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x5f, ERIAR_EXGMAC);
@@ -5618,7 +5614,6 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp)
/* Force LAN exit from ASPM if Rx/Tx are not idle */
RTL_W32(tp, FuncEvent, RTL_R32(tp, FuncEvent) | 0x002800);
- RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO);
RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB);
rtl_ephy_init(tp, e_info_8402, ARRAY_SIZE(e_info_8402));
@@ -6869,8 +6864,10 @@ static int rtl8169_suspend(struct device *device)
{
struct pci_dev *pdev = to_pci_dev(device);
struct net_device *dev = pci_get_drvdata(pdev);
+ struct rtl8169_private *tp = netdev_priv(dev);
rtl8169_net_suspend(dev);
+ clk_disable_unprepare(tp->clk);
return 0;
}
@@ -6898,6 +6895,9 @@ static int rtl8169_resume(struct device *device)
{
struct pci_dev *pdev = to_pci_dev(device);
struct net_device *dev = pci_get_drvdata(pdev);
+ struct rtl8169_private *tp = netdev_priv(dev);
+
+ clk_prepare_enable(tp->clk);
if (netif_running(dev))
__rtl8169_resume(dev);
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 3302332..3d0dd39 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -2208,29 +2208,6 @@ static void efx_fini_napi(struct efx_nic *efx)
/**************************************************************************
*
- * Kernel netpoll interface
- *
- *************************************************************************/
-
-#ifdef CONFIG_NET_POLL_CONTROLLER
-
-/* Although in the common case interrupts will be disabled, this is not
- * guaranteed. However, all our work happens inside the NAPI callback,
- * so no locking is required.
- */
-static void efx_netpoll(struct net_device *net_dev)
-{
- struct efx_nic *efx = netdev_priv(net_dev);
- struct efx_channel *channel;
-
- efx_for_each_channel(channel, efx)
- efx_schedule_channel(channel);
-}
-
-#endif
-
-/**************************************************************************
- *
* Kernel net device interface
*
*************************************************************************/
@@ -2509,9 +2486,6 @@ static const struct net_device_ops efx_netdev_ops = {
#endif
.ndo_get_phys_port_id = efx_get_phys_port_id,
.ndo_get_phys_port_name = efx_get_phys_port_name,
-#ifdef CONFIG_NET_POLL_CONTROLLER
- .ndo_poll_controller = efx_netpoll,
-#endif
.ndo_setup_tc = efx_setup_tc,
#ifdef CONFIG_RFS_ACCEL
.ndo_rx_flow_steer = efx_filter_rfs,
diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c
index dd5530a..03e2455 100644
--- a/drivers/net/ethernet/sfc/falcon/efx.c
+++ b/drivers/net/ethernet/sfc/falcon/efx.c
@@ -2054,29 +2054,6 @@ static void ef4_fini_napi(struct ef4_nic *efx)
/**************************************************************************
*
- * Kernel netpoll interface
- *
- *************************************************************************/
-
-#ifdef CONFIG_NET_POLL_CONTROLLER
-
-/* Although in the common case interrupts will be disabled, this is not
- * guaranteed. However, all our work happens inside the NAPI callback,
- * so no locking is required.
- */
-static void ef4_netpoll(struct net_device *net_dev)
-{
- struct ef4_nic *efx = netdev_priv(net_dev);
- struct ef4_channel *channel;
-
- ef4_for_each_channel(channel, efx)
- ef4_schedule_channel(channel);
-}
-
-#endif
-
-/**************************************************************************
- *
* Kernel net device interface
*
*************************************************************************/
@@ -2250,9 +2227,6 @@ static const struct net_device_ops ef4_netdev_ops = {
.ndo_set_mac_address = ef4_set_mac_address,
.ndo_set_rx_mode = ef4_set_rx_mode,
.ndo_set_features = ef4_set_features,
-#ifdef CONFIG_NET_POLL_CONTROLLER
- .ndo_poll_controller = ef4_netpoll,
-#endif
.ndo_setup_tc = ef4_setup_tc,
#ifdef CONFIG_RFS_ACCEL
.ndo_rx_flow_steer = ef4_filter_rfs,
diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c
index 23a52b9..cd1d8fa 100644
--- a/drivers/net/ieee802154/adf7242.c
+++ b/drivers/net/ieee802154/adf7242.c
@@ -1308,8 +1308,7 @@ static int adf7242_remove(struct spi_device *spi)
{
struct adf7242_local *lp = spi_get_drvdata(spi);
- if (!IS_ERR_OR_NULL(lp->debugfs_root))
- debugfs_remove_recursive(lp->debugfs_root);
+ debugfs_remove_recursive(lp->debugfs_root);
cancel_delayed_work_sync(&lp->work);
destroy_workqueue(lp->wqueue);
diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c
index 58299fb..0ff5a40 100644
--- a/drivers/net/ieee802154/ca8210.c
+++ b/drivers/net/ieee802154/ca8210.c
@@ -634,10 +634,9 @@ static int ca8210_test_int_driver_write(
for (i = 0; i < len; i++)
dev_dbg(&priv->spi->dev, "%#03x\n", buf[i]);
- fifo_buffer = kmalloc(len, GFP_KERNEL);
+ fifo_buffer = kmemdup(buf, len, GFP_KERNEL);
if (!fifo_buffer)
return -ENOMEM;
- memcpy(fifo_buffer, buf, len);
kfifo_in(&test->up_fifo, &fifo_buffer, 4);
wake_up_interruptible(&priv->test.readq);
@@ -3044,8 +3043,7 @@ static void ca8210_test_interface_clear(struct ca8210_priv *priv)
{
struct ca8210_test *test = &priv->test;
- if (!IS_ERR(test->ca8210_dfs_spi_int))
- debugfs_remove(test->ca8210_dfs_spi_int);
+ debugfs_remove(test->ca8210_dfs_spi_int);
kfifo_free(&test->up_fifo);
dev_info(&priv->spi->dev, "Test interface removed\n");
}
diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c
index e428277..04891429 100644
--- a/drivers/net/ieee802154/mcr20a.c
+++ b/drivers/net/ieee802154/mcr20a.c
@@ -903,19 +903,19 @@ mcr20a_irq_clean_complete(void *context)
switch (seq_state) {
/* TX IRQ, RX IRQ and SEQ IRQ */
- case (0x03):
+ case (DAR_IRQSTS1_TXIRQ | DAR_IRQSTS1_SEQIRQ):
if (lp->is_tx) {
lp->is_tx = 0;
dev_dbg(printdev(lp), "TX is done. No ACK\n");
mcr20a_handle_tx_complete(lp);
}
break;
- case (0x05):
+ case (DAR_IRQSTS1_RXIRQ | DAR_IRQSTS1_SEQIRQ):
/* rx is starting */
dev_dbg(printdev(lp), "RX is starting\n");
mcr20a_handle_rx(lp);
break;
- case (0x07):
+ case (DAR_IRQSTS1_RXIRQ | DAR_IRQSTS1_TXIRQ | DAR_IRQSTS1_SEQIRQ):
if (lp->is_tx) {
/* tx is done */
lp->is_tx = 0;
@@ -927,7 +927,7 @@ mcr20a_irq_clean_complete(void *context)
mcr20a_handle_rx(lp);
}
break;
- case (0x01):
+ case (DAR_IRQSTS1_SEQIRQ):
if (lp->is_tx) {
dev_dbg(printdev(lp), "TX is starting\n");
mcr20a_handle_tx(lp);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index db1172d..19ab8a7 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -93,7 +93,12 @@ static bool mdio_bus_phy_may_suspend(struct phy_device *phydev)
if (!netdev)
return !phydev->suspended;
- /* Don't suspend PHY if the attached netdev parent may wakeup.
+ if (netdev->wol_enabled)
+ return false;
+
+ /* As long as not all affected network drivers support the
+ * wol_enabled flag, let's check for hints that WoL is enabled.
+ * Don't suspend PHY if the attached netdev parent may wake up.
* The parent may point to a PCI device, as in tg3 driver.
*/
if (netdev->dev.parent && device_may_wakeup(netdev->dev.parent))
@@ -1132,9 +1137,9 @@ void phy_detach(struct phy_device *phydev)
sysfs_remove_link(&dev->dev.kobj, "phydev");
sysfs_remove_link(&phydev->mdio.dev.kobj, "attached_dev");
}
+ phy_suspend(phydev);
phydev->attached_dev->phydev = NULL;
phydev->attached_dev = NULL;
- phy_suspend(phydev);
phydev->phylink = NULL;
phy_led_triggers_unregister(phydev);
@@ -1168,12 +1173,13 @@ EXPORT_SYMBOL(phy_detach);
int phy_suspend(struct phy_device *phydev)
{
struct phy_driver *phydrv = to_phy_driver(phydev->mdio.dev.driver);
+ struct net_device *netdev = phydev->attached_dev;
struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
int ret = 0;
/* If the device has WOL enabled, we cannot suspend the PHY */
phy_ethtool_get_wol(phydev, &wol);
- if (wol.wolopts)
+ if (wol.wolopts || (netdev && netdev->wol_enabled))
return -EBUSY;
if (phydev->drv && phydrv->suspend)
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 52fffb9..6e13b88 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -1098,8 +1098,11 @@ static int sfp_hwmon_insert(struct sfp *sfp)
static void sfp_hwmon_remove(struct sfp *sfp)
{
- hwmon_device_unregister(sfp->hwmon_dev);
- kfree(sfp->hwmon_name);
+ if (!IS_ERR_OR_NULL(sfp->hwmon_dev)) {
+ hwmon_device_unregister(sfp->hwmon_dev);
+ sfp->hwmon_dev = NULL;
+ kfree(sfp->hwmon_name);
+ }
}
#else
static int sfp_hwmon_insert(struct sfp *sfp)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index e2648b5..50e9cc1 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -181,6 +181,7 @@ struct tun_file {
};
struct napi_struct napi;
bool napi_enabled;
+ bool napi_frags_enabled;
struct mutex napi_mutex; /* Protects access to the above napi */
struct list_head next;
struct tun_struct *detached;
@@ -313,32 +314,32 @@ static int tun_napi_poll(struct napi_struct *napi, int budget)
}
static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile,
- bool napi_en)
+ bool napi_en, bool napi_frags)
{
tfile->napi_enabled = napi_en;
+ tfile->napi_frags_enabled = napi_en && napi_frags;
if (napi_en) {
netif_napi_add(tun->dev, &tfile->napi, tun_napi_poll,
NAPI_POLL_WEIGHT);
napi_enable(&tfile->napi);
- mutex_init(&tfile->napi_mutex);
}
}
-static void tun_napi_disable(struct tun_struct *tun, struct tun_file *tfile)
+static void tun_napi_disable(struct tun_file *tfile)
{
if (tfile->napi_enabled)
napi_disable(&tfile->napi);
}
-static void tun_napi_del(struct tun_struct *tun, struct tun_file *tfile)
+static void tun_napi_del(struct tun_file *tfile)
{
if (tfile->napi_enabled)
netif_napi_del(&tfile->napi);
}
-static bool tun_napi_frags_enabled(const struct tun_struct *tun)
+static bool tun_napi_frags_enabled(const struct tun_file *tfile)
{
- return READ_ONCE(tun->flags) & IFF_NAPI_FRAGS;
+ return tfile->napi_frags_enabled;
}
#ifdef CONFIG_TUN_VNET_CROSS_LE
@@ -690,8 +691,8 @@ static void __tun_detach(struct tun_file *tfile, bool clean)
tun = rtnl_dereference(tfile->tun);
if (tun && clean) {
- tun_napi_disable(tun, tfile);
- tun_napi_del(tun, tfile);
+ tun_napi_disable(tfile);
+ tun_napi_del(tfile);
}
if (tun && !tfile->detached) {
@@ -758,7 +759,7 @@ static void tun_detach_all(struct net_device *dev)
for (i = 0; i < n; i++) {
tfile = rtnl_dereference(tun->tfiles[i]);
BUG_ON(!tfile);
- tun_napi_disable(tun, tfile);
+ tun_napi_disable(tfile);
tfile->socket.sk->sk_shutdown = RCV_SHUTDOWN;
tfile->socket.sk->sk_data_ready(tfile->socket.sk);
RCU_INIT_POINTER(tfile->tun, NULL);
@@ -774,7 +775,7 @@ static void tun_detach_all(struct net_device *dev)
synchronize_net();
for (i = 0; i < n; i++) {
tfile = rtnl_dereference(tun->tfiles[i]);
- tun_napi_del(tun, tfile);
+ tun_napi_del(tfile);
/* Drop read queue */
tun_queue_purge(tfile);
xdp_rxq_info_unreg(&tfile->xdp_rxq);
@@ -793,7 +794,7 @@ static void tun_detach_all(struct net_device *dev)
}
static int tun_attach(struct tun_struct *tun, struct file *file,
- bool skip_filter, bool napi)
+ bool skip_filter, bool napi, bool napi_frags)
{
struct tun_file *tfile = file->private_data;
struct net_device *dev = tun->dev;
@@ -866,7 +867,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file,
tun_enable_queue(tfile);
} else {
sock_hold(&tfile->sk);
- tun_napi_init(tun, tfile, napi);
+ tun_napi_init(tun, tfile, napi, napi_frags);
}
tun_set_real_num_queues(tun);
@@ -1709,7 +1710,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
int err;
u32 rxhash = 0;
int skb_xdp = 1;
- bool frags = tun_napi_frags_enabled(tun);
+ bool frags = tun_napi_frags_enabled(tfile);
if (!(tun->dev->flags & IFF_UP))
return -EIO;
@@ -2534,7 +2535,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
return err;
err = tun_attach(tun, file, ifr->ifr_flags & IFF_NOFILTER,
- ifr->ifr_flags & IFF_NAPI);
+ ifr->ifr_flags & IFF_NAPI,
+ ifr->ifr_flags & IFF_NAPI_FRAGS);
if (err < 0)
return err;
@@ -2632,7 +2634,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
(ifr->ifr_flags & TUN_FEATURES);
INIT_LIST_HEAD(&tun->disabled);
- err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI);
+ err = tun_attach(tun, file, false, ifr->ifr_flags & IFF_NAPI,
+ ifr->ifr_flags & IFF_NAPI_FRAGS);
if (err < 0)
goto err_free_flow;
@@ -2781,7 +2784,8 @@ static int tun_set_queue(struct file *file, struct ifreq *ifr)
ret = security_tun_dev_attach_queue(tun->security);
if (ret < 0)
goto unlock;
- ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI);
+ ret = tun_attach(tun, file, false, tun->flags & IFF_NAPI,
+ tun->flags & IFF_NAPI_FRAGS);
} else if (ifr->ifr_flags & IFF_DETACH_QUEUE) {
tun = rtnl_dereference(tfile->tun);
if (!tun || !(tun->flags & IFF_MULTI_QUEUE) || tfile->detached)
@@ -3199,6 +3203,7 @@ static int tun_chr_open(struct inode *inode, struct file * file)
return -ENOMEM;
}
+ mutex_init(&tfile->napi_mutex);
RCU_INIT_POINTER(tfile->tun, NULL);
tfile->flags = 0;
tfile->ifindex = 0;
diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c
index e95dd12..023b8d0 100644
--- a/drivers/net/usb/asix_common.c
+++ b/drivers/net/usb/asix_common.c
@@ -607,6 +607,9 @@ int asix_set_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo)
struct usbnet *dev = netdev_priv(net);
u8 opt = 0;
+ if (wolinfo->wolopts & ~(WAKE_PHY | WAKE_MAGIC))
+ return -EINVAL;
+
if (wolinfo->wolopts & WAKE_PHY)
opt |= AX_MONITOR_LINK;
if (wolinfo->wolopts & WAKE_MAGIC)
diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c
index 9e8ad37..2207f7a 100644
--- a/drivers/net/usb/ax88179_178a.c
+++ b/drivers/net/usb/ax88179_178a.c
@@ -566,6 +566,9 @@ ax88179_set_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo)
struct usbnet *dev = netdev_priv(net);
u8 opt = 0;
+ if (wolinfo->wolopts & ~(WAKE_PHY | WAKE_MAGIC))
+ return -EINVAL;
+
if (wolinfo->wolopts & WAKE_PHY)
opt |= AX_MONITOR_MODE_RWLC;
if (wolinfo->wolopts & WAKE_MAGIC)
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index a9991c5..c3c9ba4 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1401,19 +1401,10 @@ static int lan78xx_set_wol(struct net_device *netdev,
if (ret < 0)
return ret;
- pdata->wol = 0;
- if (wol->wolopts & WAKE_UCAST)
- pdata->wol |= WAKE_UCAST;
- if (wol->wolopts & WAKE_MCAST)
- pdata->wol |= WAKE_MCAST;
- if (wol->wolopts & WAKE_BCAST)
- pdata->wol |= WAKE_BCAST;
- if (wol->wolopts & WAKE_MAGIC)
- pdata->wol |= WAKE_MAGIC;
- if (wol->wolopts & WAKE_PHY)
- pdata->wol |= WAKE_PHY;
- if (wol->wolopts & WAKE_ARP)
- pdata->wol |= WAKE_ARP;
+ if (wol->wolopts & ~WAKE_ALL)
+ return -EINVAL;
+
+ pdata->wol = wol->wolopts;
device_set_wakeup_enable(&dev->udev->dev, (bool)wol->wolopts);
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 2cd71bd..f1b5201 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -4506,6 +4506,9 @@ static int rtl8152_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
if (!rtl_can_wakeup(tp))
return -EOPNOTSUPP;
+ if (wol->wolopts & ~WAKE_ANY)
+ return -EINVAL;
+
ret = usb_autopm_get_interface(tp->intf);
if (ret < 0)
goto out_set_wol;
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index 05553d2..e5a4cbb 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -731,6 +731,9 @@ static int smsc75xx_ethtool_set_wol(struct net_device *net,
struct smsc75xx_priv *pdata = (struct smsc75xx_priv *)(dev->data[0]);
int ret;
+ if (wolinfo->wolopts & ~SUPPORTED_WAKE)
+ return -EINVAL;
+
pdata->wolopts = wolinfo->wolopts & SUPPORTED_WAKE;
ret = device_set_wakeup_enable(&dev->udev->dev, pdata->wolopts);
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 06b4d29..262e7a3 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -774,6 +774,9 @@ static int smsc95xx_ethtool_set_wol(struct net_device *net,
struct smsc95xx_priv *pdata = (struct smsc95xx_priv *)(dev->data[0]);
int ret;
+ if (wolinfo->wolopts & ~SUPPORTED_WAKE)
+ return -EINVAL;
+
pdata->wolopts = wolinfo->wolopts & SUPPORTED_WAKE;
ret = device_set_wakeup_enable(&dev->udev->dev, pdata->wolopts);
diff --git a/drivers/net/usb/sr9800.c b/drivers/net/usb/sr9800.c
index 9277a0f..35f39f2 100644
--- a/drivers/net/usb/sr9800.c
+++ b/drivers/net/usb/sr9800.c
@@ -421,6 +421,9 @@ sr_set_wol(struct net_device *net, struct ethtool_wolinfo *wolinfo)
struct usbnet *dev = netdev_priv(net);
u8 opt = 0;
+ if (wolinfo->wolopts & ~(WAKE_PHY | WAKE_MAGIC))
+ return -EINVAL;
+
if (wolinfo->wolopts & WAKE_PHY)
opt |= SR_MONITOR_LINK;
if (wolinfo->wolopts & WAKE_MAGIC)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7659209..dab504e 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1699,17 +1699,6 @@ static void virtnet_stats(struct net_device *dev,
tot->rx_frame_errors = dev->stats.rx_frame_errors;
}
-#ifdef CONFIG_NET_POLL_CONTROLLER
-static void virtnet_netpoll(struct net_device *dev)
-{
- struct virtnet_info *vi = netdev_priv(dev);
- int i;
-
- for (i = 0; i < vi->curr_queue_pairs; i++)
- napi_schedule(&vi->rq[i].napi);
-}
-#endif
-
static void virtnet_ack_link_announce(struct virtnet_info *vi)
{
rtnl_lock();
@@ -2447,9 +2436,6 @@ static const struct net_device_ops virtnet_netdev = {
.ndo_get_stats64 = virtnet_stats,
.ndo_vlan_rx_add_vid = virtnet_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = virtnet_vlan_rx_kill_vid,
-#ifdef CONFIG_NET_POLL_CONTROLLER
- .ndo_poll_controller = virtnet_netpoll,
-#endif
.ndo_bpf = virtnet_xdp,
.ndo_xdp_xmit = virtnet_xdp_xmit,
.ndo_features_check = passthru_features_check,
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index ababba3..2b8da2b 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3539,6 +3539,7 @@ static size_t vxlan_get_size(const struct net_device *dev)
nla_total_size(sizeof(__u32)) + /* IFLA_VXLAN_LINK */
nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VXLAN_LOCAL{6} */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL */
+ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TTL_INHERIT */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_TOS */
nla_total_size(sizeof(__be32)) + /* IFLA_VXLAN_LABEL */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_LEARNING */
@@ -3603,6 +3604,8 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
}
if (nla_put_u8(skb, IFLA_VXLAN_TTL, vxlan->cfg.ttl) ||
+ nla_put_u8(skb, IFLA_VXLAN_TTL_INHERIT,
+ !!(vxlan->cfg.flags & VXLAN_F_TTL_INHERIT)) ||
nla_put_u8(skb, IFLA_VXLAN_TOS, vxlan->cfg.tos) ||
nla_put_be32(skb, IFLA_VXLAN_LABEL, vxlan->cfg.label) ||
nla_put_u8(skb, IFLA_VXLAN_LEARNING,
diff --git a/drivers/net/wimax/i2400m/control.c b/drivers/net/wimax/i2400m/control.c
index 094cea7..ef298d8 100644
--- a/drivers/net/wimax/i2400m/control.c
+++ b/drivers/net/wimax/i2400m/control.c
@@ -257,7 +257,7 @@ static const struct
[I2400M_MS_ACCESSIBILITY_ERROR] = { "accesibility error", -EIO },
[I2400M_MS_BUSY] = { "busy", -EBUSY },
[I2400M_MS_CORRUPTED_TLV] = { "corrupted TLV", -EILSEQ },
- [I2400M_MS_UNINITIALIZED] = { "not unitialized", -EILSEQ },
+ [I2400M_MS_UNINITIALIZED] = { "uninitialized", -EILSEQ },
[I2400M_MS_UNKNOWN_ERROR] = { "unknown error", -EIO },
[I2400M_MS_PRODUCTION_ERROR] = { "production error", -EIO },
[I2400M_MS_NO_RF] = { "no RF", -EIO },
diff --git a/drivers/net/wireless/broadcom/b43/dma.c b/drivers/net/wireless/broadcom/b43/dma.c
index 6b0e1ec..d46d57b9 100644
--- a/drivers/net/wireless/broadcom/b43/dma.c
+++ b/drivers/net/wireless/broadcom/b43/dma.c
@@ -1518,13 +1518,15 @@ void b43_dma_handle_txstatus(struct b43_wldev *dev,
}
} else {
/* More than a single header/data pair were missed.
- * Report this error, and reset the controller to
+ * Report this error. If running with open-source
+ * firmware, then reset the controller to
* revive operation.
*/
b43dbg(dev->wl,
"Out of order TX status report on DMA ring %d. Expected %d, but got %d\n",
ring->index, firstused, slot);
- b43_controller_restart(dev, "Out of order TX");
+ if (dev->fw.opensource)
+ b43_controller_restart(dev, "Out of order TX");
return;
}
}
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/1000.c b/drivers/net/wireless/intel/iwlwifi/cfg/1000.c
index 5916879..497fd76 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/1000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/1000.c
@@ -51,6 +51,7 @@
static const struct iwl_base_params iwl1000_base_params = {
.num_of_queues = IWLAGN_NUM_QUEUES,
+ .max_tfd_queue_size = 256,
.eeprom_size = OTP_LOW_IMAGE_SIZE,
.pll_cfg = true,
.max_ll_items = OTP_MAX_LL_ITEMS_1000,
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 1068757..07442ad 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -520,7 +520,6 @@ struct mac80211_hwsim_data {
int channels, idx;
bool use_chanctx;
bool destroy_on_close;
- struct work_struct destroy_work;
u32 portid;
char alpha2[2];
const struct ieee80211_regdomain *regd;
@@ -2935,8 +2934,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
hwsim_radios_generation++;
spin_unlock_bh(&hwsim_radio_lock);
- if (idx > 0)
- hwsim_mcast_new_radio(idx, info, param);
+ hwsim_mcast_new_radio(idx, info, param);
return idx;
@@ -3565,30 +3563,27 @@ static struct genl_family hwsim_genl_family __ro_after_init = {
.n_mcgrps = ARRAY_SIZE(hwsim_mcgrps),
};
-static void destroy_radio(struct work_struct *work)
-{
- struct mac80211_hwsim_data *data =
- container_of(work, struct mac80211_hwsim_data, destroy_work);
-
- hwsim_radios_generation++;
- mac80211_hwsim_del_radio(data, wiphy_name(data->hw->wiphy), NULL);
-}
-
static void remove_user_radios(u32 portid)
{
struct mac80211_hwsim_data *entry, *tmp;
+ LIST_HEAD(list);
spin_lock_bh(&hwsim_radio_lock);
list_for_each_entry_safe(entry, tmp, &hwsim_radios, list) {
if (entry->destroy_on_close && entry->portid == portid) {
- list_del(&entry->list);
+ list_move(&entry->list, &list);
rhashtable_remove_fast(&hwsim_radios_rht, &entry->rht,
hwsim_rht_params);
- INIT_WORK(&entry->destroy_work, destroy_radio);
- queue_work(hwsim_wq, &entry->destroy_work);
+ hwsim_radios_generation++;
}
}
spin_unlock_bh(&hwsim_radio_lock);
+
+ list_for_each_entry_safe(entry, tmp, &list, list) {
+ list_del(&entry->list);
+ mac80211_hwsim_del_radio(entry, wiphy_name(entry->hw->wiphy),
+ NULL);
+ }
}
static int mac80211_hwsim_netlink_notify(struct notifier_block *nb,
@@ -3646,6 +3641,7 @@ static __net_init int hwsim_init_net(struct net *net)
static void __net_exit hwsim_exit_net(struct net *net)
{
struct mac80211_hwsim_data *data, *tmp;
+ LIST_HEAD(list);
spin_lock_bh(&hwsim_radio_lock);
list_for_each_entry_safe(data, tmp, &hwsim_radios, list) {
@@ -3656,17 +3652,19 @@ static void __net_exit hwsim_exit_net(struct net *net)
if (data->netgroup == hwsim_net_get_netgroup(&init_net))
continue;
- list_del(&data->list);
+ list_move(&data->list, &list);
rhashtable_remove_fast(&hwsim_radios_rht, &data->rht,
hwsim_rht_params);
hwsim_radios_generation++;
- spin_unlock_bh(&hwsim_radio_lock);
+ }
+ spin_unlock_bh(&hwsim_radio_lock);
+
+ list_for_each_entry_safe(data, tmp, &list, list) {
+ list_del(&data->list);
mac80211_hwsim_del_radio(data,
wiphy_name(data->hw->wiphy),
NULL);
- spin_lock_bh(&hwsim_radio_lock);
}
- spin_unlock_bh(&hwsim_radio_lock);
ida_simple_remove(&hwsim_netgroup_ida, hwsim_net_get_netgroup(net));
}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
index cf6ffb1..22bc9d3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
@@ -77,9 +77,8 @@ static void mt76x0_remove_interface(struct ieee80211_hw *hw,
{
struct mt76x0_dev *dev = hw->priv;
struct mt76_vif *mvif = (struct mt76_vif *) vif->drv_priv;
- unsigned int wcid = mvif->group_wcid.idx;
- dev->wcid_mask[wcid / BITS_PER_LONG] &= ~BIT(wcid % BITS_PER_LONG);
+ dev->vif_mask &= ~BIT(mvif->idx);
}
static int mt76x0_config(struct ieee80211_hw *hw, u32 changed)
diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h
index a46a1e9..936c0b3 100644
--- a/drivers/net/xen-netback/common.h
+++ b/drivers/net/xen-netback/common.h
@@ -241,8 +241,9 @@ struct xenvif_hash_cache {
struct xenvif_hash {
unsigned int alg;
u32 flags;
+ bool mapping_sel;
u8 key[XEN_NETBK_MAX_HASH_KEY_SIZE];
- u32 mapping[XEN_NETBK_MAX_HASH_MAPPING_SIZE];
+ u32 mapping[2][XEN_NETBK_MAX_HASH_MAPPING_SIZE];
unsigned int size;
struct xenvif_hash_cache cache;
};
diff --git a/drivers/net/xen-netback/hash.c b/drivers/net/xen-netback/hash.c
index 3c4c58b..0ccb021 100644
--- a/drivers/net/xen-netback/hash.c
+++ b/drivers/net/xen-netback/hash.c
@@ -324,7 +324,8 @@ u32 xenvif_set_hash_mapping_size(struct xenvif *vif, u32 size)
return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
vif->hash.size = size;
- memset(vif->hash.mapping, 0, sizeof(u32) * size);
+ memset(vif->hash.mapping[vif->hash.mapping_sel], 0,
+ sizeof(u32) * size);
return XEN_NETIF_CTRL_STATUS_SUCCESS;
}
@@ -332,30 +333,48 @@ u32 xenvif_set_hash_mapping_size(struct xenvif *vif, u32 size)
u32 xenvif_set_hash_mapping(struct xenvif *vif, u32 gref, u32 len,
u32 off)
{
- u32 *mapping = &vif->hash.mapping[off];
- struct gnttab_copy copy_op = {
+ u32 *mapping = vif->hash.mapping[!vif->hash.mapping_sel];
+ unsigned int nr = 1;
+ struct gnttab_copy copy_op[2] = {{
.source.u.ref = gref,
.source.domid = vif->domid,
- .dest.u.gmfn = virt_to_gfn(mapping),
.dest.domid = DOMID_SELF,
- .dest.offset = xen_offset_in_page(mapping),
- .len = len * sizeof(u32),
+ .len = len * sizeof(*mapping),
.flags = GNTCOPY_source_gref
- };
+ }};
- if ((off + len > vif->hash.size) || copy_op.len > XEN_PAGE_SIZE)
+ if ((off + len < off) || (off + len > vif->hash.size) ||
+ len > XEN_PAGE_SIZE / sizeof(*mapping))
return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
+ copy_op[0].dest.u.gmfn = virt_to_gfn(mapping + off);
+ copy_op[0].dest.offset = xen_offset_in_page(mapping + off);
+ if (copy_op[0].dest.offset + copy_op[0].len > XEN_PAGE_SIZE) {
+ copy_op[1] = copy_op[0];
+ copy_op[1].source.offset = XEN_PAGE_SIZE - copy_op[0].dest.offset;
+ copy_op[1].dest.u.gmfn = virt_to_gfn(mapping + off + len);
+ copy_op[1].dest.offset = 0;
+ copy_op[1].len = copy_op[0].len - copy_op[1].source.offset;
+ copy_op[0].len = copy_op[1].source.offset;
+ nr = 2;
+ }
+
+ memcpy(mapping, vif->hash.mapping[vif->hash.mapping_sel],
+ vif->hash.size * sizeof(*mapping));
+
+ if (copy_op[0].len != 0) {
+ gnttab_batch_copy(copy_op, nr);
+
+ if (copy_op[0].status != GNTST_okay ||
+ copy_op[nr - 1].status != GNTST_okay)
+ return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
+ }
+
while (len-- != 0)
if (mapping[off++] >= vif->num_queues)
return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
- if (copy_op.len != 0) {
- gnttab_batch_copy(©_op, 1);
-
- if (copy_op.status != GNTST_okay)
- return XEN_NETIF_CTRL_STATUS_INVALID_PARAMETER;
- }
+ vif->hash.mapping_sel = !vif->hash.mapping_sel;
return XEN_NETIF_CTRL_STATUS_SUCCESS;
}
@@ -408,6 +427,8 @@ void xenvif_dump_hash_info(struct xenvif *vif, struct seq_file *m)
}
if (vif->hash.size != 0) {
+ const u32 *mapping = vif->hash.mapping[vif->hash.mapping_sel];
+
seq_puts(m, "\nHash Mapping:\n");
for (i = 0; i < vif->hash.size; ) {
@@ -420,7 +441,7 @@ void xenvif_dump_hash_info(struct xenvif *vif, struct seq_file *m)
seq_printf(m, "[%4u - %4u]: ", i, i + n - 1);
for (j = 0; j < n; j++, i++)
- seq_printf(m, "%4u ", vif->hash.mapping[i]);
+ seq_printf(m, "%4u ", mapping[i]);
seq_puts(m, "\n");
}
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 92274c2..f6ae23f 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -162,7 +162,8 @@ static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb,
if (size == 0)
return skb_get_hash_raw(skb) % dev->real_num_tx_queues;
- return vif->hash.mapping[skb_get_hash_raw(skb) % size];
+ return vif->hash.mapping[vif->hash.mapping_sel]
+ [skb_get_hash_raw(skb) % size];
}
static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev)
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index de82824..ffce6f3 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -610,7 +610,7 @@ static void qeth_put_reply(struct qeth_reply *reply)
static void qeth_issue_ipa_msg(struct qeth_ipa_cmd *cmd, int rc,
struct qeth_card *card)
{
- char *ipa_name;
+ const char *ipa_name;
int com = cmd->hdr.command;
ipa_name = qeth_get_ipa_cmd_name(com);
if (rc)
diff --git a/drivers/s390/net/qeth_core_mpc.c b/drivers/s390/net/qeth_core_mpc.c
index 5bcb8da..e891c0b 100644
--- a/drivers/s390/net/qeth_core_mpc.c
+++ b/drivers/s390/net/qeth_core_mpc.c
@@ -148,10 +148,10 @@ EXPORT_SYMBOL_GPL(IPA_PDU_HEADER);
struct ipa_rc_msg {
enum qeth_ipa_return_codes rc;
- char *msg;
+ const char *msg;
};
-static struct ipa_rc_msg qeth_ipa_rc_msg[] = {
+static const struct ipa_rc_msg qeth_ipa_rc_msg[] = {
{IPA_RC_SUCCESS, "success"},
{IPA_RC_NOTSUPP, "Command not supported"},
{IPA_RC_IP_TABLE_FULL, "Add Addr IP Table Full - ipv6"},
@@ -219,23 +219,23 @@ static struct ipa_rc_msg qeth_ipa_rc_msg[] = {
-char *qeth_get_ipa_msg(enum qeth_ipa_return_codes rc)
+const char *qeth_get_ipa_msg(enum qeth_ipa_return_codes rc)
{
- int x = 0;
- qeth_ipa_rc_msg[sizeof(qeth_ipa_rc_msg) /
- sizeof(struct ipa_rc_msg) - 1].rc = rc;
- while (qeth_ipa_rc_msg[x].rc != rc)
- x++;
+ int x;
+
+ for (x = 0; x < ARRAY_SIZE(qeth_ipa_rc_msg) - 1; x++)
+ if (qeth_ipa_rc_msg[x].rc == rc)
+ return qeth_ipa_rc_msg[x].msg;
return qeth_ipa_rc_msg[x].msg;
}
struct ipa_cmd_names {
enum qeth_ipa_cmds cmd;
- char *name;
+ const char *name;
};
-static struct ipa_cmd_names qeth_ipa_cmd_names[] = {
+static const struct ipa_cmd_names qeth_ipa_cmd_names[] = {
{IPA_CMD_STARTLAN, "startlan"},
{IPA_CMD_STOPLAN, "stoplan"},
{IPA_CMD_SETVMAC, "setvmac"},
@@ -267,13 +267,12 @@ static struct ipa_cmd_names qeth_ipa_cmd_names[] = {
{IPA_CMD_UNKNOWN, "unknown"},
};
-char *qeth_get_ipa_cmd_name(enum qeth_ipa_cmds cmd)
+const char *qeth_get_ipa_cmd_name(enum qeth_ipa_cmds cmd)
{
- int x = 0;
- qeth_ipa_cmd_names[
- sizeof(qeth_ipa_cmd_names) /
- sizeof(struct ipa_cmd_names)-1].cmd = cmd;
- while (qeth_ipa_cmd_names[x].cmd != cmd)
- x++;
+ int x;
+
+ for (x = 0; x < ARRAY_SIZE(qeth_ipa_cmd_names) - 1; x++)
+ if (qeth_ipa_cmd_names[x].cmd == cmd)
+ return qeth_ipa_cmd_names[x].name;
return qeth_ipa_cmd_names[x].name;
}
diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h
index aa8b919..aa5de1f 100644
--- a/drivers/s390/net/qeth_core_mpc.h
+++ b/drivers/s390/net/qeth_core_mpc.h
@@ -797,8 +797,8 @@ enum qeth_ipa_arp_return_codes {
QETH_IPA_ARP_RC_Q_NO_DATA = 0x0008,
};
-extern char *qeth_get_ipa_msg(enum qeth_ipa_return_codes rc);
-extern char *qeth_get_ipa_cmd_name(enum qeth_ipa_cmds cmd);
+extern const char *qeth_get_ipa_msg(enum qeth_ipa_return_codes rc);
+extern const char *qeth_get_ipa_cmd_name(enum qeth_ipa_cmds cmd);
#define QETH_SETASS_BASE_LEN (sizeof(struct qeth_ipacmd_hdr) + \
sizeof(struct qeth_ipacmd_setassparms_hdr))
diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c
index ecb2274..8cc0151 100644
--- a/drivers/soc/fsl/qbman/qman.c
+++ b/drivers/soc/fsl/qbman/qman.c
@@ -2729,6 +2729,9 @@ static int qman_alloc_range(struct gen_pool *p, u32 *result, u32 cnt)
{
unsigned long addr;
+ if (!p)
+ return -ENODEV;
+
addr = gen_pool_alloc(p, cnt);
if (!addr)
return -ENOMEM;
diff --git a/drivers/soc/fsl/qe/ucc.c b/drivers/soc/fsl/qe/ucc.c
index c646d87..681f7d4 100644
--- a/drivers/soc/fsl/qe/ucc.c
+++ b/drivers/soc/fsl/qe/ucc.c
@@ -626,7 +626,7 @@ static u32 ucc_get_tdm_sync_shift(enum comm_dir mode, u32 tdm_num)
{
u32 shift;
- shift = (mode == COMM_DIR_RX) ? RX_SYNC_SHIFT_BASE : RX_SYNC_SHIFT_BASE;
+ shift = (mode == COMM_DIR_RX) ? RX_SYNC_SHIFT_BASE : TX_SYNC_SHIFT_BASE;
shift -= tdm_num * 2;
return shift;
diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c
index 3946649..ba906876 100644
--- a/drivers/video/fbdev/efifb.c
+++ b/drivers/video/fbdev/efifb.c
@@ -42,6 +42,7 @@ struct bmp_dib_header {
u32 colors_important;
} __packed;
+static bool use_bgrt = true;
static bool request_mem_succeeded = false;
static u64 mem_flags = EFI_MEMORY_WC | EFI_MEMORY_UC;
@@ -160,6 +161,9 @@ static void efifb_show_boot_graphics(struct fb_info *info)
void *bgrt_image = NULL;
u8 *dst = info->screen_base;
+ if (!use_bgrt)
+ return;
+
if (!bgrt_tab.image_address) {
pr_info("efifb: No BGRT, not showing boot graphics\n");
return;
@@ -290,6 +294,8 @@ static int efifb_setup(char *options)
screen_info.lfb_width = simple_strtoul(this_opt+6, NULL, 0);
else if (!strcmp(this_opt, "nowc"))
mem_flags &= ~EFI_MEMORY_WC;
+ else if (!strcmp(this_opt, "nobgrt"))
+ use_bgrt = false;
}
}
diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c
index ef69273..a3edb20 100644
--- a/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c
+++ b/drivers/video/fbdev/omap2/omapfb/omapfb-ioctl.c
@@ -496,6 +496,9 @@ static int omapfb_memory_read(struct fb_info *fbi,
if (!access_ok(VERIFY_WRITE, mr->buffer, mr->buffer_size))
return -EFAULT;
+ if (mr->w > 4096 || mr->h > 4096)
+ return -EINVAL;
+
if (mr->w * mr->h * 3 > mr->buffer_size)
return -EINVAL;
@@ -509,7 +512,7 @@ static int omapfb_memory_read(struct fb_info *fbi,
mr->x, mr->y, mr->w, mr->h);
if (r > 0) {
- if (copy_to_user(mr->buffer, buf, mr->buffer_size))
+ if (copy_to_user(mr->buffer, buf, r))
r = -EFAULT;
}
diff --git a/drivers/video/fbdev/pxa168fb.c b/drivers/video/fbdev/pxa168fb.c
index def3a50..d059d04 100644
--- a/drivers/video/fbdev/pxa168fb.c
+++ b/drivers/video/fbdev/pxa168fb.c
@@ -712,7 +712,7 @@ static int pxa168fb_probe(struct platform_device *pdev)
/*
* enable controller clock
*/
- clk_enable(fbi->clk);
+ clk_prepare_enable(fbi->clk);
pxa168fb_set_par(info);
@@ -767,7 +767,7 @@ static int pxa168fb_probe(struct platform_device *pdev)
failed_free_cmap:
fb_dealloc_cmap(&info->cmap);
failed_free_clk:
- clk_disable(fbi->clk);
+ clk_disable_unprepare(fbi->clk);
failed_free_fbmem:
dma_free_coherent(fbi->dev, info->fix.smem_len,
info->screen_base, fbi->fb_start_dma);
@@ -807,7 +807,7 @@ static int pxa168fb_remove(struct platform_device *pdev)
dma_free_wc(fbi->dev, PAGE_ALIGN(info->fix.smem_len),
info->screen_base, info->fix.smem_start);
- clk_disable(fbi->clk);
+ clk_disable_unprepare(fbi->clk);
framebuffer_release(info);
diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c
index 045e8af..9e88e3f 100644
--- a/drivers/video/fbdev/stifb.c
+++ b/drivers/video/fbdev/stifb.c
@@ -1157,7 +1157,7 @@ static int __init stifb_init_fb(struct sti_struct *sti, int bpp_pref)
dev_name);
goto out_err0;
}
- /* fall though */
+ /* fall through */
case S9000_ID_ARTIST:
case S9000_ID_HCRX:
case S9000_ID_TIMBER:
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 0c9ab62..9dcaed0 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1553,6 +1553,7 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param,
/* Flags */
#define MID_WAIT_CANCELLED 1 /* Cancelled while waiting for response */
+#define MID_DELETED 2 /* Mid has been dequeued/deleted */
/* Types of response buffer returned from SendReceive2 */
#define CIFS_NO_BUFFER 0 /* Response buffer not returned */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 7aa08db..52d71b6 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -659,7 +659,15 @@ dequeue_mid(struct mid_q_entry *mid, bool malformed)
mid->mid_state = MID_RESPONSE_RECEIVED;
else
mid->mid_state = MID_RESPONSE_MALFORMED;
- list_del_init(&mid->qhead);
+ /*
+ * Trying to handle/dequeue a mid after the send_recv()
+ * function has finished processing it is a bug.
+ */
+ if (mid->mid_flags & MID_DELETED)
+ printk_once(KERN_WARNING
+ "trying to dequeue a deleted mid\n");
+ else
+ list_del_init(&mid->qhead);
spin_unlock(&GlobalMid_Lock);
}
@@ -938,8 +946,7 @@ cifs_demultiplex_thread(void *p)
} else {
mids[0] = server->ops->find_mid(server, buf);
bufs[0] = buf;
- if (mids[0])
- num_mids = 1;
+ num_mids = 1;
if (!mids[0] || !mids[0]->receive)
length = standard_receive3(server, mids[0]);
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index d954ce3..89985a0 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1477,7 +1477,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
}
srch_inf->entries_in_buffer = 0;
- srch_inf->index_of_last_entry = 0;
+ srch_inf->index_of_last_entry = 2;
rc = SMB2_query_directory(xid, tcon, fid->persistent_fid,
fid->volatile_fid, 0, srch_inf);
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 78f96fa..b48f439 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -142,7 +142,8 @@ void
cifs_delete_mid(struct mid_q_entry *mid)
{
spin_lock(&GlobalMid_Lock);
- list_del(&mid->qhead);
+ list_del_init(&mid->qhead);
+ mid->mid_flags |= MID_DELETED;
spin_unlock(&GlobalMid_Lock);
DeleteMidQEntry(mid);
@@ -772,6 +773,11 @@ cifs_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst)
return mid;
}
+static void
+cifs_noop_callback(struct mid_q_entry *mid)
+{
+}
+
int
compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
const int flags, const int num_rqst, struct smb_rqst *rqst,
@@ -826,8 +832,13 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
}
midQ[i]->mid_state = MID_REQUEST_SUBMITTED;
+ /*
+ * We don't invoke the callback compounds unless it is the last
+ * request.
+ */
+ if (i < num_rqst - 1)
+ midQ[i]->callback = cifs_noop_callback;
}
-
cifs_in_send_inc(ses->server);
rc = smb_send_rqst(ses->server, num_rqst, rqst, flags);
cifs_in_send_dec(ses->server);
@@ -908,6 +919,12 @@ compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
midQ[i]->resp_buf = NULL;
}
out:
+ /*
+ * This will dequeue all mids. After this it is important that the
+ * demultiplex_thread will not process any of these mids any futher.
+ * This is prevented above by using a noop callback that will not
+ * wake this thread except for the very last PDU.
+ */
for (i = 0; i < num_rqst; i++)
cifs_delete_mid(midQ[i]);
add_credits(ses->server, credits, optype);
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 3212c292..2005529 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -230,7 +230,7 @@ static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd,
ret = -EXDEV;
if (src_file.file->f_path.mnt != dst_file->f_path.mnt)
goto fdput;
- ret = do_clone_file_range(src_file.file, off, dst_file, destoff, olen);
+ ret = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen);
fdput:
fdput(src_file);
return ret;
diff --git a/fs/iomap.c b/fs/iomap.c
index 74762b1..ec15cf2 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1051,6 +1051,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
} else {
WARN_ON_ONCE(!PageUptodate(page));
iomap_page_create(inode, page);
+ set_page_dirty(page);
}
return length;
@@ -1090,7 +1091,6 @@ int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
length -= ret;
}
- set_page_dirty(page);
wait_for_stable_page(page);
return VM_FAULT_LOCKED;
out_unlock:
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 55a099e..b53e763 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -541,7 +541,8 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp,
__be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst,
u64 dst_pos, u64 count)
{
- return nfserrno(do_clone_file_range(src, src_pos, dst, dst_pos, count));
+ return nfserrno(vfs_clone_file_range(src, src_pos, dst, dst_pos,
+ count));
}
ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst,
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 296037a..1cc797a 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -141,7 +141,7 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len)
}
/* Try to use clone_file_range to clone up within the same fs */
- error = vfs_clone_file_range(old_file, 0, new_file, 0, len);
+ error = do_clone_file_range(old_file, 0, new_file, 0, len);
if (!error)
goto out;
/* Couldn't clone, so now we try to copy the data */
diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c
index aeaefd2..986313d 100644
--- a/fs/overlayfs/file.c
+++ b/fs/overlayfs/file.c
@@ -240,8 +240,10 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
goto out_unlock;
old_cred = ovl_override_creds(file_inode(file)->i_sb);
+ file_start_write(real.file);
ret = vfs_iter_write(real.file, iter, &iocb->ki_pos,
ovl_iocb_to_rwf(iocb));
+ file_end_write(real.file);
revert_creds(old_cred);
/* Update size */
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index b6ac545..3b7ed5d 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -504,7 +504,7 @@ static const struct inode_operations ovl_special_inode_operations = {
.update_time = ovl_update_time,
};
-const struct address_space_operations ovl_aops = {
+static const struct address_space_operations ovl_aops = {
/* For O_DIRECT dentry_open() checks f_mapping->a_ops->direct_IO */
.direct_IO = noop_direct_IO,
};
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index f287118..9c0ca6a 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -686,7 +686,7 @@ struct dentry *ovl_lookup_index(struct ovl_fs *ofs, struct dentry *upper,
index = NULL;
goto out;
}
- pr_warn_ratelimited("overlayfs: failed inode index lookup (ino=%lu, key=%*s, err=%i);\n"
+ pr_warn_ratelimited("overlayfs: failed inode index lookup (ino=%lu, key=%.*s, err=%i);\n"
"overlayfs: mount with '-o index=off' to disable inodes index.\n",
d_inode(origin)->i_ino, name.len, name.name,
err);
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index f61839e..a3c0d95 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -152,8 +152,8 @@ static inline int ovl_do_setxattr(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
int err = vfs_setxattr(dentry, name, value, size, flags);
- pr_debug("setxattr(%pd2, \"%s\", \"%*s\", 0x%x) = %i\n",
- dentry, name, (int) size, (char *) value, flags, err);
+ pr_debug("setxattr(%pd2, \"%s\", \"%*pE\", %zu, 0x%x) = %i\n",
+ dentry, name, min((int)size, 48), value, size, flags, err);
return err;
}
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 8cfb62c..ace4fe4 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -683,7 +683,7 @@ static void ovl_cleanup_index(struct dentry *dentry)
struct dentry *upperdentry = ovl_dentry_upper(dentry);
struct dentry *index = NULL;
struct inode *inode;
- struct qstr name;
+ struct qstr name = { };
int err;
err = ovl_get_index_name(lowerdentry, &name);
@@ -726,6 +726,7 @@ static void ovl_cleanup_index(struct dentry *dentry)
goto fail;
out:
+ kfree(name.name);
dput(index);
return;
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index bbd1e35..f4fd2e7 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -898,8 +898,22 @@ static struct platform_driver ramoops_driver = {
},
};
-static void ramoops_register_dummy(void)
+static inline void ramoops_unregister_dummy(void)
{
+ platform_device_unregister(dummy);
+ dummy = NULL;
+
+ kfree(dummy_data);
+ dummy_data = NULL;
+}
+
+static void __init ramoops_register_dummy(void)
+{
+ /*
+ * Prepare a dummy platform data structure to carry the module
+ * parameters. If mem_size isn't set, then there are no module
+ * parameters, and we can skip this.
+ */
if (!mem_size)
return;
@@ -932,21 +946,28 @@ static void ramoops_register_dummy(void)
if (IS_ERR(dummy)) {
pr_info("could not create platform device: %ld\n",
PTR_ERR(dummy));
+ dummy = NULL;
+ ramoops_unregister_dummy();
}
}
static int __init ramoops_init(void)
{
+ int ret;
+
ramoops_register_dummy();
- return platform_driver_register(&ramoops_driver);
+ ret = platform_driver_register(&ramoops_driver);
+ if (ret != 0)
+ ramoops_unregister_dummy();
+
+ return ret;
}
late_initcall(ramoops_init);
static void __exit ramoops_exit(void)
{
platform_driver_unregister(&ramoops_driver);
- platform_device_unregister(dummy);
- kfree(dummy_data);
+ ramoops_unregister_dummy();
}
module_exit(ramoops_exit);
diff --git a/fs/read_write.c b/fs/read_write.c
index 39b4a21..8a2737f 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1818,8 +1818,8 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
}
EXPORT_SYMBOL(vfs_clone_file_prep_inodes);
-int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out, u64 len)
+int do_clone_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out, u64 len)
{
struct inode *inode_in = file_inode(file_in);
struct inode *inode_out = file_inode(file_out);
@@ -1866,6 +1866,19 @@ int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
return ret;
}
+EXPORT_SYMBOL(do_clone_file_range);
+
+int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out, u64 len)
+{
+ int ret;
+
+ file_start_write(file_out);
+ ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len);
+ file_end_write(file_out);
+
+ return ret;
+}
EXPORT_SYMBOL(vfs_clone_file_range);
/*
diff --git a/fs/xattr.c b/fs/xattr.c
index daa7325..0d6a6a4 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -948,17 +948,19 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs,
int err = 0;
#ifdef CONFIG_FS_POSIX_ACL
- if (inode->i_acl) {
- err = xattr_list_one(&buffer, &remaining_size,
- XATTR_NAME_POSIX_ACL_ACCESS);
- if (err)
- return err;
- }
- if (inode->i_default_acl) {
- err = xattr_list_one(&buffer, &remaining_size,
- XATTR_NAME_POSIX_ACL_DEFAULT);
- if (err)
- return err;
+ if (IS_POSIXACL(inode)) {
+ if (inode->i_acl) {
+ err = xattr_list_one(&buffer, &remaining_size,
+ XATTR_NAME_POSIX_ACL_ACCESS);
+ if (err)
+ return err;
+ }
+ if (inode->i_default_acl) {
+ err = xattr_list_one(&buffer, &remaining_size,
+ XATTR_NAME_POSIX_ACL_DEFAULT);
+ if (err)
+ return err;
+ }
}
#endif
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 1e671d4..c6299f8 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -587,7 +587,7 @@ xfs_attr_leaf_addname(
*/
error = xfs_attr3_leaf_to_node(args);
if (error)
- goto out_defer_cancel;
+ return error;
error = xfs_defer_finish(&args->trans);
if (error)
return error;
@@ -675,7 +675,7 @@ xfs_attr_leaf_addname(
error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
/* bp is gone due to xfs_da_shrink_inode */
if (error)
- goto out_defer_cancel;
+ return error;
error = xfs_defer_finish(&args->trans);
if (error)
return error;
@@ -693,9 +693,6 @@ xfs_attr_leaf_addname(
error = xfs_attr3_leaf_clearflag(args);
}
return error;
-out_defer_cancel:
- xfs_defer_cancel(args->trans);
- return error;
}
/*
@@ -738,15 +735,12 @@ xfs_attr_leaf_removename(
error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
/* bp is gone due to xfs_da_shrink_inode */
if (error)
- goto out_defer_cancel;
+ return error;
error = xfs_defer_finish(&args->trans);
if (error)
return error;
}
return 0;
-out_defer_cancel:
- xfs_defer_cancel(args->trans);
- return error;
}
/*
@@ -864,7 +858,7 @@ xfs_attr_node_addname(
state = NULL;
error = xfs_attr3_leaf_to_node(args);
if (error)
- goto out_defer_cancel;
+ goto out;
error = xfs_defer_finish(&args->trans);
if (error)
goto out;
@@ -888,7 +882,7 @@ xfs_attr_node_addname(
*/
error = xfs_da3_split(state);
if (error)
- goto out_defer_cancel;
+ goto out;
error = xfs_defer_finish(&args->trans);
if (error)
goto out;
@@ -984,7 +978,7 @@ xfs_attr_node_addname(
if (retval && (state->path.active > 1)) {
error = xfs_da3_join(state);
if (error)
- goto out_defer_cancel;
+ goto out;
error = xfs_defer_finish(&args->trans);
if (error)
goto out;
@@ -1013,9 +1007,6 @@ xfs_attr_node_addname(
if (error)
return error;
return retval;
-out_defer_cancel:
- xfs_defer_cancel(args->trans);
- goto out;
}
/*
@@ -1107,7 +1098,7 @@ xfs_attr_node_removename(
if (retval && (state->path.active > 1)) {
error = xfs_da3_join(state);
if (error)
- goto out_defer_cancel;
+ goto out;
error = xfs_defer_finish(&args->trans);
if (error)
goto out;
@@ -1138,7 +1129,7 @@ xfs_attr_node_removename(
error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
/* bp is gone due to xfs_da_shrink_inode */
if (error)
- goto out_defer_cancel;
+ goto out;
error = xfs_defer_finish(&args->trans);
if (error)
goto out;
@@ -1150,9 +1141,6 @@ xfs_attr_node_removename(
out:
xfs_da_state_free(state);
return error;
-out_defer_cancel:
- xfs_defer_cancel(args->trans);
- goto out;
}
/*
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index af09406..d89363c 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -485,7 +485,7 @@ xfs_attr_rmtval_set(
blkcnt, XFS_BMAPI_ATTRFORK, args->total, &map,
&nmap);
if (error)
- goto out_defer_cancel;
+ return error;
error = xfs_defer_finish(&args->trans);
if (error)
return error;
@@ -553,9 +553,6 @@ xfs_attr_rmtval_set(
}
ASSERT(valuelen == 0);
return 0;
-out_defer_cancel:
- xfs_defer_cancel(args->trans);
- return error;
}
/*
@@ -625,7 +622,7 @@ xfs_attr_rmtval_remove(
error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
XFS_BMAPI_ATTRFORK, 1, &done);
if (error)
- goto out_defer_cancel;
+ return error;
error = xfs_defer_finish(&args->trans);
if (error)
return error;
@@ -638,7 +635,4 @@ xfs_attr_rmtval_remove(
return error;
}
return 0;
-out_defer_cancel:
- xfs_defer_cancel(args->trans);
- return error;
}
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 2760314..a476703 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -673,7 +673,8 @@ xfs_bmap_extents_to_btree(
ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS);
/*
- * Make space in the inode incore.
+ * Make space in the inode incore. This needs to be undone if we fail
+ * to expand the root.
*/
xfs_iroot_realloc(ip, 1, whichfork);
ifp->if_flags |= XFS_IFBROOT;
@@ -711,16 +712,15 @@ xfs_bmap_extents_to_btree(
args.minlen = args.maxlen = args.prod = 1;
args.wasdel = wasdel;
*logflagsp = 0;
- if ((error = xfs_alloc_vextent(&args))) {
- ASSERT(ifp->if_broot == NULL);
- goto err1;
- }
+ error = xfs_alloc_vextent(&args);
+ if (error)
+ goto out_root_realloc;
if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
- ASSERT(ifp->if_broot == NULL);
error = -ENOSPC;
- goto err1;
+ goto out_root_realloc;
}
+
/*
* Allocation can't fail, the space was reserved.
*/
@@ -732,9 +732,10 @@ xfs_bmap_extents_to_btree(
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L);
abp = xfs_btree_get_bufl(mp, tp, args.fsbno, 0);
if (!abp) {
- error = -ENOSPC;
- goto err2;
+ error = -EFSCORRUPTED;
+ goto out_unreserve_dquot;
}
+
/*
* Fill in the child block.
*/
@@ -775,11 +776,12 @@ xfs_bmap_extents_to_btree(
*logflagsp = XFS_ILOG_CORE | xfs_ilog_fbroot(whichfork);
return 0;
-err2:
+out_unreserve_dquot:
xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
-err1:
+out_root_realloc:
xfs_iroot_realloc(ip, -1, whichfork);
XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
+ ASSERT(ifp->if_broot == NULL);
xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
return error;
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 059bc44..afbe336 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -1016,6 +1016,8 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
#define XFS_DIFLAG_EXTSZINHERIT_BIT 12 /* inherit inode extent size */
#define XFS_DIFLAG_NODEFRAG_BIT 13 /* do not reorganize/defragment */
#define XFS_DIFLAG_FILESTREAM_BIT 14 /* use filestream allocator */
+/* Do not use bit 15, di_flags is legacy and unchanging now */
+
#define XFS_DIFLAG_REALTIME (1 << XFS_DIFLAG_REALTIME_BIT)
#define XFS_DIFLAG_PREALLOC (1 << XFS_DIFLAG_PREALLOC_BIT)
#define XFS_DIFLAG_NEWRTBM (1 << XFS_DIFLAG_NEWRTBM_BIT)
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 30d1d60..09d9c8c 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -415,6 +415,31 @@ xfs_dinode_verify_fork(
return NULL;
}
+static xfs_failaddr_t
+xfs_dinode_verify_forkoff(
+ struct xfs_dinode *dip,
+ struct xfs_mount *mp)
+{
+ if (!XFS_DFORK_Q(dip))
+ return NULL;
+
+ switch (dip->di_format) {
+ case XFS_DINODE_FMT_DEV:
+ if (dip->di_forkoff != (roundup(sizeof(xfs_dev_t), 8) >> 3))
+ return __this_address;
+ break;
+ case XFS_DINODE_FMT_LOCAL: /* fall through ... */
+ case XFS_DINODE_FMT_EXTENTS: /* fall through ... */
+ case XFS_DINODE_FMT_BTREE:
+ if (dip->di_forkoff >= (XFS_LITINO(mp, dip->di_version) >> 3))
+ return __this_address;
+ break;
+ default:
+ return __this_address;
+ }
+ return NULL;
+}
+
xfs_failaddr_t
xfs_dinode_verify(
struct xfs_mount *mp,
@@ -470,6 +495,11 @@ xfs_dinode_verify(
if (mode && (flags & XFS_DIFLAG_REALTIME) && !mp->m_rtdev_targp)
return __this_address;
+ /* check for illegal values of forkoff */
+ fa = xfs_dinode_verify_forkoff(dip, mp);
+ if (fa)
+ return fa;
+
/* Do we have appropriate data fork formats for the mode? */
switch (mode & S_IFMT) {
case S_IFIFO:
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index 036b5c7..376bcb5 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -17,7 +17,6 @@
#include "xfs_sb.h"
#include "xfs_alloc.h"
#include "xfs_rmap.h"
-#include "xfs_alloc.h"
#include "scrub/xfs_scrub.h"
#include "scrub/scrub.h"
#include "scrub/common.h"
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 5b3b177..e386c9b 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -126,6 +126,7 @@ xchk_inode_flags(
{
struct xfs_mount *mp = sc->mp;
+ /* di_flags are all taken, last bit cannot be used */
if (flags & ~XFS_DIFLAG_ANY)
goto bad;
@@ -172,8 +173,9 @@ xchk_inode_flags2(
{
struct xfs_mount *mp = sc->mp;
+ /* Unknown di_flags2 could be from a future kernel */
if (flags2 & ~XFS_DIFLAG2_ANY)
- goto bad;
+ xchk_ino_set_warning(sc, ino);
/* reflink flag requires reflink feature */
if ((flags2 & XFS_DIFLAG2_REFLINK) &&
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index addbd74..6de8d90 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -702,13 +702,9 @@ xfs_bmap_punch_delalloc_range(
struct xfs_iext_cursor icur;
int error = 0;
- xfs_ilock(ip, XFS_ILOCK_EXCL);
- if (!(ifp->if_flags & XFS_IFEXTENTS)) {
- error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
- if (error)
- goto out_unlock;
- }
+ ASSERT(ifp->if_flags & XFS_IFEXTENTS);
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
goto out_unlock;
@@ -1584,7 +1580,7 @@ xfs_swap_extent_rmap(
tirec.br_blockcount, &irec,
&nimaps, 0);
if (error)
- goto out_defer;
+ goto out;
ASSERT(nimaps == 1);
ASSERT(tirec.br_startoff == irec.br_startoff);
trace_xfs_swap_extent_rmap_remap_piece(ip, &irec);
@@ -1599,22 +1595,22 @@ xfs_swap_extent_rmap(
/* Remove the mapping from the donor file. */
error = xfs_bmap_unmap_extent(tp, tip, &uirec);
if (error)
- goto out_defer;
+ goto out;
/* Remove the mapping from the source file. */
error = xfs_bmap_unmap_extent(tp, ip, &irec);
if (error)
- goto out_defer;
+ goto out;
/* Map the donor file's blocks into the source file. */
error = xfs_bmap_map_extent(tp, ip, &uirec);
if (error)
- goto out_defer;
+ goto out;
/* Map the source file's blocks into the donor file. */
error = xfs_bmap_map_extent(tp, tip, &irec);
if (error)
- goto out_defer;
+ goto out;
error = xfs_defer_finish(tpp);
tp = *tpp;
@@ -1636,8 +1632,6 @@ xfs_swap_extent_rmap(
tip->i_d.di_flags2 = tip_flags2;
return 0;
-out_defer:
- xfs_defer_cancel(tp);
out:
trace_xfs_swap_extent_rmap_error(ip, error, _RET_IP_);
tip->i_d.di_flags2 = tip_flags2;
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 1c9d139..12d8455 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -532,6 +532,49 @@ xfs_buf_item_push(
}
/*
+ * Drop the buffer log item refcount and take appropriate action. This helper
+ * determines whether the bli must be freed or not, since a decrement to zero
+ * does not necessarily mean the bli is unused.
+ *
+ * Return true if the bli is freed, false otherwise.
+ */
+bool
+xfs_buf_item_put(
+ struct xfs_buf_log_item *bip)
+{
+ struct xfs_log_item *lip = &bip->bli_item;
+ bool aborted;
+ bool dirty;
+
+ /* drop the bli ref and return if it wasn't the last one */
+ if (!atomic_dec_and_test(&bip->bli_refcount))
+ return false;
+
+ /*
+ * We dropped the last ref and must free the item if clean or aborted.
+ * If the bli is dirty and non-aborted, the buffer was clean in the
+ * transaction but still awaiting writeback from previous changes. In
+ * that case, the bli is freed on buffer writeback completion.
+ */
+ aborted = test_bit(XFS_LI_ABORTED, &lip->li_flags) ||
+ XFS_FORCED_SHUTDOWN(lip->li_mountp);
+ dirty = bip->bli_flags & XFS_BLI_DIRTY;
+ if (dirty && !aborted)
+ return false;
+
+ /*
+ * The bli is aborted or clean. An aborted item may be in the AIL
+ * regardless of dirty state. For example, consider an aborted
+ * transaction that invalidated a dirty bli and cleared the dirty
+ * state.
+ */
+ if (aborted)
+ xfs_trans_ail_remove(lip, SHUTDOWN_LOG_IO_ERROR);
+ xfs_buf_item_relse(bip->bli_buf);
+ return true;
+}
+
+/*
* Release the buffer associated with the buf log item. If there is no dirty
* logged data associated with the buffer recorded in the buf log item, then
* free the buf log item and remove the reference to it in the buffer.
@@ -556,76 +599,42 @@ xfs_buf_item_unlock(
{
struct xfs_buf_log_item *bip = BUF_ITEM(lip);
struct xfs_buf *bp = bip->bli_buf;
- bool aborted;
- bool hold = !!(bip->bli_flags & XFS_BLI_HOLD);
- bool dirty = !!(bip->bli_flags & XFS_BLI_DIRTY);
+ bool released;
+ bool hold = bip->bli_flags & XFS_BLI_HOLD;
+ bool stale = bip->bli_flags & XFS_BLI_STALE;
#if defined(DEBUG) || defined(XFS_WARN)
- bool ordered = !!(bip->bli_flags & XFS_BLI_ORDERED);
+ bool ordered = bip->bli_flags & XFS_BLI_ORDERED;
+ bool dirty = bip->bli_flags & XFS_BLI_DIRTY;
#endif
- aborted = test_bit(XFS_LI_ABORTED, &lip->li_flags);
-
- /* Clear the buffer's association with this transaction. */
- bp->b_transp = NULL;
-
- /*
- * The per-transaction state has been copied above so clear it from the
- * bli.
- */
- bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED);
-
- /*
- * If the buf item is marked stale, then don't do anything. We'll
- * unlock the buffer and free the buf item when the buffer is unpinned
- * for the last time.
- */
- if (bip->bli_flags & XFS_BLI_STALE) {
- trace_xfs_buf_item_unlock_stale(bip);
- ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
- if (!aborted) {
- atomic_dec(&bip->bli_refcount);
- return;
- }
- }
-
trace_xfs_buf_item_unlock(bip);
/*
- * If the buf item isn't tracking any data, free it, otherwise drop the
- * reference we hold to it. If we are aborting the transaction, this may
- * be the only reference to the buf item, so we free it anyway
- * regardless of whether it is dirty or not. A dirty abort implies a
- * shutdown, anyway.
- *
* The bli dirty state should match whether the blf has logged segments
* except for ordered buffers, where only the bli should be dirty.
*/
ASSERT((!ordered && dirty == xfs_buf_item_dirty_format(bip)) ||
(ordered && dirty && !xfs_buf_item_dirty_format(bip)));
+ ASSERT(!stale || (bip->__bli_format.blf_flags & XFS_BLF_CANCEL));
/*
- * Clean buffers, by definition, cannot be in the AIL. However, aborted
- * buffers may be in the AIL regardless of dirty state. An aborted
- * transaction that invalidates a buffer already in the AIL may have
- * marked it stale and cleared the dirty state, for example.
- *
- * Therefore if we are aborting a buffer and we've just taken the last
- * reference away, we have to check if it is in the AIL before freeing
- * it. We need to free it in this case, because an aborted transaction
- * has already shut the filesystem down and this is the last chance we
- * will have to do so.
+ * Clear the buffer's association with this transaction and
+ * per-transaction state from the bli, which has been copied above.
*/
- if (atomic_dec_and_test(&bip->bli_refcount)) {
- if (aborted) {
- ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp));
- xfs_trans_ail_remove(lip, SHUTDOWN_LOG_IO_ERROR);
- xfs_buf_item_relse(bp);
- } else if (!dirty)
- xfs_buf_item_relse(bp);
- }
+ bp->b_transp = NULL;
+ bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED);
- if (!hold)
- xfs_buf_relse(bp);
+ /*
+ * Unref the item and unlock the buffer unless held or stale. Stale
+ * buffers remain locked until final unpin unless the bli is freed by
+ * the unref call. The latter implies shutdown because buffer
+ * invalidation dirties the bli and transaction.
+ */
+ released = xfs_buf_item_put(bip);
+ if (hold || (stale && !released))
+ return;
+ ASSERT(!stale || test_bit(XFS_LI_ABORTED, &lip->li_flags));
+ xfs_buf_relse(bp);
}
/*
diff --git a/fs/xfs/xfs_buf_item.h b/fs/xfs/xfs_buf_item.h
index 3f7d7b7..90f65f8 100644
--- a/fs/xfs/xfs_buf_item.h
+++ b/fs/xfs/xfs_buf_item.h
@@ -51,6 +51,7 @@ struct xfs_buf_log_item {
int xfs_buf_item_init(struct xfs_buf *, struct xfs_mount *);
void xfs_buf_item_relse(struct xfs_buf *);
+bool xfs_buf_item_put(struct xfs_buf_log_item *);
void xfs_buf_item_log(struct xfs_buf_log_item *, uint, uint);
bool xfs_buf_item_dirty_format(struct xfs_buf_log_item *);
void xfs_buf_attach_iodone(struct xfs_buf *,
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index d957a46..05db954 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1563,7 +1563,7 @@ xfs_itruncate_extents_flags(
error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
XFS_ITRUNC_MAX_EXTENTS, &done);
if (error)
- goto out_bmap_cancel;
+ goto out;
/*
* Duplicate the transaction that has the permanent
@@ -1599,14 +1599,6 @@ xfs_itruncate_extents_flags(
out:
*tpp = tp;
return error;
-out_bmap_cancel:
- /*
- * If the bunmapi call encounters an error, return to the caller where
- * the transaction can be properly aborted. We just need to make sure
- * we're not holding any resources that we were not when we came in.
- */
- xfs_defer_cancel(tp);
- goto out;
}
int
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index c3e74f9..f48ffd7 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -471,8 +471,18 @@ xfs_vn_get_link_inline(
struct inode *inode,
struct delayed_call *done)
{
+ char *link;
+
ASSERT(XFS_I(inode)->i_df.if_flags & XFS_IFINLINE);
- return XFS_I(inode)->i_df.if_u1.if_data;
+
+ /*
+ * The VFS crashes on a NULL pointer, so return -EFSCORRUPTED if
+ * if_data is junk.
+ */
+ link = XFS_I(inode)->i_df.if_u1.if_data;
+ if (!link)
+ return ERR_PTR(-EFSCORRUPTED);
+ return link;
}
STATIC int
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index a21dc61..1fc9e90 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1570,16 +1570,6 @@ xlog_find_zeroed(
if (last_cycle != 0) { /* log completely written to */
xlog_put_bp(bp);
return 0;
- } else if (first_cycle != 1) {
- /*
- * If the cycle of the last block is zero, the cycle of
- * the first block must be 1. If it's not, maybe we're
- * not looking at a log... Bail out.
- */
- xfs_warn(log->l_mp,
- "Log inconsistent or not a log (last==0, first!=1)");
- error = -EINVAL;
- goto bp_err;
}
/* we have a partially zeroed log */
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 38f4054..5289e22 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -352,6 +352,47 @@ xfs_reflink_convert_cow(
return error;
}
+/*
+ * Find the extent that maps the given range in the COW fork. Even if the extent
+ * is not shared we might have a preallocation for it in the COW fork. If so we
+ * use it that rather than trigger a new allocation.
+ */
+static int
+xfs_find_trim_cow_extent(
+ struct xfs_inode *ip,
+ struct xfs_bmbt_irec *imap,
+ bool *shared,
+ bool *found)
+{
+ xfs_fileoff_t offset_fsb = imap->br_startoff;
+ xfs_filblks_t count_fsb = imap->br_blockcount;
+ struct xfs_iext_cursor icur;
+ struct xfs_bmbt_irec got;
+ bool trimmed;
+
+ *found = false;
+
+ /*
+ * If we don't find an overlapping extent, trim the range we need to
+ * allocate to fit the hole we found.
+ */
+ if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got) ||
+ got.br_startoff > offset_fsb)
+ return xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);
+
+ *shared = true;
+ if (isnullstartblock(got.br_startblock)) {
+ xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
+ return 0;
+ }
+
+ /* real extent found - no need to allocate */
+ xfs_trim_extent(&got, offset_fsb, count_fsb);
+ *imap = got;
+ *found = true;
+ return 0;
+}
+
/* Allocate all CoW reservations covering a range of blocks in a file. */
int
xfs_reflink_allocate_cow(
@@ -363,78 +404,64 @@ xfs_reflink_allocate_cow(
struct xfs_mount *mp = ip->i_mount;
xfs_fileoff_t offset_fsb = imap->br_startoff;
xfs_filblks_t count_fsb = imap->br_blockcount;
- struct xfs_bmbt_irec got;
- struct xfs_trans *tp = NULL;
+ struct xfs_trans *tp;
int nimaps, error = 0;
- bool trimmed;
+ bool found;
xfs_filblks_t resaligned;
xfs_extlen_t resblks = 0;
- struct xfs_iext_cursor icur;
-retry:
- ASSERT(xfs_is_reflink_inode(ip));
ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+ ASSERT(xfs_is_reflink_inode(ip));
+
+ error = xfs_find_trim_cow_extent(ip, imap, shared, &found);
+ if (error || !*shared)
+ return error;
+ if (found)
+ goto convert;
+
+ resaligned = xfs_aligned_fsb_count(imap->br_startoff,
+ imap->br_blockcount, xfs_get_cowextsz_hint(ip));
+ resblks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned);
+
+ xfs_iunlock(ip, *lockmode);
+ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
+ *lockmode = XFS_ILOCK_EXCL;
+ xfs_ilock(ip, *lockmode);
+
+ if (error)
+ return error;
+
+ error = xfs_qm_dqattach_locked(ip, false);
+ if (error)
+ goto out_trans_cancel;
/*
- * Even if the extent is not shared we might have a preallocation for
- * it in the COW fork. If so use it.
+ * Check for an overlapping extent again now that we dropped the ilock.
*/
- if (xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got) &&
- got.br_startoff <= offset_fsb) {
- *shared = true;
-
- /* If we have a real allocation in the COW fork we're done. */
- if (!isnullstartblock(got.br_startblock)) {
- xfs_trim_extent(&got, offset_fsb, count_fsb);
- *imap = got;
- goto convert;
- }
-
- xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
- } else {
- error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);
- if (error || !*shared)
- goto out;
- }
-
- if (!tp) {
- resaligned = xfs_aligned_fsb_count(imap->br_startoff,
- imap->br_blockcount, xfs_get_cowextsz_hint(ip));
- resblks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned);
-
- xfs_iunlock(ip, *lockmode);
- error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
- *lockmode = XFS_ILOCK_EXCL;
- xfs_ilock(ip, *lockmode);
-
- if (error)
- return error;
-
- error = xfs_qm_dqattach_locked(ip, false);
- if (error)
- goto out;
- goto retry;
+ error = xfs_find_trim_cow_extent(ip, imap, shared, &found);
+ if (error || !*shared)
+ goto out_trans_cancel;
+ if (found) {
+ xfs_trans_cancel(tp);
+ goto convert;
}
error = xfs_trans_reserve_quota_nblks(tp, ip, resblks, 0,
XFS_QMOPT_RES_REGBLKS);
if (error)
- goto out;
+ goto out_trans_cancel;
xfs_trans_ijoin(tp, ip, 0);
- nimaps = 1;
-
/* Allocate the entire reservation as unwritten blocks. */
+ nimaps = 1;
error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount,
XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC,
resblks, imap, &nimaps);
if (error)
- goto out_trans_cancel;
+ goto out_unreserve;
xfs_inode_set_cowblocks_tag(ip);
-
- /* Finish up. */
error = xfs_trans_commit(tp);
if (error)
return error;
@@ -447,12 +474,12 @@ xfs_reflink_allocate_cow(
return -ENOSPC;
convert:
return xfs_reflink_convert_cow_extent(ip, imap, offset_fsb, count_fsb);
-out_trans_cancel:
+
+out_unreserve:
xfs_trans_unreserve_quota_nblks(tp, ip, (long)resblks, 0,
XFS_QMOPT_RES_REGBLKS);
-out:
- if (tp)
- xfs_trans_cancel(tp);
+out_trans_cancel:
+ xfs_trans_cancel(tp);
return error;
}
@@ -666,14 +693,12 @@ xfs_reflink_end_cow(
if (!del.br_blockcount)
goto prev_extent;
- ASSERT(!isnullstartblock(got.br_startblock));
-
/*
- * Don't remap unwritten extents; these are
- * speculatively preallocated CoW extents that have been
- * allocated but have not yet been involved in a write.
+ * Only remap real extent that contain data. With AIO
+ * speculatively preallocations can leak into the range we
+ * are called upon, and we need to skip them.
*/
- if (got.br_state == XFS_EXT_UNWRITTEN)
+ if (!xfs_bmap_is_real_extent(&got))
goto prev_extent;
/* Unmap the old blocks in the data fork. */
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index ad315e8..3043e5e 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -473,7 +473,6 @@ DEFINE_BUF_ITEM_EVENT(xfs_buf_item_pin);
DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin);
DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin_stale);
DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unlock);
-DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unlock_stale);
DEFINE_BUF_ITEM_EVENT(xfs_buf_item_committed);
DEFINE_BUF_ITEM_EVENT(xfs_buf_item_push);
DEFINE_BUF_ITEM_EVENT(xfs_trans_get_buf);
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index bedc5a5..912b42f 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -259,6 +259,14 @@ xfs_trans_alloc(
struct xfs_trans *tp;
int error;
+ /*
+ * Allocate the handle before we do our freeze accounting and setting up
+ * GFP_NOFS allocation context so that we avoid lockdep false positives
+ * by doing GFP_KERNEL allocations inside sb_start_intwrite().
+ */
+ tp = kmem_zone_zalloc(xfs_trans_zone,
+ (flags & XFS_TRANS_NOFS) ? KM_NOFS : KM_SLEEP);
+
if (!(flags & XFS_TRANS_NO_WRITECOUNT))
sb_start_intwrite(mp->m_super);
@@ -270,8 +278,6 @@ xfs_trans_alloc(
mp->m_super->s_writers.frozen == SB_FREEZE_COMPLETE);
atomic_inc(&mp->m_active_trans);
- tp = kmem_zone_zalloc(xfs_trans_zone,
- (flags & XFS_TRANS_NOFS) ? KM_NOFS : KM_SLEEP);
tp->t_magic = XFS_TRANS_HEADER_MAGIC;
tp->t_flags = flags;
tp->t_mountp = mp;
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 15919f6..286a287 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -322,49 +322,38 @@ xfs_trans_read_buf_map(
}
/*
- * Release the buffer bp which was previously acquired with one of the
- * xfs_trans_... buffer allocation routines if the buffer has not
- * been modified within this transaction. If the buffer is modified
- * within this transaction, do decrement the recursion count but do
- * not release the buffer even if the count goes to 0. If the buffer is not
- * modified within the transaction, decrement the recursion count and
- * release the buffer if the recursion count goes to 0.
+ * Release a buffer previously joined to the transaction. If the buffer is
+ * modified within this transaction, decrement the recursion count but do not
+ * release the buffer even if the count goes to 0. If the buffer is not modified
+ * within the transaction, decrement the recursion count and release the buffer
+ * if the recursion count goes to 0.
*
- * If the buffer is to be released and it was not modified before
- * this transaction began, then free the buf_log_item associated with it.
+ * If the buffer is to be released and it was not already dirty before this
+ * transaction began, then also free the buf_log_item associated with it.
*
- * If the transaction pointer is NULL, make this just a normal
- * brelse() call.
+ * If the transaction pointer is NULL, this is a normal xfs_buf_relse() call.
*/
void
xfs_trans_brelse(
- xfs_trans_t *tp,
- xfs_buf_t *bp)
+ struct xfs_trans *tp,
+ struct xfs_buf *bp)
{
- struct xfs_buf_log_item *bip;
- int freed;
+ struct xfs_buf_log_item *bip = bp->b_log_item;
- /*
- * Default to a normal brelse() call if the tp is NULL.
- */
- if (tp == NULL) {
- ASSERT(bp->b_transp == NULL);
+ ASSERT(bp->b_transp == tp);
+
+ if (!tp) {
xfs_buf_relse(bp);
return;
}
- ASSERT(bp->b_transp == tp);
- bip = bp->b_log_item;
+ trace_xfs_trans_brelse(bip);
ASSERT(bip->bli_item.li_type == XFS_LI_BUF);
- ASSERT(!(bip->bli_flags & XFS_BLI_STALE));
- ASSERT(!(bip->__bli_format.blf_flags & XFS_BLF_CANCEL));
ASSERT(atomic_read(&bip->bli_refcount) > 0);
- trace_xfs_trans_brelse(bip);
-
/*
- * If the release is just for a recursive lock,
- * then decrement the count and return.
+ * If the release is for a recursive lookup, then decrement the count
+ * and return.
*/
if (bip->bli_recur > 0) {
bip->bli_recur--;
@@ -372,64 +361,24 @@ xfs_trans_brelse(
}
/*
- * If the buffer is dirty within this transaction, we can't
+ * If the buffer is invalidated or dirty in this transaction, we can't
* release it until we commit.
*/
if (test_bit(XFS_LI_DIRTY, &bip->bli_item.li_flags))
return;
-
- /*
- * If the buffer has been invalidated, then we can't release
- * it until the transaction commits to disk unless it is re-dirtied
- * as part of this transaction. This prevents us from pulling
- * the item from the AIL before we should.
- */
if (bip->bli_flags & XFS_BLI_STALE)
return;
+ /*
+ * Unlink the log item from the transaction and clear the hold flag, if
+ * set. We wouldn't want the next user of the buffer to get confused.
+ */
ASSERT(!(bip->bli_flags & XFS_BLI_LOGGED));
-
- /*
- * Free up the log item descriptor tracking the released item.
- */
xfs_trans_del_item(&bip->bli_item);
+ bip->bli_flags &= ~XFS_BLI_HOLD;
- /*
- * Clear the hold flag in the buf log item if it is set.
- * We wouldn't want the next user of the buffer to
- * get confused.
- */
- if (bip->bli_flags & XFS_BLI_HOLD) {
- bip->bli_flags &= ~XFS_BLI_HOLD;
- }
-
- /*
- * Drop our reference to the buf log item.
- */
- freed = atomic_dec_and_test(&bip->bli_refcount);
-
- /*
- * If the buf item is not tracking data in the log, then we must free it
- * before releasing the buffer back to the free pool.
- *
- * If the fs has shutdown and we dropped the last reference, it may fall
- * on us to release a (possibly dirty) bli if it never made it to the
- * AIL (e.g., the aborted unpin already happened and didn't release it
- * due to our reference). Since we're already shutdown and need
- * ail_lock, just force remove from the AIL and release the bli here.
- */
- if (XFS_FORCED_SHUTDOWN(tp->t_mountp) && freed) {
- xfs_trans_ail_remove(&bip->bli_item, SHUTDOWN_LOG_IO_ERROR);
- xfs_buf_item_relse(bp);
- } else if (!(bip->bli_flags & XFS_BLI_DIRTY)) {
-/***
- ASSERT(bp->b_pincount == 0);
-***/
- ASSERT(atomic_read(&bip->bli_refcount) == 0);
- ASSERT(!test_bit(XFS_LI_IN_AIL, &bip->bli_item.li_flags));
- ASSERT(!(bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF));
- xfs_buf_item_relse(bp);
- }
+ /* drop the reference to the bli */
+ xfs_buf_item_put(bip);
bp->b_transp = NULL;
xfs_buf_relse(bp);
diff --git a/include/drm/drm_client.h b/include/drm/drm_client.h
index 989f8e5..971bb78 100644
--- a/include/drm/drm_client.h
+++ b/include/drm/drm_client.h
@@ -87,9 +87,10 @@ struct drm_client_dev {
struct drm_file *file;
};
-int drm_client_new(struct drm_device *dev, struct drm_client_dev *client,
- const char *name, const struct drm_client_funcs *funcs);
+int drm_client_init(struct drm_device *dev, struct drm_client_dev *client,
+ const char *name, const struct drm_client_funcs *funcs);
void drm_client_release(struct drm_client_dev *client);
+void drm_client_add(struct drm_client_dev *client);
void drm_client_dev_unregister(struct drm_device *dev);
void drm_client_dev_hotplug(struct drm_device *dev);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 6c0b4a1..897eae8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1828,8 +1828,10 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in,
struct inode *inode_out, loff_t pos_out,
u64 *len, bool is_dedupe);
+extern int do_clone_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out, u64 len);
extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out, u64 len);
+ struct file *file_out, loff_t pos_out, u64 len);
extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
struct inode *dest, loff_t destoff,
loff_t len, bool *is_same);
@@ -2773,19 +2775,6 @@ static inline void file_end_write(struct file *file)
__sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE);
}
-static inline int do_clone_file_range(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out,
- u64 len)
-{
- int ret;
-
- file_start_write(file_out);
- ret = vfs_clone_file_range(file_in, pos_in, file_out, pos_out, len);
- file_end_write(file_out);
-
- return ret;
-}
-
/*
* get_write_access() gets write permission for a file.
* put_write_access() releases this write permission.
diff --git a/include/linux/mlx5/transobj.h b/include/linux/mlx5/transobj.h
index 83a33a1..7f5ca2c 100644
--- a/include/linux/mlx5/transobj.h
+++ b/include/linux/mlx5/transobj.h
@@ -90,6 +90,8 @@ struct mlx5_hairpin {
u32 *rqn;
u32 *sqn;
+
+ bool peer_gone;
};
struct mlx5_hairpin *
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 1e22d96..3f4c0b1 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -671,12 +671,6 @@ typedef struct pglist_data {
#ifdef CONFIG_NUMA_BALANCING
/* Lock serializing the migrate rate limiting window */
spinlock_t numabalancing_migrate_lock;
-
- /* Rate limiting time interval */
- unsigned long numabalancing_migrate_next_window;
-
- /* Number of pages migrated during the rate limiting time interval */
- unsigned long numabalancing_migrate_nr_pages;
#endif
/*
* This is a per-node reserve of pages that are not available
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ca5ab98..c7861e4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1730,6 +1730,8 @@ enum netdev_priv_flags {
* switch driver and used to set the phys state of the
* switch port.
*
+ * @wol_enabled: Wake-on-LAN is enabled
+ *
* FIXME: cleanup struct net_device such that network protocol info
* moves out.
*/
@@ -2014,6 +2016,7 @@ struct net_device {
struct lock_class_key *qdisc_tx_busylock;
struct lock_class_key *qdisc_running_key;
bool proto_down;
+ unsigned wol_enabled:1;
};
#define to_net_dev(d) container_of(d, struct net_device, dev)
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 07efffd0..bbe99d2 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -215,6 +215,8 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net,
break;
case NFPROTO_ARP:
#ifdef CONFIG_NETFILTER_FAMILY_ARP
+ if (WARN_ON_ONCE(hook >= ARRAY_SIZE(net->nf.hooks_arp)))
+ break;
hook_head = rcu_dereference(net->nf.hooks_arp[hook]);
#endif
break;
diff --git a/include/media/v4l2-fh.h b/include/media/v4l2-fh.h
index ea73fef..8586cfb 100644
--- a/include/media/v4l2-fh.h
+++ b/include/media/v4l2-fh.h
@@ -38,10 +38,13 @@ struct v4l2_ctrl_handler;
* @prio: priority of the file handler, as defined by &enum v4l2_priority
*
* @wait: event' s wait queue
+ * @subscribe_lock: serialise changes to the subscribed list; guarantee that
+ * the add and del event callbacks are orderly called
* @subscribed: list of subscribed events
* @available: list of events waiting to be dequeued
* @navailable: number of available events at @available list
* @sequence: event sequence number
+ *
* @m2m_ctx: pointer to &struct v4l2_m2m_ctx
*/
struct v4l2_fh {
@@ -52,6 +55,7 @@ struct v4l2_fh {
/* Events */
wait_queue_head_t wait;
+ struct mutex subscribe_lock;
struct list_head subscribed;
struct list_head available;
unsigned int navailable;
diff --git a/include/net/bonding.h b/include/net/bonding.h
index a2d0581..b46d68a 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -139,12 +139,6 @@ struct bond_parm_tbl {
int mode;
};
-struct netdev_notify_work {
- struct delayed_work work;
- struct net_device *dev;
- struct netdev_bonding_info bonding_info;
-};
-
struct slave {
struct net_device *dev; /* first - useful for panic debug */
struct bonding *bond; /* our master */
@@ -172,6 +166,7 @@ struct slave {
#ifdef CONFIG_NET_POLL_CONTROLLER
struct netpoll *np;
#endif
+ struct delayed_work notify_work;
struct kobject kobj;
struct rtnl_link_stats64 slave_stats;
};
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 8ebabc9..4de121e 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -4852,8 +4852,6 @@ const char *reg_initiator_name(enum nl80211_reg_initiator initiator);
*
* @alpha2: the ISO/IEC 3166 alpha2 wmm rule to be queried.
* @freq: the freqency(in MHz) to be queried.
- * @ptr: pointer where the regdb wmm data is to be stored (or %NULL if
- * irrelevant). This can be used later for deduplication.
* @rule: pointer to store the wmm rule from the regulatory db.
*
* Self-managed wireless drivers can use this function to query
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index e03b933..a80fd0a 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -130,12 +130,6 @@ static inline int inet_request_bound_dev_if(const struct sock *sk,
return sk->sk_bound_dev_if;
}
-static inline struct ip_options_rcu *ireq_opt_deref(const struct inet_request_sock *ireq)
-{
- return rcu_dereference_check(ireq->ireq_opt,
- refcount_read(&ireq->req.rsk_refcnt) > 0);
-}
-
struct inet_cork {
unsigned int flags;
__be32 addr;
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 0c154f9..39e1d87 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -153,7 +153,7 @@
* nla_find() find attribute in stream of attributes
* nla_find_nested() find attribute in nested attributes
* nla_parse() parse and validate stream of attrs
- * nla_parse_nested() parse nested attribuets
+ * nla_parse_nested() parse nested attributes
* nla_for_each_attr() loop over all attributes
* nla_for_each_nested() loop over the nested attributes
*=========================================================================
diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h
index 7113728..705b33d 100644
--- a/include/trace/events/migrate.h
+++ b/include/trace/events/migrate.h
@@ -70,33 +70,6 @@ TRACE_EVENT(mm_migrate_pages,
__print_symbolic(__entry->mode, MIGRATE_MODE),
__print_symbolic(__entry->reason, MIGRATE_REASON))
);
-
-TRACE_EVENT(mm_numa_migrate_ratelimit,
-
- TP_PROTO(struct task_struct *p, int dst_nid, unsigned long nr_pages),
-
- TP_ARGS(p, dst_nid, nr_pages),
-
- TP_STRUCT__entry(
- __array( char, comm, TASK_COMM_LEN)
- __field( pid_t, pid)
- __field( int, dst_nid)
- __field( unsigned long, nr_pages)
- ),
-
- TP_fast_assign(
- memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
- __entry->pid = p->pid;
- __entry->dst_nid = dst_nid;
- __entry->nr_pages = nr_pages;
- ),
-
- TP_printk("comm=%s pid=%d dst_nid=%d nr_pages=%lu",
- __entry->comm,
- __entry->pid,
- __entry->dst_nid,
- __entry->nr_pages)
-);
#endif /* _TRACE_MIGRATE_H */
/* This part must be outside protection */
diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 196587b..837393f 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -56,7 +56,6 @@ enum rxrpc_peer_trace {
rxrpc_peer_new,
rxrpc_peer_processing,
rxrpc_peer_put,
- rxrpc_peer_queued_error,
};
enum rxrpc_conn_trace {
@@ -257,8 +256,7 @@ enum rxrpc_tx_point {
EM(rxrpc_peer_got, "GOT") \
EM(rxrpc_peer_new, "NEW") \
EM(rxrpc_peer_processing, "PRO") \
- EM(rxrpc_peer_put, "PUT") \
- E_(rxrpc_peer_queued_error, "QER")
+ E_(rxrpc_peer_put, "PUT")
#define rxrpc_conn_traces \
EM(rxrpc_conn_got, "GOT") \
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index 0be047d..65a3b7e 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -260,7 +260,7 @@ static void test_cycle_work(struct work_struct *work)
{
struct test_cycle *cycle = container_of(work, typeof(*cycle), work);
struct ww_acquire_ctx ctx;
- int err;
+ int err, erra = 0;
ww_acquire_init(&ctx, &ww_class);
ww_mutex_lock(&cycle->a_mutex, &ctx);
@@ -270,17 +270,19 @@ static void test_cycle_work(struct work_struct *work)
err = ww_mutex_lock(cycle->b_mutex, &ctx);
if (err == -EDEADLK) {
+ err = 0;
ww_mutex_unlock(&cycle->a_mutex);
ww_mutex_lock_slow(cycle->b_mutex, &ctx);
- err = ww_mutex_lock(&cycle->a_mutex, &ctx);
+ erra = ww_mutex_lock(&cycle->a_mutex, &ctx);
}
if (!err)
ww_mutex_unlock(cycle->b_mutex);
- ww_mutex_unlock(&cycle->a_mutex);
+ if (!erra)
+ ww_mutex_unlock(&cycle->a_mutex);
ww_acquire_fini(&ctx);
- cycle->result = err;
+ cycle->result = err ?: erra;
}
static int __test_cycle(unsigned int nthreads)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 625bc98..ad97f3b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1167,7 +1167,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
if (task_cpu(p) != new_cpu) {
if (p->sched_class->migrate_task_rq)
- p->sched_class->migrate_task_rq(p);
+ p->sched_class->migrate_task_rq(p, new_cpu);
p->se.nr_migrations++;
rseq_migrate(p);
perf_event_task_migrate(p);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 997ea7b..91e4202 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1607,7 +1607,7 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
return cpu;
}
-static void migrate_task_rq_dl(struct task_struct *p)
+static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused)
{
struct rq *rq;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f808ddf..7fc4a37 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1392,6 +1392,17 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
int last_cpupid, this_cpupid;
this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid);
+ last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
+
+ /*
+ * Allow first faults or private faults to migrate immediately early in
+ * the lifetime of a task. The magic number 4 is based on waiting for
+ * two full passes of the "multi-stage node selection" test that is
+ * executed below.
+ */
+ if ((p->numa_preferred_nid == -1 || p->numa_scan_seq <= 4) &&
+ (cpupid_pid_unset(last_cpupid) || cpupid_match_pid(p, last_cpupid)))
+ return true;
/*
* Multi-stage node selection is used in conjunction with a periodic
@@ -1410,7 +1421,6 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
* This quadric squishes small probabilities, making it less likely we
* act on an unlikely task<->page relation.
*/
- last_cpupid = page_cpupid_xchg_last(page, this_cpupid);
if (!cpupid_pid_unset(last_cpupid) &&
cpupid_to_nid(last_cpupid) != dst_nid)
return false;
@@ -1514,6 +1524,21 @@ struct task_numa_env {
static void task_numa_assign(struct task_numa_env *env,
struct task_struct *p, long imp)
{
+ struct rq *rq = cpu_rq(env->dst_cpu);
+
+ /* Bail out if run-queue part of active NUMA balance. */
+ if (xchg(&rq->numa_migrate_on, 1))
+ return;
+
+ /*
+ * Clear previous best_cpu/rq numa-migrate flag, since task now
+ * found a better CPU to move/swap.
+ */
+ if (env->best_cpu != -1) {
+ rq = cpu_rq(env->best_cpu);
+ WRITE_ONCE(rq->numa_migrate_on, 0);
+ }
+
if (env->best_task)
put_task_struct(env->best_task);
if (p)
@@ -1553,6 +1578,13 @@ static bool load_too_imbalanced(long src_load, long dst_load,
}
/*
+ * Maximum NUMA importance can be 1998 (2*999);
+ * SMALLIMP @ 30 would be close to 1998/64.
+ * Used to deter task migration.
+ */
+#define SMALLIMP 30
+
+/*
* This checks if the overall compute and NUMA accesses of the system would
* be improved if the source tasks was migrated to the target dst_cpu taking
* into account that it might be best if task running on the dst_cpu should
@@ -1569,6 +1601,9 @@ static void task_numa_compare(struct task_numa_env *env,
long moveimp = imp;
int dist = env->dist;
+ if (READ_ONCE(dst_rq->numa_migrate_on))
+ return;
+
rcu_read_lock();
cur = task_rcu_dereference(&dst_rq->curr);
if (cur && ((cur->flags & PF_EXITING) || is_idle_task(cur)))
@@ -1582,7 +1617,7 @@ static void task_numa_compare(struct task_numa_env *env,
goto unlock;
if (!cur) {
- if (maymove || imp > env->best_imp)
+ if (maymove && moveimp >= env->best_imp)
goto assign;
else
goto unlock;
@@ -1625,16 +1660,22 @@ static void task_numa_compare(struct task_numa_env *env,
task_weight(cur, env->dst_nid, dist);
}
- if (imp <= env->best_imp)
- goto unlock;
-
if (maymove && moveimp > imp && moveimp > env->best_imp) {
- imp = moveimp - 1;
+ imp = moveimp;
cur = NULL;
goto assign;
}
/*
+ * If the NUMA importance is less than SMALLIMP,
+ * task migration might only result in ping pong
+ * of tasks and also hurt performance due to cache
+ * misses.
+ */
+ if (imp < SMALLIMP || imp <= env->best_imp + SMALLIMP / 2)
+ goto unlock;
+
+ /*
* In the overloaded case, try and keep the load balanced.
*/
load = task_h_load(env->p) - task_h_load(cur);
@@ -1710,6 +1751,7 @@ static int task_numa_migrate(struct task_struct *p)
.best_cpu = -1,
};
struct sched_domain *sd;
+ struct rq *best_rq;
unsigned long taskweight, groupweight;
int nid, ret, dist;
long taskimp, groupimp;
@@ -1805,20 +1847,17 @@ static int task_numa_migrate(struct task_struct *p)
if (env.best_cpu == -1)
return -EAGAIN;
- /*
- * Reset the scan period if the task is being rescheduled on an
- * alternative node to recheck if the tasks is now properly placed.
- */
- p->numa_scan_period = task_scan_start(p);
-
+ best_rq = cpu_rq(env.best_cpu);
if (env.best_task == NULL) {
ret = migrate_task_to(p, env.best_cpu);
+ WRITE_ONCE(best_rq->numa_migrate_on, 0);
if (ret != 0)
trace_sched_stick_numa(p, env.src_cpu, env.best_cpu);
return ret;
}
ret = migrate_swap(p, env.best_task, env.best_cpu, env.src_cpu);
+ WRITE_ONCE(best_rq->numa_migrate_on, 0);
if (ret != 0)
trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
@@ -2596,6 +2635,39 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
}
}
+static void update_scan_period(struct task_struct *p, int new_cpu)
+{
+ int src_nid = cpu_to_node(task_cpu(p));
+ int dst_nid = cpu_to_node(new_cpu);
+
+ if (!static_branch_likely(&sched_numa_balancing))
+ return;
+
+ if (!p->mm || !p->numa_faults || (p->flags & PF_EXITING))
+ return;
+
+ if (src_nid == dst_nid)
+ return;
+
+ /*
+ * Allow resets if faults have been trapped before one scan
+ * has completed. This is most likely due to a new task that
+ * is pulled cross-node due to wakeups or load balancing.
+ */
+ if (p->numa_scan_seq) {
+ /*
+ * Avoid scan adjustments if moving to the preferred
+ * node or if the task was not previously running on
+ * the preferred node.
+ */
+ if (dst_nid == p->numa_preferred_nid ||
+ (p->numa_preferred_nid != -1 && src_nid != p->numa_preferred_nid))
+ return;
+ }
+
+ p->numa_scan_period = task_scan_start(p);
+}
+
#else
static void task_tick_numa(struct rq *rq, struct task_struct *curr)
{
@@ -2609,6 +2681,10 @@ static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p)
{
}
+static inline void update_scan_period(struct task_struct *p, int new_cpu)
+{
+}
+
#endif /* CONFIG_NUMA_BALANCING */
static void
@@ -6275,7 +6351,7 @@ static void detach_entity_cfs_rq(struct sched_entity *se);
* cfs_rq_of(p) references at time of call are still valid and identify the
* previous CPU. The caller guarantees p->pi_lock or task_rq(p)->lock is held.
*/
-static void migrate_task_rq_fair(struct task_struct *p)
+static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
{
/*
* As blocked tasks retain absolute vruntime the migration needs to
@@ -6328,6 +6404,8 @@ static void migrate_task_rq_fair(struct task_struct *p)
/* We have migrated, no longer consider this task hot */
p->se.exec_start = 0;
+
+ update_scan_period(p, new_cpu);
}
static void task_dead_fair(struct task_struct *p)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 4a2e8ca..455fa33 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -783,6 +783,7 @@ struct rq {
#ifdef CONFIG_NUMA_BALANCING
unsigned int nr_numa_running;
unsigned int nr_preferred_running;
+ unsigned int numa_migrate_on;
#endif
#define CPU_LOAD_IDX_MAX 5
unsigned long cpu_load[CPU_LOAD_IDX_MAX];
@@ -1523,7 +1524,7 @@ struct sched_class {
#ifdef CONFIG_SMP
int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
- void (*migrate_task_rq)(struct task_struct *p);
+ void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
void (*task_woken)(struct rq *this_rq, struct task_struct *task);
diff --git a/mm/migrate.c b/mm/migrate.c
index d6a2e89..5e285c1 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1855,46 +1855,6 @@ static struct page *alloc_misplaced_dst_page(struct page *page,
return newpage;
}
-/*
- * page migration rate limiting control.
- * Do not migrate more than @pages_to_migrate in a @migrate_interval_millisecs
- * window of time. Default here says do not migrate more than 1280M per second.
- */
-static unsigned int migrate_interval_millisecs __read_mostly = 100;
-static unsigned int ratelimit_pages __read_mostly = 128 << (20 - PAGE_SHIFT);
-
-/* Returns true if the node is migrate rate-limited after the update */
-static bool numamigrate_update_ratelimit(pg_data_t *pgdat,
- unsigned long nr_pages)
-{
- /*
- * Rate-limit the amount of data that is being migrated to a node.
- * Optimal placement is no good if the memory bus is saturated and
- * all the time is being spent migrating!
- */
- if (time_after(jiffies, pgdat->numabalancing_migrate_next_window)) {
- spin_lock(&pgdat->numabalancing_migrate_lock);
- pgdat->numabalancing_migrate_nr_pages = 0;
- pgdat->numabalancing_migrate_next_window = jiffies +
- msecs_to_jiffies(migrate_interval_millisecs);
- spin_unlock(&pgdat->numabalancing_migrate_lock);
- }
- if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) {
- trace_mm_numa_migrate_ratelimit(current, pgdat->node_id,
- nr_pages);
- return true;
- }
-
- /*
- * This is an unlocked non-atomic update so errors are possible.
- * The consequences are failing to migrate when we potentiall should
- * have which is not severe enough to warrant locking. If it is ever
- * a problem, it can be converted to a per-cpu counter.
- */
- pgdat->numabalancing_migrate_nr_pages += nr_pages;
- return false;
-}
-
static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
{
int page_lru;
@@ -1967,14 +1927,6 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
if (page_is_file_cache(page) && PageDirty(page))
goto out;
- /*
- * Rate-limit the amount of data that is being migrated to a node.
- * Optimal placement is no good if the memory bus is saturated and
- * all the time is being spent migrating!
- */
- if (numamigrate_update_ratelimit(pgdat, 1))
- goto out;
-
isolated = numamigrate_isolate_page(pgdat, page);
if (!isolated)
goto out;
@@ -2021,14 +1973,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
unsigned long mmun_start = address & HPAGE_PMD_MASK;
unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE;
- /*
- * Rate-limit the amount of data that is being migrated to a node.
- * Optimal placement is no good if the memory bus is saturated and
- * all the time is being spent migrating!
- */
- if (numamigrate_update_ratelimit(pgdat, HPAGE_PMD_NR))
- goto out_dropref;
-
new_page = alloc_pages_node(node,
(GFP_TRANSHUGE_LIGHT | __GFP_THISNODE),
HPAGE_PMD_ORDER);
@@ -2125,7 +2069,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
out_fail:
count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
-out_dropref:
ptl = pmd_lock(mm, pmd);
if (pmd_same(*pmd, entry)) {
entry = pmd_modify(entry, vma->vm_page_prot);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 89d2a2a..706a738 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6197,8 +6197,6 @@ static unsigned long __init calc_memmap_size(unsigned long spanned_pages,
static void pgdat_init_numabalancing(struct pglist_data *pgdat)
{
spin_lock_init(&pgdat->numabalancing_migrate_lock);
- pgdat->numabalancing_migrate_nr_pages = 0;
- pgdat->numabalancing_migrate_next_window = jiffies;
}
#else
static void pgdat_init_numabalancing(struct pglist_data *pgdat) {}
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 3bdc8f3..ccce954 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -2434,9 +2434,8 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data,
/* LE address type */
addr_type = le_addr_type(cp->addr.type);
- hci_remove_irk(hdev, &cp->addr.bdaddr, addr_type);
-
- err = hci_remove_ltk(hdev, &cp->addr.bdaddr, addr_type);
+ /* Abort any ongoing SMP pairing. Removes ltk and irk if they exist. */
+ err = smp_cancel_and_remove_pairing(hdev, &cp->addr.bdaddr, addr_type);
if (err < 0) {
err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_UNPAIR_DEVICE,
MGMT_STATUS_NOT_PAIRED, &rp,
@@ -2450,8 +2449,6 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data,
goto done;
}
- /* Abort any ongoing SMP pairing */
- smp_cancel_pairing(conn);
/* Defer clearing up the connection parameters until closing to
* give a chance of keeping them if a repairing happens.
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 3a7b077..73f7211d 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -2422,30 +2422,51 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
return ret;
}
-void smp_cancel_pairing(struct hci_conn *hcon)
+int smp_cancel_and_remove_pairing(struct hci_dev *hdev, bdaddr_t *bdaddr,
+ u8 addr_type)
{
- struct l2cap_conn *conn = hcon->l2cap_data;
+ struct hci_conn *hcon;
+ struct l2cap_conn *conn;
struct l2cap_chan *chan;
struct smp_chan *smp;
+ int err;
+ err = hci_remove_ltk(hdev, bdaddr, addr_type);
+ hci_remove_irk(hdev, bdaddr, addr_type);
+
+ hcon = hci_conn_hash_lookup_le(hdev, bdaddr, addr_type);
+ if (!hcon)
+ goto done;
+
+ conn = hcon->l2cap_data;
if (!conn)
- return;
+ goto done;
chan = conn->smp;
if (!chan)
- return;
+ goto done;
l2cap_chan_lock(chan);
smp = chan->data;
if (smp) {
+ /* Set keys to NULL to make sure smp_failure() does not try to
+ * remove and free already invalidated rcu list entries. */
+ smp->ltk = NULL;
+ smp->slave_ltk = NULL;
+ smp->remote_irk = NULL;
+
if (test_bit(SMP_FLAG_COMPLETE, &smp->flags))
smp_failure(conn, 0);
else
smp_failure(conn, SMP_UNSPECIFIED);
+ err = 0;
}
l2cap_chan_unlock(chan);
+
+done:
+ return err;
}
static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb)
diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h
index 0ff6247..121edad 100644
--- a/net/bluetooth/smp.h
+++ b/net/bluetooth/smp.h
@@ -181,7 +181,8 @@ enum smp_key_pref {
};
/* SMP Commands */
-void smp_cancel_pairing(struct hci_conn *hcon);
+int smp_cancel_and_remove_pairing(struct hci_dev *hdev, bdaddr_t *bdaddr,
+ u8 addr_type);
bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level,
enum smp_key_pref key_pref);
int smp_conn_security(struct hci_conn *hcon, __u8 sec_level);
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 6e0dc6b..37278dc 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -835,7 +835,8 @@ static unsigned int ip_sabotage_in(void *priv,
struct sk_buff *skb,
const struct nf_hook_state *state)
{
- if (skb->nf_bridge && !skb->nf_bridge->in_prerouting) {
+ if (skb->nf_bridge && !skb->nf_bridge->in_prerouting &&
+ !netif_is_l3_master(skb->dev)) {
state->okfn(state->net, state->sk, skb);
return NF_STOLEN;
}
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 234a0ec..0762aaf 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -1483,6 +1483,7 @@ static int ethtool_get_wol(struct net_device *dev, char __user *useraddr)
static int ethtool_set_wol(struct net_device *dev, char __user *useraddr)
{
struct ethtool_wolinfo wol;
+ int ret;
if (!dev->ethtool_ops->set_wol)
return -EOPNOTSUPP;
@@ -1490,7 +1491,13 @@ static int ethtool_set_wol(struct net_device *dev, char __user *useraddr)
if (copy_from_user(&wol, useraddr, sizeof(wol)))
return -EFAULT;
- return dev->ethtool_ops->set_wol(dev, &wol);
+ ret = dev->ethtool_ops->set_wol(dev, &wol);
+ if (ret)
+ return ret;
+
+ dev->wol_enabled = !!wol.wolopts;
+
+ return 0;
}
static int ethtool_get_eee(struct net_device *dev, char __user *useraddr)
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 3219a2932..de1d1ba 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -135,27 +135,9 @@ static void queue_process(struct work_struct *work)
}
}
-/*
- * Check whether delayed processing was scheduled for our NIC. If so,
- * we attempt to grab the poll lock and use ->poll() to pump the card.
- * If this fails, either we've recursed in ->poll() or it's already
- * running on another CPU.
- *
- * Note: we don't mask interrupts with this lock because we're using
- * trylock here and interrupts are already disabled in the softirq
- * case. Further, we test the poll_owner to avoid recursion on UP
- * systems where the lock doesn't exist.
- */
static void poll_one_napi(struct napi_struct *napi)
{
- int work = 0;
-
- /* net_rx_action's ->poll() invocations and our's are
- * synchronized by this test which is only made while
- * holding the napi->poll_lock.
- */
- if (!test_bit(NAPI_STATE_SCHED, &napi->state))
- return;
+ int work;
/* If we set this bit but see that it has already been set,
* that indicates that napi has been disabled and we need
@@ -330,6 +312,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
/* It is up to the caller to keep npinfo alive. */
struct netpoll_info *npinfo;
+ rcu_read_lock_bh();
lockdep_assert_irqs_disabled();
npinfo = rcu_dereference_bh(np->dev->npinfo);
@@ -374,6 +357,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
skb_queue_tail(&npinfo->txq, skb);
schedule_delayed_work(&npinfo->tx_work,0);
}
+ rcu_read_unlock_bh();
}
EXPORT_SYMBOL(netpoll_send_skb_on_dev);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 63ce2283..4487033 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1898,10 +1898,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb)
if (tb[IFLA_IF_NETNSID]) {
netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]);
tgt_net = get_target_net(skb->sk, netnsid);
- if (IS_ERR(tgt_net)) {
- tgt_net = net;
- netnsid = -1;
- }
+ if (IS_ERR(tgt_net))
+ return PTR_ERR(tgt_net);
}
if (tb[IFLA_EXT_MASK])
@@ -2837,6 +2835,12 @@ struct net_device *rtnl_create_link(struct net *net,
else if (ops->get_num_rx_queues)
num_rx_queues = ops->get_num_rx_queues();
+ if (num_tx_queues < 1 || num_tx_queues > 4096)
+ return ERR_PTR(-EINVAL);
+
+ if (num_rx_queues < 1 || num_rx_queues > 4096)
+ return ERR_PTR(-EINVAL);
+
dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type,
ops->setup, num_tx_queues, num_rx_queues);
if (!dev)
diff --git a/net/dccp/input.c b/net/dccp/input.c
index d28d46b..85d6c87 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -606,11 +606,13 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
if (sk->sk_state == DCCP_LISTEN) {
if (dh->dccph_type == DCCP_PKT_REQUEST) {
/* It is possible that we process SYN packets from backlog,
- * so we need to make sure to disable BH right there.
+ * so we need to make sure to disable BH and RCU right there.
*/
+ rcu_read_lock();
local_bh_disable();
acceptable = inet_csk(sk)->icsk_af_ops->conn_request(sk, skb) >= 0;
local_bh_enable();
+ rcu_read_unlock();
if (!acceptable)
return 1;
consume_skb(skb);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index b08feb2..8e08cea6 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -493,9 +493,11 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req
dh->dccph_checksum = dccp_v4_csum_finish(skb, ireq->ir_loc_addr,
ireq->ir_rmt_addr);
+ rcu_read_lock();
err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
ireq->ir_rmt_addr,
- ireq_opt_deref(ireq));
+ rcu_dereference(ireq->ireq_opt));
+ rcu_read_unlock();
err = net_xmit_eval(err);
}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index dfd5009..15e7f79 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -544,7 +544,8 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
struct ip_options_rcu *opt;
struct rtable *rt;
- opt = ireq_opt_deref(ireq);
+ rcu_read_lock();
+ opt = rcu_dereference(ireq->ireq_opt);
flowi4_init_output(fl4, ireq->ir_iif, ireq->ir_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
@@ -558,11 +559,13 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
goto no_route;
if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
goto route_err;
+ rcu_read_unlock();
return &rt->dst;
route_err:
ip_rt_put(rt);
no_route:
+ rcu_read_unlock();
__IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
return NULL;
}
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index c0fe5ad..26c36cc 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -149,7 +149,6 @@ static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb)
static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
{
struct sockaddr_in sin;
- const struct iphdr *iph = ip_hdr(skb);
__be16 *ports;
int end;
@@ -164,7 +163,7 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb)
ports = (__be16 *)skb_transport_header(skb);
sin.sin_family = AF_INET;
- sin.sin_addr.s_addr = iph->daddr;
+ sin.sin_addr.s_addr = ip_hdr(skb)->daddr;
sin.sin_port = ports[1];
memset(sin.sin_zero, 0, sizeof(sin.sin_zero));
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index b92f422..891ed2f 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -48,6 +48,7 @@ static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
static int ip_ping_group_range_min[] = { 0, 0 };
static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
static int comp_sack_nr_max = 255;
+static u32 u32_max_div_HZ = UINT_MAX / HZ;
/* obsolete */
static int sysctl_tcp_low_latency __read_mostly;
@@ -745,9 +746,10 @@ static struct ctl_table ipv4_net_table[] = {
{
.procname = "tcp_probe_interval",
.data = &init_net.ipv4.sysctl_tcp_probe_interval,
- .maxlen = sizeof(int),
+ .maxlen = sizeof(u32),
.mode = 0644,
- .proc_handler = proc_dointvec,
+ .proc_handler = proc_douintvec_minmax,
+ .extra2 = &u32_max_div_HZ,
},
{
.procname = "igmp_link_local_mcast_reports",
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4cf2f7b..47e08c1 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6009,11 +6009,13 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
if (th->fin)
goto discard;
/* It is possible that we process SYN packets from backlog,
- * so we need to make sure to disable BH right there.
+ * so we need to make sure to disable BH and RCU right there.
*/
+ rcu_read_lock();
local_bh_disable();
acceptable = icsk->icsk_af_ops->conn_request(sk, skb) >= 0;
local_bh_enable();
+ rcu_read_unlock();
if (!acceptable)
return 1;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 44c09ed..cd42631 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -943,9 +943,11 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
if (skb) {
__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
+ rcu_read_lock();
err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
ireq->ir_rmt_addr,
- ireq_opt_deref(ireq));
+ rcu_dereference(ireq->ireq_opt));
+ rcu_read_unlock();
err = net_xmit_eval(err);
}
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index bcfc00e..f8de248 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -67,6 +67,7 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async)
if (xo && (xo->flags & XFRM_GRO)) {
skb_mac_header_rebuild(skb);
+ skb_reset_transport_header(skb);
return 0;
}
diff --git a/net/ipv4/xfrm4_mode_transport.c b/net/ipv4/xfrm4_mode_transport.c
index 3d36644..1ad2c2c 100644
--- a/net/ipv4/xfrm4_mode_transport.c
+++ b/net/ipv4/xfrm4_mode_transport.c
@@ -46,7 +46,6 @@ static int xfrm4_transport_output(struct xfrm_state *x, struct sk_buff *skb)
static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
{
int ihl = skb->data - skb_transport_header(skb);
- struct xfrm_offload *xo = xfrm_offload(skb);
if (skb->transport_header != skb->network_header) {
memmove(skb_transport_header(skb),
@@ -54,8 +53,7 @@ static int xfrm4_transport_input(struct xfrm_state *x, struct sk_buff *skb)
skb->network_header = skb->transport_header;
}
ip_hdr(skb)->tot_len = htons(skb->len + ihl);
- if (!xo || !(xo->flags & XFRM_GRO))
- skb_reset_transport_header(skb);
+ skb_reset_transport_header(skb);
return 0;
}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 826b14d..a366c05 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -4321,11 +4321,6 @@ static int ip6_route_info_append(struct net *net,
if (!nh)
return -ENOMEM;
nh->fib6_info = rt;
- err = ip6_convert_metrics(net, rt, r_cfg);
- if (err) {
- kfree(nh);
- return err;
- }
memcpy(&nh->r_cfg, r_cfg, sizeof(*r_cfg));
list_add_tail(&nh->next, rt6_nh_list);
diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c
index 841f4a0..9ef490d 100644
--- a/net/ipv6/xfrm6_input.c
+++ b/net/ipv6/xfrm6_input.c
@@ -59,6 +59,7 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async)
if (xo && (xo->flags & XFRM_GRO)) {
skb_mac_header_rebuild(skb);
+ skb_reset_transport_header(skb);
return -1;
}
diff --git a/net/ipv6/xfrm6_mode_transport.c b/net/ipv6/xfrm6_mode_transport.c
index 9ad07a9..3c29da5 100644
--- a/net/ipv6/xfrm6_mode_transport.c
+++ b/net/ipv6/xfrm6_mode_transport.c
@@ -51,7 +51,6 @@ static int xfrm6_transport_output(struct xfrm_state *x, struct sk_buff *skb)
static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb)
{
int ihl = skb->data - skb_transport_header(skb);
- struct xfrm_offload *xo = xfrm_offload(skb);
if (skb->transport_header != skb->network_header) {
memmove(skb_transport_header(skb),
@@ -60,8 +59,7 @@ static int xfrm6_transport_input(struct xfrm_state *x, struct sk_buff *skb)
}
ipv6_hdr(skb)->payload_len = htons(skb->len + ihl -
sizeof(struct ipv6hdr));
- if (!xo || !(xo->flags & XFRM_GRO))
- skb_reset_transport_header(skb);
+ skb_reset_transport_header(skb);
return 0;
}
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index 5959ce9..6a74080 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -170,9 +170,11 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
if (toobig && xfrm6_local_dontfrag(skb)) {
xfrm6_local_rxpmtu(skb, mtu);
+ kfree_skb(skb);
return -EMSGSIZE;
} else if (!skb->ignore_df && toobig && skb->sk) {
xfrm_local_error(skb, mtu);
+ kfree_skb(skb);
return -EMSGSIZE;
}
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 5e6cf2c..5836dde 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1756,7 +1756,8 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name,
if (local->ops->wake_tx_queue &&
type != NL80211_IFTYPE_AP_VLAN &&
- type != NL80211_IFTYPE_MONITOR)
+ (type != NL80211_IFTYPE_MONITOR ||
+ (params->flags & MONITOR_FLAG_ACTIVE)))
txq_size += sizeof(struct txq_info) +
local->hw.txq_data_size;
diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h
index ee56f18..2152663 100644
--- a/net/mac80211/mesh.h
+++ b/net/mac80211/mesh.h
@@ -217,7 +217,8 @@ void mesh_rmc_free(struct ieee80211_sub_if_data *sdata);
int mesh_rmc_init(struct ieee80211_sub_if_data *sdata);
void ieee80211s_init(void);
void ieee80211s_update_metric(struct ieee80211_local *local,
- struct sta_info *sta, struct sk_buff *skb);
+ struct sta_info *sta,
+ struct ieee80211_tx_status *st);
void ieee80211_mesh_init_sdata(struct ieee80211_sub_if_data *sdata);
void ieee80211_mesh_teardown_sdata(struct ieee80211_sub_if_data *sdata);
int ieee80211_start_mesh(struct ieee80211_sub_if_data *sdata);
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index daf9db3..6950cd0 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -295,15 +295,12 @@ int mesh_path_error_tx(struct ieee80211_sub_if_data *sdata,
}
void ieee80211s_update_metric(struct ieee80211_local *local,
- struct sta_info *sta, struct sk_buff *skb)
+ struct sta_info *sta,
+ struct ieee80211_tx_status *st)
{
- struct ieee80211_tx_info *txinfo = IEEE80211_SKB_CB(skb);
- struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
+ struct ieee80211_tx_info *txinfo = st->info;
int failed;
- if (!ieee80211_is_data(hdr->frame_control))
- return;
-
failed = !(txinfo->flags & IEEE80211_TX_STAT_ACK);
/* moving average, scaled to 100.
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 9a6d720..91d7c0c 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -479,11 +479,6 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local,
if (!skb)
return;
- if (dropped) {
- dev_kfree_skb_any(skb);
- return;
- }
-
if (info->flags & IEEE80211_TX_INTFL_NL80211_FRAME_TX) {
u64 cookie = IEEE80211_SKB_CB(skb)->ack.cookie;
struct ieee80211_sub_if_data *sdata;
@@ -507,6 +502,8 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local,
rcu_read_unlock();
dev_kfree_skb_any(skb);
+ } else if (dropped) {
+ dev_kfree_skb_any(skb);
} else {
/* consumes skb */
skb_complete_wifi_ack(skb, acked);
@@ -811,7 +808,7 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
rate_control_tx_status(local, sband, status);
if (ieee80211_vif_is_mesh(&sta->sdata->vif))
- ieee80211s_update_metric(local, sta, skb);
+ ieee80211s_update_metric(local, sta, status);
if (!(info->flags & IEEE80211_TX_CTL_INJECTED) && acked)
ieee80211_frame_acked(sta, skb);
@@ -972,6 +969,8 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw,
}
rate_control_tx_status(local, sband, status);
+ if (ieee80211_vif_is_mesh(&sta->sdata->vif))
+ ieee80211s_update_metric(local, sta, status);
}
if (acked || noack_success) {
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index 5cd5e6e..6c647f4 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -16,6 +16,7 @@
#include "ieee80211_i.h"
#include "driver-ops.h"
#include "rate.h"
+#include "wme.h"
/* give usermode some time for retries in setting up the TDLS session */
#define TDLS_PEER_SETUP_TIMEOUT (15 * HZ)
@@ -1010,14 +1011,13 @@ ieee80211_tdls_prep_mgmt_packet(struct wiphy *wiphy, struct net_device *dev,
switch (action_code) {
case WLAN_TDLS_SETUP_REQUEST:
case WLAN_TDLS_SETUP_RESPONSE:
- skb_set_queue_mapping(skb, IEEE80211_AC_BK);
- skb->priority = 2;
+ skb->priority = 256 + 2;
break;
default:
- skb_set_queue_mapping(skb, IEEE80211_AC_VI);
- skb->priority = 5;
+ skb->priority = 256 + 5;
break;
}
+ skb_set_queue_mapping(skb, ieee80211_select_queue(sdata, skb));
/*
* Set the WLAN_TDLS_TEARDOWN flag to indicate a teardown in progress.
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index f353d9d..25ba24b 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -214,6 +214,7 @@ ieee80211_tx_h_dynamic_ps(struct ieee80211_tx_data *tx)
{
struct ieee80211_local *local = tx->local;
struct ieee80211_if_managed *ifmgd;
+ struct ieee80211_tx_info *info = IEEE80211_SKB_CB(tx->skb);
/* driver doesn't support power save */
if (!ieee80211_hw_check(&local->hw, SUPPORTS_PS))
@@ -242,6 +243,9 @@ ieee80211_tx_h_dynamic_ps(struct ieee80211_tx_data *tx)
if (tx->sdata->vif.type != NL80211_IFTYPE_STATION)
return TX_CONTINUE;
+ if (unlikely(info->flags & IEEE80211_TX_INTFL_OFFCHAN_TX_OK))
+ return TX_CONTINUE;
+
ifmgd = &tx->sdata->u.mgd;
/*
@@ -1890,7 +1894,7 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
sdata->vif.hw_queue[skb_get_queue_mapping(skb)];
if (invoke_tx_handlers_early(&tx))
- return false;
+ return true;
if (ieee80211_queue_skb(local, sdata, tx.sta, tx.skb))
return true;
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index b4bdf9e..247b897 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -1213,8 +1213,8 @@ static const struct nla_policy tcp_nla_policy[CTA_PROTOINFO_TCP_MAX+1] = {
#define TCP_NLATTR_SIZE ( \
NLA_ALIGN(NLA_HDRLEN + 1) + \
NLA_ALIGN(NLA_HDRLEN + 1) + \
- NLA_ALIGN(NLA_HDRLEN + sizeof(sizeof(struct nf_ct_tcp_flags))) + \
- NLA_ALIGN(NLA_HDRLEN + sizeof(sizeof(struct nf_ct_tcp_flags))))
+ NLA_ALIGN(NLA_HDRLEN + sizeof(struct nf_ct_tcp_flags)) + \
+ NLA_ALIGN(NLA_HDRLEN + sizeof(struct nf_ct_tcp_flags)))
static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct)
{
diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c
index 5af74b3..a35fb59 100644
--- a/net/netfilter/nft_osf.c
+++ b/net/netfilter/nft_osf.c
@@ -49,7 +49,7 @@ static int nft_osf_init(const struct nft_ctx *ctx,
priv->dreg = nft_parse_register(tb[NFTA_OSF_DREG]);
err = nft_validate_register_store(ctx, priv->dreg, NULL,
- NFTA_DATA_VALUE, NFT_OSF_MAXGENRELEN);
+ NFT_DATA_VALUE, NFT_OSF_MAXGENRELEN);
if (err < 0)
return err;
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 55e2d92..0e5ec12 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -355,12 +355,11 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
static void nft_rbtree_gc(struct work_struct *work)
{
+ struct nft_rbtree_elem *rbe, *rbe_end = NULL, *rbe_prev = NULL;
struct nft_set_gc_batch *gcb = NULL;
- struct rb_node *node, *prev = NULL;
- struct nft_rbtree_elem *rbe;
struct nft_rbtree *priv;
+ struct rb_node *node;
struct nft_set *set;
- int i;
priv = container_of(work, struct nft_rbtree, gc_work.work);
set = nft_set_container_of(priv);
@@ -371,7 +370,7 @@ static void nft_rbtree_gc(struct work_struct *work)
rbe = rb_entry(node, struct nft_rbtree_elem, node);
if (nft_rbtree_interval_end(rbe)) {
- prev = node;
+ rbe_end = rbe;
continue;
}
if (!nft_set_elem_expired(&rbe->ext))
@@ -379,29 +378,30 @@ static void nft_rbtree_gc(struct work_struct *work)
if (nft_set_elem_mark_busy(&rbe->ext))
continue;
+ if (rbe_prev) {
+ rb_erase(&rbe_prev->node, &priv->root);
+ rbe_prev = NULL;
+ }
gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC);
if (!gcb)
break;
atomic_dec(&set->nelems);
nft_set_gc_batch_add(gcb, rbe);
+ rbe_prev = rbe;
- if (prev) {
- rbe = rb_entry(prev, struct nft_rbtree_elem, node);
+ if (rbe_end) {
atomic_dec(&set->nelems);
- nft_set_gc_batch_add(gcb, rbe);
- prev = NULL;
+ nft_set_gc_batch_add(gcb, rbe_end);
+ rb_erase(&rbe_end->node, &priv->root);
+ rbe_end = NULL;
}
node = rb_next(node);
if (!node)
break;
}
- if (gcb) {
- for (i = 0; i < gcb->head.cnt; i++) {
- rbe = gcb->elems[i];
- rb_erase(&rbe->node, &priv->root);
- }
- }
+ if (rbe_prev)
+ rb_erase(&rbe_prev->node, &priv->root);
write_seqcount_end(&priv->count);
write_unlock_bh(&priv->lock);
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 0472f34..ada144e 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -56,7 +56,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
struct sk_buff *pskb = (struct sk_buff *)skb;
struct sock *sk = skb->sk;
- if (!net_eq(xt_net(par), sock_net(sk)))
+ if (sk && !net_eq(xt_net(par), sock_net(sk)))
sk = NULL;
if (!sk)
@@ -117,7 +117,7 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par)
struct sk_buff *pskb = (struct sk_buff *)skb;
struct sock *sk = skb->sk;
- if (!net_eq(xt_net(par), sock_net(sk)))
+ if (sk && !net_eq(xt_net(par), sock_net(sk)))
sk = NULL;
if (!sk)
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 86a7510..0aeb34c 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1624,10 +1624,6 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
OVS_NLERR(log, "Failed to allocate conntrack template");
return -ENOMEM;
}
-
- __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status);
- nf_conntrack_get(&ct_info.ct->ct_general);
-
if (helper) {
err = ovs_ct_add_helper(&ct_info, helper, key, log);
if (err)
@@ -1639,6 +1635,8 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
if (err)
goto err_free_ct;
+ __set_bit(IPS_CONFIRMED_BIT, &ct_info.ct->status);
+ nf_conntrack_get(&ct_info.ct->ct_general);
return 0;
err_free_ct:
__ovs_ct_free_action(&ct_info);
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index c9755871..ef95541 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -40,17 +40,12 @@ struct rxrpc_crypt {
struct rxrpc_connection;
/*
- * Mark applied to socket buffers.
+ * Mark applied to socket buffers in skb->mark. skb->priority is used
+ * to pass supplementary information.
*/
enum rxrpc_skb_mark {
- RXRPC_SKB_MARK_DATA, /* data message */
- RXRPC_SKB_MARK_FINAL_ACK, /* final ACK received message */
- RXRPC_SKB_MARK_BUSY, /* server busy message */
- RXRPC_SKB_MARK_REMOTE_ABORT, /* remote abort message */
- RXRPC_SKB_MARK_LOCAL_ABORT, /* local abort message */
- RXRPC_SKB_MARK_NET_ERROR, /* network error message */
- RXRPC_SKB_MARK_LOCAL_ERROR, /* local error message */
- RXRPC_SKB_MARK_NEW_CALL, /* local error message */
+ RXRPC_SKB_MARK_REJECT_BUSY, /* Reject with BUSY */
+ RXRPC_SKB_MARK_REJECT_ABORT, /* Reject with ABORT (code in skb->priority) */
};
/*
@@ -293,7 +288,6 @@ struct rxrpc_peer {
struct hlist_node hash_link;
struct rxrpc_local *local;
struct hlist_head error_targets; /* targets for net error distribution */
- struct work_struct error_distributor;
struct rb_root service_conns; /* Service connections */
struct list_head keepalive_link; /* Link in net->peer_keepalive[] */
time64_t last_tx_at; /* Last time packet sent here */
@@ -304,8 +298,6 @@ struct rxrpc_peer {
unsigned int maxdata; /* data size (MTU - hdrsize) */
unsigned short hdrsize; /* header size (IP + UDP + RxRPC) */
int debug_id; /* debug ID for printks */
- int error_report; /* Net (+0) or local (+1000000) to distribute */
-#define RXRPC_LOCAL_ERROR_OFFSET 1000000
struct sockaddr_rxrpc srx; /* remote address */
/* calculated RTT cache */
@@ -463,6 +455,16 @@ struct rxrpc_connection {
u8 out_clientflag; /* RXRPC_CLIENT_INITIATED if we are client */
};
+static inline bool rxrpc_to_server(const struct rxrpc_skb_priv *sp)
+{
+ return sp->hdr.flags & RXRPC_CLIENT_INITIATED;
+}
+
+static inline bool rxrpc_to_client(const struct rxrpc_skb_priv *sp)
+{
+ return !rxrpc_to_server(sp);
+}
+
/*
* Flags in call->flags.
*/
@@ -717,6 +719,8 @@ extern struct workqueue_struct *rxrpc_workqueue;
int rxrpc_service_prealloc(struct rxrpc_sock *, gfp_t);
void rxrpc_discard_prealloc(struct rxrpc_sock *);
struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *,
+ struct rxrpc_sock *,
+ struct rxrpc_peer *,
struct rxrpc_connection *,
struct sk_buff *);
void rxrpc_accept_incoming_calls(struct rxrpc_local *);
@@ -908,7 +912,8 @@ extern unsigned int rxrpc_closed_conn_expiry;
struct rxrpc_connection *rxrpc_alloc_connection(gfp_t);
struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *,
- struct sk_buff *);
+ struct sk_buff *,
+ struct rxrpc_peer **);
void __rxrpc_disconnect_call(struct rxrpc_connection *, struct rxrpc_call *);
void rxrpc_disconnect_call(struct rxrpc_call *);
void rxrpc_kill_connection(struct rxrpc_connection *);
@@ -1031,7 +1036,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *);
* peer_event.c
*/
void rxrpc_error_report(struct sock *);
-void rxrpc_peer_error_distributor(struct work_struct *);
void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace,
rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t);
void rxrpc_peer_keepalive_worker(struct work_struct *);
@@ -1044,13 +1048,11 @@ struct rxrpc_peer *rxrpc_lookup_peer_rcu(struct rxrpc_local *,
struct rxrpc_peer *rxrpc_lookup_peer(struct rxrpc_local *,
struct sockaddr_rxrpc *, gfp_t);
struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *, gfp_t);
-struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *,
- struct rxrpc_peer *);
+void rxrpc_new_incoming_peer(struct rxrpc_local *, struct rxrpc_peer *);
void rxrpc_destroy_all_peers(struct rxrpc_net *);
struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *);
struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *);
void rxrpc_put_peer(struct rxrpc_peer *);
-void __rxrpc_queue_peer_error(struct rxrpc_peer *);
/*
* proc.c
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 9d1e298..9c7f26d 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -249,11 +249,11 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx)
*/
static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
struct rxrpc_local *local,
+ struct rxrpc_peer *peer,
struct rxrpc_connection *conn,
struct sk_buff *skb)
{
struct rxrpc_backlog *b = rx->backlog;
- struct rxrpc_peer *peer, *xpeer;
struct rxrpc_call *call;
unsigned short call_head, conn_head, peer_head;
unsigned short call_tail, conn_tail, peer_tail;
@@ -276,21 +276,18 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
return NULL;
if (!conn) {
- /* No connection. We're going to need a peer to start off
- * with. If one doesn't yet exist, use a spare from the
- * preallocation set. We dump the address into the spare in
- * anticipation - and to save on stack space.
- */
- xpeer = b->peer_backlog[peer_tail];
- if (rxrpc_extract_addr_from_skb(local, &xpeer->srx, skb) < 0)
- return NULL;
-
- peer = rxrpc_lookup_incoming_peer(local, xpeer);
- if (peer == xpeer) {
+ if (peer && !rxrpc_get_peer_maybe(peer))
+ peer = NULL;
+ if (!peer) {
+ peer = b->peer_backlog[peer_tail];
+ if (rxrpc_extract_addr_from_skb(local, &peer->srx, skb) < 0)
+ return NULL;
b->peer_backlog[peer_tail] = NULL;
smp_store_release(&b->peer_backlog_tail,
(peer_tail + 1) &
(RXRPC_BACKLOG_MAX - 1));
+
+ rxrpc_new_incoming_peer(local, peer);
}
/* Now allocate and set up the connection */
@@ -335,45 +332,31 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
* The call is returned with the user access mutex held.
*/
struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
+ struct rxrpc_sock *rx,
+ struct rxrpc_peer *peer,
struct rxrpc_connection *conn,
struct sk_buff *skb)
{
struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
- struct rxrpc_sock *rx;
struct rxrpc_call *call;
- u16 service_id = sp->hdr.serviceId;
_enter("");
- /* Get the socket providing the service */
- rx = rcu_dereference(local->service);
- if (rx && (service_id == rx->srx.srx_service ||
- service_id == rx->second_service))
- goto found_service;
-
- trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
- RX_INVALID_OPERATION, EOPNOTSUPP);
- skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT;
- skb->priority = RX_INVALID_OPERATION;
- _leave(" = NULL [service]");
- return NULL;
-
-found_service:
spin_lock(&rx->incoming_lock);
if (rx->sk.sk_state == RXRPC_SERVER_LISTEN_DISABLED ||
rx->sk.sk_state == RXRPC_CLOSE) {
trace_rxrpc_abort(0, "CLS", sp->hdr.cid, sp->hdr.callNumber,
sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN);
- skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT;
+ skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
skb->priority = RX_INVALID_OPERATION;
_leave(" = NULL [close]");
call = NULL;
goto out;
}
- call = rxrpc_alloc_incoming_call(rx, local, conn, skb);
+ call = rxrpc_alloc_incoming_call(rx, local, peer, conn, skb);
if (!call) {
- skb->mark = RXRPC_SKB_MARK_BUSY;
+ skb->mark = RXRPC_SKB_MARK_REJECT_BUSY;
_leave(" = NULL [busy]");
call = NULL;
goto out;
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index 9486293..799f75b 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -400,7 +400,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx,
rcu_assign_pointer(conn->channels[chan].call, call);
spin_lock(&conn->params.peer->lock);
- hlist_add_head(&call->error_link, &conn->params.peer->error_targets);
+ hlist_add_head_rcu(&call->error_link, &conn->params.peer->error_targets);
spin_unlock(&conn->params.peer->lock);
_net("CALL incoming %d on CONN %d", call->debug_id, call->conn->debug_id);
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index f8f3718..8acf74f 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -710,8 +710,8 @@ int rxrpc_connect_call(struct rxrpc_call *call,
}
spin_lock_bh(&call->conn->params.peer->lock);
- hlist_add_head(&call->error_link,
- &call->conn->params.peer->error_targets);
+ hlist_add_head_rcu(&call->error_link,
+ &call->conn->params.peer->error_targets);
spin_unlock_bh(&call->conn->params.peer->lock);
out:
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 77440a3..885dae8 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -69,10 +69,14 @@ struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp)
* If successful, a pointer to the connection is returned, but no ref is taken.
* NULL is returned if there is no match.
*
+ * When searching for a service call, if we find a peer but no connection, we
+ * return that through *_peer in case we need to create a new service call.
+ *
* The caller must be holding the RCU read lock.
*/
struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
- struct sk_buff *skb)
+ struct sk_buff *skb,
+ struct rxrpc_peer **_peer)
{
struct rxrpc_connection *conn;
struct rxrpc_conn_proto k;
@@ -85,9 +89,6 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
if (rxrpc_extract_addr_from_skb(local, &srx, skb) < 0)
goto not_found;
- k.epoch = sp->hdr.epoch;
- k.cid = sp->hdr.cid & RXRPC_CIDMASK;
-
/* We may have to handle mixing IPv4 and IPv6 */
if (srx.transport.family != local->srx.transport.family) {
pr_warn_ratelimited("AF_RXRPC: Protocol mismatch %u not %u\n",
@@ -99,7 +100,7 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
k.epoch = sp->hdr.epoch;
k.cid = sp->hdr.cid & RXRPC_CIDMASK;
- if (sp->hdr.flags & RXRPC_CLIENT_INITIATED) {
+ if (rxrpc_to_server(sp)) {
/* We need to look up service connections by the full protocol
* parameter set. We look up the peer first as an intermediate
* step and then the connection from the peer's tree.
@@ -107,6 +108,7 @@ struct rxrpc_connection *rxrpc_find_connection_rcu(struct rxrpc_local *local,
peer = rxrpc_lookup_peer_rcu(local, &srx);
if (!peer)
goto not_found;
+ *_peer = peer;
conn = rxrpc_find_service_conn_rcu(peer, skb);
if (!conn || atomic_read(&conn->usage) == 0)
goto not_found;
@@ -214,7 +216,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
call->peer->cong_cwnd = call->cong_cwnd;
spin_lock_bh(&conn->params.peer->lock);
- hlist_del_init(&call->error_link);
+ hlist_del_rcu(&call->error_link);
spin_unlock_bh(&conn->params.peer->lock);
if (rxrpc_is_client_call(call))
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index cfdc199..800f5b8 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -622,13 +622,14 @@ static void rxrpc_input_requested_ack(struct rxrpc_call *call,
if (!skb)
continue;
+ sent_at = skb->tstamp;
+ smp_rmb(); /* Read timestamp before serial. */
sp = rxrpc_skb(skb);
if (sp->hdr.serial != orig_serial)
continue;
- smp_rmb();
- sent_at = skb->tstamp;
goto found;
}
+
return;
found:
@@ -1124,12 +1125,14 @@ void rxrpc_data_ready(struct sock *udp_sk)
{
struct rxrpc_connection *conn;
struct rxrpc_channel *chan;
- struct rxrpc_call *call;
+ struct rxrpc_call *call = NULL;
struct rxrpc_skb_priv *sp;
struct rxrpc_local *local = udp_sk->sk_user_data;
+ struct rxrpc_peer *peer = NULL;
+ struct rxrpc_sock *rx = NULL;
struct sk_buff *skb;
unsigned int channel;
- int ret, skew;
+ int ret, skew = 0;
_enter("%p", udp_sk);
@@ -1143,6 +1146,9 @@ void rxrpc_data_ready(struct sock *udp_sk)
return;
}
+ if (skb->tstamp == 0)
+ skb->tstamp = ktime_get_real();
+
rxrpc_new_skb(skb, rxrpc_skb_rx_received);
_net("recv skb %p", skb);
@@ -1177,46 +1183,75 @@ void rxrpc_data_ready(struct sock *udp_sk)
trace_rxrpc_rx_packet(sp);
- _net("Rx RxRPC %s ep=%x call=%x:%x",
- sp->hdr.flags & RXRPC_CLIENT_INITIATED ? "ToServer" : "ToClient",
- sp->hdr.epoch, sp->hdr.cid, sp->hdr.callNumber);
-
- if (sp->hdr.type >= RXRPC_N_PACKET_TYPES ||
- !((RXRPC_SUPPORTED_PACKET_TYPES >> sp->hdr.type) & 1)) {
- _proto("Rx Bad Packet Type %u", sp->hdr.type);
- goto bad_message;
- }
-
switch (sp->hdr.type) {
case RXRPC_PACKET_TYPE_VERSION:
- if (!(sp->hdr.flags & RXRPC_CLIENT_INITIATED))
+ if (rxrpc_to_client(sp))
goto discard;
rxrpc_post_packet_to_local(local, skb);
goto out;
case RXRPC_PACKET_TYPE_BUSY:
- if (sp->hdr.flags & RXRPC_CLIENT_INITIATED)
+ if (rxrpc_to_server(sp))
goto discard;
/* Fall through */
+ case RXRPC_PACKET_TYPE_ACK:
+ case RXRPC_PACKET_TYPE_ACKALL:
+ if (sp->hdr.callNumber == 0)
+ goto bad_message;
+ /* Fall through */
+ case RXRPC_PACKET_TYPE_ABORT:
+ break;
case RXRPC_PACKET_TYPE_DATA:
- if (sp->hdr.callNumber == 0)
+ if (sp->hdr.callNumber == 0 ||
+ sp->hdr.seq == 0)
goto bad_message;
if (sp->hdr.flags & RXRPC_JUMBO_PACKET &&
!rxrpc_validate_jumbo(skb))
goto bad_message;
break;
+ case RXRPC_PACKET_TYPE_CHALLENGE:
+ if (rxrpc_to_server(sp))
+ goto discard;
+ break;
+ case RXRPC_PACKET_TYPE_RESPONSE:
+ if (rxrpc_to_client(sp))
+ goto discard;
+ break;
+
/* Packet types 9-11 should just be ignored. */
case RXRPC_PACKET_TYPE_PARAMS:
case RXRPC_PACKET_TYPE_10:
case RXRPC_PACKET_TYPE_11:
goto discard;
+
+ default:
+ _proto("Rx Bad Packet Type %u", sp->hdr.type);
+ goto bad_message;
}
+ if (sp->hdr.serviceId == 0)
+ goto bad_message;
+
rcu_read_lock();
- conn = rxrpc_find_connection_rcu(local, skb);
+ if (rxrpc_to_server(sp)) {
+ /* Weed out packets to services we're not offering. Packets
+ * that would begin a call are explicitly rejected and the rest
+ * are just discarded.
+ */
+ rx = rcu_dereference(local->service);
+ if (!rx || (sp->hdr.serviceId != rx->srx.srx_service &&
+ sp->hdr.serviceId != rx->second_service)) {
+ if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA &&
+ sp->hdr.seq == 1)
+ goto unsupported_service;
+ goto discard_unlock;
+ }
+ }
+
+ conn = rxrpc_find_connection_rcu(local, skb, &peer);
if (conn) {
if (sp->hdr.securityIndex != conn->security_ix)
goto wrong_security;
@@ -1280,7 +1315,7 @@ void rxrpc_data_ready(struct sock *udp_sk)
call = rcu_dereference(chan->call);
if (sp->hdr.callNumber > chan->call_id) {
- if (!(sp->hdr.flags & RXRPC_CLIENT_INITIATED)) {
+ if (rxrpc_to_client(sp)) {
rcu_read_unlock();
goto reject_packet;
}
@@ -1297,19 +1332,15 @@ void rxrpc_data_ready(struct sock *udp_sk)
if (!test_bit(RXRPC_CALL_RX_HEARD, &call->flags))
set_bit(RXRPC_CALL_RX_HEARD, &call->flags);
}
- } else {
- skew = 0;
- call = NULL;
}
if (!call || atomic_read(&call->usage) == 0) {
- if (!(sp->hdr.type & RXRPC_CLIENT_INITIATED) ||
- sp->hdr.callNumber == 0 ||
+ if (rxrpc_to_client(sp) ||
sp->hdr.type != RXRPC_PACKET_TYPE_DATA)
goto bad_message_unlock;
if (sp->hdr.seq != 1)
goto discard_unlock;
- call = rxrpc_new_incoming_call(local, conn, skb);
+ call = rxrpc_new_incoming_call(local, rx, peer, conn, skb);
if (!call) {
rcu_read_unlock();
goto reject_packet;
@@ -1340,6 +1371,13 @@ void rxrpc_data_ready(struct sock *udp_sk)
skb->priority = RXKADINCONSISTENCY;
goto post_abort;
+unsupported_service:
+ rcu_read_unlock();
+ trace_rxrpc_abort(0, "INV", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+ RX_INVALID_OPERATION, EOPNOTSUPP);
+ skb->priority = RX_INVALID_OPERATION;
+ goto post_abort;
+
reupgrade:
rcu_read_unlock();
trace_rxrpc_abort(0, "UPG", sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
@@ -1354,7 +1392,7 @@ void rxrpc_data_ready(struct sock *udp_sk)
protocol_error:
skb->priority = RX_PROTOCOL_ERROR;
post_abort:
- skb->mark = RXRPC_SKB_MARK_LOCAL_ABORT;
+ skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
reject_packet:
trace_rxrpc_rx_done(skb->mark, skb->priority);
rxrpc_reject_packet(local, skb);
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 777c3ed..94d234e 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -135,6 +135,29 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
}
switch (local->srx.transport.family) {
+ case AF_INET6:
+ /* we want to receive ICMPv6 errors */
+ opt = 1;
+ ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR,
+ (char *) &opt, sizeof(opt));
+ if (ret < 0) {
+ _debug("setsockopt failed");
+ goto error;
+ }
+
+ /* we want to set the don't fragment bit */
+ opt = IPV6_PMTUDISC_DO;
+ ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER,
+ (char *) &opt, sizeof(opt));
+ if (ret < 0) {
+ _debug("setsockopt failed");
+ goto error;
+ }
+
+ /* Fall through and set IPv4 options too otherwise we don't get
+ * errors from IPv4 packets sent through the IPv6 socket.
+ */
+
case AF_INET:
/* we want to receive ICMP errors */
opt = 1;
@@ -153,22 +176,11 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net)
_debug("setsockopt failed");
goto error;
}
- break;
- case AF_INET6:
- /* we want to receive ICMP errors */
+ /* We want receive timestamps. */
opt = 1;
- ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_RECVERR,
- (char *) &opt, sizeof(opt));
- if (ret < 0) {
- _debug("setsockopt failed");
- goto error;
- }
-
- /* we want to set the don't fragment bit */
- opt = IPV6_PMTUDISC_DO;
- ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER,
- (char *) &opt, sizeof(opt));
+ ret = kernel_setsockopt(local->socket, SOL_SOCKET, SO_TIMESTAMPNS,
+ (char *)&opt, sizeof(opt));
if (ret < 0) {
_debug("setsockopt failed");
goto error;
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index ccf5de1..e8fb892 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -124,7 +124,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
struct kvec iov[2];
rxrpc_serial_t serial;
rxrpc_seq_t hard_ack, top;
- ktime_t now;
size_t len, n;
int ret;
u8 reason;
@@ -196,9 +195,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
/* We need to stick a time in before we send the packet in case
* the reply gets back before kernel_sendmsg() completes - but
* asking UDP to send the packet can take a relatively long
- * time, so we update the time after, on the assumption that
- * the packet transmission is more likely to happen towards the
- * end of the kernel_sendmsg() call.
+ * time.
*/
call->ping_time = ktime_get_real();
set_bit(RXRPC_CALL_PINGING, &call->flags);
@@ -206,9 +203,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
}
ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
- now = ktime_get_real();
- if (ping)
- call->ping_time = now;
conn->params.peer->last_tx_at = ktime_get_seconds();
if (ret < 0)
trace_rxrpc_tx_fail(call->debug_id, serial, ret,
@@ -363,8 +357,14 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
/* If our RTT cache needs working on, request an ACK. Also request
* ACKs if a DATA packet appears to have been lost.
+ *
+ * However, we mustn't request an ACK on the last reply packet of a
+ * service call, lest OpenAFS incorrectly send us an ACK with some
+ * soft-ACKs in it and then never follow up with a proper hard ACK.
*/
- if (!(sp->hdr.flags & RXRPC_LAST_PACKET) &&
+ if ((!(sp->hdr.flags & RXRPC_LAST_PACKET) ||
+ rxrpc_to_server(sp)
+ ) &&
(test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events) ||
retrans ||
call->cong_mode == RXRPC_CALL_SLOW_START ||
@@ -390,6 +390,11 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
goto send_fragmentable;
down_read(&conn->params.local->defrag_sem);
+
+ sp->hdr.serial = serial;
+ smp_wmb(); /* Set serial before timestamp */
+ skb->tstamp = ktime_get_real();
+
/* send the packet by UDP
* - returns -EMSGSIZE if UDP would have to fragment the packet
* to go out of the interface
@@ -413,12 +418,8 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
trace_rxrpc_tx_data(call, sp->hdr.seq, serial, whdr.flags,
retrans, lost);
if (ret >= 0) {
- ktime_t now = ktime_get_real();
- skb->tstamp = now;
- smp_wmb();
- sp->hdr.serial = serial;
if (whdr.flags & RXRPC_REQUEST_ACK) {
- call->peer->rtt_last_req = now;
+ call->peer->rtt_last_req = skb->tstamp;
trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial);
if (call->peer->rtt_usage > 1) {
unsigned long nowj = jiffies, ack_lost_at;
@@ -457,6 +458,10 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
down_write(&conn->params.local->defrag_sem);
+ sp->hdr.serial = serial;
+ smp_wmb(); /* Set serial before timestamp */
+ skb->tstamp = ktime_get_real();
+
switch (conn->params.local->srx.transport.family) {
case AF_INET:
opt = IP_PMTUDISC_DONT;
@@ -519,7 +524,7 @@ void rxrpc_reject_packets(struct rxrpc_local *local)
struct kvec iov[2];
size_t size;
__be32 code;
- int ret;
+ int ret, ioc;
_enter("%d", local->debug_id);
@@ -527,7 +532,6 @@ void rxrpc_reject_packets(struct rxrpc_local *local)
iov[0].iov_len = sizeof(whdr);
iov[1].iov_base = &code;
iov[1].iov_len = sizeof(code);
- size = sizeof(whdr) + sizeof(code);
msg.msg_name = &srx.transport;
msg.msg_control = NULL;
@@ -535,17 +539,31 @@ void rxrpc_reject_packets(struct rxrpc_local *local)
msg.msg_flags = 0;
memset(&whdr, 0, sizeof(whdr));
- whdr.type = RXRPC_PACKET_TYPE_ABORT;
while ((skb = skb_dequeue(&local->reject_queue))) {
rxrpc_see_skb(skb, rxrpc_skb_rx_seen);
sp = rxrpc_skb(skb);
+ switch (skb->mark) {
+ case RXRPC_SKB_MARK_REJECT_BUSY:
+ whdr.type = RXRPC_PACKET_TYPE_BUSY;
+ size = sizeof(whdr);
+ ioc = 1;
+ break;
+ case RXRPC_SKB_MARK_REJECT_ABORT:
+ whdr.type = RXRPC_PACKET_TYPE_ABORT;
+ code = htonl(skb->priority);
+ size = sizeof(whdr) + sizeof(code);
+ ioc = 2;
+ break;
+ default:
+ rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
+ continue;
+ }
+
if (rxrpc_extract_addr_from_skb(local, &srx, skb) == 0) {
msg.msg_namelen = srx.transport_len;
- code = htonl(skb->priority);
-
whdr.epoch = htonl(sp->hdr.epoch);
whdr.cid = htonl(sp->hdr.cid);
whdr.callNumber = htonl(sp->hdr.callNumber);
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index 4f9da2f..f3e6fc6 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -23,6 +23,8 @@
#include "ar-internal.h"
static void rxrpc_store_error(struct rxrpc_peer *, struct sock_exterr_skb *);
+static void rxrpc_distribute_error(struct rxrpc_peer *, int,
+ enum rxrpc_call_completion);
/*
* Find the peer associated with an ICMP packet.
@@ -194,8 +196,6 @@ void rxrpc_error_report(struct sock *sk)
rcu_read_unlock();
rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
- /* The ref we obtained is passed off to the work item */
- __rxrpc_queue_peer_error(peer);
_leave("");
}
@@ -205,6 +205,7 @@ void rxrpc_error_report(struct sock *sk)
static void rxrpc_store_error(struct rxrpc_peer *peer,
struct sock_exterr_skb *serr)
{
+ enum rxrpc_call_completion compl = RXRPC_CALL_NETWORK_ERROR;
struct sock_extended_err *ee;
int err;
@@ -255,7 +256,7 @@ static void rxrpc_store_error(struct rxrpc_peer *peer,
case SO_EE_ORIGIN_NONE:
case SO_EE_ORIGIN_LOCAL:
_proto("Rx Received local error { error=%d }", err);
- err += RXRPC_LOCAL_ERROR_OFFSET;
+ compl = RXRPC_CALL_LOCAL_ERROR;
break;
case SO_EE_ORIGIN_ICMP6:
@@ -264,48 +265,23 @@ static void rxrpc_store_error(struct rxrpc_peer *peer,
break;
}
- peer->error_report = err;
+ rxrpc_distribute_error(peer, err, compl);
}
/*
- * Distribute an error that occurred on a peer
+ * Distribute an error that occurred on a peer.
*/
-void rxrpc_peer_error_distributor(struct work_struct *work)
+static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error,
+ enum rxrpc_call_completion compl)
{
- struct rxrpc_peer *peer =
- container_of(work, struct rxrpc_peer, error_distributor);
struct rxrpc_call *call;
- enum rxrpc_call_completion compl;
- int error;
- _enter("");
-
- error = READ_ONCE(peer->error_report);
- if (error < RXRPC_LOCAL_ERROR_OFFSET) {
- compl = RXRPC_CALL_NETWORK_ERROR;
- } else {
- compl = RXRPC_CALL_LOCAL_ERROR;
- error -= RXRPC_LOCAL_ERROR_OFFSET;
- }
-
- _debug("ISSUE ERROR %s %d", rxrpc_call_completions[compl], error);
-
- spin_lock_bh(&peer->lock);
-
- while (!hlist_empty(&peer->error_targets)) {
- call = hlist_entry(peer->error_targets.first,
- struct rxrpc_call, error_link);
- hlist_del_init(&call->error_link);
+ hlist_for_each_entry_rcu(call, &peer->error_targets, error_link) {
rxrpc_see_call(call);
-
- if (rxrpc_set_call_completion(call, compl, 0, -error))
+ if (call->state < RXRPC_CALL_COMPLETE &&
+ rxrpc_set_call_completion(call, compl, 0, -error))
rxrpc_notify_socket(call);
}
-
- spin_unlock_bh(&peer->lock);
-
- rxrpc_put_peer(peer);
- _leave("");
}
/*
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 1dc7648..01a9feb 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -124,11 +124,9 @@ static struct rxrpc_peer *__rxrpc_lookup_peer_rcu(
struct rxrpc_net *rxnet = local->rxnet;
hash_for_each_possible_rcu(rxnet->peer_hash, peer, hash_link, hash_key) {
- if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0) {
- if (atomic_read(&peer->usage) == 0)
- return NULL;
+ if (rxrpc_peer_cmp_key(peer, local, srx, hash_key) == 0 &&
+ atomic_read(&peer->usage) > 0)
return peer;
- }
}
return NULL;
@@ -222,8 +220,6 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp)
atomic_set(&peer->usage, 1);
peer->local = local;
INIT_HLIST_HEAD(&peer->error_targets);
- INIT_WORK(&peer->error_distributor,
- &rxrpc_peer_error_distributor);
peer->service_conns = RB_ROOT;
seqlock_init(&peer->service_conn_lock);
spin_lock_init(&peer->lock);
@@ -299,34 +295,23 @@ static struct rxrpc_peer *rxrpc_create_peer(struct rxrpc_local *local,
}
/*
- * Set up a new incoming peer. The address is prestored in the preallocated
- * peer.
+ * Set up a new incoming peer. There shouldn't be any other matching peers
+ * since we've already done a search in the list from the non-reentrant context
+ * (the data_ready handler) that is the only place we can add new peers.
*/
-struct rxrpc_peer *rxrpc_lookup_incoming_peer(struct rxrpc_local *local,
- struct rxrpc_peer *prealloc)
+void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer)
{
- struct rxrpc_peer *peer;
struct rxrpc_net *rxnet = local->rxnet;
unsigned long hash_key;
- hash_key = rxrpc_peer_hash_key(local, &prealloc->srx);
- prealloc->local = local;
- rxrpc_init_peer(prealloc, hash_key);
+ hash_key = rxrpc_peer_hash_key(local, &peer->srx);
+ peer->local = local;
+ rxrpc_init_peer(peer, hash_key);
spin_lock(&rxnet->peer_hash_lock);
-
- /* Need to check that we aren't racing with someone else */
- peer = __rxrpc_lookup_peer_rcu(local, &prealloc->srx, hash_key);
- if (peer && !rxrpc_get_peer_maybe(peer))
- peer = NULL;
- if (!peer) {
- peer = prealloc;
- hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
- list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new);
- }
-
+ hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
+ list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new);
spin_unlock(&rxnet->peer_hash_lock);
- return peer;
}
/*
@@ -416,21 +401,6 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer)
}
/*
- * Queue a peer record. This passes the caller's ref to the workqueue.
- */
-void __rxrpc_queue_peer_error(struct rxrpc_peer *peer)
-{
- const void *here = __builtin_return_address(0);
- int n;
-
- n = atomic_read(&peer->usage);
- if (rxrpc_queue_work(&peer->error_distributor))
- trace_rxrpc_peer(peer, rxrpc_peer_queued_error, n, here);
- else
- rxrpc_put_peer(peer);
-}
-
-/*
* Discard a peer record.
*/
static void __rxrpc_put_peer(struct rxrpc_peer *peer)
diff --git a/net/rxrpc/protocol.h b/net/rxrpc/protocol.h
index 93da73b..f9cb83c 100644
--- a/net/rxrpc/protocol.h
+++ b/net/rxrpc/protocol.h
@@ -50,7 +50,6 @@ struct rxrpc_wire_header {
#define RXRPC_PACKET_TYPE_10 10 /* Ignored */
#define RXRPC_PACKET_TYPE_11 11 /* Ignored */
#define RXRPC_PACKET_TYPE_VERSION 13 /* version string request */
-#define RXRPC_N_PACKET_TYPES 14 /* number of packet types (incl type 0) */
uint8_t flags; /* packet flags */
#define RXRPC_CLIENT_INITIATED 0x01 /* signifies a packet generated by a client */
@@ -72,20 +71,6 @@ struct rxrpc_wire_header {
} __packed;
-#define RXRPC_SUPPORTED_PACKET_TYPES ( \
- (1 << RXRPC_PACKET_TYPE_DATA) | \
- (1 << RXRPC_PACKET_TYPE_ACK) | \
- (1 << RXRPC_PACKET_TYPE_BUSY) | \
- (1 << RXRPC_PACKET_TYPE_ABORT) | \
- (1 << RXRPC_PACKET_TYPE_ACKALL) | \
- (1 << RXRPC_PACKET_TYPE_CHALLENGE) | \
- (1 << RXRPC_PACKET_TYPE_RESPONSE) | \
- /*(1 << RXRPC_PACKET_TYPE_DEBUG) | */ \
- (1 << RXRPC_PACKET_TYPE_PARAMS) | \
- (1 << RXRPC_PACKET_TYPE_10) | \
- (1 << RXRPC_PACKET_TYPE_11) | \
- (1 << RXRPC_PACKET_TYPE_VERSION))
-
/*****************************************************************************/
/*
* jumbo packet secondary header
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 23273b5..8525de81 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -135,7 +135,7 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
}
td = (struct xt_entry_target *)nla_data(tb[TCA_IPT_TARG]);
- if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size) {
+ if (nla_len(tb[TCA_IPT_TARG]) != td->u.target_size) {
if (exists)
tcf_idr_release(*a, bind);
else
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index d74d00b..42191ed 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -1048,7 +1048,7 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx,
if (!ctx->packet || !ctx->packet->has_cookie_echo)
return;
- /* fallthru */
+ /* fall through */
case SCTP_STATE_ESTABLISHED:
case SCTP_STATE_SHUTDOWN_PENDING:
case SCTP_STATE_SHUTDOWN_RECEIVED:
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 418f03d..645c160 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -609,16 +609,18 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt,
switch (evt) {
case NETDEV_CHANGE:
- if (netif_carrier_ok(dev))
+ if (netif_carrier_ok(dev) && netif_oper_up(dev)) {
+ test_and_set_bit_lock(0, &b->up);
break;
- /* else: fall through */
- case NETDEV_UP:
- test_and_set_bit_lock(0, &b->up);
- break;
+ }
+ /* fall through */
case NETDEV_GOING_DOWN:
clear_bit_unlock(0, &b->up);
tipc_reset_bearer(net, b);
break;
+ case NETDEV_UP:
+ test_and_set_bit_lock(0, &b->up);
+ break;
case NETDEV_CHANGEMTU:
if (tipc_mtu_bad(dev, 0)) {
bearer_disable(net, b);
diff --git a/net/tipc/link.c b/net/tipc/link.c
index b1f0bee..fb886b5 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -410,6 +410,11 @@ char *tipc_link_name(struct tipc_link *l)
return l->name;
}
+u32 tipc_link_state(struct tipc_link *l)
+{
+ return l->state;
+}
+
/**
* tipc_link_create - create a new link
* @n: pointer to associated node
@@ -841,9 +846,14 @@ void tipc_link_reset(struct tipc_link *l)
l->in_session = false;
l->session++;
l->mtu = l->advertised_mtu;
+ spin_lock_bh(&l->wakeupq.lock);
+ spin_lock_bh(&l->inputq->lock);
+ skb_queue_splice_init(&l->wakeupq, l->inputq);
+ spin_unlock_bh(&l->inputq->lock);
+ spin_unlock_bh(&l->wakeupq.lock);
+
__skb_queue_purge(&l->transmq);
__skb_queue_purge(&l->deferdq);
- skb_queue_splice_init(&l->wakeupq, l->inputq);
__skb_queue_purge(&l->backlogq);
l->backlog[TIPC_LOW_IMPORTANCE].len = 0;
l->backlog[TIPC_MEDIUM_IMPORTANCE].len = 0;
@@ -1380,6 +1390,36 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
__skb_queue_tail(xmitq, skb);
}
+void tipc_link_create_dummy_tnl_msg(struct tipc_link *l,
+ struct sk_buff_head *xmitq)
+{
+ u32 onode = tipc_own_addr(l->net);
+ struct tipc_msg *hdr, *ihdr;
+ struct sk_buff_head tnlq;
+ struct sk_buff *skb;
+ u32 dnode = l->addr;
+
+ skb_queue_head_init(&tnlq);
+ skb = tipc_msg_create(TUNNEL_PROTOCOL, FAILOVER_MSG,
+ INT_H_SIZE, BASIC_H_SIZE,
+ dnode, onode, 0, 0, 0);
+ if (!skb) {
+ pr_warn("%sunable to create tunnel packet\n", link_co_err);
+ return;
+ }
+
+ hdr = buf_msg(skb);
+ msg_set_msgcnt(hdr, 1);
+ msg_set_bearer_id(hdr, l->peer_bearer_id);
+
+ ihdr = (struct tipc_msg *)msg_data(hdr);
+ tipc_msg_init(onode, ihdr, TIPC_LOW_IMPORTANCE, TIPC_DIRECT_MSG,
+ BASIC_H_SIZE, dnode);
+ msg_set_errcode(ihdr, TIPC_ERR_NO_PORT);
+ __skb_queue_tail(&tnlq, skb);
+ tipc_link_xmit(l, &tnlq, xmitq);
+}
+
/* tipc_link_tnl_prepare(): prepare and return a list of tunnel packets
* with contents of the link's transmit and backlog queues.
*/
@@ -1476,6 +1516,9 @@ bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr)
return false;
if (session != curr_session)
return false;
+ /* Extra sanity check */
+ if (!link_is_up(l) && msg_ack(hdr))
+ return false;
if (!(l->peer_caps & TIPC_LINK_PROTO_SEQNO))
return true;
/* Accept only STATE with new sequence number */
diff --git a/net/tipc/link.h b/net/tipc/link.h
index 7bc494a3..90488c5 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -88,6 +88,8 @@ bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer,
struct tipc_link **link);
void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl,
int mtyp, struct sk_buff_head *xmitq);
+void tipc_link_create_dummy_tnl_msg(struct tipc_link *tnl,
+ struct sk_buff_head *xmitq);
void tipc_link_build_reset_msg(struct tipc_link *l, struct sk_buff_head *xmitq);
int tipc_link_fsm_evt(struct tipc_link *l, int evt);
bool tipc_link_is_up(struct tipc_link *l);
@@ -107,6 +109,7 @@ u16 tipc_link_rcv_nxt(struct tipc_link *l);
u16 tipc_link_acked(struct tipc_link *l);
u32 tipc_link_id(struct tipc_link *l);
char *tipc_link_name(struct tipc_link *l);
+u32 tipc_link_state(struct tipc_link *l);
char tipc_link_plane(struct tipc_link *l);
int tipc_link_prio(struct tipc_link *l);
int tipc_link_window(struct tipc_link *l);
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 68014f1..2afc4f8 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -111,6 +111,7 @@ struct tipc_node {
int action_flags;
struct list_head list;
int state;
+ bool failover_sent;
u16 sync_point;
int link_cnt;
u16 working_links;
@@ -680,6 +681,7 @@ static void __tipc_node_link_up(struct tipc_node *n, int bearer_id,
*slot0 = bearer_id;
*slot1 = bearer_id;
tipc_node_fsm_evt(n, SELF_ESTABL_CONTACT_EVT);
+ n->failover_sent = false;
n->action_flags |= TIPC_NOTIFY_NODE_UP;
tipc_link_set_active(nl, true);
tipc_bcast_add_peer(n->net, nl, xmitq);
@@ -911,6 +913,7 @@ void tipc_node_check_dest(struct net *net, u32 addr,
bool reset = true;
char *if_name;
unsigned long intv;
+ u16 session;
*dupl_addr = false;
*respond = false;
@@ -997,9 +1000,10 @@ void tipc_node_check_dest(struct net *net, u32 addr,
goto exit;
if_name = strchr(b->name, ':') + 1;
+ get_random_bytes(&session, sizeof(u16));
if (!tipc_link_create(net, if_name, b->identity, b->tolerance,
b->net_plane, b->mtu, b->priority,
- b->window, mod(tipc_net(net)->random),
+ b->window, session,
tipc_own_addr(net), addr, peer_id,
n->capabilities,
tipc_bc_sndlink(n->net), n->bc_entry.link,
@@ -1615,6 +1619,14 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
tipc_skb_queue_splice_tail_init(tipc_link_inputq(pl),
tipc_link_inputq(l));
}
+ /* If parallel link was already down, and this happened before
+ * the tunnel link came up, FAILOVER was never sent. Ensure that
+ * FAILOVER is sent to get peer out of NODE_FAILINGOVER state.
+ */
+ if (n->state != NODE_FAILINGOVER && !n->failover_sent) {
+ tipc_link_create_dummy_tnl_msg(l, xmitq);
+ n->failover_sent = true;
+ }
/* If pkts arrive out of order, use lowest calculated syncpt */
if (less(syncpt, n->sync_point))
n->sync_point = syncpt;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 3f03ddd..b6f99b0 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1419,8 +1419,10 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen)
/* Handle implicit connection setup */
if (unlikely(dest)) {
rc = __tipc_sendmsg(sock, m, dlen);
- if (dlen && (dlen == rc))
+ if (dlen && dlen == rc) {
+ tsk->peer_caps = tipc_node_get_capabilities(net, dnode);
tsk->snt_unacked = tsk_inc(tsk, dlen + msg_hdr_sz(hdr));
+ }
return rc;
}
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 4b8ec65..176edfe 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3756,6 +3756,7 @@ static bool ht_rateset_to_mask(struct ieee80211_supported_band *sband,
return false;
/* check availability */
+ ridx = array_index_nospec(ridx, IEEE80211_HT_MCS_MASK_LEN);
if (sband->ht_cap.mcs.rx_mask[ridx] & rbit)
mcs[ridx] |= rbit;
else
@@ -10230,7 +10231,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev,
struct wireless_dev *wdev = dev->ieee80211_ptr;
s32 last, low, high;
u32 hyst;
- int i, n;
+ int i, n, low_index;
int err;
/* RSSI reporting disabled? */
@@ -10267,10 +10268,19 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev,
if (last < wdev->cqm_config->rssi_thresholds[i])
break;
- low = i > 0 ?
- (wdev->cqm_config->rssi_thresholds[i - 1] - hyst) : S32_MIN;
- high = i < n ?
- (wdev->cqm_config->rssi_thresholds[i] + hyst - 1) : S32_MAX;
+ low_index = i - 1;
+ if (low_index >= 0) {
+ low_index = array_index_nospec(low_index, n);
+ low = wdev->cqm_config->rssi_thresholds[low_index] - hyst;
+ } else {
+ low = S32_MIN;
+ }
+ if (i < n) {
+ i = array_index_nospec(i, n);
+ high = wdev->cqm_config->rssi_thresholds[i] + hyst - 1;
+ } else {
+ high = S32_MAX;
+ }
return rdev_set_cqm_rssi_range_config(rdev, dev, low, high);
}
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 2f702ad..765dedb 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -2867,6 +2867,7 @@ static int regulatory_hint_core(const char *alpha2)
request->alpha2[0] = alpha2[0];
request->alpha2[1] = alpha2[1];
request->initiator = NL80211_REGDOM_SET_BY_CORE;
+ request->wiphy_idx = WIPHY_IDX_INVALID;
queue_regulatory_request(request);
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index d36c3eb..d0e7472 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1058,13 +1058,23 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev,
return NULL;
}
+/*
+ * Update RX channel information based on the available frame payload
+ * information. This is mainly for the 2.4 GHz band where frames can be received
+ * from neighboring channels and the Beacon frames use the DSSS Parameter Set
+ * element to indicate the current (transmitting) channel, but this might also
+ * be needed on other bands if RX frequency does not match with the actual
+ * operating channel of a BSS.
+ */
static struct ieee80211_channel *
cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen,
- struct ieee80211_channel *channel)
+ struct ieee80211_channel *channel,
+ enum nl80211_bss_scan_width scan_width)
{
const u8 *tmp;
u32 freq;
int channel_number = -1;
+ struct ieee80211_channel *alt_channel;
tmp = cfg80211_find_ie(WLAN_EID_DS_PARAMS, ie, ielen);
if (tmp && tmp[1] == 1) {
@@ -1078,16 +1088,45 @@ cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen,
}
}
- if (channel_number < 0)
+ if (channel_number < 0) {
+ /* No channel information in frame payload */
return channel;
+ }
freq = ieee80211_channel_to_frequency(channel_number, channel->band);
- channel = ieee80211_get_channel(wiphy, freq);
- if (!channel)
+ alt_channel = ieee80211_get_channel(wiphy, freq);
+ if (!alt_channel) {
+ if (channel->band == NL80211_BAND_2GHZ) {
+ /*
+ * Better not allow unexpected channels when that could
+ * be going beyond the 1-11 range (e.g., discovering
+ * BSS on channel 12 when radio is configured for
+ * channel 11.
+ */
+ return NULL;
+ }
+
+ /* No match for the payload channel number - ignore it */
+ return channel;
+ }
+
+ if (scan_width == NL80211_BSS_CHAN_WIDTH_10 ||
+ scan_width == NL80211_BSS_CHAN_WIDTH_5) {
+ /*
+ * Ignore channel number in 5 and 10 MHz channels where there
+ * may not be an n:1 or 1:n mapping between frequencies and
+ * channel numbers.
+ */
+ return channel;
+ }
+
+ /*
+ * Use the channel determined through the payload channel number
+ * instead of the RX channel reported by the driver.
+ */
+ if (alt_channel->flags & IEEE80211_CHAN_DISABLED)
return NULL;
- if (channel->flags & IEEE80211_CHAN_DISABLED)
- return NULL;
- return channel;
+ return alt_channel;
}
/* Returned bss is reference counted and must be cleaned up appropriately. */
@@ -1112,7 +1151,8 @@ cfg80211_inform_bss_data(struct wiphy *wiphy,
(data->signal < 0 || data->signal > 100)))
return NULL;
- channel = cfg80211_get_bss_channel(wiphy, ie, ielen, data->chan);
+ channel = cfg80211_get_bss_channel(wiphy, ie, ielen, data->chan,
+ data->scan_width);
if (!channel)
return NULL;
@@ -1210,7 +1250,7 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
return NULL;
channel = cfg80211_get_bss_channel(wiphy, mgmt->u.beacon.variable,
- ielen, data->chan);
+ ielen, data->chan, data->scan_width);
if (!channel)
return NULL;
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index b89c9c7..be3520e 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -458,6 +458,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
goto drop;
}
+ crypto_done = false;
} while (!err);
err = xfrm_rcv_cb(skb, family, x->type->proto, 0);
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 45ba07a..261995d3 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -100,6 +100,10 @@ static int xfrm_output_one(struct sk_buff *skb, int err)
spin_unlock_bh(&x->lock);
skb_dst_force(skb);
+ if (!skb_dst(skb)) {
+ XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
+ goto error_nolock;
+ }
if (xfrm_offload(skb)) {
x->type_offload->encap(x, skb);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 3110c3f..f094d4b 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -2491,6 +2491,10 @@ int __xfrm_route_forward(struct sk_buff *skb, unsigned short family)
}
skb_dst_force(skb);
+ if (!skb_dst(skb)) {
+ XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR);
+ return 0;
+ }
dst = xfrm_lookup(net, skb_dst(skb), &fl, NULL, XFRM_LOOKUP_QUEUE);
if (IS_ERR(dst)) {
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 4791aa8..df7ca2d 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -151,10 +151,16 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
err = -EINVAL;
switch (p->family) {
case AF_INET:
+ if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32)
+ goto out;
+
break;
case AF_INET6:
#if IS_ENABLED(CONFIG_IPV6)
+ if (p->sel.prefixlen_d > 128 || p->sel.prefixlen_s > 128)
+ goto out;
+
break;
#else
err = -EAFNOSUPPORT;
@@ -1396,10 +1402,16 @@ static int verify_newpolicy_info(struct xfrm_userpolicy_info *p)
switch (p->sel.family) {
case AF_INET:
+ if (p->sel.prefixlen_d > 32 || p->sel.prefixlen_s > 32)
+ return -EINVAL;
+
break;
case AF_INET6:
#if IS_ENABLED(CONFIG_IPV6)
+ if (p->sel.prefixlen_d > 128 || p->sel.prefixlen_s > 128)
+ return -EINVAL;
+
break;
#else
return -EAFNOSUPPORT;
@@ -1480,6 +1492,9 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family)
(ut[i].family != prev_family))
return -EINVAL;
+ if (ut[i].mode >= XFRM_MODE_MAX)
+ return -EINVAL;
+
prev_family = ut[i].family;
switch (ut[i].family) {
diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c
index b5282cbb..617ff1a 100644
--- a/sound/hda/hdac_i915.c
+++ b/sound/hda/hdac_i915.c
@@ -145,9 +145,11 @@ int snd_hdac_i915_init(struct hdac_bus *bus)
if (!acomp->ops) {
request_module("i915");
/* 10s timeout */
- wait_for_completion_timeout(&bind_complete, 10 * 1000);
+ wait_for_completion_timeout(&bind_complete,
+ msecs_to_jiffies(10 * 1000));
}
if (!acomp->ops) {
+ dev_info(bus->dev, "couldn't bind with audio component\n");
snd_hdac_acomp_exit(bus);
return -ENODEV;
}
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 1d117f0..3ac7ba9 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -6409,6 +6409,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
SND_PCI_QUIRK(0x1028, 0x0706, "Dell Inspiron 7559", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER),
SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE),
SND_PCI_QUIRK(0x1028, 0x075b, "Dell XPS 13 9360", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE),
+ SND_PCI_QUIRK(0x1028, 0x075c, "Dell XPS 27 7760", ALC298_FIXUP_SPK_VOLUME),
SND_PCI_QUIRK(0x1028, 0x075d, "Dell AIO", ALC298_FIXUP_SPK_VOLUME),
SND_PCI_QUIRK(0x1028, 0x07b0, "Dell Precision 7520", ALC295_FIXUP_DISABLE_DAC3),
SND_PCI_QUIRK(0x1028, 0x0798, "Dell Inspiron 17 7000 Gaming", ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER),
diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index 439b8a2..195ba48 100755
--- a/tools/kvm/kvm_stat/kvm_stat
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -1325,7 +1325,7 @@
msg = ''
while True:
self.screen.erase()
- self.screen.addstr(0, 0, 'Set update interval (defaults to %fs).' %
+ self.screen.addstr(0, 0, 'Set update interval (defaults to %.1fs).' %
DELAY_DEFAULT, curses.A_BOLD)
self.screen.addstr(4, 0, msg)
self.screen.addstr(2, 0, 'Change delay from %.1fs to ' %
diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index 642d4e1..eec2663 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -56,15 +56,13 @@ unsigned int yield_mod_cnt, nr_abort;
printf(fmt, ## __VA_ARGS__); \
} while (0)
-#if defined(__x86_64__) || defined(__i386__)
+#ifdef __i386__
#define INJECT_ASM_REG "eax"
#define RSEQ_INJECT_CLOBBER \
, INJECT_ASM_REG
-#ifdef __i386__
-
#define RSEQ_INJECT_ASM(n) \
"mov asm_loop_cnt_" #n ", %%" INJECT_ASM_REG "\n\t" \
"test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \
@@ -76,9 +74,16 @@ unsigned int yield_mod_cnt, nr_abort;
#elif defined(__x86_64__)
+#define INJECT_ASM_REG_P "rax"
+#define INJECT_ASM_REG "eax"
+
+#define RSEQ_INJECT_CLOBBER \
+ , INJECT_ASM_REG_P \
+ , INJECT_ASM_REG
+
#define RSEQ_INJECT_ASM(n) \
- "lea asm_loop_cnt_" #n "(%%rip), %%" INJECT_ASM_REG "\n\t" \
- "mov (%%" INJECT_ASM_REG "), %%" INJECT_ASM_REG "\n\t" \
+ "lea asm_loop_cnt_" #n "(%%rip), %%" INJECT_ASM_REG_P "\n\t" \
+ "mov (%%" INJECT_ASM_REG_P "), %%" INJECT_ASM_REG "\n\t" \
"test %%" INJECT_ASM_REG ",%%" INJECT_ASM_REG "\n\t" \
"jz 333f\n\t" \
"222:\n\t" \
@@ -86,10 +91,6 @@ unsigned int yield_mod_cnt, nr_abort;
"jnz 222b\n\t" \
"333:\n\t"
-#else
-#error "Unsupported architecture"
-#endif
-
#elif defined(__s390__)
#define RSEQ_INJECT_INPUT \