aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/netlink/specs/devlink.yaml18
-rw-r--r--Documentation/networking/representors.rst8
-rw-r--r--Documentation/trace/fprobe.rst8
-rw-r--r--arch/arm64/include/asm/kvm_arm.h4
-rw-r--r--arch/arm64/kvm/arch_timer.c13
-rw-r--r--arch/arm64/kvm/emulate-nested.c2
-rw-r--r--arch/arm64/kvm/hyp/vhe/switch.c44
-rw-r--r--arch/arm64/kvm/pmu.c4
-rw-r--r--arch/arm64/kvm/sys_regs.c4
-rw-r--r--arch/loongarch/include/asm/io.h5
-rw-r--r--arch/loongarch/include/asm/linkage.h8
-rw-r--r--arch/loongarch/include/asm/pgtable-bits.h4
-rw-r--r--arch/loongarch/kernel/entry.S4
-rw-r--r--arch/loongarch/kernel/genex.S16
-rw-r--r--arch/loongarch/kernel/setup.c10
-rw-r--r--arch/loongarch/mm/init.c9
-rw-r--r--arch/loongarch/mm/tlbex.S36
-rw-r--r--arch/mips/kvm/mmu.c3
-rw-r--r--arch/s390/kvm/interrupt.c16
-rw-r--r--arch/x86/boot/compressed/sev.c10
-rw-r--r--arch/x86/include/asm/fpu/api.h3
-rw-r--r--arch/x86/include/asm/kvm_host.h1
-rw-r--r--arch/x86/include/asm/svm.h1
-rw-r--r--arch/x86/kernel/fpu/core.c5
-rw-r--r--arch/x86/kernel/fpu/xstate.c12
-rw-r--r--arch/x86/kernel/fpu/xstate.h3
-rw-r--r--arch/x86/kernel/sev-shared.c53
-rw-r--r--arch/x86/kernel/sev.c30
-rw-r--r--arch/x86/kvm/cpuid.c8
-rw-r--r--arch/x86/kvm/lapic.c8
-rw-r--r--arch/x86/kvm/pmu.c27
-rw-r--r--arch/x86/kvm/pmu.h6
-rw-r--r--arch/x86/kvm/svm/avic.c5
-rw-r--r--arch/x86/kvm/svm/nested.c3
-rw-r--r--arch/x86/kvm/svm/pmu.c2
-rw-r--r--arch/x86/kvm/svm/svm.c5
-rw-r--r--arch/x86/kvm/vmx/pmu_intel.c4
-rw-r--r--arch/x86/kvm/x86.c40
-rw-r--r--drivers/base/regmap/regmap.c2
-rw-r--r--drivers/bluetooth/btrtl.c10
-rw-r--r--drivers/bluetooth/hci_vhci.c3
-rw-r--r--drivers/net/bonding/bond_main.c2
-rw-r--r--drivers/net/dsa/bcm_sf2.c24
-rw-r--r--drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c36
-rw-r--r--drivers/net/ethernet/google/gve/gve_rx.c18
-rw-r--r--drivers/net/ethernet/intel/i40e/i40e_common.c4
-rw-r--r--drivers/net/ethernet/intel/ice/ice_lib.c3
-rw-r--r--drivers/net/ethernet/intel/ice/ice_main.c18
-rw-r--r--drivers/net/ethernet/marvell/octeon_ep/octep_main.c13
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/cmd.c64
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c2
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c11
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c3
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c8
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_rep.c10
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_rx.c35
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_stats.h11
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/en_tc.c5
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c25
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h3
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h1
-rw-r--r--drivers/net/ethernet/mellanox/mlx5/core/eswitch.c17
-rw-r--r--drivers/net/ethernet/qlogic/qed/qed_ll2.c7
-rw-r--r--drivers/net/ethernet/ti/Kconfig5
-rw-r--r--drivers/net/ethernet/ti/Makefile7
-rw-r--r--drivers/net/ethernet/ti/icssg/icssg_config.c4
-rw-r--r--drivers/net/ethernet/ti/icssg/icssg_stats.c9
-rw-r--r--drivers/net/ethernet/ti/k3-cppi-desc-pool.c10
-rw-r--r--drivers/net/mdio/mdio-mux.c47
-rw-r--r--drivers/net/phy/bcm7xxx.c3
-rw-r--r--drivers/net/tun.c7
-rw-r--r--drivers/net/usb/smsc95xx.c2
-rw-r--r--drivers/net/wwan/iosm/iosm_ipc_imem.c17
-rw-r--r--drivers/net/wwan/iosm/iosm_ipc_imem.h2
-rw-r--r--drivers/net/wwan/iosm/iosm_ipc_pcie.c4
-rw-r--r--drivers/net/wwan/iosm/iosm_ipc_port.c17
-rw-r--r--drivers/net/wwan/iosm/iosm_ipc_trace.c8
-rw-r--r--drivers/net/wwan/iosm/iosm_ipc_wwan.c21
-rw-r--r--drivers/spi/spi-npcm-fiu.c5
-rw-r--r--drivers/video/fbdev/aty/atyfb_base.c4
-rw-r--r--drivers/video/fbdev/core/cfbcopyarea.c2
-rw-r--r--drivers/video/fbdev/core/syscopyarea.c2
-rw-r--r--drivers/video/fbdev/mmp/hw/mmp_ctrl.h2
-rw-r--r--drivers/video/fbdev/omap/omapfb_main.c4
-rw-r--r--drivers/video/fbdev/sa1100fb.c2
-rw-r--r--drivers/video/fbdev/uvesafb.c2
-rw-r--r--fs/btrfs/volumes.c2
-rw-r--r--fs/namei.c9
-rw-r--r--fs/ntfs3/attrib.c12
-rw-r--r--fs/ntfs3/attrlist.c15
-rw-r--r--fs/ntfs3/bitmap.c4
-rw-r--r--fs/ntfs3/dir.c6
-rw-r--r--fs/ntfs3/file.c4
-rw-r--r--fs/ntfs3/frecord.c8
-rw-r--r--fs/ntfs3/fslog.c6
-rw-r--r--fs/ntfs3/fsntfs.c19
-rw-r--r--fs/ntfs3/index.c3
-rw-r--r--fs/ntfs3/inode.c5
-rw-r--r--fs/ntfs3/namei.c6
-rw-r--r--fs/ntfs3/ntfs.h2
-rw-r--r--fs/ntfs3/ntfs_fs.h4
-rw-r--r--fs/ntfs3/record.c74
-rw-r--r--fs/ntfs3/super.c104
-rw-r--r--fs/ntfs3/xattr.c7
-rw-r--r--include/kvm/arm_arch_timer.h7
-rw-r--r--include/linux/fs.h2
-rw-r--r--include/linux/virtio_net.h19
-rw-r--r--include/net/bluetooth/hci_mon.h2
-rw-r--r--include/net/netns/xfrm.h1
-rw-r--r--include/net/sock.h10
-rw-r--r--include/net/tcp.h3
-rw-r--r--include/trace/events/neigh.h4
-rw-r--r--include/video/mmp_disp.h2
-rw-r--r--include/video/uvesafb.h2
-rw-r--r--kernel/auditsc.c8
-rw-r--r--kernel/trace/fprobe.c6
-rw-r--r--mm/slab_common.c7
-rw-r--r--net/bluetooth/hci_conn.c9
-rw-r--r--net/bluetooth/hci_event.c48
-rw-r--r--net/bluetooth/hci_sock.c3
-rw-r--r--net/bluetooth/hci_sync.c26
-rw-r--r--net/core/dev.c65
-rw-r--r--net/core/dev.h3
-rw-r--r--net/core/pktgen.c14
-rw-r--r--net/core/rtnetlink.c4
-rw-r--r--net/core/stream.c12
-rw-r--r--net/ethtool/bitset.c32
-rw-r--r--net/ipv4/af_inet.c10
-rw-r--r--net/ipv4/esp4.c4
-rw-r--r--net/ipv4/fib_semantics.c14
-rw-r--r--net/ipv4/inet_connection_sock.c1
-rw-r--r--net/ipv4/inet_hashtables.c24
-rw-r--r--net/ipv4/tcp.c16
-rw-r--r--net/ipv4/tcp_bpf.c12
-rw-r--r--net/ipv4/tcp_ipv4.c1
-rw-r--r--net/ipv4/tcp_output.c25
-rw-r--r--net/ipv4/tcp_recovery.c2
-rw-r--r--net/ipv6/esp6.c4
-rw-r--r--net/ipv6/xfrm6_policy.c4
-rw-r--r--net/mac80211/key.c3
-rw-r--r--net/mptcp/protocol.c43
-rw-r--r--net/netfilter/nf_tables_api.c70
-rw-r--r--net/netfilter/nfnetlink_log.c2
-rw-r--r--net/netfilter/nft_inner.c1
-rw-r--r--net/netfilter/nft_payload.c2
-rw-r--r--net/netfilter/nft_set_pipapo.h2
-rw-r--r--net/netfilter/nft_set_rbtree.c2
-rw-r--r--net/nfc/nci/spi.c2
-rw-r--r--net/rfkill/core.c5
-rw-r--r--net/rfkill/rfkill-gpio.c4
-rw-r--r--net/sched/sch_hfsc.c18
-rw-r--r--net/smc/af_smc.c5
-rw-r--r--net/smc/smc_ib.c7
-rw-r--r--net/smc/smc_ib.h2
-rw-r--r--net/tls/tls_main.c10
-rw-r--r--net/tls/tls_sw.c19
-rw-r--r--net/wireless/core.c2
-rw-r--r--net/xfrm/xfrm_interface_core.c22
-rw-r--r--net/xfrm/xfrm_policy.c27
-rw-r--r--tools/arch/x86/include/uapi/asm/unistd_32.h2
-rw-r--r--tools/net/ynl/generated/devlink-user.c54
-rw-r--r--tools/testing/selftests/kvm/include/ucall_common.h2
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/processor.h23
-rw-r--r--tools/testing/selftests/kvm/lib/guest_sprintf.c7
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/apic.c2
-rw-r--r--tools/testing/selftests/kvm/memslot_perf_test.c9
-rw-r--r--tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c2
-rw-r--r--tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c2
-rwxr-xr-xtools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh1
-rw-r--r--tools/testing/selftests/kvm/x86_64/state_test.c110
-rw-r--r--tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c4
-rw-r--r--tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c4
-rw-r--r--tools/testing/selftests/net/Makefile1
-rwxr-xr-xtools/testing/selftests/net/fib_tests.sh7
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_join.sh21
-rwxr-xr-xtools/testing/selftests/net/netns-name.sh87
-rwxr-xr-xtools/testing/selftests/net/openvswitch/openvswitch.sh21
-rw-r--r--tools/testing/selftests/net/openvswitch/ovs-dpctl.py48
-rwxr-xr-xtools/testing/selftests/netfilter/nft_audit.sh52
179 files changed, 1617 insertions, 749 deletions
diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index d1ebcd927149..065661acb878 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -323,7 +323,7 @@ operations:
- dev-name
- sb-index
reply: &sb-get-reply
- value: 11
+ value: 13
attributes: *sb-id-attrs
dump:
request:
@@ -350,7 +350,7 @@ operations:
- sb-index
- sb-pool-index
reply: &sb-pool-get-reply
- value: 15
+ value: 17
attributes: *sb-pool-id-attrs
dump:
request:
@@ -378,7 +378,7 @@ operations:
- sb-index
- sb-pool-index
reply: &sb-port-pool-get-reply
- value: 19
+ value: 21
attributes: *sb-port-pool-id-attrs
dump:
request:
@@ -407,7 +407,7 @@ operations:
- sb-pool-type
- sb-tc-index
reply: &sb-tc-pool-bind-get-reply
- value: 23
+ value: 25
attributes: *sb-tc-pool-bind-id-attrs
dump:
request:
@@ -538,7 +538,7 @@ operations:
- dev-name
- trap-name
reply: &trap-get-reply
- value: 61
+ value: 63
attributes: *trap-id-attrs
dump:
request:
@@ -564,7 +564,7 @@ operations:
- dev-name
- trap-group-name
reply: &trap-group-get-reply
- value: 65
+ value: 67
attributes: *trap-group-id-attrs
dump:
request:
@@ -590,7 +590,7 @@ operations:
- dev-name
- trap-policer-id
reply: &trap-policer-get-reply
- value: 69
+ value: 71
attributes: *trap-policer-id-attrs
dump:
request:
@@ -617,7 +617,7 @@ operations:
- port-index
- rate-node-name
reply: &rate-get-reply
- value: 74
+ value: 76
attributes: *rate-id-attrs
dump:
request:
@@ -643,7 +643,7 @@ operations:
- dev-name
- linecard-index
reply: &linecard-get-reply
- value: 78
+ value: 80
attributes: *linecard-id-attrs
dump:
request:
diff --git a/Documentation/networking/representors.rst b/Documentation/networking/representors.rst
index ee1f5cd54496..decb39c19b9e 100644
--- a/Documentation/networking/representors.rst
+++ b/Documentation/networking/representors.rst
@@ -162,9 +162,11 @@ How are representors identified?
The representor netdevice should *not* directly refer to a PCIe device (e.g.
through ``net_dev->dev.parent`` / ``SET_NETDEV_DEV()``), either of the
representee or of the switchdev function.
-Instead, it should implement the ``ndo_get_devlink_port()`` netdevice op, which
-the kernel uses to provide the ``phys_switch_id`` and ``phys_port_name`` sysfs
-nodes. (Some legacy drivers implement ``ndo_get_port_parent_id()`` and
+Instead, the driver should use the ``SET_NETDEV_DEVLINK_PORT`` macro to
+assign a devlink port instance to the netdevice before registering the
+netdevice; the kernel uses the devlink port to provide the ``phys_switch_id``
+and ``phys_port_name`` sysfs nodes.
+(Some legacy drivers implement ``ndo_get_port_parent_id()`` and
``ndo_get_phys_port_name()`` directly, but this is deprecated.) See
:ref:`Documentation/networking/devlink/devlink-port.rst <devlink_port>` for the
details of this API.
diff --git a/Documentation/trace/fprobe.rst b/Documentation/trace/fprobe.rst
index 7a895514b537..196f52386aaa 100644
--- a/Documentation/trace/fprobe.rst
+++ b/Documentation/trace/fprobe.rst
@@ -91,9 +91,9 @@ The prototype of the entry/exit callback function are as follows:
.. code-block:: c
- int entry_callback(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs, void *entry_data);
+ int entry_callback(struct fprobe *fp, unsigned long entry_ip, unsigned long ret_ip, struct pt_regs *regs, void *entry_data);
- void exit_callback(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs, void *entry_data);
+ void exit_callback(struct fprobe *fp, unsigned long entry_ip, unsigned long ret_ip, struct pt_regs *regs, void *entry_data);
Note that the @entry_ip is saved at function entry and passed to exit handler.
If the entry callback function returns !0, the corresponding exit callback will be cancelled.
@@ -108,6 +108,10 @@ If the entry callback function returns !0, the corresponding exit callback will
Note that this may not be the actual entry address of the function but
the address where the ftrace is instrumented.
+@ret_ip
+ This is the return address that the traced function will return to,
+ somewhere in the caller. This can be used at both entry and exit.
+
@regs
This is the `pt_regs` data structure at the entry and exit. Note that
the instruction pointer of @regs may be different from the @entry_ip
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 5882b2415596..1095c6647e96 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -344,14 +344,14 @@
*/
#define __HFGRTR_EL2_RES0 (GENMASK(63, 56) | GENMASK(53, 51))
#define __HFGRTR_EL2_MASK GENMASK(49, 0)
-#define __HFGRTR_EL2_nMASK (GENMASK(55, 54) | BIT(50))
+#define __HFGRTR_EL2_nMASK (GENMASK(58, 57) | GENMASK(55, 54) | BIT(50))
#define __HFGWTR_EL2_RES0 (GENMASK(63, 56) | GENMASK(53, 51) | \
BIT(46) | BIT(42) | BIT(40) | BIT(28) | \
GENMASK(26, 25) | BIT(21) | BIT(18) | \
GENMASK(15, 14) | GENMASK(10, 9) | BIT(2))
#define __HFGWTR_EL2_MASK GENMASK(49, 0)
-#define __HFGWTR_EL2_nMASK (GENMASK(55, 54) | BIT(50))
+#define __HFGWTR_EL2_nMASK (GENMASK(58, 57) | GENMASK(55, 54) | BIT(50))
#define __HFGITR_EL2_RES0 GENMASK(63, 57)
#define __HFGITR_EL2_MASK GENMASK(54, 0)
diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c
index 6dcdae4d38cb..a1e24228aaaa 100644
--- a/arch/arm64/kvm/arch_timer.c
+++ b/arch/arm64/kvm/arch_timer.c
@@ -55,11 +55,6 @@ static struct irq_ops arch_timer_irq_ops = {
.get_input_level = kvm_arch_timer_get_input_level,
};
-static bool has_cntpoff(void)
-{
- return (has_vhe() && cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF));
-}
-
static int nr_timers(struct kvm_vcpu *vcpu)
{
if (!vcpu_has_nv(vcpu))
@@ -180,7 +175,7 @@ u64 kvm_phys_timer_read(void)
return timecounter->cc->read(timecounter->cc);
}
-static void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map)
+void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map)
{
if (vcpu_has_nv(vcpu)) {
if (is_hyp_ctxt(vcpu)) {
@@ -548,8 +543,7 @@ static void timer_save_state(struct arch_timer_context *ctx)
timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTP_CTL));
cval = read_sysreg_el0(SYS_CNTP_CVAL);
- if (!has_cntpoff())
- cval -= timer_get_offset(ctx);
+ cval -= timer_get_offset(ctx);
timer_set_cval(ctx, cval);
@@ -636,8 +630,7 @@ static void timer_restore_state(struct arch_timer_context *ctx)
cval = timer_get_cval(ctx);
offset = timer_get_offset(ctx);
set_cntpoff(offset);
- if (!has_cntpoff())
- cval += offset;
+ cval += offset;
write_sysreg_el0(cval, SYS_CNTP_CVAL);
isb();
write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTP_CTL);
diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c
index 9ced1bf0c2b7..ee902ff2a50f 100644
--- a/arch/arm64/kvm/emulate-nested.c
+++ b/arch/arm64/kvm/emulate-nested.c
@@ -977,6 +977,8 @@ enum fg_filter_id {
static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = {
/* HFGRTR_EL2, HFGWTR_EL2 */
+ SR_FGT(SYS_PIR_EL1, HFGxTR, nPIR_EL1, 0),
+ SR_FGT(SYS_PIRE0_EL1, HFGxTR, nPIRE0_EL1, 0),
SR_FGT(SYS_TPIDR2_EL0, HFGxTR, nTPIDR2_EL0, 0),
SR_FGT(SYS_SMPRI_EL1, HFGxTR, nSMPRI_EL1, 0),
SR_FGT(SYS_ACCDATA_EL1, HFGxTR, nACCDATA_EL1, 0),
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 6537f58b1a8c..448b17080d36 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -39,6 +39,26 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
___activate_traps(vcpu);
+ if (has_cntpoff()) {
+ struct timer_map map;
+
+ get_timer_map(vcpu, &map);
+
+ /*
+ * We're entrering the guest. Reload the correct
+ * values from memory now that TGE is clear.
+ */
+ if (map.direct_ptimer == vcpu_ptimer(vcpu))
+ val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
+ if (map.direct_ptimer == vcpu_hptimer(vcpu))
+ val = __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2);
+
+ if (map.direct_ptimer) {
+ write_sysreg_el0(val, SYS_CNTP_CVAL);
+ isb();
+ }
+ }
+
val = read_sysreg(cpacr_el1);
val |= CPACR_ELx_TTA;
val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN |
@@ -77,6 +97,30 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+ if (has_cntpoff()) {
+ struct timer_map map;
+ u64 val, offset;
+
+ get_timer_map(vcpu, &map);
+
+ /*
+ * We're exiting the guest. Save the latest CVAL value
+ * to memory and apply the offset now that TGE is set.
+ */
+ val = read_sysreg_el0(SYS_CNTP_CVAL);
+ if (map.direct_ptimer == vcpu_ptimer(vcpu))
+ __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = val;
+ if (map.direct_ptimer == vcpu_hptimer(vcpu))
+ __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2) = val;
+
+ offset = read_sysreg_s(SYS_CNTPOFF_EL2);
+
+ if (map.direct_ptimer && offset) {
+ write_sysreg_el0(val + offset, SYS_CNTP_CVAL);
+ isb();
+ }
+ }
+
/*
* ARM errata 1165522 and 1530923 require the actual execution of the
* above before we can switch to the EL2/EL0 translation regime used by
diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c
index 0eea225fd09a..a243934c5568 100644
--- a/arch/arm64/kvm/pmu.c
+++ b/arch/arm64/kvm/pmu.c
@@ -39,7 +39,7 @@ void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr)
{
struct kvm_pmu_events *pmu = kvm_get_pmu_events();
- if (!kvm_arm_support_pmu_v3() || !pmu || !kvm_pmu_switch_needed(attr))
+ if (!kvm_arm_support_pmu_v3() || !kvm_pmu_switch_needed(attr))
return;
if (!attr->exclude_host)
@@ -55,7 +55,7 @@ void kvm_clr_pmu_events(u32 clr)
{
struct kvm_pmu_events *pmu = kvm_get_pmu_events();
- if (!kvm_arm_support_pmu_v3() || !pmu)
+ if (!kvm_arm_support_pmu_v3())
return;
pmu->events_host &= ~clr;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index e92ec810d449..0afd6136e275 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -2122,8 +2122,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
{ SYS_DESC(SYS_PMMIR_EL1), trap_raz_wi },
{ SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 },
- { SYS_DESC(SYS_PIRE0_EL1), access_vm_reg, reset_unknown, PIRE0_EL1 },
- { SYS_DESC(SYS_PIR_EL1), access_vm_reg, reset_unknown, PIR_EL1 },
+ { SYS_DESC(SYS_PIRE0_EL1), NULL, reset_unknown, PIRE0_EL1 },
+ { SYS_DESC(SYS_PIR_EL1), NULL, reset_unknown, PIR_EL1 },
{ SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 },
{ SYS_DESC(SYS_LORSA_EL1), trap_loregion },
diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h
index 0dcb36b32cb2..c486c2341b66 100644
--- a/arch/loongarch/include/asm/io.h
+++ b/arch/loongarch/include/asm/io.h
@@ -52,10 +52,9 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
* @offset: bus address of the memory
* @size: size of the resource to map
*/
-extern pgprot_t pgprot_wc;
-
#define ioremap_wc(offset, size) \
- ioremap_prot((offset), (size), pgprot_val(pgprot_wc))
+ ioremap_prot((offset), (size), \
+ pgprot_val(wc_enabled ? PAGE_KERNEL_WUC : PAGE_KERNEL_SUC))
#define ioremap_cache(offset, size) \
ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL))
diff --git a/arch/loongarch/include/asm/linkage.h b/arch/loongarch/include/asm/linkage.h
index 81b0c4cfbf4f..e2eca1a25b4e 100644
--- a/arch/loongarch/include/asm/linkage.h
+++ b/arch/loongarch/include/asm/linkage.h
@@ -33,4 +33,12 @@
.cfi_endproc; \
SYM_END(name, SYM_T_FUNC)
+#define SYM_CODE_START(name) \
+ SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) \
+ .cfi_startproc;
+
+#define SYM_CODE_END(name) \
+ .cfi_endproc; \
+ SYM_END(name, SYM_T_NONE)
+
#endif
diff --git a/arch/loongarch/include/asm/pgtable-bits.h b/arch/loongarch/include/asm/pgtable-bits.h
index 35348d4c4209..21319c1e045c 100644
--- a/arch/loongarch/include/asm/pgtable-bits.h
+++ b/arch/loongarch/include/asm/pgtable-bits.h
@@ -105,13 +105,15 @@ static inline pgprot_t pgprot_noncached(pgprot_t _prot)
return __pgprot(prot);
}
+extern bool wc_enabled;
+
#define pgprot_writecombine pgprot_writecombine
static inline pgprot_t pgprot_writecombine(pgprot_t _prot)
{
unsigned long prot = pgprot_val(_prot);
- prot = (prot & ~_CACHE_MASK) | _CACHE_WUC;
+ prot = (prot & ~_CACHE_MASK) | (wc_enabled ? _CACHE_WUC : _CACHE_SUC);
return __pgprot(prot);
}
diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S
index 65518bb8f472..1ec8e4c4cc2b 100644
--- a/arch/loongarch/kernel/entry.S
+++ b/arch/loongarch/kernel/entry.S
@@ -18,7 +18,7 @@
.text
.cfi_sections .debug_frame
.align 5
-SYM_FUNC_START(handle_syscall)
+SYM_CODE_START(handle_syscall)
csrrd t0, PERCPU_BASE_KS
la.pcrel t1, kernelsp
add.d t1, t1, t0
@@ -71,7 +71,7 @@ SYM_FUNC_START(handle_syscall)
bl do_syscall
RESTORE_ALL_AND_RET
-SYM_FUNC_END(handle_syscall)
+SYM_CODE_END(handle_syscall)
_ASM_NOKPROBE(handle_syscall)
SYM_CODE_START(ret_from_fork)
diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S
index 78f066384657..2bb3aa2dcfcb 100644
--- a/arch/loongarch/kernel/genex.S
+++ b/arch/loongarch/kernel/genex.S
@@ -31,7 +31,7 @@ SYM_FUNC_START(__arch_cpu_idle)
1: jr ra
SYM_FUNC_END(__arch_cpu_idle)
-SYM_FUNC_START(handle_vint)
+SYM_CODE_START(handle_vint)
BACKUP_T0T1
SAVE_ALL
la_abs t1, __arch_cpu_idle
@@ -46,11 +46,11 @@ SYM_FUNC_START(handle_vint)
la_abs t0, do_vint
jirl ra, t0, 0
RESTORE_ALL_AND_RET
-SYM_FUNC_END(handle_vint)
+SYM_CODE_END(handle_vint)
-SYM_FUNC_START(except_vec_cex)
+SYM_CODE_START(except_vec_cex)
b cache_parity_error
-SYM_FUNC_END(except_vec_cex)
+SYM_CODE_END(except_vec_cex)
.macro build_prep_badv
csrrd t0, LOONGARCH_CSR_BADV
@@ -66,7 +66,7 @@ SYM_FUNC_END(except_vec_cex)
.macro BUILD_HANDLER exception handler prep
.align 5
- SYM_FUNC_START(handle_\exception)
+ SYM_CODE_START(handle_\exception)
666:
BACKUP_T0T1
SAVE_ALL
@@ -76,7 +76,7 @@ SYM_FUNC_END(except_vec_cex)
jirl ra, t0, 0
668:
RESTORE_ALL_AND_RET
- SYM_FUNC_END(handle_\exception)
+ SYM_CODE_END(handle_\exception)
SYM_DATA(unwind_hint_\exception, .word 668b - 666b)
.endm
@@ -93,7 +93,7 @@ SYM_FUNC_END(except_vec_cex)
BUILD_HANDLER watch watch none
BUILD_HANDLER reserved reserved none /* others */
-SYM_FUNC_START(handle_sys)
+SYM_CODE_START(handle_sys)
la_abs t0, handle_syscall
jr t0
-SYM_FUNC_END(handle_sys)
+SYM_CODE_END(handle_sys)
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index 7783f0a3d742..aed65915e932 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -161,19 +161,19 @@ static void __init smbios_parse(void)
}
#ifdef CONFIG_ARCH_WRITECOMBINE
-pgprot_t pgprot_wc = PAGE_KERNEL_WUC;
+bool wc_enabled = true;
#else
-pgprot_t pgprot_wc = PAGE_KERNEL_SUC;
+bool wc_enabled = false;
#endif
-EXPORT_SYMBOL(pgprot_wc);
+EXPORT_SYMBOL(wc_enabled);
static int __init setup_writecombine(char *p)
{
if (!strcmp(p, "on"))
- pgprot_wc = PAGE_KERNEL_WUC;
+ wc_enabled = true;
else if (!strcmp(p, "off"))
- pgprot_wc = PAGE_KERNEL_SUC;
+ wc_enabled = false;
else
pr_warn("Unknown writecombine setting \"%s\".\n", p);
diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c
index f3fe8c06ba4d..4dd53427f657 100644
--- a/arch/loongarch/mm/init.c
+++ b/arch/loongarch/mm/init.c
@@ -43,11 +43,11 @@ void copy_user_highpage(struct page *to, struct page *from,
{
void *vfrom, *vto;
- vto = kmap_atomic(to);
- vfrom = kmap_atomic(from);
+ vfrom = kmap_local_page(from);
+ vto = kmap_local_page(to);
copy_page(vto, vfrom);
- kunmap_atomic(vfrom);
- kunmap_atomic(vto);
+ kunmap_local(vfrom);
+ kunmap_local(vto);
/* Make sure this page is cleared on other CPU's too before using it */
smp_wmb();
}
@@ -240,6 +240,7 @@ pgd_t swapper_pg_dir[_PTRS_PER_PGD] __section(".bss..swapper_pg_dir");
pgd_t invalid_pg_dir[_PTRS_PER_PGD] __page_aligned_bss;
#ifndef __PAGETABLE_PUD_FOLDED
pud_t invalid_pud_table[PTRS_PER_PUD] __page_aligned_bss;
+EXPORT_SYMBOL(invalid_pud_table);
#endif
#ifndef __PAGETABLE_PMD_FOLDED
pmd_t invalid_pmd_table[PTRS_PER_PMD] __page_aligned_bss;
diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S
index ca17dd3a1915..d5d682f3d29f 100644
--- a/arch/loongarch/mm/tlbex.S
+++ b/arch/loongarch/mm/tlbex.S
@@ -17,7 +17,7 @@
#define PTRS_PER_PTE_BITS (PAGE_SHIFT - 3)
.macro tlb_do_page_fault, write
- SYM_FUNC_START(tlb_do_page_fault_\write)
+ SYM_CODE_START(tlb_do_page_fault_\write)
SAVE_ALL
csrrd a2, LOONGARCH_CSR_BADV
move a0, sp
@@ -25,13 +25,13 @@
li.w a1, \write
bl do_page_fault
RESTORE_ALL_AND_RET
- SYM_FUNC_END(tlb_do_page_fault_\write)
+ SYM_CODE_END(tlb_do_page_fault_\write)
.endm
tlb_do_page_fault 0
tlb_do_page_fault 1
-SYM_FUNC_START(handle_tlb_protect)
+SYM_CODE_START(handle_tlb_protect)
BACKUP_T0T1
SAVE_ALL
move a0, sp
@@ -41,9 +41,9 @@ SYM_FUNC_START(handle_tlb_protect)
la_abs t0, do_page_fault
jirl ra, t0, 0
RESTORE_ALL_AND_RET
-SYM_FUNC_END(handle_tlb_protect)
+SYM_CODE_END(handle_tlb_protect)
-SYM_FUNC_START(handle_tlb_load)
+SYM_CODE_START(handle_tlb_load)
csrwr t0, EXCEPTION_KS0
csrwr t1, EXCEPTION_KS1
csrwr ra, EXCEPTION_KS2
@@ -187,16 +187,16 @@ nopage_tlb_load:
csrrd ra, EXCEPTION_KS2
la_abs t0, tlb_do_page_fault_0
jr t0
-SYM_FUNC_END(handle_tlb_load)
+SYM_CODE_END(handle_tlb_load)
-SYM_FUNC_START(handle_tlb_load_ptw)
+SYM_CODE_START(handle_tlb_load_ptw)
csrwr t0, LOONGARCH_CSR_KS0
csrwr t1, LOONGARCH_CSR_KS1
la_abs t0, tlb_do_page_fault_0
jr t0
-SYM_FUNC_END(handle_tlb_load_ptw)
+SYM_CODE_END(handle_tlb_load_ptw)
-SYM_FUNC_START(handle_tlb_store)
+SYM_CODE_START(handle_tlb_store)
csrwr t0, EXCEPTION_KS0
csrwr t1, EXCEPTION_KS1
csrwr ra, EXCEPTION_KS2
@@ -343,16 +343,16 @@ nopage_tlb_store:
csrrd ra, EXCEPTION_KS2
la_abs t0, tlb_do_page_fault_1
jr t0
-SYM_FUNC_END(handle_tlb_store)
+SYM_CODE_END(handle_tlb_store)
-SYM_FUNC_START(handle_tlb_store_ptw)
+SYM_CODE_START(handle_tlb_store_ptw)
csrwr t0, LOONGARCH_CSR_KS0
csrwr t1, LOONGARCH_CSR_KS1
la_abs t0, tlb_do_page_fault_1
jr t0
-SYM_FUNC_END(handle_tlb_store_ptw)
+SYM_CODE_END(handle_tlb_store_ptw)
-SYM_FUNC_START(handle_tlb_modify)
+SYM_CODE_START(handle_tlb_modify)
csrwr t0, EXCEPTION_KS0
csrwr t1, EXCEPTION_KS1
csrwr ra, EXCEPTION_KS2
@@ -497,16 +497,16 @@ nopage_tlb_modify:
csrrd ra, EXCEPTION_KS2
la_abs t0, tlb_do_page_fault_1
jr t0
-SYM_FUNC_END(handle_tlb_modify)
+SYM_CODE_END(handle_tlb_modify)
-SYM_FUNC_START(handle_tlb_modify_ptw)
+SYM_CODE_START(handle_tlb_modify_ptw)
csrwr t0, LOONGARCH_CSR_KS0
csrwr t1, LOONGARCH_CSR_KS1
la_abs t0, tlb_do_page_fault_1
jr t0
-SYM_FUNC_END(handle_tlb_modify_ptw)
+SYM_CODE_END(handle_tlb_modify_ptw)
-SYM_FUNC_START(handle_tlb_refill)
+SYM_CODE_START(handle_tlb_refill)
csrwr t0, LOONGARCH_CSR_TLBRSAVE
csrrd t0, LOONGARCH_CSR_PGD
lddir t0, t0, 3
@@ -521,4 +521,4 @@ SYM_FUNC_START(handle_tlb_refill)
tlbfill
csrrd t0, LOONGARCH_CSR_TLBRSAVE
ertn
-SYM_FUNC_END(handle_tlb_refill)
+SYM_CODE_END(handle_tlb_refill)
diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c
index 7b2ac1319d70..467ee6b95ae1 100644
--- a/arch/mips/kvm/mmu.c
+++ b/arch/mips/kvm/mmu.c
@@ -592,7 +592,7 @@ static int kvm_mips_map_page(struct kvm_vcpu *vcpu, unsigned long gpa,
gfn_t gfn = gpa >> PAGE_SHIFT;
int srcu_idx, err;
kvm_pfn_t pfn;
- pte_t *ptep, entry, old_pte;
+ pte_t *ptep, entry;
bool writeable;
unsigned long prot_bits;
unsigned long mmu_seq;
@@ -664,7 +664,6 @@ retry:
entry = pfn_pte(pfn, __pgprot(prot_bits));
/* Write the PTE */
- old_pte = *ptep;
set_pte(ptep, entry);
err = 0;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index c1b47d608a2b..efaebba5ee19 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -303,11 +303,6 @@ static inline u8 gisa_get_ipm_or_restore_iam(struct kvm_s390_gisa_interrupt *gi)
return 0;
}
-static inline int gisa_in_alert_list(struct kvm_s390_gisa *gisa)
-{
- return READ_ONCE(gisa->next_alert) != (u32)virt_to_phys(gisa);
-}
-
static inline void gisa_set_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc)
{
set_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa);
@@ -3216,11 +3211,12 @@ void kvm_s390_gisa_destroy(struct kvm *kvm)
if (!gi->origin)
return;
- if (gi->alert.mask)
- KVM_EVENT(3, "vm 0x%pK has unexpected iam 0x%02x",
- kvm, gi->alert.mask);
- while (gisa_in_alert_list(gi->origin))
- cpu_relax();
+ WARN(gi->alert.mask != 0x00,
+ "unexpected non zero alert.mask 0x%02x",
+ gi->alert.mask);
+ gi->alert.mask = 0x00;
+ if (gisa_set_iam(gi->origin, gi->alert.mask))
+ process_gib_alert_list();
hrtimer_cancel(&gi->timer);
gi->origin = NULL;
VM_EVENT(kvm, 3, "gisa 0x%pK destroyed", gisa);
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index dc8c876fbd8f..80d76aea1f7b 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -103,6 +103,16 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
return ES_OK;
}
+static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
+{
+ return ES_OK;
+}
+
+static bool fault_in_kernel_space(unsigned long address)
+{
+ return false;
+}
+
#undef __init
#define __init
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 31089b851c4f..a2be3aefff9f 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -157,7 +157,8 @@ static inline void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) {
static inline void fpu_sync_guest_vmexit_xfd_state(void) { }
#endif
-extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, unsigned int size, u32 pkru);
+extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf,
+ unsigned int size, u64 xfeatures, u32 pkru);
extern int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru);
static inline void fpstate_set_confidential(struct fpu_guest *gfpu)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 17715cb8731d..70d139406bc8 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -528,7 +528,6 @@ struct kvm_pmu {
u64 raw_event_mask;
struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC];
struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED];
- struct irq_work irq_work;
/*
* Overlay the bitmap with a 64-bit atomic so that all bits can be
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 19bf955b67e0..3ac0ffc4f3e2 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -268,6 +268,7 @@ enum avic_ipi_failure_cause {
AVIC_IPI_FAILURE_TARGET_NOT_RUNNING,
AVIC_IPI_FAILURE_INVALID_TARGET,
AVIC_IPI_FAILURE_INVALID_BACKING_PAGE,
+ AVIC_IPI_FAILURE_INVALID_IPI_VECTOR,
};
#define AVIC_PHYSICAL_MAX_INDEX_MASK GENMASK_ULL(8, 0)
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index a86d37052a64..a21a4d0ecc34 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -369,14 +369,15 @@ int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest)
EXPORT_SYMBOL_GPL(fpu_swap_kvm_fpstate);
void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf,
- unsigned int size, u32 pkru)
+ unsigned int size, u64 xfeatures, u32 pkru)
{
struct fpstate *kstate = gfpu->fpstate;
union fpregs_state *ustate = buf;
struct membuf mb = { .p = buf, .left = size };
if (cpu_feature_enabled(X86_FEATURE_XSAVE)) {
- __copy_xstate_to_uabi_buf(mb, kstate, pkru, XSTATE_COPY_XSAVE);
+ __copy_xstate_to_uabi_buf(mb, kstate, xfeatures, pkru,
+ XSTATE_COPY_XSAVE);
} else {
memcpy(&ustate->fxsave, &kstate->regs.fxsave,
sizeof(ustate->fxsave));
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index cadf68737e6b..ef6906107c54 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -1049,6 +1049,7 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate,
* __copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer
* @to: membuf descriptor
* @fpstate: The fpstate buffer from which to copy
+ * @xfeatures: The mask of xfeatures to save (XSAVE mode only)
* @pkru_val: The PKRU value to store in the PKRU component
* @copy_mode: The requested copy mode
*
@@ -1059,7 +1060,8 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate,
* It supports partial copy but @to.pos always starts from zero.
*/
void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
- u32 pkru_val, enum xstate_copy_mode copy_mode)
+ u64 xfeatures, u32 pkru_val,
+ enum xstate_copy_mode copy_mode)
{
const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr);
struct xregs_state *xinit = &init_fpstate.regs.xsave;
@@ -1083,7 +1085,7 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
break;
case XSTATE_COPY_XSAVE:
- header.xfeatures &= fpstate->user_xfeatures;
+ header.xfeatures &= fpstate->user_xfeatures & xfeatures;
break;
}
@@ -1185,6 +1187,7 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
enum xstate_copy_mode copy_mode)
{
__copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate,
+ tsk->thread.fpu.fpstate->user_xfeatures,
tsk->thread.pkru, copy_mode);
}
@@ -1536,10 +1539,7 @@ static int fpstate_realloc(u64 xfeatures, unsigned int ksize,
fpregs_restore_userregs();
newfps->xfeatures = curfps->xfeatures | xfeatures;
-
- if (!guest_fpu)
- newfps->user_xfeatures = curfps->user_xfeatures | xfeatures;
-
+ newfps->user_xfeatures = curfps->user_xfeatures | xfeatures;
newfps->xfd = curfps->xfd & ~xfeatures;
/* Do the final updates within the locked region */
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index a4ecb04d8d64..3518fb26d06b 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -43,7 +43,8 @@ enum xstate_copy_mode {
struct membuf;
extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
- u32 pkru_val, enum xstate_copy_mode copy_mode);
+ u64 xfeatures, u32 pkru_val,
+ enum xstate_copy_mode copy_mode);
extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
enum xstate_copy_mode mode);
extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru);
diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c
index dcf325b7b022..ccb0915e84e1 100644
--- a/arch/x86/kernel/sev-shared.c
+++ b/arch/x86/kernel/sev-shared.c
@@ -632,6 +632,23 @@ fail:
sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
}
+static enum es_result vc_insn_string_check(struct es_em_ctxt *ctxt,
+ unsigned long address,
+ bool write)
+{
+ if (user_mode(ctxt->regs) && fault_in_kernel_space(address)) {
+ ctxt->fi.vector = X86_TRAP_PF;
+ ctxt->fi.error_code = X86_PF_USER;
+ ctxt->fi.cr2 = address;
+ if (write)
+ ctxt->fi.error_code |= X86_PF_WRITE;
+
+ return ES_EXCEPTION;
+ }
+
+ return ES_OK;
+}
+
static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,
void *src, char *buf,
unsigned int data_size,
@@ -639,7 +656,12 @@ static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,
bool backwards)
{
int i, b = backwards ? -1 : 1;
- enum es_result ret = ES_OK;
+ unsigned long address = (unsigned long)src;
+ enum es_result ret;
+
+ ret = vc_insn_string_check(ctxt, address, false);
+ if (ret != ES_OK)
+ return ret;
for (i = 0; i < count; i++) {
void *s = src + (i * data_size * b);
@@ -660,7 +682,12 @@ static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt,
bool backwards)
{
int i, s = backwards ? -1 : 1;
- enum es_result ret = ES_OK;
+ unsigned long address = (unsigned long)dst;
+ enum es_result ret;
+
+ ret = vc_insn_string_check(ctxt, address, true);
+ if (ret != ES_OK)
+ return ret;
for (i = 0; i < count; i++) {
void *d = dst + (i * data_size * s);
@@ -696,6 +723,9 @@ static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt,
static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
{
struct insn *insn = &ctxt->insn;
+ size_t size;
+ u64 port;
+
*exitinfo = 0;
switch (insn->opcode.bytes[0]) {
@@ -704,7 +734,7 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
case 0x6d:
*exitinfo |= IOIO_TYPE_INS;
*exitinfo |= IOIO_SEG_ES;
- *exitinfo |= (ctxt->regs->dx & 0xffff) << 16;
+ port = ctxt->regs->dx & 0xffff;
break;
/* OUTS opcodes */
@@ -712,41 +742,43 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
case 0x6f:
*exitinfo |= IOIO_TYPE_OUTS;
*exitinfo |= IOIO_SEG_DS;
- *exitinfo |= (ctxt->regs->dx & 0xffff) << 16;
+ port = ctxt->regs->dx & 0xffff;
break;
/* IN immediate opcodes */
case 0xe4:
case 0xe5:
*exitinfo |= IOIO_TYPE_IN;
- *exitinfo |= (u8)insn->immediate.value << 16;
+ port = (u8)insn->immediate.value & 0xffff;
break;
/* OUT immediate opcodes */
case 0xe6:
case 0xe7:
*exitinfo |= IOIO_TYPE_OUT;
- *exitinfo |= (u8)insn->immediate.value << 16;
+ port = (u8)insn->immediate.value & 0xffff;
break;
/* IN register opcodes */
case 0xec:
case 0xed:
*exitinfo |= IOIO_TYPE_IN;
- *exitinfo |= (ctxt->regs->dx & 0xffff) << 16;
+ port = ctxt->regs->dx & 0xffff;
break;
/* OUT register opcodes */
case 0xee:
case 0xef:
*exitinfo |= IOIO_TYPE_OUT;
- *exitinfo |= (ctxt->regs->dx & 0xffff) << 16;
+ port = ctxt->regs->dx & 0xffff;
break;
default:
return ES_DECODE_FAILED;
}
+ *exitinfo |= port << 16;
+
switch (insn->opcode.bytes[0]) {
case 0x6c:
case 0x6e:
@@ -756,12 +788,15 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
case 0xee:
/* Single byte opcodes */
*exitinfo |= IOIO_DATA_8;
+ size = 1;
break;
default:
/* Length determined by instruction parsing */
*exitinfo |= (insn->opnd_bytes == 2) ? IOIO_DATA_16
: IOIO_DATA_32;
+ size = (insn->opnd_bytes == 2) ? 2 : 4;
}
+
switch (insn->addr_bytes) {
case 2:
*exitinfo |= IOIO_ADDR_16;
@@ -777,7 +812,7 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
if (insn_has_rep_prefix(insn))
*exitinfo |= IOIO_REP;
- return ES_OK;
+ return vc_ioio_check(ctxt, (u16)port, size);
}
static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
index d8c1e3be74c0..6395bfd87b68 100644
--- a/arch/x86/kernel/sev.c
+++ b/arch/x86/kernel/sev.c
@@ -524,6 +524,33 @@ static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt
return ES_OK;
}
+static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
+{
+ BUG_ON(size > 4);
+
+ if (user_mode(ctxt->regs)) {
+ struct thread_struct *t = &current->thread;
+ struct io_bitmap *iobm = t->io_bitmap;
+ size_t idx;
+
+ if (!iobm)
+ goto fault;
+
+ for (idx = port; idx < port + size; ++idx) {
+ if (test_bit(idx, iobm->bitmap))
+ goto fault;
+ }
+ }
+
+ return ES_OK;
+
+fault:
+ ctxt->fi.vector = X86_TRAP_GP;
+ ctxt->fi.error_code = 0;
+
+ return ES_EXCEPTION;
+}
+
/* Include code shared with pre-decompression boot stage */
#include "sev-shared.c"
@@ -1508,6 +1535,9 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
return ES_DECODE_FAILED;
}
+ if (user_mode(ctxt->regs))
+ return ES_UNSUPPORTED;
+
switch (mmio) {
case INSN_MMIO_WRITE:
memcpy(ghcb->shared_buffer, reg_data, bytes);
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 0544e30b4946..773132c3bf5a 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -360,14 +360,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
vcpu->arch.guest_supported_xcr0 =
cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent);
- /*
- * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if
- * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't
- * supported by the host.
- */
- vcpu->arch.guest_fpu.fpstate->user_xfeatures = vcpu->arch.guest_supported_xcr0 |
- XFEATURE_MASK_FPSSE;
-
kvm_update_pv_runtime(vcpu);
vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index dcd60b39e794..3e977dbbf993 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2759,13 +2759,17 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type)
{
u32 reg = kvm_lapic_get_reg(apic, lvt_type);
int vector, mode, trig_mode;
+ int r;
if (kvm_apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) {
vector = reg & APIC_VECTOR_MASK;
mode = reg & APIC_MODE_MASK;
trig_mode = reg & APIC_LVT_LEVEL_TRIGGER;
- return __apic_accept_irq(apic, mode, vector, 1, trig_mode,
- NULL);
+
+ r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL);
+ if (r && lvt_type == APIC_LVTPC)
+ kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED);
+ return r;
}
return 0;
}
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index edb89b51b383..9ae07db6f0f6 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -93,14 +93,6 @@ void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops)
#undef __KVM_X86_PMU_OP
}
-static void kvm_pmi_trigger_fn(struct irq_work *irq_work)
-{
- struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work);
- struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu);
-
- kvm_pmu_deliver_pmi(vcpu);
-}
-
static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi)
{
struct kvm_pmu *pmu = pmc_to_pmu(pmc);
@@ -124,20 +116,7 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi)
__set_bit(pmc->idx, (unsigned long *)&pmu->global_status);
}
- if (!pmc->intr || skip_pmi)
- return;
-
- /*
- * Inject PMI. If vcpu was in a guest mode during NMI PMI
- * can be ejected on a guest mode re-entry. Otherwise we can't
- * be sure that vcpu wasn't executing hlt instruction at the
- * time of vmexit and is not going to re-enter guest mode until
- * woken up. So we should wake it, but this is impossible from
- * NMI context. Do it from irq work instead.
- */
- if (in_pmi && !kvm_handling_nmi_from_guest(pmc->vcpu))
- irq_work_queue(&pmc_to_pmu(pmc)->irq_work);
- else
+ if (pmc->intr && !skip_pmi)
kvm_make_request(KVM_REQ_PMI, pmc->vcpu);
}
@@ -675,9 +654,6 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu)
void kvm_pmu_reset(struct kvm_vcpu *vcpu)
{
- struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
-
- irq_work_sync(&pmu->irq_work);
static_call(kvm_x86_pmu_reset)(vcpu);
}
@@ -687,7 +663,6 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu)
memset(pmu, 0, sizeof(*pmu));
static_call(kvm_x86_pmu_init)(vcpu);
- init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn);
pmu->event_count = 0;
pmu->need_cleanup = false;
kvm_pmu_refresh(vcpu);
diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h
index 7d9ba301c090..1d64113de488 100644
--- a/arch/x86/kvm/pmu.h
+++ b/arch/x86/kvm/pmu.h
@@ -74,6 +74,12 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc)
return counter & pmc_bitmask(pmc);
}
+static inline void pmc_write_counter(struct kvm_pmc *pmc, u64 val)
+{
+ pmc->counter += val - pmc_read_counter(pmc);
+ pmc->counter &= pmc_bitmask(pmc);
+}
+
static inline void pmc_release_perf_event(struct kvm_pmc *pmc)
{
if (pmc->perf_event) {
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 2092db892d7d..4b74ea91f4e6 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -529,8 +529,11 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu)
case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE:
WARN_ONCE(1, "Invalid backing page\n");
break;
+ case AVIC_IPI_FAILURE_INVALID_IPI_VECTOR:
+ /* Invalid IPI with vector < 16 */
+ break;
default:
- pr_err("Unknown IPI interception\n");
+ vcpu_unimpl(vcpu, "Unknown avic incomplete IPI interception\n");
}
return 1;
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index dd496c9e5f91..3fea8c47679e 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -1253,6 +1253,9 @@ void svm_leave_nested(struct kvm_vcpu *vcpu)
nested_svm_uninit_mmu_context(vcpu);
vmcb_mark_all_dirty(svm->vmcb);
+
+ if (kvm_apicv_activated(vcpu->kvm))
+ kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu);
}
kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c
index cef5a3d0abd0..373ff6a6687b 100644
--- a/arch/x86/kvm/svm/pmu.c
+++ b/arch/x86/kvm/svm/pmu.c
@@ -160,7 +160,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
/* MSR_PERFCTRn */
pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER);
if (pmc) {
- pmc->counter += data - pmc_read_counter(pmc);
+ pmc_write_counter(pmc, data);
pmc_update_sample_period(pmc);
return 0;
}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 9507df93f410..beea99c8e8e0 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -691,7 +691,7 @@ static int svm_hardware_enable(void)
*/
if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) {
struct sev_es_save_area *hostsa;
- u32 msr_hi;
+ u32 __maybe_unused msr_hi;
hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400);
@@ -913,8 +913,7 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept)
if (intercept == svm->x2avic_msrs_intercepted)
return;
- if (!x2avic_enabled ||
- !apic_x2apic_mode(svm->vcpu.arch.apic))
+ if (!x2avic_enabled)
return;
for (i = 0; i < MAX_DIRECT_ACCESS_MSRS; i++) {
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index f2efa0bf7ae8..820d3e1f6b4f 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -436,11 +436,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
if (!msr_info->host_initiated &&
!(msr & MSR_PMC_FULL_WIDTH_BIT))
data = (s64)(s32)data;
- pmc->counter += data - pmc_read_counter(pmc);
+ pmc_write_counter(pmc, data);
pmc_update_sample_period(pmc);
break;
} else if ((pmc = get_fixed_pmc(pmu, msr))) {
- pmc->counter += data - pmc_read_counter(pmc);
+ pmc_write_counter(pmc, data);
pmc_update_sample_period(pmc);
break;
} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9f18b06bbda6..41cce5031126 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5382,26 +5382,37 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
return 0;
}
-static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
- struct kvm_xsave *guest_xsave)
-{
- if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
- return;
-
- fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu,
- guest_xsave->region,
- sizeof(guest_xsave->region),
- vcpu->arch.pkru);
-}
static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu,
u8 *state, unsigned int size)
{
+ /*
+ * Only copy state for features that are enabled for the guest. The
+ * state itself isn't problematic, but setting bits in the header for
+ * features that are supported in *this* host but not exposed to the
+ * guest can result in KVM_SET_XSAVE failing when live migrating to a
+ * compatible host without the features that are NOT exposed to the
+ * guest.
+ *
+ * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if
+ * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't
+ * supported by the host.
+ */
+ u64 supported_xcr0 = vcpu->arch.guest_supported_xcr0 |
+ XFEATURE_MASK_FPSSE;
+
if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
return;
- fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu,
- state, size, vcpu->arch.pkru);
+ fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, state, size,
+ supported_xcr0, vcpu->arch.pkru);
+}
+
+static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
+ struct kvm_xsave *guest_xsave)
+{
+ return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region,
+ sizeof(guest_xsave->region));
}
static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
@@ -12843,6 +12854,9 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
return true;
#endif
+ if (kvm_test_request(KVM_REQ_PMI, vcpu))
+ return true;
+
if (kvm_arch_interrupt_allowed(vcpu) &&
(kvm_cpu_has_interrupt(vcpu) ||
kvm_guest_apic_has_interrupt(vcpu)))
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 884cb51c8f67..234a84ecde8b 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -1478,7 +1478,7 @@ static int dev_get_regmap_match(struct device *dev, void *res, void *data)
/* If the user didn't specify a name match any */
if (data)
- return !strcmp((*r)->name, data);
+ return (*r)->name && !strcmp((*r)->name, data);
else
return 1;
}
diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index 84c2c2e1122f..277d039ecbb4 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -962,13 +962,10 @@ static void btrtl_dmp_hdr(struct hci_dev *hdev, struct sk_buff *skb)
skb_put_data(skb, buf, strlen(buf));
}
-static int btrtl_register_devcoredump_support(struct hci_dev *hdev)
+static void btrtl_register_devcoredump_support(struct hci_dev *hdev)
{
- int err;
+ hci_devcd_register(hdev, btrtl_coredump, btrtl_dmp_hdr, NULL);
- err = hci_devcd_register(hdev, btrtl_coredump, btrtl_dmp_hdr, NULL);
-
- return err;
}
void btrtl_set_driver_name(struct hci_dev *hdev, const char *driver_name)
@@ -1255,8 +1252,7 @@ int btrtl_download_firmware(struct hci_dev *hdev,
}
done:
- if (!err)
- err = btrtl_register_devcoredump_support(hdev);
+ btrtl_register_devcoredump_support(hdev);
return err;
}
diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index 40e2b9fa11a2..f3892e9ce800 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -74,7 +74,10 @@ static int vhci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
struct vhci_data *data = hci_get_drvdata(hdev);
memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1);
+
+ mutex_lock(&data->open_mutex);
skb_queue_tail(&data->readq, skb);
+ mutex_unlock(&data->open_mutex);
wake_up_interruptible(&data->read_wait);
return 0;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index ed7212e61c54..51d47eda1c87 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4023,7 +4023,7 @@ static inline const void *bond_pull_data(struct sk_buff *skb,
if (likely(n <= hlen))
return data;
else if (skb && likely(pskb_may_pull(skb, n)))
- return skb->head;
+ return skb->data;
return NULL;
}
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 72374b066f64..cd1f240c90f3 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -617,17 +617,16 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds)
dn = of_find_compatible_node(NULL, NULL, "brcm,unimac-mdio");
priv->master_mii_bus = of_mdio_find_bus(dn);
if (!priv->master_mii_bus) {
- of_node_put(dn);
- return -EPROBE_DEFER;
+ err = -EPROBE_DEFER;
+ goto err_of_node_put;
}
- get_device(&priv->master_mii_bus->dev);
priv->master_mii_dn = dn;
priv->slave_mii_bus = mdiobus_alloc();
if (!priv->slave_mii_bus) {
- of_node_put(dn);
- return -ENOMEM;
+ err = -ENOMEM;
+ goto err_put_master_mii_bus_dev;
}
priv->slave_mii_bus->priv = priv;
@@ -684,11 +683,17 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds)
}
err = mdiobus_register(priv->slave_mii_bus);
- if (err && dn) {
- mdiobus_free(priv->slave_mii_bus);
- of_node_put(dn);
- }
+ if (err && dn)
+ goto err_free_slave_mii_bus;
+ return 0;
+
+err_free_slave_mii_bus:
+ mdiobus_free(priv->slave_mii_bus);
+err_put_master_mii_bus_dev:
+ put_device(&priv->master_mii_bus->dev);
+err_of_node_put:
+ of_node_put(dn);
return err;
}
@@ -696,6 +701,7 @@ static void bcm_sf2_mdio_unregister(struct bcm_sf2_priv *priv)
{
mdiobus_unregister(priv->slave_mii_bus);
mdiobus_free(priv->slave_mii_bus);
+ put_device(&priv->master_mii_bus->dev);
of_node_put(priv->master_mii_dn);
}
diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
index 5fc64e47568a..d567e42e1760 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
@@ -911,7 +911,7 @@ static int csk_wait_memory(struct chtls_dev *cdev,
struct sock *sk, long *timeo_p)
{
DEFINE_WAIT_FUNC(wait, woken_wake_function);
- int err = 0;
+ int ret, err = 0;
long current_timeo;
long vm_wait = 0;
bool noblock;
@@ -942,10 +942,13 @@ static int csk_wait_memory(struct chtls_dev *cdev,
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
sk->sk_write_pending++;
- sk_wait_event(sk, &current_timeo, sk->sk_err ||
- (sk->sk_shutdown & SEND_SHUTDOWN) ||
- (csk_mem_free(cdev, sk) && !vm_wait), &wait);
+ ret = sk_wait_event(sk, &current_timeo, sk->sk_err ||
+ (sk->sk_shutdown & SEND_SHUTDOWN) ||
+ (csk_mem_free(cdev, sk) && !vm_wait),
+ &wait);
sk->sk_write_pending--;
+ if (ret < 0)
+ goto do_error;
if (vm_wait) {
vm_wait -= current_timeo;
@@ -1348,6 +1351,7 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int copied = 0;
int target;
long timeo;
+ int ret;
buffers_freed = 0;
@@ -1423,7 +1427,11 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
if (copied >= target)
break;
chtls_cleanup_rbuf(sk, copied);
- sk_wait_data(sk, &timeo, NULL);
+ ret = sk_wait_data(sk, &timeo, NULL);
+ if (ret < 0) {
+ copied = copied ? : ret;
+ goto unlock;
+ }
continue;
found_ok_skb:
if (!skb->len) {
@@ -1518,6 +1526,8 @@ skip_copy:
if (buffers_freed)
chtls_cleanup_rbuf(sk, copied);
+
+unlock:
release_sock(sk);
return copied;
}
@@ -1534,6 +1544,7 @@ static int peekmsg(struct sock *sk, struct msghdr *msg,
int copied = 0;
size_t avail; /* amount of available data in current skb */
long timeo;
+ int ret;
lock_sock(sk);
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
@@ -1585,7 +1596,12 @@ static int peekmsg(struct sock *sk, struct msghdr *msg,
release_sock(sk);
lock_sock(sk);
} else {
- sk_wait_data(sk, &timeo, NULL);
+ ret = sk_wait_data(sk, &timeo, NULL);
+ if (ret < 0) {
+ /* here 'copied' is 0 due to previous checks */
+ copied = ret;
+ break;
+ }
}
if (unlikely(peek_seq != tp->copied_seq)) {
@@ -1656,6 +1672,7 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int copied = 0;
long timeo;
int target; /* Read at least this many bytes */
+ int ret;
buffers_freed = 0;
@@ -1747,7 +1764,11 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
if (copied >= target)
break;
chtls_cleanup_rbuf(sk, copied);
- sk_wait_data(sk, &timeo, NULL);
+ ret = sk_wait_data(sk, &timeo, NULL);
+ if (ret < 0) {
+ copied = copied ? : ret;
+ goto unlock;
+ }
continue;
found_ok_skb:
@@ -1816,6 +1837,7 @@ skip_copy:
if (buffers_freed)
chtls_cleanup_rbuf(sk, copied);
+unlock:
release_sock(sk);
return copied;
}
diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index d1da7413dc4d..e84a066aa1a4 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -146,7 +146,7 @@ static int gve_prefill_rx_pages(struct gve_rx_ring *rx)
err = gve_rx_alloc_buffer(priv, &priv->pdev->dev, &rx->data.page_info[i],
&rx->data.data_ring[i]);
if (err)
- goto alloc_err;
+ goto alloc_err_rda;
}
if (!rx->data.raw_addressing) {
@@ -171,12 +171,26 @@ static int gve_prefill_rx_pages(struct gve_rx_ring *rx)
return slots;
alloc_err_qpl:
+ /* Fully free the copy pool pages. */
while (j--) {
page_ref_sub(rx->qpl_copy_pool[j].page,
rx->qpl_copy_pool[j].pagecnt_bias - 1);
put_page(rx->qpl_copy_pool[j].page);
}
-alloc_err:
+
+ /* Do not fully free QPL pages - only remove the bias added in this
+ * function with gve_setup_rx_buffer.
+ */
+ while (i--)
+ page_ref_sub(rx->data.page_info[i].page,
+ rx->data.page_info[i].pagecnt_bias - 1);
+
+ gve_unassign_qpl(priv, rx->data.qpl->id);
+ rx->data.qpl = NULL;
+
+ return err;
+
+alloc_err_rda:
while (i--)
gve_rx_free_buffer(&priv->pdev->dev,
&rx->data.page_info[i],
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index eeef20f77106..1b493854f522 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -1082,7 +1082,7 @@ void i40e_clear_hw(struct i40e_hw *hw)
I40E_PFLAN_QALLOC_FIRSTQ_SHIFT;
j = (val & I40E_PFLAN_QALLOC_LASTQ_MASK) >>
I40E_PFLAN_QALLOC_LASTQ_SHIFT;
- if (val & I40E_PFLAN_QALLOC_VALID_MASK)
+ if (val & I40E_PFLAN_QALLOC_VALID_MASK && j >= base_queue)
num_queues = (j - base_queue) + 1;
else
num_queues = 0;
@@ -1092,7 +1092,7 @@ void i40e_clear_hw(struct i40e_hw *hw)
I40E_PF_VT_PFALLOC_FIRSTVF_SHIFT;
j = (val & I40E_PF_VT_PFALLOC_LASTVF_MASK) >>
I40E_PF_VT_PFALLOC_LASTVF_SHIFT;
- if (val & I40E_PF_VT_PFALLOC_VALID_MASK)
+ if (val & I40E_PF_VT_PFALLOC_VALID_MASK && j >= i)
num_vfs = (j - i) + 1;
else
num_vfs = 0;
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 7bf9b7069754..73bbf06a76db 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1201,8 +1201,7 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
ctxt->info.q_opt_rss = ((lut_type << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) &
ICE_AQ_VSI_Q_OPT_RSS_LUT_M) |
- ((hash_type << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) &
- ICE_AQ_VSI_Q_OPT_RSS_HASH_M);
+ (hash_type & ICE_AQ_VSI_Q_OPT_RSS_HASH_M);
}
static void
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index c8286adae946..7784135160fd 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -6,6 +6,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <generated/utsrelease.h>
+#include <linux/crash_dump.h>
#include "ice.h"
#include "ice_base.h"
#include "ice_lib.h"
@@ -4683,6 +4684,9 @@ static void ice_init_features(struct ice_pf *pf)
static void ice_deinit_features(struct ice_pf *pf)
{
+ if (ice_is_safe_mode(pf))
+ return;
+
ice_deinit_lag(pf);
if (test_bit(ICE_FLAG_DCB_CAPABLE, pf->flags))
ice_cfg_lldp_mib_change(&pf->hw, false);
@@ -5014,6 +5018,20 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
return -EINVAL;
}
+ /* when under a kdump kernel initiate a reset before enabling the
+ * device in order to clear out any pending DMA transactions. These
+ * transactions can cause some systems to machine check when doing
+ * the pcim_enable_device() below.
+ */
+ if (is_kdump_kernel()) {
+ pci_save_state(pdev);
+ pci_clear_master(pdev);
+ err = pcie_flr(pdev);
+ if (err)
+ return err;
+ pci_restore_state(pdev);
+ }
+
/* this driver uses devres, see
* Documentation/driver-api/driver-model/devres.rst
*/
diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
index dbc518ff8276..5b46ca47c8e5 100644
--- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
+++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c
@@ -715,20 +715,19 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb,
hw_desc->dptr = tx_buffer->sglist_dma;
}
- /* Flush the hw descriptor before writing to doorbell */
- wmb();
-
- /* Ring Doorbell to notify the NIC there is a new packet */
- writel(1, iq->doorbell_reg);
+ netdev_tx_sent_queue(iq->netdev_q, skb->len);
+ skb_tx_timestamp(skb);
atomic_inc(&iq->instr_pending);
wi++;
if (wi == iq->max_count)
wi = 0;
iq->host_write_index = wi;
+ /* Flush the hw descriptor before writing to doorbell */
+ wmb();
- netdev_tx_sent_queue(iq->netdev_q, skb->len);
+ /* Ring Doorbell to notify the NIC there is a new packet */
+ writel(1, iq->doorbell_reg);
iq->stats.instr_posted++;
- skb_tx_timestamp(skb);
return NETDEV_TX_OK;
dma_map_sg_err:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index afb348579577..c22b0ad0c870 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -2186,52 +2186,23 @@ static u16 cmdif_rev(struct mlx5_core_dev *dev)
int mlx5_cmd_init(struct mlx5_core_dev *dev)
{
- int size = sizeof(struct mlx5_cmd_prot_block);
- int align = roundup_pow_of_two(size);
struct mlx5_cmd *cmd = &dev->cmd;
- u32 cmd_l;
- int err;
-
- cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0);
- if (!cmd->pool)
- return -ENOMEM;
- err = alloc_cmd_page(dev, cmd);
- if (err)
- goto err_free_pool;
-
- cmd_l = (u32)(cmd->dma);
- if (cmd_l & 0xfff) {
- mlx5_core_err(dev, "invalid command queue address\n");
- err = -ENOMEM;
- goto err_cmd_page;
- }
cmd->checksum_disabled = 1;
spin_lock_init(&cmd->alloc_lock);
spin_lock_init(&cmd->token_lock);
- create_msg_cache(dev);
-
set_wqname(dev);
cmd->wq = create_singlethread_workqueue(cmd->wq_name);
if (!cmd->wq) {
mlx5_core_err(dev, "failed to create command workqueue\n");
- err = -ENOMEM;
- goto err_cache;
+ return -ENOMEM;
}
mlx5_cmdif_debugfs_init(dev);
return 0;
-
-err_cache:
- destroy_msg_cache(dev);
-err_cmd_page:
- free_cmd_page(dev, cmd);
-err_free_pool:
- dma_pool_destroy(cmd->pool);
- return err;
}
void mlx5_cmd_cleanup(struct mlx5_core_dev *dev)
@@ -2240,15 +2211,15 @@ void mlx5_cmd_cleanup(struct mlx5_core_dev *dev)
mlx5_cmdif_debugfs_cleanup(dev);
destroy_workqueue(cmd->wq);
- destroy_msg_cache(dev);
- free_cmd_page(dev, cmd);
- dma_pool_destroy(cmd->pool);
}
int mlx5_cmd_enable(struct mlx5_core_dev *dev)
{
+ int size = sizeof(struct mlx5_cmd_prot_block);
+ int align = roundup_pow_of_two(size);
struct mlx5_cmd *cmd = &dev->cmd;
u32 cmd_h, cmd_l;
+ int err;
memset(&cmd->vars, 0, sizeof(cmd->vars));
cmd->vars.cmdif_rev = cmdif_rev(dev);
@@ -2281,10 +2252,21 @@ int mlx5_cmd_enable(struct mlx5_core_dev *dev)
sema_init(&cmd->vars.pages_sem, 1);
sema_init(&cmd->vars.throttle_sem, DIV_ROUND_UP(cmd->vars.max_reg_cmds, 2));
+ cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0);
+ if (!cmd->pool)
+ return -ENOMEM;
+
+ err = alloc_cmd_page(dev, cmd);
+ if (err)
+ goto err_free_pool;
+
cmd_h = (u32)((u64)(cmd->dma) >> 32);
cmd_l = (u32)(cmd->dma);
- if (WARN_ON(cmd_l & 0xfff))
- return -EINVAL;
+ if (cmd_l & 0xfff) {
+ mlx5_core_err(dev, "invalid command queue address\n");
+ err = -ENOMEM;
+ goto err_cmd_page;
+ }
iowrite32be(cmd_h, &dev->iseg->cmdq_addr_h);
iowrite32be(cmd_l, &dev->iseg->cmdq_addr_l_sz);
@@ -2297,17 +2279,27 @@ int mlx5_cmd_enable(struct mlx5_core_dev *dev)
cmd->mode = CMD_MODE_POLLING;
cmd->allowed_opcode = CMD_ALLOWED_OPCODE_ALL;
+ create_msg_cache(dev);
create_debugfs_files(dev);
return 0;
+
+err_cmd_page:
+ free_cmd_page(dev, cmd);
+err_free_pool:
+ dma_pool_destroy(cmd->pool);
+ return err;
}
void mlx5_cmd_disable(struct mlx5_core_dev *dev)
{
struct mlx5_cmd *cmd = &dev->cmd;
- clean_debug_files(dev);
flush_workqueue(cmd->wq);
+ clean_debug_files(dev);
+ destroy_msg_cache(dev);
+ free_cmd_page(dev, cmd);
+ dma_pool_destroy(cmd->pool);
}
void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index 7c0f2adbea00..ad789349c06e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -848,7 +848,7 @@ static void mlx5_fw_tracer_ownership_change(struct work_struct *work)
mlx5_core_dbg(tracer->dev, "FWTracer: ownership changed, current=(%d)\n", tracer->owner);
if (tracer->owner) {
- tracer->owner = false;
+ mlx5_fw_tracer_ownership_acquire(tracer);
return;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
index 0fef853eab62..5d128c5b4529 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
@@ -467,6 +467,17 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb,
/* only handle the event on peers */
if (mlx5_esw_bridge_is_local(dev, rep, esw))
break;
+
+ fdb_info = container_of(info,
+ struct switchdev_notifier_fdb_info,
+ info);
+ /* Mark for deletion to prevent the update wq task from
+ * spuriously refreshing the entry which would mark it again as
+ * offloaded in SW bridge. After this fallthrough to regular
+ * async delete code.
+ */
+ mlx5_esw_bridge_fdb_mark_deleted(dev, vport_num, esw_owner_vhca_id, br_offloads,
+ fdb_info);
fallthrough;
case SWITCHDEV_FDB_ADD_TO_DEVICE:
case SWITCHDEV_FDB_DEL_TO_DEVICE:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
index 1730f6a716ee..b10e40e1a9c1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -24,7 +24,8 @@ static int mlx5e_set_int_port_tunnel(struct mlx5e_priv *priv,
route_dev = dev_get_by_index(dev_net(e->out_dev), e->route_dev_ifindex);
- if (!route_dev || !netif_is_ovs_master(route_dev))
+ if (!route_dev || !netif_is_ovs_master(route_dev) ||
+ attr->parse_attr->filter_dev == e->out_dev)
goto out;
err = mlx5e_set_fwd_to_int_port_actions(priv, attr, e->route_dev_ifindex,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 12f56d0db0af..8bed17d8fe56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -874,11 +874,11 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
}
out:
- if (flags & XDP_XMIT_FLUSH) {
- if (sq->mpwqe.wqe)
- mlx5e_xdp_mpwqe_complete(sq);
+ if (sq->mpwqe.wqe)
+ mlx5e_xdp_mpwqe_complete(sq);
+
+ if (flags & XDP_XMIT_FLUSH)
mlx5e_xmit_xdp_doorbell(sq);
- }
return nxmit;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 2fdb8895aecd..fd1cce542b68 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -701,7 +701,7 @@ mlx5e_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
/* update HW stats in background for next time */
mlx5e_queue_update_stats(priv);
- memcpy(stats, &priv->stats.vf_vport, sizeof(*stats));
+ mlx5e_stats_copy_rep_stats(stats, &priv->stats.rep_stats);
}
static int mlx5e_rep_change_mtu(struct net_device *netdev, int new_mtu)
@@ -769,6 +769,7 @@ static int mlx5e_rep_max_nch_limit(struct mlx5_core_dev *mdev)
static void mlx5e_build_rep_params(struct net_device *netdev)
{
+ const bool take_rtnl = netdev->reg_state == NETREG_REGISTERED;
struct mlx5e_priv *priv = netdev_priv(netdev);
struct mlx5e_rep_priv *rpriv = priv->ppriv;
struct mlx5_eswitch_rep *rep = rpriv->rep;
@@ -794,8 +795,15 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
/* RQ */
mlx5e_build_rq_params(mdev, params);
+ /* If netdev is already registered (e.g. move from nic profile to uplink,
+ * RTNL lock must be held before triggering netdev notifiers.
+ */
+ if (take_rtnl)
+ rtnl_lock();
/* update XDP supported features */
mlx5e_set_xdp_feature(netdev);
+ if (take_rtnl)
+ rtnl_unlock();
/* CQ moderation params */
params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 3fd11b0761e0..8d9743a5e42c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -457,26 +457,41 @@ static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk)
static int mlx5e_refill_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk)
{
int remaining = wqe_bulk;
- int i = 0;
+ int total_alloc = 0;
+ int refill_alloc;
+ int refill;
/* The WQE bulk is split into smaller bulks that are sized
* according to the page pool cache refill size to avoid overflowing
* the page pool cache due to too many page releases at once.
*/
do {
- int refill = min_t(u16, rq->wqe.info.refill_unit, remaining);
- int alloc_count;
+ refill = min_t(u16, rq->wqe.info.refill_unit, remaining);
- mlx5e_free_rx_wqes(rq, ix + i, refill);
- alloc_count = mlx5e_alloc_rx_wqes(rq, ix + i, refill);
- i += alloc_count;
- if (unlikely(alloc_count != refill))
- break;
+ mlx5e_free_rx_wqes(rq, ix + total_alloc, refill);
+ refill_alloc = mlx5e_alloc_rx_wqes(rq, ix + total_alloc, refill);
+ if (unlikely(refill_alloc != refill))
+ goto err_free;
+ total_alloc += refill_alloc;
remaining -= refill;
} while (remaining);
- return i;
+ return total_alloc;
+
+err_free:
+ mlx5e_free_rx_wqes(rq, ix, total_alloc + refill_alloc);
+
+ for (int i = 0; i < total_alloc + refill; i++) {
+ int j = mlx5_wq_cyc_ctr2ix(&rq->wqe.wq, ix + i);
+ struct mlx5e_wqe_frag_info *frag;
+
+ frag = get_frag(rq, j);
+ for (int k = 0; k < rq->wqe.info.num_frags; k++, frag++)
+ frag->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE);
+ }
+
+ return 0;
}
static void
@@ -816,6 +831,8 @@ err_unmap:
mlx5e_page_release_fragmented(rq, frag_page);
}
+ bitmap_fill(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe);
+
err:
rq->stats->buff_alloc_err++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 176fa5976259..477c547dcc04 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -484,11 +484,20 @@ struct mlx5e_stats {
struct mlx5e_vnic_env_stats vnic;
struct mlx5e_vport_stats vport;
struct mlx5e_pport_stats pport;
- struct rtnl_link_stats64 vf_vport;
struct mlx5e_pcie_stats pcie;
struct mlx5e_rep_stats rep_stats;
};
+static inline void mlx5e_stats_copy_rep_stats(struct rtnl_link_stats64 *vf_vport,
+ struct mlx5e_rep_stats *rep_stats)
+{
+ memset(vf_vport, 0, sizeof(*vf_vport));
+ vf_vport->rx_packets = rep_stats->vport_rx_packets;
+ vf_vport->tx_packets = rep_stats->vport_tx_packets;
+ vf_vport->rx_bytes = rep_stats->vport_rx_bytes;
+ vf_vport->tx_bytes = rep_stats->vport_tx_bytes;
+}
+
extern mlx5e_stats_grp_t mlx5e_nic_stats_grps[];
unsigned int mlx5e_nic_stats_grps_num(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index c24828b688ac..c8590483ddc6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -4972,7 +4972,8 @@ static int scan_tc_matchall_fdb_actions(struct mlx5e_priv *priv,
if (err)
return err;
- rpriv->prev_vf_vport_stats = priv->stats.vf_vport;
+ mlx5e_stats_copy_rep_stats(&rpriv->prev_vf_vport_stats,
+ &priv->stats.rep_stats);
break;
default:
NL_SET_ERR_MSG_MOD(extack, "mlx5 supports only police action for matchall");
@@ -5012,7 +5013,7 @@ void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv,
u64 dbytes;
u64 dpkts;
- cur_stats = priv->stats.vf_vport;
+ mlx5e_stats_copy_rep_stats(&cur_stats, &priv->stats.rep_stats);
dpkts = cur_stats.rx_packets - rpriv->prev_vf_vport_stats.rx_packets;
dbytes = cur_stats.rx_bytes - rpriv->prev_vf_vport_stats.rx_bytes;
rpriv->prev_vf_vport_stats = cur_stats;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
index e36294b7ade2..1b9bc32efd6f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
@@ -1748,6 +1748,28 @@ void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16
entry->lastuse = jiffies;
}
+void mlx5_esw_bridge_fdb_mark_deleted(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+ struct mlx5_esw_bridge_offloads *br_offloads,
+ struct switchdev_notifier_fdb_info *fdb_info)
+{
+ struct mlx5_esw_bridge_fdb_entry *entry;
+ struct mlx5_esw_bridge *bridge;
+
+ bridge = mlx5_esw_bridge_from_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
+ if (!bridge)
+ return;
+
+ entry = mlx5_esw_bridge_fdb_lookup(bridge, fdb_info->addr, fdb_info->vid);
+ if (!entry) {
+ esw_debug(br_offloads->esw->dev,
+ "FDB mark deleted entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n",
+ fdb_info->addr, fdb_info->vid, vport_num);
+ return;
+ }
+
+ entry->flags |= MLX5_ESW_BRIDGE_FLAG_DELETED;
+}
+
void mlx5_esw_bridge_fdb_create(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
struct mlx5_esw_bridge_offloads *br_offloads,
struct switchdev_notifier_fdb_info *fdb_info)
@@ -1810,7 +1832,8 @@ void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads)
unsigned long lastuse =
(unsigned long)mlx5_fc_query_lastuse(entry->ingress_counter);
- if (entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER)
+ if (entry->flags & (MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER |
+ MLX5_ESW_BRIDGE_FLAG_DELETED))
continue;
if (time_after(lastuse, entry->lastuse))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h
index c2c7c70d99eb..d6f539161993 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h
@@ -62,6 +62,9 @@ int mlx5_esw_bridge_vport_peer_unlink(struct net_device *br_netdev, u16 vport_nu
void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
struct mlx5_esw_bridge_offloads *br_offloads,
struct switchdev_notifier_fdb_info *fdb_info);
+void mlx5_esw_bridge_fdb_mark_deleted(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+ struct mlx5_esw_bridge_offloads *br_offloads,
+ struct switchdev_notifier_fdb_info *fdb_info);
void mlx5_esw_bridge_fdb_create(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
struct mlx5_esw_bridge_offloads *br_offloads,
struct switchdev_notifier_fdb_info *fdb_info);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h
index 4911cc32161b..7c251af566c6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h
@@ -133,6 +133,7 @@ struct mlx5_esw_bridge_mdb_key {
enum {
MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER = BIT(0),
MLX5_ESW_BRIDGE_FLAG_PEER = BIT(1),
+ MLX5_ESW_BRIDGE_FLAG_DELETED = BIT(2),
};
enum {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index d4cde6555063..8d0b915a3121 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1038,11 +1038,8 @@ const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)
return ERR_PTR(err);
}
-static void mlx5_eswitch_event_handlers_register(struct mlx5_eswitch *esw)
+static void mlx5_eswitch_event_handler_register(struct mlx5_eswitch *esw)
{
- MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE);
- mlx5_eq_notifier_register(esw->dev, &esw->nb);
-
if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev)) {
MLX5_NB_INIT(&esw->esw_funcs.nb, mlx5_esw_funcs_changed_handler,
ESW_FUNCTIONS_CHANGED);
@@ -1050,13 +1047,11 @@ static void mlx5_eswitch_event_handlers_register(struct mlx5_eswitch *esw)
}
}
-static void mlx5_eswitch_event_handlers_unregister(struct mlx5_eswitch *esw)
+static void mlx5_eswitch_event_handler_unregister(struct mlx5_eswitch *esw)
{
if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev))
mlx5_eq_notifier_unregister(esw->dev, &esw->esw_funcs.nb);
- mlx5_eq_notifier_unregister(esw->dev, &esw->nb);
-
flush_workqueue(esw->work_queue);
}
@@ -1483,6 +1478,9 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs)
mlx5_eswitch_update_num_of_vfs(esw, num_vfs);
+ MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE);
+ mlx5_eq_notifier_register(esw->dev, &esw->nb);
+
if (esw->mode == MLX5_ESWITCH_LEGACY) {
err = esw_legacy_enable(esw);
} else {
@@ -1495,7 +1493,7 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs)
esw->fdb_table.flags |= MLX5_ESW_FDB_CREATED;
- mlx5_eswitch_event_handlers_register(esw);
+ mlx5_eswitch_event_handler_register(esw);
esw_info(esw->dev, "Enable: mode(%s), nvfs(%d), necvfs(%d), active vports(%d)\n",
esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
@@ -1622,7 +1620,8 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw)
*/
mlx5_esw_mode_change_notify(esw, MLX5_ESWITCH_LEGACY);
- mlx5_eswitch_event_handlers_unregister(esw);
+ mlx5_eq_notifier_unregister(esw->dev, &esw->nb);
+ mlx5_eswitch_event_handler_unregister(esw);
esw_info(esw->dev, "Disable: mode(%s), nvfs(%d), necvfs(%d), active vports(%d)\n",
esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 717a0b3f89bd..ab5ef254a748 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -113,7 +113,10 @@ static void qed_ll2b_complete_tx_packet(void *cxt,
static int qed_ll2_alloc_buffer(struct qed_dev *cdev,
u8 **data, dma_addr_t *phys_addr)
{
- *data = kmalloc(cdev->ll2->rx_size, GFP_ATOMIC);
+ size_t size = cdev->ll2->rx_size + NET_SKB_PAD +
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+ *data = kmalloc(size, GFP_ATOMIC);
if (!(*data)) {
DP_INFO(cdev, "Failed to allocate LL2 buffer data\n");
return -ENOMEM;
@@ -2589,7 +2592,7 @@ static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params)
INIT_LIST_HEAD(&cdev->ll2->list);
spin_lock_init(&cdev->ll2->lock);
- cdev->ll2->rx_size = NET_SKB_PAD + ETH_HLEN +
+ cdev->ll2->rx_size = PRM_DMA_PAD_BYTES_NUM + ETH_HLEN +
L1_CACHE_BYTES + params->mtu;
/* Allocate memory for LL2.
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 0a3346650e03..cac61f5d3fd4 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -90,12 +90,16 @@ config TI_CPTS
The unit can time stamp PTP UDP/IPv4 and Layer 2 packets, and the
driver offers a PTP Hardware Clock.
+config TI_K3_CPPI_DESC_POOL
+ tristate
+
config TI_K3_AM65_CPSW_NUSS
tristate "TI K3 AM654x/J721E CPSW Ethernet driver"
depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER
select NET_DEVLINK
select TI_DAVINCI_MDIO
select PHYLINK
+ select TI_K3_CPPI_DESC_POOL
imply PHY_TI_GMII_SEL
depends on TI_K3_AM65_CPTS || !TI_K3_AM65_CPTS
help
@@ -187,6 +191,7 @@ config TI_ICSSG_PRUETH
tristate "TI Gigabit PRU Ethernet driver"
select PHYLIB
select TI_ICSS_IEP
+ select TI_K3_CPPI_DESC_POOL
depends on PRU_REMOTEPROC
depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER
help
diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile
index 34fd7a716ba6..67bed861f31d 100644
--- a/drivers/net/ethernet/ti/Makefile
+++ b/drivers/net/ethernet/ti/Makefile
@@ -24,14 +24,15 @@ keystone_netcp-y := netcp_core.o cpsw_ale.o
obj-$(CONFIG_TI_KEYSTONE_NETCP_ETHSS) += keystone_netcp_ethss.o
keystone_netcp_ethss-y := netcp_ethss.o netcp_sgmii.o netcp_xgbepcsr.o cpsw_ale.o
+obj-$(CONFIG_TI_K3_CPPI_DESC_POOL) += k3-cppi-desc-pool.o
+
obj-$(CONFIG_TI_K3_AM65_CPSW_NUSS) += ti-am65-cpsw-nuss.o
-ti-am65-cpsw-nuss-y := am65-cpsw-nuss.o cpsw_sl.o am65-cpsw-ethtool.o cpsw_ale.o k3-cppi-desc-pool.o am65-cpsw-qos.o
+ti-am65-cpsw-nuss-y := am65-cpsw-nuss.o cpsw_sl.o am65-cpsw-ethtool.o cpsw_ale.o am65-cpsw-qos.o
ti-am65-cpsw-nuss-$(CONFIG_TI_K3_AM65_CPSW_SWITCHDEV) += am65-cpsw-switchdev.o
obj-$(CONFIG_TI_K3_AM65_CPTS) += am65-cpts.o
obj-$(CONFIG_TI_ICSSG_PRUETH) += icssg-prueth.o
-icssg-prueth-y := k3-cppi-desc-pool.o \
- icssg/icssg_prueth.o \
+icssg-prueth-y := icssg/icssg_prueth.o \
icssg/icssg_classifier.o \
icssg/icssg_queues.o \
icssg/icssg_config.o \
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c
index 933b84666574..b272361e378f 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_config.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.c
@@ -379,9 +379,9 @@ int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice)
/* Bitmask for ICSSG r30 commands */
static const struct icssg_r30_cmd emac_r32_bitmask[] = {
- {{0xffff0004, 0xffff0100, 0xffff0100, EMAC_NONE}}, /* EMAC_PORT_DISABLE */
+ {{0xffff0004, 0xffff0100, 0xffff0004, EMAC_NONE}}, /* EMAC_PORT_DISABLE */
{{0xfffb0040, 0xfeff0200, 0xfeff0200, EMAC_NONE}}, /* EMAC_PORT_BLOCK */
- {{0xffbb0000, 0xfcff0000, 0xdcff0000, EMAC_NONE}}, /* EMAC_PORT_FORWARD */
+ {{0xffbb0000, 0xfcff0000, 0xdcfb0000, EMAC_NONE}}, /* EMAC_PORT_FORWARD */
{{0xffbb0000, 0xfcff0000, 0xfcff2000, EMAC_NONE}}, /* EMAC_PORT_FORWARD_WO_LEARNING */
{{0xffff0001, EMAC_NONE, EMAC_NONE, EMAC_NONE}}, /* ACCEPT ALL */
{{0xfffe0002, EMAC_NONE, EMAC_NONE, EMAC_NONE}}, /* ACCEPT TAGGED */
diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.c b/drivers/net/ethernet/ti/icssg/icssg_stats.c
index bb0b33927e3b..3dbadddd7e35 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_stats.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_stats.c
@@ -9,6 +9,9 @@
#include "icssg_stats.h"
#include <linux/regmap.h>
+#define ICSSG_TX_PACKET_OFFSET 0xA0
+#define ICSSG_TX_BYTE_OFFSET 0xEC
+
static u32 stats_base[] = { 0x54c, /* Slice 0 stats start */
0xb18, /* Slice 1 stats start */
};
@@ -18,6 +21,7 @@ void emac_update_hardware_stats(struct prueth_emac *emac)
struct prueth *prueth = emac->prueth;
int slice = prueth_emac_slice(emac);
u32 base = stats_base[slice];
+ u32 tx_pkt_cnt = 0;
u32 val;
int i;
@@ -29,7 +33,12 @@ void emac_update_hardware_stats(struct prueth_emac *emac)
base + icssg_all_stats[i].offset,
val);
+ if (icssg_all_stats[i].offset == ICSSG_TX_PACKET_OFFSET)
+ tx_pkt_cnt = val;
+
emac->stats[i] += val;
+ if (icssg_all_stats[i].offset == ICSSG_TX_BYTE_OFFSET)
+ emac->stats[i] -= tx_pkt_cnt * 8;
}
}
diff --git a/drivers/net/ethernet/ti/k3-cppi-desc-pool.c b/drivers/net/ethernet/ti/k3-cppi-desc-pool.c
index 38cc12f9f133..05cc7aab1ec8 100644
--- a/drivers/net/ethernet/ti/k3-cppi-desc-pool.c
+++ b/drivers/net/ethernet/ti/k3-cppi-desc-pool.c
@@ -39,6 +39,7 @@ void k3_cppi_desc_pool_destroy(struct k3_cppi_desc_pool *pool)
gen_pool_destroy(pool->gen_pool); /* frees pool->name */
}
+EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_destroy);
struct k3_cppi_desc_pool *
k3_cppi_desc_pool_create_name(struct device *dev, size_t size,
@@ -98,29 +99,38 @@ gen_pool_create_fail:
devm_kfree(pool->dev, pool);
return ERR_PTR(ret);
}
+EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_create_name);
dma_addr_t k3_cppi_desc_pool_virt2dma(struct k3_cppi_desc_pool *pool,
void *addr)
{
return addr ? pool->dma_addr + (addr - pool->cpumem) : 0;
}
+EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_virt2dma);
void *k3_cppi_desc_pool_dma2virt(struct k3_cppi_desc_pool *pool, dma_addr_t dma)
{
return dma ? pool->cpumem + (dma - pool->dma_addr) : NULL;
}
+EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_dma2virt);
void *k3_cppi_desc_pool_alloc(struct k3_cppi_desc_pool *pool)
{
return (void *)gen_pool_alloc(pool->gen_pool, pool->desc_size);
}
+EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_alloc);
void k3_cppi_desc_pool_free(struct k3_cppi_desc_pool *pool, void *addr)
{
gen_pool_free(pool->gen_pool, (unsigned long)addr, pool->desc_size);
}
+EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_free);
size_t k3_cppi_desc_pool_avail(struct k3_cppi_desc_pool *pool)
{
return gen_pool_avail(pool->gen_pool) / pool->desc_size;
}
+EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_avail);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("TI K3 CPPI5 descriptors pool API");
diff --git a/drivers/net/mdio/mdio-mux.c b/drivers/net/mdio/mdio-mux.c
index a881e3523328..bef4cce71287 100644
--- a/drivers/net/mdio/mdio-mux.c
+++ b/drivers/net/mdio/mdio-mux.c
@@ -55,6 +55,27 @@ out:
return r;
}
+static int mdio_mux_read_c45(struct mii_bus *bus, int phy_id, int dev_addr,
+ int regnum)
+{
+ struct mdio_mux_child_bus *cb = bus->priv;
+ struct mdio_mux_parent_bus *pb = cb->parent;
+ int r;
+
+ mutex_lock_nested(&pb->mii_bus->mdio_lock, MDIO_MUTEX_MUX);
+ r = pb->switch_fn(pb->current_child, cb->bus_number, pb->switch_data);
+ if (r)
+ goto out;
+
+ pb->current_child = cb->bus_number;
+
+ r = pb->mii_bus->read_c45(pb->mii_bus, phy_id, dev_addr, regnum);
+out:
+ mutex_unlock(&pb->mii_bus->mdio_lock);
+
+ return r;
+}
+
/*
* The parent bus' lock is used to order access to the switch_fn.
*/
@@ -80,6 +101,28 @@ out:
return r;
}
+static int mdio_mux_write_c45(struct mii_bus *bus, int phy_id, int dev_addr,
+ int regnum, u16 val)
+{
+ struct mdio_mux_child_bus *cb = bus->priv;
+ struct mdio_mux_parent_bus *pb = cb->parent;
+
+ int r;
+
+ mutex_lock_nested(&pb->mii_bus->mdio_lock, MDIO_MUTEX_MUX);
+ r = pb->switch_fn(pb->current_child, cb->bus_number, pb->switch_data);
+ if (r)
+ goto out;
+
+ pb->current_child = cb->bus_number;
+
+ r = pb->mii_bus->write_c45(pb->mii_bus, phy_id, dev_addr, regnum, val);
+out:
+ mutex_unlock(&pb->mii_bus->mdio_lock);
+
+ return r;
+}
+
static int parent_count;
static void mdio_mux_uninit_children(struct mdio_mux_parent_bus *pb)
@@ -173,6 +216,10 @@ int mdio_mux_init(struct device *dev,
cb->mii_bus->parent = dev;
cb->mii_bus->read = mdio_mux_read;
cb->mii_bus->write = mdio_mux_write;
+ if (parent_bus->read_c45)
+ cb->mii_bus->read_c45 = mdio_mux_read_c45;
+ if (parent_bus->write_c45)
+ cb->mii_bus->write_c45 = mdio_mux_write_c45;
r = of_mdiobus_register(cb->mii_bus, child_bus_node);
if (r) {
mdiobus_free(cb->mii_bus);
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 8478b081c058..97638ba7ae85 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -894,6 +894,9 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev)
.name = _name, \
/* PHY_BASIC_FEATURES */ \
.flags = PHY_IS_INTERNAL, \
+ .get_sset_count = bcm_phy_get_sset_count, \
+ .get_strings = bcm_phy_get_strings, \
+ .get_stats = bcm7xxx_28nm_get_phy_stats, \
.probe = bcm7xxx_28nm_probe, \
.config_init = bcm7xxx_16nm_ephy_config_init, \
.config_aneg = genphy_config_aneg, \
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 89ab9efe522c..afa5497f7c35 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -3073,10 +3073,11 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
struct net *net = sock_net(&tfile->sk);
struct tun_struct *tun;
void __user* argp = (void __user*)arg;
- unsigned int ifindex, carrier;
+ unsigned int carrier;
struct ifreq ifr;
kuid_t owner;
kgid_t group;
+ int ifindex;
int sndbuf;
int vnet_hdr_sz;
int le;
@@ -3132,7 +3133,9 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
ret = -EFAULT;
if (copy_from_user(&ifindex, argp, sizeof(ifindex)))
goto unlock;
-
+ ret = -EINVAL;
+ if (ifindex < 0)
+ goto unlock;
ret = 0;
tfile->ifindex = ifindex;
goto unlock;
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index 563ecd27b93e..17da42fe605c 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -897,7 +897,7 @@ static int smsc95xx_reset(struct usbnet *dev)
if (timeout >= 100) {
netdev_warn(dev->net, "timeout waiting for completion of Lite Reset\n");
- return ret;
+ return -ETIMEDOUT;
}
ret = smsc95xx_set_mac_address(dev);
diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.c b/drivers/net/wwan/iosm/iosm_ipc_imem.c
index 635301d677e1..829515a601b3 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_imem.c
+++ b/drivers/net/wwan/iosm/iosm_ipc_imem.c
@@ -4,7 +4,6 @@
*/
#include <linux/delay.h>
-#include <linux/pm_runtime.h>
#include "iosm_ipc_chnl_cfg.h"
#include "iosm_ipc_devlink.h"
@@ -632,11 +631,6 @@ static void ipc_imem_run_state_worker(struct work_struct *instance)
/* Complete all memory stores after setting bit */
smp_mb__after_atomic();
- if (ipc_imem->pcie->pci->device == INTEL_CP_DEVICE_7560_ID) {
- pm_runtime_mark_last_busy(ipc_imem->dev);
- pm_runtime_put_autosuspend(ipc_imem->dev);
- }
-
return;
err_ipc_mux_deinit:
@@ -1240,7 +1234,6 @@ void ipc_imem_cleanup(struct iosm_imem *ipc_imem)
/* forward MDM_NOT_READY to listeners */
ipc_uevent_send(ipc_imem->dev, UEVENT_MDM_NOT_READY);
- pm_runtime_get_sync(ipc_imem->dev);
hrtimer_cancel(&ipc_imem->td_alloc_timer);
hrtimer_cancel(&ipc_imem->tdupdate_timer);
@@ -1426,16 +1419,6 @@ struct iosm_imem *ipc_imem_init(struct iosm_pcie *pcie, unsigned int device_id,
set_bit(IOSM_DEVLINK_INIT, &ipc_imem->flag);
}
-
- if (!pm_runtime_enabled(ipc_imem->dev))
- pm_runtime_enable(ipc_imem->dev);
-
- pm_runtime_set_autosuspend_delay(ipc_imem->dev,
- IPC_MEM_AUTO_SUSPEND_DELAY_MS);
- pm_runtime_use_autosuspend(ipc_imem->dev);
- pm_runtime_allow(ipc_imem->dev);
- pm_runtime_mark_last_busy(ipc_imem->dev);
-
return ipc_imem;
devlink_channel_fail:
ipc_devlink_deinit(ipc_imem->ipc_devlink);
diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.h b/drivers/net/wwan/iosm/iosm_ipc_imem.h
index 0144b45e2afb..5664ac507c90 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_imem.h
+++ b/drivers/net/wwan/iosm/iosm_ipc_imem.h
@@ -103,8 +103,6 @@ struct ipc_chnl_cfg;
#define FULLY_FUNCTIONAL 0
#define IOSM_DEVLINK_INIT 1
-#define IPC_MEM_AUTO_SUSPEND_DELAY_MS 5000
-
/* List of the supported UL/DL pipes. */
enum ipc_mem_pipes {
IPC_MEM_PIPE_0 = 0,
diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.c b/drivers/net/wwan/iosm/iosm_ipc_pcie.c
index 3a259c9abefd..04517bd3325a 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_pcie.c
+++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.c
@@ -6,7 +6,6 @@
#include <linux/acpi.h>
#include <linux/bitfield.h>
#include <linux/module.h>
-#include <linux/pm_runtime.h>
#include <net/rtnetlink.h>
#include "iosm_ipc_imem.h"
@@ -438,8 +437,7 @@ static int __maybe_unused ipc_pcie_resume_cb(struct device *dev)
return 0;
}
-static DEFINE_RUNTIME_DEV_PM_OPS(iosm_ipc_pm, ipc_pcie_suspend_cb,
- ipc_pcie_resume_cb, NULL);
+static SIMPLE_DEV_PM_OPS(iosm_ipc_pm, ipc_pcie_suspend_cb, ipc_pcie_resume_cb);
static struct pci_driver iosm_ipc_driver = {
.name = KBUILD_MODNAME,
diff --git a/drivers/net/wwan/iosm/iosm_ipc_port.c b/drivers/net/wwan/iosm/iosm_ipc_port.c
index 2ba1ddca3945..5d5b4183e14a 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_port.c
+++ b/drivers/net/wwan/iosm/iosm_ipc_port.c
@@ -3,8 +3,6 @@
* Copyright (C) 2020-21 Intel Corporation.
*/
-#include <linux/pm_runtime.h>
-
#include "iosm_ipc_chnl_cfg.h"
#include "iosm_ipc_imem_ops.h"
#include "iosm_ipc_port.h"
@@ -15,16 +13,12 @@ static int ipc_port_ctrl_start(struct wwan_port *port)
struct iosm_cdev *ipc_port = wwan_port_get_drvdata(port);
int ret = 0;
- pm_runtime_get_sync(ipc_port->ipc_imem->dev);
ipc_port->channel = ipc_imem_sys_port_open(ipc_port->ipc_imem,
ipc_port->chl_id,
IPC_HP_CDEV_OPEN);
if (!ipc_port->channel)
ret = -EIO;
- pm_runtime_mark_last_busy(ipc_port->ipc_imem->dev);
- pm_runtime_put_autosuspend(ipc_port->ipc_imem->dev);
-
return ret;
}
@@ -33,24 +27,15 @@ static void ipc_port_ctrl_stop(struct wwan_port *port)
{
struct iosm_cdev *ipc_port = wwan_port_get_drvdata(port);
- pm_runtime_get_sync(ipc_port->ipc_imem->dev);
ipc_imem_sys_port_close(ipc_port->ipc_imem, ipc_port->channel);
- pm_runtime_mark_last_busy(ipc_port->ipc_imem->dev);
- pm_runtime_put_autosuspend(ipc_port->ipc_imem->dev);
}
/* transfer control data to modem */
static int ipc_port_ctrl_tx(struct wwan_port *port, struct sk_buff *skb)
{
struct iosm_cdev *ipc_port = wwan_port_get_drvdata(port);
- int ret;
- pm_runtime_get_sync(ipc_port->ipc_imem->dev);
- ret = ipc_imem_sys_cdev_write(ipc_port, skb);
- pm_runtime_mark_last_busy(ipc_port->ipc_imem->dev);
- pm_runtime_put_autosuspend(ipc_port->ipc_imem->dev);
-
- return ret;
+ return ipc_imem_sys_cdev_write(ipc_port, skb);
}
static const struct wwan_port_ops ipc_wwan_ctrl_ops = {
diff --git a/drivers/net/wwan/iosm/iosm_ipc_trace.c b/drivers/net/wwan/iosm/iosm_ipc_trace.c
index 4368373797b6..eeecfa3d10c5 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_trace.c
+++ b/drivers/net/wwan/iosm/iosm_ipc_trace.c
@@ -3,9 +3,7 @@
* Copyright (C) 2020-2021 Intel Corporation.
*/
-#include <linux/pm_runtime.h>
#include <linux/wwan.h>
-
#include "iosm_ipc_trace.h"
/* sub buffer size and number of sub buffer */
@@ -99,8 +97,6 @@ static ssize_t ipc_trace_ctrl_file_write(struct file *filp,
if (ret)
return ret;
- pm_runtime_get_sync(ipc_trace->ipc_imem->dev);
-
mutex_lock(&ipc_trace->trc_mutex);
if (val == TRACE_ENABLE && ipc_trace->mode != TRACE_ENABLE) {
ipc_trace->channel = ipc_imem_sys_port_open(ipc_trace->ipc_imem,
@@ -121,10 +117,6 @@ static ssize_t ipc_trace_ctrl_file_write(struct file *filp,
ret = count;
unlock:
mutex_unlock(&ipc_trace->trc_mutex);
-
- pm_runtime_mark_last_busy(ipc_trace->ipc_imem->dev);
- pm_runtime_put_autosuspend(ipc_trace->ipc_imem->dev);
-
return ret;
}
diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.c b/drivers/net/wwan/iosm/iosm_ipc_wwan.c
index 93d17de08786..ff747fc79aaf 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_wwan.c
+++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.c
@@ -6,7 +6,6 @@
#include <linux/etherdevice.h>
#include <linux/if_arp.h>
#include <linux/if_link.h>
-#include <linux/pm_runtime.h>
#include <linux/rtnetlink.h>
#include <linux/wwan.h>
#include <net/pkt_sched.h>
@@ -52,13 +51,11 @@ static int ipc_wwan_link_open(struct net_device *netdev)
struct iosm_netdev_priv *priv = wwan_netdev_drvpriv(netdev);
struct iosm_wwan *ipc_wwan = priv->ipc_wwan;
int if_id = priv->if_id;
- int ret = 0;
if (if_id < IP_MUX_SESSION_START ||
if_id >= ARRAY_SIZE(ipc_wwan->sub_netlist))
return -EINVAL;
- pm_runtime_get_sync(ipc_wwan->ipc_imem->dev);
/* get channel id */
priv->ch_id = ipc_imem_sys_wwan_open(ipc_wwan->ipc_imem, if_id);
@@ -66,8 +63,7 @@ static int ipc_wwan_link_open(struct net_device *netdev)
dev_err(ipc_wwan->dev,
"cannot connect wwan0 & id %d to the IPC mem layer",
if_id);
- ret = -ENODEV;
- goto err_out;
+ return -ENODEV;
}
/* enable tx path, DL data may follow */
@@ -76,11 +72,7 @@ static int ipc_wwan_link_open(struct net_device *netdev)
dev_dbg(ipc_wwan->dev, "Channel id %d allocated to if_id %d",
priv->ch_id, priv->if_id);
-err_out:
- pm_runtime_mark_last_busy(ipc_wwan->ipc_imem->dev);
- pm_runtime_put_autosuspend(ipc_wwan->ipc_imem->dev);
-
- return ret;
+ return 0;
}
/* Bring-down the wwan net link */
@@ -90,12 +82,9 @@ static int ipc_wwan_link_stop(struct net_device *netdev)
netif_stop_queue(netdev);
- pm_runtime_get_sync(priv->ipc_wwan->ipc_imem->dev);
ipc_imem_sys_wwan_close(priv->ipc_wwan->ipc_imem, priv->if_id,
priv->ch_id);
priv->ch_id = -1;
- pm_runtime_mark_last_busy(priv->ipc_wwan->ipc_imem->dev);
- pm_runtime_put_autosuspend(priv->ipc_wwan->ipc_imem->dev);
return 0;
}
@@ -117,7 +106,6 @@ static netdev_tx_t ipc_wwan_link_transmit(struct sk_buff *skb,
if_id >= ARRAY_SIZE(ipc_wwan->sub_netlist))
return -EINVAL;
- pm_runtime_get(ipc_wwan->ipc_imem->dev);
/* Send the SKB to device for transmission */
ret = ipc_imem_sys_wwan_transmit(ipc_wwan->ipc_imem,
if_id, priv->ch_id, skb);
@@ -131,14 +119,9 @@ static netdev_tx_t ipc_wwan_link_transmit(struct sk_buff *skb,
ret = NETDEV_TX_BUSY;
dev_err(ipc_wwan->dev, "unable to push packets");
} else {
- pm_runtime_mark_last_busy(ipc_wwan->ipc_imem->dev);
- pm_runtime_put_autosuspend(ipc_wwan->ipc_imem->dev);
goto exit;
}
- pm_runtime_mark_last_busy(ipc_wwan->ipc_imem->dev);
- pm_runtime_put_autosuspend(ipc_wwan->ipc_imem->dev);
-
return ret;
exit:
diff --git a/drivers/spi/spi-npcm-fiu.c b/drivers/spi/spi-npcm-fiu.c
index 0ca21ff0e9cc..e42248519688 100644
--- a/drivers/spi/spi-npcm-fiu.c
+++ b/drivers/spi/spi-npcm-fiu.c
@@ -353,8 +353,9 @@ static int npcm_fiu_uma_read(struct spi_mem *mem,
uma_cfg |= ilog2(op->cmd.buswidth);
uma_cfg |= ilog2(op->addr.buswidth)
<< NPCM_FIU_UMA_CFG_ADBPCK_SHIFT;
- uma_cfg |= ilog2(op->dummy.buswidth)
- << NPCM_FIU_UMA_CFG_DBPCK_SHIFT;
+ if (op->dummy.nbytes)
+ uma_cfg |= ilog2(op->dummy.buswidth)
+ << NPCM_FIU_UMA_CFG_DBPCK_SHIFT;
uma_cfg |= ilog2(op->data.buswidth)
<< NPCM_FIU_UMA_CFG_RDBPCK_SHIFT;
uma_cfg |= op->dummy.nbytes << NPCM_FIU_UMA_CFG_DBSIZ_SHIFT;
diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c
index 5c87817a4f4c..3dcf83f5e7b4 100644
--- a/drivers/video/fbdev/aty/atyfb_base.c
+++ b/drivers/video/fbdev/aty/atyfb_base.c
@@ -3440,11 +3440,15 @@ static int atyfb_setup_generic(struct pci_dev *pdev, struct fb_info *info,
}
info->fix.mmio_start = raddr;
+#if defined(__i386__) || defined(__ia64__)
/*
* By using strong UC we force the MTRR to never have an
* effect on the MMIO region on both non-PAT and PAT systems.
*/
par->ati_regbase = ioremap_uc(info->fix.mmio_start, 0x1000);
+#else
+ par->ati_regbase = ioremap(info->fix.mmio_start, 0x1000);
+#endif
if (par->ati_regbase == NULL)
return -ENOMEM;
diff --git a/drivers/video/fbdev/core/cfbcopyarea.c b/drivers/video/fbdev/core/cfbcopyarea.c
index 6d4bfeecee35..5b80bf3dae50 100644
--- a/drivers/video/fbdev/core/cfbcopyarea.c
+++ b/drivers/video/fbdev/core/cfbcopyarea.c
@@ -382,7 +382,7 @@ void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area)
{
u32 dx = area->dx, dy = area->dy, sx = area->sx, sy = area->sy;
u32 height = area->height, width = area->width;
- unsigned long const bits_per_line = p->fix.line_length*8u;
+ unsigned int const bits_per_line = p->fix.line_length * 8u;
unsigned long __iomem *base = NULL;
int bits = BITS_PER_LONG, bytes = bits >> 3;
unsigned dst_idx = 0, src_idx = 0, rev_copy = 0;
diff --git a/drivers/video/fbdev/core/syscopyarea.c b/drivers/video/fbdev/core/syscopyarea.c
index c1eda3190968..7b8bd3a2bedc 100644
--- a/drivers/video/fbdev/core/syscopyarea.c
+++ b/drivers/video/fbdev/core/syscopyarea.c
@@ -316,7 +316,7 @@ void sys_copyarea(struct fb_info *p, const struct fb_copyarea *area)
{
u32 dx = area->dx, dy = area->dy, sx = area->sx, sy = area->sy;
u32 height = area->height, width = area->width;
- unsigned long const bits_per_line = p->fix.line_length*8u;
+ unsigned int const bits_per_line = p->fix.line_length * 8u;
unsigned long *base = NULL;
int bits = BITS_PER_LONG, bytes = bits >> 3;
unsigned dst_idx = 0, src_idx = 0, rev_copy = 0;
diff --git a/drivers/video/fbdev/mmp/hw/mmp_ctrl.h b/drivers/video/fbdev/mmp/hw/mmp_ctrl.h
index 167585a889d3..719b99a9bc77 100644
--- a/drivers/video/fbdev/mmp/hw/mmp_ctrl.h
+++ b/drivers/video/fbdev/mmp/hw/mmp_ctrl.h
@@ -1406,7 +1406,7 @@ struct mmphw_ctrl {
/*pathes*/
int path_num;
- struct mmphw_path_plat path_plats[];
+ struct mmphw_path_plat path_plats[] __counted_by(path_num);
};
static inline int overlay_is_vid(struct mmp_overlay *overlay)
diff --git a/drivers/video/fbdev/omap/omapfb_main.c b/drivers/video/fbdev/omap/omapfb_main.c
index f28cb90947a3..42c96f1cfc93 100644
--- a/drivers/video/fbdev/omap/omapfb_main.c
+++ b/drivers/video/fbdev/omap/omapfb_main.c
@@ -1645,13 +1645,13 @@ static int omapfb_do_probe(struct platform_device *pdev,
}
fbdev->int_irq = platform_get_irq(pdev, 0);
if (fbdev->int_irq < 0) {
- r = ENXIO;
+ r = -ENXIO;
goto cleanup;
}
fbdev->ext_irq = platform_get_irq(pdev, 1);
if (fbdev->ext_irq < 0) {
- r = ENXIO;
+ r = -ENXIO;
goto cleanup;
}
diff --git a/drivers/video/fbdev/sa1100fb.c b/drivers/video/fbdev/sa1100fb.c
index 3d76ce111488..cf0f706762b4 100644
--- a/drivers/video/fbdev/sa1100fb.c
+++ b/drivers/video/fbdev/sa1100fb.c
@@ -1214,7 +1214,7 @@ static struct platform_driver sa1100fb_driver = {
},
};
-int __init sa1100fb_init(void)
+static int __init sa1100fb_init(void)
{
if (fb_get_options("sa1100fb", NULL))
return -ENODEV;
diff --git a/drivers/video/fbdev/uvesafb.c b/drivers/video/fbdev/uvesafb.c
index a1a67830fbbc..e1f421e91b4f 100644
--- a/drivers/video/fbdev/uvesafb.c
+++ b/drivers/video/fbdev/uvesafb.c
@@ -1928,10 +1928,10 @@ static void uvesafb_exit(void)
}
}
- cn_del_callback(&uvesafb_cn_id);
driver_remove_file(&uvesafb_driver.driver, &driver_attr_v86d);
platform_device_unregister(uvesafb_device);
platform_driver_unregister(&uvesafb_driver);
+ cn_del_callback(&uvesafb_cn_id);
}
module_exit(uvesafb_exit);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 5a5a8d488a7b..b9ef6f54635c 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5109,7 +5109,7 @@ static void init_alloc_chunk_ctl_policy_regular(
ASSERT(space_info);
ctl->max_chunk_size = READ_ONCE(space_info->chunk_size);
- ctl->max_stripe_size = ctl->max_chunk_size;
+ ctl->max_stripe_size = min_t(u64, ctl->max_chunk_size, SZ_1G);
if (ctl->type & BTRFS_BLOCK_GROUP_SYSTEM)
ctl->devs_max = min_t(int, ctl->devs_max, BTRFS_MAX_DEVS_SYS_CHUNK);
diff --git a/fs/namei.c b/fs/namei.c
index 567ee547492b..94565bd7e73f 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -188,7 +188,7 @@ getname_flags(const char __user *filename, int flags, int *empty)
}
}
- result->refcnt = 1;
+ atomic_set(&result->refcnt, 1);
/* The empty path is special. */
if (unlikely(!len)) {
if (empty)
@@ -249,7 +249,7 @@ getname_kernel(const char * filename)
memcpy((char *)result->name, filename, len);
result->uptr = NULL;
result->aname = NULL;
- result->refcnt = 1;
+ atomic_set(&result->refcnt, 1);
audit_getname(result);
return result;
@@ -261,9 +261,10 @@ void putname(struct filename *name)
if (IS_ERR(name))
return;
- BUG_ON(name->refcnt <= 0);
+ if (WARN_ON_ONCE(!atomic_read(&name->refcnt)))
+ return;
- if (--name->refcnt > 0)
+ if (!atomic_dec_and_test(&name->refcnt))
return;
if (name->name != name->iname) {
diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c
index a9d82bbb4729..63f70259edc0 100644
--- a/fs/ntfs3/attrib.c
+++ b/fs/ntfs3/attrib.c
@@ -1106,10 +1106,10 @@ repack:
}
}
- /*
+ /*
* The code below may require additional cluster (to extend attribute list)
- * and / or one MFT record
- * It is too complex to undo operations if -ENOSPC occurs deep inside
+ * and / or one MFT record
+ * It is too complex to undo operations if -ENOSPC occurs deep inside
* in 'ni_insert_nonresident'.
* Return in advance -ENOSPC here if there are no free cluster and no free MFT.
*/
@@ -1736,10 +1736,8 @@ repack:
le_b = NULL;
attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL,
0, NULL, &mi_b);
- if (!attr_b) {
- err = -ENOENT;
- goto out;
- }
+ if (!attr_b)
+ return -ENOENT;
attr = attr_b;
le = le_b;
diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c
index 42631b31adf1..7c01735d1219 100644
--- a/fs/ntfs3/attrlist.c
+++ b/fs/ntfs3/attrlist.c
@@ -52,7 +52,8 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr)
if (!attr->non_res) {
lsize = le32_to_cpu(attr->res.data_size);
- le = kmalloc(al_aligned(lsize), GFP_NOFS | __GFP_NOWARN);
+ /* attr is resident: lsize < record_size (1K or 4K) */
+ le = kvmalloc(al_aligned(lsize), GFP_KERNEL);
if (!le) {
err = -ENOMEM;
goto out;
@@ -80,7 +81,17 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr)
if (err < 0)
goto out;
- le = kmalloc(al_aligned(lsize), GFP_NOFS | __GFP_NOWARN);
+ /* attr is nonresident.
+ * The worst case:
+ * 1T (2^40) extremely fragmented file.
+ * cluster = 4K (2^12) => 2^28 fragments
+ * 2^9 fragments per one record => 2^19 records
+ * 2^5 bytes of ATTR_LIST_ENTRY per one record => 2^24 bytes.
+ *
+ * the result is 16M bytes per attribute list.
+ * Use kvmalloc to allocate in range [several Kbytes - dozen Mbytes]
+ */
+ le = kvmalloc(al_aligned(lsize), GFP_KERNEL);
if (!le) {
err = -ENOMEM;
goto out;
diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c
index 107e808e06ea..63f14a0232f6 100644
--- a/fs/ntfs3/bitmap.c
+++ b/fs/ntfs3/bitmap.c
@@ -125,6 +125,7 @@ void wnd_close(struct wnd_bitmap *wnd)
struct rb_node *node, *next;
kfree(wnd->free_bits);
+ wnd->free_bits = NULL;
run_close(&wnd->run);
node = rb_first(&wnd->start_tree);
@@ -659,7 +660,8 @@ int wnd_init(struct wnd_bitmap *wnd, struct super_block *sb, size_t nbits)
wnd->bits_last = wbits;
wnd->free_bits =
- kcalloc(wnd->nwnd, sizeof(u16), GFP_NOFS | __GFP_NOWARN);
+ kvmalloc_array(wnd->nwnd, sizeof(u16), GFP_KERNEL | __GFP_ZERO);
+
if (!wnd->free_bits)
return -ENOMEM;
diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
index 063a6654199b..ec0566b322d5 100644
--- a/fs/ntfs3/dir.c
+++ b/fs/ntfs3/dir.c
@@ -309,7 +309,11 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
return 0;
}
- dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG;
+ /* NTFS: symlinks are "dir + reparse" or "file + reparse" */
+ if (fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT)
+ dt_type = DT_LNK;
+ else
+ dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG;
return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type);
}
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 962f12ce6c0a..1f7a194983c5 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -745,8 +745,8 @@ static ssize_t ntfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter)
}
static ssize_t ntfs_file_splice_read(struct file *in, loff_t *ppos,
- struct pipe_inode_info *pipe,
- size_t len, unsigned int flags)
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags)
{
struct inode *inode = in->f_mapping->host;
struct ntfs_inode *ni = ntfs_i(inode);
diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
index 2b85cb10f0be..dad976a68985 100644
--- a/fs/ntfs3/frecord.c
+++ b/fs/ntfs3/frecord.c
@@ -2148,7 +2148,7 @@ out1:
for (i = 0; i < pages_per_frame; i++) {
pg = pages[i];
- if (i == idx)
+ if (i == idx || !pg)
continue;
unlock_page(pg);
put_page(pg);
@@ -3208,6 +3208,12 @@ static bool ni_update_parent(struct ntfs_inode *ni, struct NTFS_DUP_INFO *dup,
if (!fname || !memcmp(&fname->dup, dup, sizeof(fname->dup)))
continue;
+ /* Check simple case when parent inode equals current inode. */
+ if (ino_get(&fname->home) == ni->vfs_inode.i_ino) {
+ ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
+ continue;
+ }
+
/* ntfs_iget5 may sleep. */
dir = ntfs_iget5(sb, &fname->home, NULL);
if (IS_ERR(dir)) {
diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c
index 12f28cdf5c83..98ccb6650858 100644
--- a/fs/ntfs3/fslog.c
+++ b/fs/ntfs3/fslog.c
@@ -2168,8 +2168,10 @@ file_is_valid:
if (!page) {
page = kmalloc(log->page_size, GFP_NOFS);
- if (!page)
- return -ENOMEM;
+ if (!page) {
+ err = -ENOMEM;
+ goto out;
+ }
}
/*
diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c
index 33afee0f5559..fbfe21dbb425 100644
--- a/fs/ntfs3/fsntfs.c
+++ b/fs/ntfs3/fsntfs.c
@@ -983,18 +983,11 @@ out:
if (err)
return err;
- mark_inode_dirty(&ni->vfs_inode);
+ mark_inode_dirty_sync(&ni->vfs_inode);
/* verify(!ntfs_update_mftmirr()); */
- /*
- * If we used wait=1, sync_inode_metadata waits for the io for the
- * inode to finish. It hangs when media is removed.
- * So wait=0 is sent down to sync_inode_metadata
- * and filemap_fdatawrite is used for the data blocks.
- */
- err = sync_inode_metadata(&ni->vfs_inode, 0);
- if (!err)
- err = filemap_fdatawrite(ni->vfs_inode.i_mapping);
+ /* write mft record on disk. */
+ err = _ni_write_inode(&ni->vfs_inode, 1);
return err;
}
@@ -2461,10 +2454,12 @@ void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim)
{
CLST end, i, zone_len, zlen;
struct wnd_bitmap *wnd = &sbi->used.bitmap;
+ bool dirty = false;
down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS);
if (!wnd_is_used(wnd, lcn, len)) {
- ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
+ /* mark volume as dirty out of wnd->rw_lock */
+ dirty = true;
end = lcn + len;
len = 0;
@@ -2518,6 +2513,8 @@ void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim)
out:
up_write(&wnd->rw_lock);
+ if (dirty)
+ ntfs_set_state(sbi, NTFS_DIRTY_ERROR);
}
/*
diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c
index 124c6e822623..cf92b2433f7a 100644
--- a/fs/ntfs3/index.c
+++ b/fs/ntfs3/index.c
@@ -729,6 +729,9 @@ static struct NTFS_DE *hdr_find_e(const struct ntfs_index *indx,
u32 total = le32_to_cpu(hdr->total);
u16 offs[128];
+ if (unlikely(!cmp))
+ return NULL;
+
fill_table:
if (end > total)
return NULL;
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index eb2ed0701495..d6d021e19aaa 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -170,8 +170,8 @@ next_attr:
nt2kernel(std5->cr_time, &ni->i_crtime);
#endif
nt2kernel(std5->a_time, &inode->i_atime);
- ctime = inode_get_ctime(inode);
nt2kernel(std5->c_time, &ctime);
+ inode_set_ctime_to_ts(inode, ctime);
nt2kernel(std5->m_time, &inode->i_mtime);
ni->std_fa = std5->fa;
@@ -1660,7 +1660,8 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir,
d_instantiate(dentry, inode);
/* Set original time. inode times (i_ctime) may be changed in ntfs_init_acl. */
- inode->i_atime = inode->i_mtime = inode_set_ctime_to_ts(inode, ni->i_crtime);
+ inode->i_atime = inode->i_mtime =
+ inode_set_ctime_to_ts(inode, ni->i_crtime);
dir->i_mtime = inode_set_ctime_to_ts(dir, ni->i_crtime);
mark_inode_dirty(dir);
diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c
index ad430d50bd79..eedacf94edd8 100644
--- a/fs/ntfs3/namei.c
+++ b/fs/ntfs3/namei.c
@@ -156,8 +156,8 @@ static int ntfs_link(struct dentry *ode, struct inode *dir, struct dentry *de)
err = ntfs_link_inode(inode, de);
if (!err) {
- dir->i_mtime = inode_set_ctime_to_ts(inode,
- inode_set_ctime_current(dir));
+ dir->i_mtime = inode_set_ctime_to_ts(
+ inode, inode_set_ctime_current(dir));
mark_inode_dirty(inode);
mark_inode_dirty(dir);
d_instantiate(de, inode);
@@ -373,7 +373,7 @@ static int ntfs_atomic_open(struct inode *dir, struct dentry *dentry,
#ifdef CONFIG_NTFS3_FS_POSIX_ACL
if (IS_POSIXACL(dir)) {
- /*
+ /*
* Load in cache current acl to avoid ni_lock(dir):
* ntfs_create_inode -> ntfs_init_acl -> posix_acl_create ->
* ntfs_get_acl -> ntfs_get_acl_ex -> ni_lock
diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h
index 98b76d1b09e7..86aecbb01a92 100644
--- a/fs/ntfs3/ntfs.h
+++ b/fs/ntfs3/ntfs.h
@@ -847,7 +847,7 @@ struct OBJECT_ID {
// Birth Volume Id is the Object Id of the Volume on.
// which the Object Id was allocated. It never changes.
struct GUID BirthVolumeId; //0x10:
-
+
// Birth Object Id is the first Object Id that was
// ever assigned to this MFT Record. I.e. If the Object Id
// is changed for some reason, this field will reflect the
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 629403ede6e5..0e6a2777870c 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -42,9 +42,11 @@ enum utf16_endian;
#define MINUS_ONE_T ((size_t)(-1))
/* Biggest MFT / smallest cluster */
#define MAXIMUM_BYTES_PER_MFT 4096
+#define MAXIMUM_SHIFT_BYTES_PER_MFT 12
#define NTFS_BLOCKS_PER_MFT_RECORD (MAXIMUM_BYTES_PER_MFT / 512)
#define MAXIMUM_BYTES_PER_INDEX 4096
+#define MAXIMUM_SHIFT_BYTES_PER_INDEX 12
#define NTFS_BLOCKS_PER_INODE (MAXIMUM_BYTES_PER_INDEX / 512)
/* NTFS specific error code when fixup failed. */
@@ -495,8 +497,6 @@ int ntfs_getattr(struct mnt_idmap *idmap, const struct path *path,
struct kstat *stat, u32 request_mask, u32 flags);
int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
struct iattr *attr);
-void ntfs_sparse_cluster(struct inode *inode, struct page *page0, CLST vcn,
- CLST len);
int ntfs_file_open(struct inode *inode, struct file *file);
int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
__u64 start, __u64 len);
diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c
index c12ebffc94da..53629b1f65e9 100644
--- a/fs/ntfs3/record.c
+++ b/fs/ntfs3/record.c
@@ -189,12 +189,19 @@ out:
return err;
}
+/*
+ * mi_enum_attr - start/continue attributes enumeration in record.
+ *
+ * NOTE: mi->mrec - memory of size sbi->record_size
+ * here we sure that mi->mrec->total == sbi->record_size (see mi_read)
+ */
struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
{
const struct MFT_REC *rec = mi->mrec;
u32 used = le32_to_cpu(rec->used);
- u32 t32, off, asize;
+ u32 t32, off, asize, prev_type;
u16 t16;
+ u64 data_size, alloc_size, tot_size;
if (!attr) {
u32 total = le32_to_cpu(rec->total);
@@ -213,6 +220,7 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
if (!is_rec_inuse(rec))
return NULL;
+ prev_type = 0;
attr = Add2Ptr(rec, off);
} else {
/* Check if input attr inside record. */
@@ -226,11 +234,11 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
return NULL;
}
- if (off + asize < off) {
- /* Overflow check. */
+ /* Overflow check. */
+ if (off + asize < off)
return NULL;
- }
+ prev_type = le32_to_cpu(attr->type);
attr = Add2Ptr(attr, asize);
off += asize;
}
@@ -250,7 +258,11 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
/* 0x100 is last known attribute for now. */
t32 = le32_to_cpu(attr->type);
- if ((t32 & 0xf) || (t32 > 0x100))
+ if (!t32 || (t32 & 0xf) || (t32 > 0x100))
+ return NULL;
+
+ /* attributes in record must be ordered by type */
+ if (t32 < prev_type)
return NULL;
/* Check overflow and boundary. */
@@ -259,16 +271,15 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
/* Check size of attribute. */
if (!attr->non_res) {
+ /* Check resident fields. */
if (asize < SIZEOF_RESIDENT)
return NULL;
t16 = le16_to_cpu(attr->res.data_off);
-
if (t16 > asize)
return NULL;
- t32 = le32_to_cpu(attr->res.data_size);
- if (t16 + t32 > asize)
+ if (t16 + le32_to_cpu(attr->res.data_size) > asize)
return NULL;
t32 = sizeof(short) * attr->name_len;
@@ -278,21 +289,52 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr)
return attr;
}
- /* Check some nonresident fields. */
- if (attr->name_len &&
- le16_to_cpu(attr->name_off) + sizeof(short) * attr->name_len >
- le16_to_cpu(attr->nres.run_off)) {
+ /* Check nonresident fields. */
+ if (attr->non_res != 1)
+ return NULL;
+
+ t16 = le16_to_cpu(attr->nres.run_off);
+ if (t16 > asize)
+ return NULL;
+
+ t32 = sizeof(short) * attr->name_len;
+ if (t32 && le16_to_cpu(attr->name_off) + t32 > t16)
+ return NULL;
+
+ /* Check start/end vcn. */
+ if (le64_to_cpu(attr->nres.svcn) > le64_to_cpu(attr->nres.evcn) + 1)
return NULL;
- }
- if (attr->nres.svcn || !is_attr_ext(attr)) {
+ data_size = le64_to_cpu(attr->nres.data_size);
+ if (le64_to_cpu(attr->nres.valid_size) > data_size)
+ return NULL;
+
+ alloc_size = le64_to_cpu(attr->nres.alloc_size);
+ if (data_size > alloc_size)
+ return NULL;
+
+ t32 = mi->sbi->cluster_mask;
+ if (alloc_size & t32)
+ return NULL;
+
+ if (!attr->nres.svcn && is_attr_ext(attr)) {
+ /* First segment of sparse/compressed attribute */
+ if (asize + 8 < SIZEOF_NONRESIDENT_EX)
+ return NULL;
+
+ tot_size = le64_to_cpu(attr->nres.total_size);
+ if (tot_size & t32)
+ return NULL;
+
+ if (tot_size > alloc_size)
+ return NULL;
+ } else {
if (asize + 8 < SIZEOF_NONRESIDENT)
return NULL;
if (attr->nres.c_unit)
return NULL;
- } else if (asize + 8 < SIZEOF_NONRESIDENT_EX)
- return NULL;
+ }
return attr;
}
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index 5661a363005e..f763e3256ccc 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -453,15 +453,23 @@ static struct proc_dir_entry *proc_info_root;
* ntfs3.1
* cluster size
* number of clusters
+ * total number of mft records
+ * number of used mft records ~= number of files + folders
+ * real state of ntfs "dirty"/"clean"
+ * current state of ntfs "dirty"/"clean"
*/
static int ntfs3_volinfo(struct seq_file *m, void *o)
{
struct super_block *sb = m->private;
struct ntfs_sb_info *sbi = sb->s_fs_info;
- seq_printf(m, "ntfs%d.%d\n%u\n%zu\n", sbi->volume.major_ver,
- sbi->volume.minor_ver, sbi->cluster_size,
- sbi->used.bitmap.nbits);
+ seq_printf(m, "ntfs%d.%d\n%u\n%zu\n\%zu\n%zu\n%s\n%s\n",
+ sbi->volume.major_ver, sbi->volume.minor_ver,
+ sbi->cluster_size, sbi->used.bitmap.nbits,
+ sbi->mft.bitmap.nbits,
+ sbi->mft.bitmap.nbits - wnd_zeroes(&sbi->mft.bitmap),
+ sbi->volume.real_dirty ? "dirty" : "clean",
+ (sbi->volume.flags & VOLUME_FLAG_DIRTY) ? "dirty" : "clean");
return 0;
}
@@ -488,9 +496,13 @@ static ssize_t ntfs3_label_write(struct file *file, const char __user *buffer,
{
int err;
struct super_block *sb = pde_data(file_inode(file));
- struct ntfs_sb_info *sbi = sb->s_fs_info;
ssize_t ret = count;
- u8 *label = kmalloc(count, GFP_NOFS);
+ u8 *label;
+
+ if (sb_rdonly(sb))
+ return -EROFS;
+
+ label = kmalloc(count, GFP_NOFS);
if (!label)
return -ENOMEM;
@@ -502,7 +514,7 @@ static ssize_t ntfs3_label_write(struct file *file, const char __user *buffer,
while (ret > 0 && label[ret - 1] == '\n')
ret -= 1;
- err = ntfs_set_label(sbi, label, ret);
+ err = ntfs_set_label(sb->s_fs_info, label, ret);
if (err < 0) {
ntfs_err(sb, "failed (%d) to write label", err);
@@ -576,20 +588,30 @@ static noinline void ntfs3_put_sbi(struct ntfs_sb_info *sbi)
wnd_close(&sbi->mft.bitmap);
wnd_close(&sbi->used.bitmap);
- if (sbi->mft.ni)
+ if (sbi->mft.ni) {
iput(&sbi->mft.ni->vfs_inode);
+ sbi->mft.ni = NULL;
+ }
- if (sbi->security.ni)
+ if (sbi->security.ni) {
iput(&sbi->security.ni->vfs_inode);
+ sbi->security.ni = NULL;
+ }
- if (sbi->reparse.ni)
+ if (sbi->reparse.ni) {
iput(&sbi->reparse.ni->vfs_inode);
+ sbi->reparse.ni = NULL;
+ }
- if (sbi->objid.ni)
+ if (sbi->objid.ni) {
iput(&sbi->objid.ni->vfs_inode);
+ sbi->objid.ni = NULL;
+ }
- if (sbi->volume.ni)
+ if (sbi->volume.ni) {
iput(&sbi->volume.ni->vfs_inode);
+ sbi->volume.ni = NULL;
+ }
ntfs_update_mftmirr(sbi, 0);
@@ -836,7 +858,7 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size,
struct ntfs_sb_info *sbi = sb->s_fs_info;
int err;
u32 mb, gb, boot_sector_size, sct_per_clst, record_size;
- u64 sectors, clusters, mlcn, mlcn2;
+ u64 sectors, clusters, mlcn, mlcn2, dev_size0;
struct NTFS_BOOT *boot;
struct buffer_head *bh;
struct MFT_REC *rec;
@@ -845,6 +867,9 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size,
u32 boot_off = 0;
const char *hint = "Primary boot";
+ /* Save original dev_size. Used with alternative boot. */
+ dev_size0 = dev_size;
+
sbi->volume.blocks = dev_size >> PAGE_SHIFT;
bh = ntfs_bread(sb, 0);
@@ -853,6 +878,11 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size,
check_boot:
err = -EINVAL;
+
+ /* Corrupted image; do not read OOB */
+ if (bh->b_size - sizeof(*boot) < boot_off)
+ goto out;
+
boot = (struct NTFS_BOOT *)Add2Ptr(bh->b_data, boot_off);
if (memcmp(boot->system_id, "NTFS ", sizeof("NTFS ") - 1)) {
@@ -899,9 +929,17 @@ check_boot:
goto out;
}
- sbi->record_size = record_size =
- boot->record_size < 0 ? 1 << (-boot->record_size) :
- (u32)boot->record_size << cluster_bits;
+ if (boot->record_size >= 0) {
+ record_size = (u32)boot->record_size << cluster_bits;
+ } else if (-boot->record_size <= MAXIMUM_SHIFT_BYTES_PER_MFT) {
+ record_size = 1u << (-boot->record_size);
+ } else {
+ ntfs_err(sb, "%s: invalid record size %d.", hint,
+ boot->record_size);
+ goto out;
+ }
+
+ sbi->record_size = record_size;
sbi->record_bits = blksize_bits(record_size);
sbi->attr_size_tr = (5 * record_size >> 4); // ~320 bytes
@@ -918,9 +956,15 @@ check_boot:
goto out;
}
- sbi->index_size = boot->index_size < 0 ?
- 1u << (-boot->index_size) :
- (u32)boot->index_size << cluster_bits;
+ if (boot->index_size >= 0) {
+ sbi->index_size = (u32)boot->index_size << cluster_bits;
+ } else if (-boot->index_size <= MAXIMUM_SHIFT_BYTES_PER_INDEX) {
+ sbi->index_size = 1u << (-boot->index_size);
+ } else {
+ ntfs_err(sb, "%s: invalid index size %d.", hint,
+ boot->index_size);
+ goto out;
+ }
/* Check index record size. */
if (sbi->index_size < SECTOR_SIZE || !is_power_of_2(sbi->index_size)) {
@@ -1055,17 +1099,17 @@ check_boot:
if (bh->b_blocknr && !sb_rdonly(sb)) {
/*
- * Alternative boot is ok but primary is not ok.
- * Do not update primary boot here 'cause it may be faked boot.
- * Let ntfs to be mounted and update boot later.
- */
+ * Alternative boot is ok but primary is not ok.
+ * Do not update primary boot here 'cause it may be faked boot.
+ * Let ntfs to be mounted and update boot later.
+ */
*boot2 = kmemdup(boot, sizeof(*boot), GFP_NOFS | __GFP_NOWARN);
}
out:
- if (err == -EINVAL && !bh->b_blocknr && dev_size > PAGE_SHIFT) {
+ if (err == -EINVAL && !bh->b_blocknr && dev_size0 > PAGE_SHIFT) {
u32 block_size = min_t(u32, sector_size, PAGE_SIZE);
- u64 lbo = dev_size - sizeof(*boot);
+ u64 lbo = dev_size0 - sizeof(*boot);
/*
* Try alternative boot (last sector)
@@ -1079,6 +1123,7 @@ out:
boot_off = lbo & (block_size - 1);
hint = "Alternative boot";
+ dev_size = dev_size0; /* restore original size. */
goto check_boot;
}
brelse(bh);
@@ -1367,7 +1412,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc)
}
bytes = inode->i_size;
- sbi->def_table = t = kmalloc(bytes, GFP_NOFS | __GFP_NOWARN);
+ sbi->def_table = t = kvmalloc(bytes, GFP_KERNEL);
if (!t) {
err = -ENOMEM;
goto put_inode_out;
@@ -1521,9 +1566,9 @@ load_root:
if (boot2) {
/*
- * Alternative boot is ok but primary is not ok.
- * Volume is recognized as NTFS. Update primary boot.
- */
+ * Alternative boot is ok but primary is not ok.
+ * Volume is recognized as NTFS. Update primary boot.
+ */
struct buffer_head *bh0 = sb_getblk(sb, 0);
if (bh0) {
if (buffer_locked(bh0))
@@ -1564,6 +1609,7 @@ put_inode_out:
out:
ntfs3_put_sbi(sbi);
kfree(boot2);
+ ntfs3_put_sbi(sbi);
return err;
}
@@ -1757,7 +1803,6 @@ static int __init init_ntfs_fs(void)
if (IS_ENABLED(CONFIG_NTFS3_LZX_XPRESS))
pr_info("ntfs3: Read-only LZX/Xpress compression included\n");
-
#ifdef CONFIG_PROC_FS
/* Create "/proc/fs/ntfs3" */
proc_info_root = proc_mkdir("fs/ntfs3", NULL);
@@ -1799,7 +1844,6 @@ static void __exit exit_ntfs_fs(void)
if (proc_info_root)
remove_proc_entry("fs/ntfs3", NULL);
#endif
-
}
MODULE_LICENSE("GPL");
diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c
index 29fd391899e5..4920548192a0 100644
--- a/fs/ntfs3/xattr.c
+++ b/fs/ntfs3/xattr.c
@@ -211,7 +211,8 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer,
size = le32_to_cpu(info->size);
/* Enumerate all xattrs. */
- for (ret = 0, off = 0; off < size; off += ea_size) {
+ ret = 0;
+ for (off = 0; off + sizeof(struct EA_FULL) < size; off += ea_size) {
ea = Add2Ptr(ea_all, off);
ea_size = unpacked_ea_size(ea);
@@ -219,6 +220,10 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer,
break;
if (buffer) {
+ /* Check if we can use field ea->name */
+ if (off + ea_size > size)
+ break;
+
if (ret + ea->name_len + 1 > bytes_per_buffer) {
err = -ERANGE;
goto out;
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index bb3cb005873e..e748bc957d83 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -82,6 +82,8 @@ struct timer_map {
struct arch_timer_context *emul_ptimer;
};
+void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map);
+
struct arch_timer_cpu {
struct arch_timer_context timers[NR_KVM_TIMERS];
@@ -145,4 +147,9 @@ u64 timer_get_cval(struct arch_timer_context *ctxt);
void kvm_timer_cpu_up(void);
void kvm_timer_cpu_down(void);
+static inline bool has_cntpoff(void)
+{
+ return (has_vhe() && cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF));
+}
+
#endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b528f063e8ff..4a40823c3c67 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2403,7 +2403,7 @@ struct audit_names;
struct filename {
const char *name; /* pointer to actual string */
const __user char *uptr; /* original userland pointer */
- int refcnt;
+ atomic_t refcnt;
struct audit_names *aname;
const char iname[];
};
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 7b4dd69555e4..27cc1d464321 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -3,8 +3,8 @@
#define _LINUX_VIRTIO_NET_H
#include <linux/if_vlan.h>
+#include <linux/udp.h>
#include <uapi/linux/tcp.h>
-#include <uapi/linux/udp.h>
#include <uapi/linux/virtio_net.h>
static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type)
@@ -151,9 +151,22 @@ retry:
unsigned int nh_off = p_off;
struct skb_shared_info *shinfo = skb_shinfo(skb);
- /* UFO may not include transport header in gso_size. */
- if (gso_type & SKB_GSO_UDP)
+ switch (gso_type & ~SKB_GSO_TCP_ECN) {
+ case SKB_GSO_UDP:
+ /* UFO may not include transport header in gso_size. */
nh_off -= thlen;
+ break;
+ case SKB_GSO_UDP_L4:
+ if (!(hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM))
+ return -EINVAL;
+ if (skb->csum_offset != offsetof(struct udphdr, check))
+ return -EINVAL;
+ if (skb->len - p_off > gso_size * UDP_MAX_SEGMENTS)
+ return -EINVAL;
+ if (gso_type != SKB_GSO_UDP_L4)
+ return -EINVAL;
+ break;
+ }
/* Kernel has a special handling for GSO_BY_FRAGS. */
if (gso_size == GSO_BY_FRAGS)
diff --git a/include/net/bluetooth/hci_mon.h b/include/net/bluetooth/hci_mon.h
index 2d5fcda1bcd0..082f89531b88 100644
--- a/include/net/bluetooth/hci_mon.h
+++ b/include/net/bluetooth/hci_mon.h
@@ -56,7 +56,7 @@ struct hci_mon_new_index {
__u8 type;
__u8 bus;
bdaddr_t bdaddr;
- char name[8];
+ char name[8] __nonstring;
} __packed;
#define HCI_MON_NEW_INDEX_SIZE 16
diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index bd7c3be4af5d..423b52eca908 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -50,6 +50,7 @@ struct netns_xfrm {
struct list_head policy_all;
struct hlist_head *policy_byidx;
unsigned int policy_idx_hmask;
+ unsigned int idx_generator;
struct hlist_head policy_inexact[XFRM_POLICY_MAX];
struct xfrm_policy_hash policy_bydst[XFRM_POLICY_MAX];
unsigned int policy_count[XFRM_POLICY_MAX * 2];
diff --git a/include/net/sock.h b/include/net/sock.h
index b770261fbdaf..92f7ea62a915 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -336,7 +336,7 @@ struct sk_filter;
* @sk_cgrp_data: cgroup data for this cgroup
* @sk_memcg: this socket's memory cgroup association
* @sk_write_pending: a write to stream socket waits to start
- * @sk_wait_pending: number of threads blocked on this socket
+ * @sk_disconnects: number of disconnect operations performed on this sock
* @sk_state_change: callback to indicate change in the state of the sock
* @sk_data_ready: callback to indicate there is data to be processed
* @sk_write_space: callback to indicate there is bf sending space available
@@ -429,7 +429,7 @@ struct sock {
unsigned int sk_napi_id;
#endif
int sk_rcvbuf;
- int sk_wait_pending;
+ int sk_disconnects;
struct sk_filter __rcu *sk_filter;
union {
@@ -1189,8 +1189,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk)
}
#define sk_wait_event(__sk, __timeo, __condition, __wait) \
- ({ int __rc; \
- __sk->sk_wait_pending++; \
+ ({ int __rc, __dis = __sk->sk_disconnects; \
release_sock(__sk); \
__rc = __condition; \
if (!__rc) { \
@@ -1200,8 +1199,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk)
} \
sched_annotate_sleep(); \
lock_sock(__sk); \
- __sk->sk_wait_pending--; \
- __rc = __condition; \
+ __rc = __dis == __sk->sk_disconnects ? __condition : -EPIPE; \
__rc; \
})
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 7b1a720691ae..4b03ca7cb8a5 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -141,6 +141,9 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
#define TCP_RTO_MAX ((unsigned)(120*HZ))
#define TCP_RTO_MIN ((unsigned)(HZ/5))
#define TCP_TIMEOUT_MIN (2U) /* Min timeout for TCP timers in jiffies */
+
+#define TCP_TIMEOUT_MIN_US (2*USEC_PER_MSEC) /* Min TCP timeout in microsecs */
+
#define TCP_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */
#define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value, now
* used as a fallback RTO for the
diff --git a/include/trace/events/neigh.h b/include/trace/events/neigh.h
index 5eaa1fa99171..833143d0992e 100644
--- a/include/trace/events/neigh.h
+++ b/include/trace/events/neigh.h
@@ -39,7 +39,6 @@ TRACE_EVENT(neigh_create,
),
TP_fast_assign(
- struct in6_addr *pin6;
__be32 *p32;
__entry->family = tbl->family;
@@ -47,7 +46,6 @@ TRACE_EVENT(neigh_create,
__entry->entries = atomic_read(&tbl->gc_entries);
__entry->created = n != NULL;
__entry->gc_exempt = exempt_from_gc;
- pin6 = (struct in6_addr *)__entry->primary_key6;
p32 = (__be32 *)__entry->primary_key4;
if (tbl->family == AF_INET)
@@ -57,6 +55,8 @@ TRACE_EVENT(neigh_create,
#if IS_ENABLED(CONFIG_IPV6)
if (tbl->family == AF_INET6) {
+ struct in6_addr *pin6;
+
pin6 = (struct in6_addr *)__entry->primary_key6;
*pin6 = *(struct in6_addr *)pkey;
}
diff --git a/include/video/mmp_disp.h b/include/video/mmp_disp.h
index 77252cb46361..a722dcbf5073 100644
--- a/include/video/mmp_disp.h
+++ b/include/video/mmp_disp.h
@@ -231,7 +231,7 @@ struct mmp_path {
/* layers */
int overlay_num;
- struct mmp_overlay overlays[];
+ struct mmp_overlay overlays[] __counted_by(overlay_num);
};
extern struct mmp_path *mmp_get_path(const char *name);
diff --git a/include/video/uvesafb.h b/include/video/uvesafb.h
index 8d2a3bfc8dac..47d96e75e8ef 100644
--- a/include/video/uvesafb.h
+++ b/include/video/uvesafb.h
@@ -109,8 +109,6 @@ struct uvesafb_ktask {
u32 ack;
};
-static int uvesafb_exec(struct uvesafb_ktask *tsk);
-
#define UVESAFB_EXACT_RES 1
#define UVESAFB_EXACT_DEPTH 2
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 21d2fa815e78..6f0d6fb6523f 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -2212,7 +2212,7 @@ __audit_reusename(const __user char *uptr)
if (!n->name)
continue;
if (n->name->uptr == uptr) {
- n->name->refcnt++;
+ atomic_inc(&n->name->refcnt);
return n->name;
}
}
@@ -2241,7 +2241,7 @@ void __audit_getname(struct filename *name)
n->name = name;
n->name_len = AUDIT_NAME_FULL;
name->aname = n;
- name->refcnt++;
+ atomic_inc(&name->refcnt);
}
static inline int audit_copy_fcaps(struct audit_names *name,
@@ -2373,7 +2373,7 @@ out_alloc:
return;
if (name) {
n->name = name;
- name->refcnt++;
+ atomic_inc(&name->refcnt);
}
out:
@@ -2500,7 +2500,7 @@ void __audit_inode_child(struct inode *parent,
if (found_parent) {
found_child->name = found_parent->name;
found_child->name_len = AUDIT_NAME_FULL;
- found_child->name->refcnt++;
+ atomic_inc(&found_child->name->refcnt);
}
}
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 3b21f4063258..881f90f0cbcf 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -189,7 +189,7 @@ static int fprobe_init_rethook(struct fprobe *fp, int num)
{
int i, size;
- if (num < 0)
+ if (num <= 0)
return -EINVAL;
if (!fp->exit_handler) {
@@ -202,8 +202,8 @@ static int fprobe_init_rethook(struct fprobe *fp, int num)
size = fp->nr_maxactive;
else
size = num * num_possible_cpus() * 2;
- if (size < 0)
- return -E2BIG;
+ if (size <= 0)
+ return -EINVAL;
fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler);
if (!fp->rethook)
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 8fda308e400d..9bbffe82d65a 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -895,10 +895,13 @@ void __init setup_kmalloc_cache_index_table(void)
static unsigned int __kmalloc_minalign(void)
{
+ unsigned int minalign = dma_get_cache_alignment();
+
if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) &&
is_swiotlb_allocated())
- return ARCH_KMALLOC_MINALIGN;
- return dma_get_cache_alignment();
+ minalign = ARCH_KMALLOC_MINALIGN;
+
+ return max(minalign, arch_slab_minalign());
}
void __init
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 7a6f20338db8..73470cc3518a 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -1627,6 +1627,15 @@ struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst,
return ERR_PTR(-EOPNOTSUPP);
}
+ /* Reject outgoing connection to device with same BD ADDR against
+ * CVE-2020-26555
+ */
+ if (!bacmp(&hdev->bdaddr, dst)) {
+ bt_dev_dbg(hdev, "Reject connection with same BD_ADDR %pMR\n",
+ dst);
+ return ERR_PTR(-ECONNREFUSED);
+ }
+
acl = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst);
if (!acl) {
acl = hci_conn_add(hdev, ACL_LINK, dst, HCI_ROLE_MASTER);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 31d02b54eea1..1e1c9147356c 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -26,6 +26,8 @@
/* Bluetooth HCI event handling. */
#include <asm/unaligned.h>
+#include <linux/crypto.h>
+#include <crypto/algapi.h>
#include <net/bluetooth/bluetooth.h>
#include <net/bluetooth/hci_core.h>
@@ -3268,6 +3270,16 @@ static void hci_conn_request_evt(struct hci_dev *hdev, void *data,
bt_dev_dbg(hdev, "bdaddr %pMR type 0x%x", &ev->bdaddr, ev->link_type);
+ /* Reject incoming connection from device with same BD ADDR against
+ * CVE-2020-26555
+ */
+ if (hdev && !bacmp(&hdev->bdaddr, &ev->bdaddr)) {
+ bt_dev_dbg(hdev, "Reject connection with same BD_ADDR %pMR\n",
+ &ev->bdaddr);
+ hci_reject_conn(hdev, &ev->bdaddr);
+ return;
+ }
+
mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, ev->link_type,
&flags);
@@ -4742,6 +4754,15 @@ static void hci_link_key_notify_evt(struct hci_dev *hdev, void *data,
if (!conn)
goto unlock;
+ /* Ignore NULL link key against CVE-2020-26555 */
+ if (!crypto_memneq(ev->link_key, ZERO_KEY, HCI_LINK_KEY_SIZE)) {
+ bt_dev_dbg(hdev, "Ignore NULL link key (ZERO KEY) for %pMR",
+ &ev->bdaddr);
+ hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE);
+ hci_conn_drop(conn);
+ goto unlock;
+ }
+
hci_conn_hold(conn);
conn->disc_timeout = HCI_DISCONN_TIMEOUT;
hci_conn_drop(conn);
@@ -5274,8 +5295,8 @@ static u8 bredr_oob_data_present(struct hci_conn *conn)
* available, then do not declare that OOB data is
* present.
*/
- if (!memcmp(data->rand256, ZERO_KEY, 16) ||
- !memcmp(data->hash256, ZERO_KEY, 16))
+ if (!crypto_memneq(data->rand256, ZERO_KEY, 16) ||
+ !crypto_memneq(data->hash256, ZERO_KEY, 16))
return 0x00;
return 0x02;
@@ -5285,8 +5306,8 @@ static u8 bredr_oob_data_present(struct hci_conn *conn)
* not supported by the hardware, then check that if
* P-192 data values are present.
*/
- if (!memcmp(data->rand192, ZERO_KEY, 16) ||
- !memcmp(data->hash192, ZERO_KEY, 16))
+ if (!crypto_memneq(data->rand192, ZERO_KEY, 16) ||
+ !crypto_memneq(data->hash192, ZERO_KEY, 16))
return 0x00;
return 0x01;
@@ -5303,7 +5324,7 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, void *data,
hci_dev_lock(hdev);
conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
- if (!conn)
+ if (!conn || !hci_conn_ssp_enabled(conn))
goto unlock;
hci_conn_hold(conn);
@@ -5550,7 +5571,7 @@ static void hci_simple_pair_complete_evt(struct hci_dev *hdev, void *data,
hci_dev_lock(hdev);
conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr);
- if (!conn)
+ if (!conn || !hci_conn_ssp_enabled(conn))
goto unlock;
/* Reset the authentication requirement to unknown */
@@ -7021,6 +7042,14 @@ unlock:
hci_dev_unlock(hdev);
}
+static int hci_iso_term_big_sync(struct hci_dev *hdev, void *data)
+{
+ u8 handle = PTR_UINT(data);
+
+ return hci_le_terminate_big_sync(hdev, handle,
+ HCI_ERROR_LOCAL_HOST_TERM);
+}
+
static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data,
struct sk_buff *skb)
{
@@ -7065,16 +7094,17 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data,
rcu_read_lock();
}
+ rcu_read_unlock();
+
if (!ev->status && !i)
/* If no BISes have been connected for the BIG,
* terminate. This is in case all bound connections
* have been closed before the BIG creation
* has completed.
*/
- hci_le_terminate_big_sync(hdev, ev->handle,
- HCI_ERROR_LOCAL_HOST_TERM);
+ hci_cmd_sync_queue(hdev, hci_iso_term_big_sync,
+ UINT_PTR(ev->handle), NULL);
- rcu_read_unlock();
hci_dev_unlock(hdev);
}
diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c
index 5e4f718073b7..3e7cd330d731 100644
--- a/net/bluetooth/hci_sock.c
+++ b/net/bluetooth/hci_sock.c
@@ -488,7 +488,8 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event)
ni->type = hdev->dev_type;
ni->bus = hdev->bus;
bacpy(&ni->bdaddr, &hdev->bdaddr);
- memcpy(ni->name, hdev->name, 8);
+ memcpy_and_pad(ni->name, sizeof(ni->name), hdev->name,
+ strnlen(hdev->name, sizeof(ni->name)), '\0');
opcode = cpu_to_le16(HCI_MON_NEW_INDEX);
break;
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index d06e07a0ea5a..a15ab0b874a9 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -5369,6 +5369,7 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason)
{
int err = 0;
u16 handle = conn->handle;
+ bool disconnect = false;
struct hci_conn *c;
switch (conn->state) {
@@ -5399,24 +5400,15 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason)
hci_dev_unlock(hdev);
return 0;
case BT_BOUND:
- hci_dev_lock(hdev);
- hci_conn_failed(conn, reason);
- hci_dev_unlock(hdev);
- return 0;
+ break;
default:
- hci_dev_lock(hdev);
- conn->state = BT_CLOSED;
- hci_disconn_cfm(conn, reason);
- hci_conn_del(conn);
- hci_dev_unlock(hdev);
- return 0;
+ disconnect = true;
+ break;
}
hci_dev_lock(hdev);
- /* Check if the connection hasn't been cleanup while waiting
- * commands to complete.
- */
+ /* Check if the connection has been cleaned up concurrently */
c = hci_conn_hash_lookup_handle(hdev, handle);
if (!c || c != conn) {
err = 0;
@@ -5428,7 +5420,13 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason)
* or in case of LE it was still scanning so it can be cleanup
* safely.
*/
- hci_conn_failed(conn, reason);
+ if (disconnect) {
+ conn->state = BT_CLOSED;
+ hci_disconn_cfm(conn, reason);
+ hci_conn_del(conn);
+ } else {
+ hci_conn_failed(conn, reason);
+ }
unlock:
hci_dev_unlock(hdev);
diff --git a/net/core/dev.c b/net/core/dev.c
index 5aaf5753d4e4..9f3f8930c691 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -345,7 +345,6 @@ int netdev_name_node_alt_create(struct net_device *dev, const char *name)
static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node)
{
list_del(&name_node->list);
- netdev_name_node_del(name_node);
kfree(name_node->name);
netdev_name_node_free(name_node);
}
@@ -364,6 +363,8 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name)
if (name_node == dev->name_node || name_node->dev != dev)
return -EINVAL;
+ netdev_name_node_del(name_node);
+ synchronize_rcu();
__netdev_name_node_alt_destroy(name_node);
return 0;
@@ -380,6 +381,7 @@ static void netdev_name_node_alt_flush(struct net_device *dev)
/* Device list insertion */
static void list_netdevice(struct net_device *dev)
{
+ struct netdev_name_node *name_node;
struct net *net = dev_net(dev);
ASSERT_RTNL();
@@ -390,6 +392,10 @@ static void list_netdevice(struct net_device *dev)
hlist_add_head_rcu(&dev->index_hlist,
dev_index_hash(net, dev->ifindex));
write_unlock(&dev_base_lock);
+
+ netdev_for_each_altname(dev, name_node)
+ netdev_name_node_add(net, name_node);
+
/* We reserved the ifindex, this can't fail */
WARN_ON(xa_store(&net->dev_by_index, dev->ifindex, dev, GFP_KERNEL));
@@ -401,12 +407,16 @@ static void list_netdevice(struct net_device *dev)
*/
static void unlist_netdevice(struct net_device *dev, bool lock)
{
+ struct netdev_name_node *name_node;
struct net *net = dev_net(dev);
ASSERT_RTNL();
xa_erase(&net->dev_by_index, dev->ifindex);
+ netdev_for_each_altname(dev, name_node)
+ netdev_name_node_del(name_node);
+
/* Unlink dev from the device chain */
if (lock)
write_lock(&dev_base_lock);
@@ -1086,7 +1096,8 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
for_each_netdev(net, d) {
struct netdev_name_node *name_node;
- list_for_each_entry(name_node, &d->name_node->list, list) {
+
+ netdev_for_each_altname(d, name_node) {
if (!sscanf(name_node->name, name, &i))
continue;
if (i < 0 || i >= max_netdevices)
@@ -1123,6 +1134,26 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf)
return -ENFILE;
}
+static int dev_prep_valid_name(struct net *net, struct net_device *dev,
+ const char *want_name, char *out_name)
+{
+ int ret;
+
+ if (!dev_valid_name(want_name))
+ return -EINVAL;
+
+ if (strchr(want_name, '%')) {
+ ret = __dev_alloc_name(net, want_name, out_name);
+ return ret < 0 ? ret : 0;
+ } else if (netdev_name_in_use(net, want_name)) {
+ return -EEXIST;
+ } else if (out_name != want_name) {
+ strscpy(out_name, want_name, IFNAMSIZ);
+ }
+
+ return 0;
+}
+
static int dev_alloc_name_ns(struct net *net,
struct net_device *dev,
const char *name)
@@ -1160,19 +1191,13 @@ EXPORT_SYMBOL(dev_alloc_name);
static int dev_get_valid_name(struct net *net, struct net_device *dev,
const char *name)
{
- BUG_ON(!net);
-
- if (!dev_valid_name(name))
- return -EINVAL;
-
- if (strchr(name, '%'))
- return dev_alloc_name_ns(net, dev, name);
- else if (netdev_name_in_use(net, name))
- return -EEXIST;
- else if (dev->name != name)
- strscpy(dev->name, name, IFNAMSIZ);
+ char buf[IFNAMSIZ];
+ int ret;
- return 0;
+ ret = dev_prep_valid_name(net, dev, name, buf);
+ if (ret >= 0)
+ strscpy(dev->name, buf, IFNAMSIZ);
+ return ret;
}
/**
@@ -11037,7 +11062,9 @@ EXPORT_SYMBOL(unregister_netdev);
int __dev_change_net_namespace(struct net_device *dev, struct net *net,
const char *pat, int new_ifindex)
{
+ struct netdev_name_node *name_node;
struct net *net_old = dev_net(dev);
+ char new_name[IFNAMSIZ] = {};
int err, new_nsid;
ASSERT_RTNL();
@@ -11064,10 +11091,15 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
/* We get here if we can't use the current device name */
if (!pat)
goto out;
- err = dev_get_valid_name(net, dev, pat);
+ err = dev_prep_valid_name(net, dev, pat, new_name);
if (err < 0)
goto out;
}
+ /* Check that none of the altnames conflicts. */
+ err = -EEXIST;
+ netdev_for_each_altname(dev, name_node)
+ if (netdev_name_in_use(net, name_node->name))
+ goto out;
/* Check that new_ifindex isn't used yet. */
if (new_ifindex) {
@@ -11135,6 +11167,9 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
kobject_uevent(&dev->dev.kobj, KOBJ_ADD);
netdev_adjacent_add_links(dev);
+ if (new_name[0]) /* Rename the netdev to prepared name */
+ strscpy(dev->name, new_name, IFNAMSIZ);
+
/* Fixup kobjects */
err = device_rename(&dev->dev, dev->name);
WARN_ON(err);
diff --git a/net/core/dev.h b/net/core/dev.h
index e075e198092c..fa2e9c5c4122 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -62,6 +62,9 @@ struct netdev_name_node {
int netdev_get_name(struct net *net, char *name, int ifindex);
int dev_change_name(struct net_device *dev, const char *newname);
+#define netdev_for_each_altname(dev, namenode) \
+ list_for_each_entry((namenode), &(dev)->name_node->list, list)
+
int netdev_name_node_alt_create(struct net_device *dev, const char *name);
int netdev_name_node_alt_destroy(struct net_device *dev, const char *name);
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index f56b8d697014..4d1696677c48 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -669,19 +669,19 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
seq_puts(seq, " Flags: ");
for (i = 0; i < NR_PKT_FLAGS; i++) {
- if (i == F_FLOW_SEQ)
+ if (i == FLOW_SEQ_SHIFT)
if (!pkt_dev->cflows)
continue;
- if (pkt_dev->flags & (1 << i))
+ if (pkt_dev->flags & (1 << i)) {
seq_printf(seq, "%s ", pkt_flag_names[i]);
- else if (i == F_FLOW_SEQ)
- seq_puts(seq, "FLOW_RND ");
-
#ifdef CONFIG_XFRM
- if (i == F_IPSEC && pkt_dev->spi)
- seq_printf(seq, "spi:%u", pkt_dev->spi);
+ if (i == IPSEC_SHIFT && pkt_dev->spi)
+ seq_printf(seq, "spi:%u ", pkt_dev->spi);
#endif
+ } else if (i == FLOW_SEQ_SHIFT) {
+ seq_puts(seq, "FLOW_RND ");
+ }
}
seq_puts(seq, "\n");
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 4a2ec33bfb51..53c377d054f0 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -5503,13 +5503,11 @@ static unsigned int
rtnl_offload_xstats_get_size_hw_s_info_one(const struct net_device *dev,
enum netdev_offload_xstats_type type)
{
- bool enabled = netdev_offload_xstats_enabled(dev, type);
-
return nla_total_size(0) +
/* IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST */
nla_total_size(sizeof(u8)) +
/* IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED */
- (enabled ? nla_total_size(sizeof(u8)) : 0) +
+ nla_total_size(sizeof(u8)) +
0;
}
diff --git a/net/core/stream.c b/net/core/stream.c
index f5c4e47df165..96fbcb9bbb30 100644
--- a/net/core/stream.c
+++ b/net/core/stream.c
@@ -117,7 +117,7 @@ EXPORT_SYMBOL(sk_stream_wait_close);
*/
int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
{
- int err = 0;
+ int ret, err = 0;
long vm_wait = 0;
long current_timeo = *timeo_p;
DEFINE_WAIT_FUNC(wait, woken_wake_function);
@@ -142,11 +142,13 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
sk->sk_write_pending++;
- sk_wait_event(sk, &current_timeo, READ_ONCE(sk->sk_err) ||
- (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) ||
- (sk_stream_memory_free(sk) &&
- !vm_wait), &wait);
+ ret = sk_wait_event(sk, &current_timeo, READ_ONCE(sk->sk_err) ||
+ (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) ||
+ (sk_stream_memory_free(sk) && !vm_wait),
+ &wait);
sk->sk_write_pending--;
+ if (ret < 0)
+ goto do_error;
if (vm_wait) {
vm_wait -= current_timeo;
diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c
index 883ed9be81f9..0515d6604b3b 100644
--- a/net/ethtool/bitset.c
+++ b/net/ethtool/bitset.c
@@ -431,10 +431,8 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits,
ethnl_string_array_t names,
struct netlink_ext_ack *extack, bool *mod)
{
- u32 *orig_bitmap, *saved_bitmap = NULL;
struct nlattr *bit_attr;
bool no_mask;
- bool dummy;
int rem;
int ret;
@@ -450,22 +448,8 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits,
}
no_mask = tb[ETHTOOL_A_BITSET_NOMASK];
- if (no_mask) {
- unsigned int nwords = DIV_ROUND_UP(nbits, 32);
- unsigned int nbytes = nwords * sizeof(u32);
-
- /* The bitmap size is only the size of the map part without
- * its mask part.
- */
- saved_bitmap = kcalloc(nwords, sizeof(u32), GFP_KERNEL);
- if (!saved_bitmap)
- return -ENOMEM;
- memcpy(saved_bitmap, bitmap, nbytes);
- ethnl_bitmap32_clear(bitmap, 0, nbits, &dummy);
- orig_bitmap = saved_bitmap;
- } else {
- orig_bitmap = bitmap;
- }
+ if (no_mask)
+ ethnl_bitmap32_clear(bitmap, 0, nbits, mod);
nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) {
bool old_val, new_val;
@@ -474,14 +458,13 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits,
if (nla_type(bit_attr) != ETHTOOL_A_BITSET_BITS_BIT) {
NL_SET_ERR_MSG_ATTR(extack, bit_attr,
"only ETHTOOL_A_BITSET_BITS_BIT allowed in ETHTOOL_A_BITSET_BITS");
- ret = -EINVAL;
- goto out;
+ return -EINVAL;
}
ret = ethnl_parse_bit(&idx, &new_val, nbits, bit_attr, no_mask,
names, extack);
if (ret < 0)
- goto out;
- old_val = orig_bitmap[idx / 32] & ((u32)1 << (idx % 32));
+ return ret;
+ old_val = bitmap[idx / 32] & ((u32)1 << (idx % 32));
if (new_val != old_val) {
if (new_val)
bitmap[idx / 32] |= ((u32)1 << (idx % 32));
@@ -491,10 +474,7 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits,
}
}
- ret = 0;
-out:
- kfree(saved_bitmap);
- return ret;
+ return 0;
}
static int ethnl_compact_sanity_checks(unsigned int nbits,
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 3d2e30e20473..2713c9b06c4c 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -597,7 +597,6 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
add_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending += writebias;
- sk->sk_wait_pending++;
/* Basic assumption: if someone sets sk->sk_err, he _must_
* change state of the socket from TCP_SYN_*.
@@ -613,7 +612,6 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
}
remove_wait_queue(sk_sleep(sk), &wait);
sk->sk_write_pending -= writebias;
- sk->sk_wait_pending--;
return timeo;
}
@@ -642,6 +640,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
return -EINVAL;
if (uaddr->sa_family == AF_UNSPEC) {
+ sk->sk_disconnects++;
err = sk->sk_prot->disconnect(sk, flags);
sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
goto out;
@@ -696,6 +695,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
int writebias = (sk->sk_protocol == IPPROTO_TCP) &&
tcp_sk(sk)->fastopen_req &&
tcp_sk(sk)->fastopen_req->data ? 1 : 0;
+ int dis = sk->sk_disconnects;
/* Error code is set above */
if (!timeo || !inet_wait_for_connect(sk, timeo, writebias))
@@ -704,6 +704,11 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
err = sock_intr_errno(timeo);
if (signal_pending(current))
goto out;
+
+ if (dis != sk->sk_disconnects) {
+ err = -EPIPE;
+ goto out;
+ }
}
/* Connection was closed by RST, timeout, ICMP error
@@ -725,6 +730,7 @@ out:
sock_error:
err = sock_error(sk) ? : -ECONNABORTED;
sock->state = SS_UNCONNECTED;
+ sk->sk_disconnects++;
if (sk->sk_prot->disconnect(sk, flags))
sock->state = SS_DISCONNECTING;
goto out;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 2be2d4922557..d18f0f092fe7 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -732,7 +732,9 @@ static inline int esp_remove_trailer(struct sk_buff *skb)
skb->csum = csum_block_sub(skb->csum, csumdiff,
skb->len - trimlen);
}
- pskb_trim(skb, skb->len - trimlen);
+ ret = pskb_trim(skb, skb->len - trimlen);
+ if (unlikely(ret))
+ return ret;
ret = nexthdr[1];
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 1ea82bc33ef1..5eb1b8d302bb 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1325,15 +1325,18 @@ __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc,
unsigned char scope)
{
struct fib_nh *nh;
+ __be32 saddr;
if (nhc->nhc_family != AF_INET)
return inet_select_addr(nhc->nhc_dev, 0, scope);
nh = container_of(nhc, struct fib_nh, nh_common);
- nh->nh_saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope);
- nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid);
+ saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope);
- return nh->nh_saddr;
+ WRITE_ONCE(nh->nh_saddr, saddr);
+ WRITE_ONCE(nh->nh_saddr_genid, atomic_read(&net->ipv4.dev_addr_genid));
+
+ return saddr;
}
__be32 fib_result_prefsrc(struct net *net, struct fib_result *res)
@@ -1347,8 +1350,9 @@ __be32 fib_result_prefsrc(struct net *net, struct fib_result *res)
struct fib_nh *nh;
nh = container_of(nhc, struct fib_nh, nh_common);
- if (nh->nh_saddr_genid == atomic_read(&net->ipv4.dev_addr_genid))
- return nh->nh_saddr;
+ if (READ_ONCE(nh->nh_saddr_genid) ==
+ atomic_read(&net->ipv4.dev_addr_genid))
+ return READ_ONCE(nh->nh_saddr);
}
return fib_info_update_nhc_saddr(net, nhc, res->fi->fib_scope);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index aeebe8816689..394a498c2823 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1145,7 +1145,6 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
if (newsk) {
struct inet_connection_sock *newicsk = inet_csk(newsk);
- newsk->sk_wait_pending = 0;
inet_sk_set_state(newsk, TCP_SYN_RECV);
newicsk->icsk_bind_hash = NULL;
newicsk->icsk_bind2_hash = NULL;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index c32f5e28758b..598c1b114d2c 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -149,8 +149,14 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2,
const struct sock *sk)
{
#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family != tb2->family)
- return false;
+ if (sk->sk_family != tb2->family) {
+ if (sk->sk_family == AF_INET)
+ return ipv6_addr_v4mapped(&tb2->v6_rcv_saddr) &&
+ tb2->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr;
+
+ return ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr) &&
+ sk->sk_v6_rcv_saddr.s6_addr32[3] == tb2->rcv_saddr;
+ }
if (sk->sk_family == AF_INET6)
return ipv6_addr_equal(&tb2->v6_rcv_saddr,
@@ -819,19 +825,7 @@ static bool inet_bind2_bucket_match(const struct inet_bind2_bucket *tb,
tb->l3mdev != l3mdev)
return false;
-#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family != tb->family) {
- if (sk->sk_family == AF_INET)
- return ipv6_addr_v4mapped(&tb->v6_rcv_saddr) &&
- tb->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr;
-
- return false;
- }
-
- if (sk->sk_family == AF_INET6)
- return ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr);
-#endif
- return tb->rcv_saddr == sk->sk_rcv_saddr;
+ return inet_bind2_bucket_addr_match(tb, sk);
}
bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const struct net *net,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3f66cdeef7de..d3456cf840de 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -831,7 +831,9 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
*/
if (!skb_queue_empty(&sk->sk_receive_queue))
break;
- sk_wait_data(sk, &timeo, NULL);
+ ret = sk_wait_data(sk, &timeo, NULL);
+ if (ret < 0)
+ break;
if (signal_pending(current)) {
ret = sock_intr_errno(timeo);
break;
@@ -2442,7 +2444,11 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
__sk_flush_backlog(sk);
} else {
tcp_cleanup_rbuf(sk, copied);
- sk_wait_data(sk, &timeo, last);
+ err = sk_wait_data(sk, &timeo, last);
+ if (err < 0) {
+ err = copied ? : err;
+ goto out;
+ }
}
if ((flags & MSG_PEEK) &&
@@ -2966,12 +2972,6 @@ int tcp_disconnect(struct sock *sk, int flags)
int old_state = sk->sk_state;
u32 seq;
- /* Deny disconnect if other threads are blocked in sk_wait_event()
- * or inet_wait_for_connect().
- */
- if (sk->sk_wait_pending)
- return -EBUSY;
-
if (old_state != TCP_CLOSE)
tcp_set_state(sk, TCP_CLOSE);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 327268203001..53b0d62fd2c2 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -307,6 +307,10 @@ msg_bytes_ready:
}
data = tcp_msg_wait_data(sk, psock, timeo);
+ if (data < 0) {
+ copied = data;
+ goto unlock;
+ }
if (data && !sk_psock_queue_empty(psock))
goto msg_bytes_ready;
copied = -EAGAIN;
@@ -317,6 +321,8 @@ out:
tcp_rcv_space_adjust(sk);
if (copied > 0)
__tcp_cleanup_rbuf(sk, copied);
+
+unlock:
release_sock(sk);
sk_psock_put(sk, psock);
return copied;
@@ -351,6 +357,10 @@ msg_bytes_ready:
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
data = tcp_msg_wait_data(sk, psock, timeo);
+ if (data < 0) {
+ ret = data;
+ goto unlock;
+ }
if (data) {
if (!sk_psock_queue_empty(psock))
goto msg_bytes_ready;
@@ -361,6 +371,8 @@ msg_bytes_ready:
copied = -EAGAIN;
}
ret = copied;
+
+unlock:
release_sock(sk);
sk_psock_put(sk, psock);
return ret;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 27140e5cdc06..4167e8a48b60 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1869,6 +1869,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
#ifdef CONFIG_TLS_DEVICE
tail->decrypted != skb->decrypted ||
#endif
+ !mptcp_skb_can_collapse(tail, skb) ||
thtail->doff != th->doff ||
memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th)))
goto no_coalesce;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9c8c42c280b7..f0723460753c 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2542,6 +2542,18 @@ static bool tcp_pacing_check(struct sock *sk)
return true;
}
+static bool tcp_rtx_queue_empty_or_single_skb(const struct sock *sk)
+{
+ const struct rb_node *node = sk->tcp_rtx_queue.rb_node;
+
+ /* No skb in the rtx queue. */
+ if (!node)
+ return true;
+
+ /* Only one skb in rtx queue. */
+ return !node->rb_left && !node->rb_right;
+}
+
/* TCP Small Queues :
* Control number of packets in qdisc/devices to two packets / or ~1 ms.
* (These limits are doubled for retransmits)
@@ -2579,12 +2591,12 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb,
limit += extra_bytes;
}
if (refcount_read(&sk->sk_wmem_alloc) > limit) {
- /* Always send skb if rtx queue is empty.
+ /* Always send skb if rtx queue is empty or has one skb.
* No need to wait for TX completion to call us back,
* after softirq/tasklet schedule.
* This helps when TX completions are delayed too much.
*/
- if (tcp_rtx_queue_empty(sk))
+ if (tcp_rtx_queue_empty_or_single_skb(sk))
return false;
set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags);
@@ -2788,7 +2800,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- u32 timeout, rto_delta_us;
+ u32 timeout, timeout_us, rto_delta_us;
int early_retrans;
/* Don't do any loss probe on a Fast Open connection before 3WHS
@@ -2812,11 +2824,12 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
* sample is available then probe after TCP_TIMEOUT_INIT.
*/
if (tp->srtt_us) {
- timeout = usecs_to_jiffies(tp->srtt_us >> 2);
+ timeout_us = tp->srtt_us >> 2;
if (tp->packets_out == 1)
- timeout += TCP_RTO_MIN;
+ timeout_us += tcp_rto_min_us(sk);
else
- timeout += TCP_TIMEOUT_MIN;
+ timeout_us += TCP_TIMEOUT_MIN_US;
+ timeout = usecs_to_jiffies(timeout_us);
} else {
timeout = TCP_TIMEOUT_INIT;
}
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index acf4869c5d3b..bba10110fbbc 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -104,7 +104,7 @@ bool tcp_rack_mark_lost(struct sock *sk)
tp->rack.advanced = 0;
tcp_rack_detect_loss(sk, &timeout);
if (timeout) {
- timeout = usecs_to_jiffies(timeout) + TCP_TIMEOUT_MIN;
+ timeout = usecs_to_jiffies(timeout + TCP_TIMEOUT_MIN_US);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT,
timeout, inet_csk(sk)->icsk_rto);
}
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index fddd0cbdede1..e023d29e919c 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -770,7 +770,9 @@ static inline int esp_remove_trailer(struct sk_buff *skb)
skb->csum = csum_block_sub(skb->csum, csumdiff,
skb->len - trimlen);
}
- pskb_trim(skb, skb->len - trimlen);
+ ret = pskb_trim(skb, skb->len - trimlen);
+ if (unlikely(ret))
+ return ret;
ret = nexthdr[1];
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 41a680c76d2e..42fb6996b077 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -117,10 +117,10 @@ static void xfrm6_dst_destroy(struct dst_entry *dst)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
- if (likely(xdst->u.rt6.rt6i_idev))
- in6_dev_put(xdst->u.rt6.rt6i_idev);
dst_destroy_metrics_generic(dst);
rt6_uncached_list_del(&xdst->u.rt6);
+ if (likely(xdst->u.rt6.rt6i_idev))
+ in6_dev_put(xdst->u.rt6.rt6i_idev);
xfrm_dst_destroy(xdst);
}
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 0665ff5e456e..a2db0585dce0 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -912,7 +912,7 @@ int ieee80211_key_link(struct ieee80211_key *key,
*/
if (ieee80211_key_identical(sdata, old_key, key)) {
ret = -EALREADY;
- goto unlock;
+ goto out;
}
key->local = sdata->local;
@@ -940,7 +940,6 @@ int ieee80211_key_link(struct ieee80211_key *key,
out:
ieee80211_key_free_unused(key);
- unlock:
mutex_unlock(&sdata->local->key_mtx);
return ret;
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index c3b83cb390d9..886ab689a8ae 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -1298,7 +1298,7 @@ alloc_skb:
if (copy == 0) {
u64 snd_una = READ_ONCE(msk->snd_una);
- if (snd_una != msk->snd_nxt) {
+ if (snd_una != msk->snd_nxt || tcp_write_queue_tail(ssk)) {
tcp_remove_empty_skb(ssk);
return 0;
}
@@ -1306,11 +1306,6 @@ alloc_skb:
zero_window_probe = true;
data_seq = snd_una - 1;
copy = 1;
-
- /* all mptcp-level data is acked, no skbs should be present into the
- * ssk write queue
- */
- WARN_ON_ONCE(reuse_skb);
}
copy = min_t(size_t, copy, info->limit - info->sent);
@@ -1339,7 +1334,6 @@ alloc_skb:
if (reuse_skb) {
TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
mpext->data_len += copy;
- WARN_ON_ONCE(zero_window_probe);
goto out;
}
@@ -2354,6 +2348,26 @@ bool __mptcp_retransmit_pending_data(struct sock *sk)
#define MPTCP_CF_PUSH BIT(1)
#define MPTCP_CF_FASTCLOSE BIT(2)
+/* be sure to send a reset only if the caller asked for it, also
+ * clean completely the subflow status when the subflow reaches
+ * TCP_CLOSE state
+ */
+static void __mptcp_subflow_disconnect(struct sock *ssk,
+ struct mptcp_subflow_context *subflow,
+ unsigned int flags)
+{
+ if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+ (flags & MPTCP_CF_FASTCLOSE)) {
+ /* The MPTCP code never wait on the subflow sockets, TCP-level
+ * disconnect should never fail
+ */
+ WARN_ON_ONCE(tcp_disconnect(ssk, 0));
+ mptcp_subflow_ctx_reset(subflow);
+ } else {
+ tcp_shutdown(ssk, SEND_SHUTDOWN);
+ }
+}
+
/* subflow sockets can be either outgoing (connect) or incoming
* (accept).
*
@@ -2391,7 +2405,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) {
- /* be sure to force the tcp_disconnect() path,
+ /* be sure to force the tcp_close path
* to generate the egress reset
*/
ssk->sk_lingertime = 0;
@@ -2401,11 +2415,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk);
if (!dispose_it) {
- /* The MPTCP code never wait on the subflow sockets, TCP-level
- * disconnect should never fail
- */
- WARN_ON_ONCE(tcp_disconnect(ssk, 0));
- mptcp_subflow_ctx_reset(subflow);
+ __mptcp_subflow_disconnect(ssk, subflow, flags);
release_sock(ssk);
goto out;
@@ -3098,12 +3108,6 @@ static int mptcp_disconnect(struct sock *sk, int flags)
{
struct mptcp_sock *msk = mptcp_sk(sk);
- /* Deny disconnect if other threads are blocked in sk_wait_event()
- * or inet_wait_for_connect().
- */
- if (sk->sk_wait_pending)
- return -EBUSY;
-
/* We are on the fastopen error path. We can't call straight into the
* subflows cleanup code due to lock nesting (we are already under
* msk->firstsocket lock).
@@ -3173,7 +3177,6 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk);
#endif
- nsk->sk_wait_pending = 0;
__mptcp_init_sock(nsk);
msk = mptcp_sk(nsk);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index a72b6aeefb1b..29c651804cb2 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -3166,7 +3166,7 @@ int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla,
if (err < 0)
return err;
- if (!tb[NFTA_EXPR_DATA])
+ if (!tb[NFTA_EXPR_DATA] || !tb[NFTA_EXPR_NAME])
return -EINVAL;
type = __nft_expr_type_get(ctx->family, tb[NFTA_EXPR_NAME]);
@@ -5556,7 +5556,6 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv);
unsigned char *b = skb_tail_pointer(skb);
struct nlattr *nest;
- u64 timeout = 0;
nest = nla_nest_start_noflag(skb, NFTA_LIST_ELEM);
if (nest == NULL)
@@ -5592,15 +5591,11 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
htonl(*nft_set_ext_flags(ext))))
goto nla_put_failure;
- if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) {
- timeout = *nft_set_ext_timeout(ext);
- if (nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT,
- nf_jiffies64_to_msecs(timeout),
- NFTA_SET_ELEM_PAD))
- goto nla_put_failure;
- } else if (set->flags & NFT_SET_TIMEOUT) {
- timeout = READ_ONCE(set->timeout);
- }
+ if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) &&
+ nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT,
+ nf_jiffies64_to_msecs(*nft_set_ext_timeout(ext)),
+ NFTA_SET_ELEM_PAD))
+ goto nla_put_failure;
if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
u64 expires, now = get_jiffies_64();
@@ -5615,9 +5610,6 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
nf_jiffies64_to_msecs(expires),
NFTA_SET_ELEM_PAD))
goto nla_put_failure;
-
- if (reset)
- *nft_set_ext_expiration(ext) = now + timeout;
}
if (nft_set_ext_exists(ext, NFT_SET_EXT_USERDATA)) {
@@ -7615,6 +7607,16 @@ nla_put_failure:
return -1;
}
+static void audit_log_obj_reset(const struct nft_table *table,
+ unsigned int base_seq, unsigned int nentries)
+{
+ char *buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, base_seq);
+
+ audit_log_nfcfg(buf, table->family, nentries,
+ AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC);
+ kfree(buf);
+}
+
struct nft_obj_filter {
char *table;
u32 type;
@@ -7629,8 +7631,10 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
struct net *net = sock_net(skb->sk);
int family = nfmsg->nfgen_family;
struct nftables_pernet *nft_net;
+ unsigned int entries = 0;
struct nft_object *obj;
bool reset = false;
+ int rc = 0;
if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET)
reset = true;
@@ -7643,6 +7647,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
if (family != NFPROTO_UNSPEC && family != table->family)
continue;
+ entries = 0;
list_for_each_entry_rcu(obj, &table->objects, list) {
if (!nft_is_active(net, obj))
goto cont;
@@ -7658,34 +7663,27 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
filter->type != NFT_OBJECT_UNSPEC &&
obj->ops->type->type != filter->type)
goto cont;
- if (reset) {
- char *buf = kasprintf(GFP_ATOMIC,
- "%s:%u",
- table->name,
- nft_net->base_seq);
-
- audit_log_nfcfg(buf,
- family,
- obj->handle,
- AUDIT_NFT_OP_OBJ_RESET,
- GFP_ATOMIC);
- kfree(buf);
- }
- if (nf_tables_fill_obj_info(skb, net, NETLINK_CB(cb->skb).portid,
- cb->nlh->nlmsg_seq,
- NFT_MSG_NEWOBJ,
- NLM_F_MULTI | NLM_F_APPEND,
- table->family, table,
- obj, reset) < 0)
- goto done;
+ rc = nf_tables_fill_obj_info(skb, net,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq,
+ NFT_MSG_NEWOBJ,
+ NLM_F_MULTI | NLM_F_APPEND,
+ table->family, table,
+ obj, reset);
+ if (rc < 0)
+ break;
+ entries++;
nl_dump_check_consistent(cb, nlmsg_hdr(skb));
cont:
idx++;
}
+ if (reset && entries)
+ audit_log_obj_reset(table, nft_net->base_seq, entries);
+ if (rc < 0)
+ break;
}
-done:
rcu_read_unlock();
cb->args[0] = idx;
@@ -7790,7 +7788,7 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,
audit_log_nfcfg(buf,
family,
- obj->handle,
+ 1,
AUDIT_NFT_OP_OBJ_RESET,
GFP_ATOMIC);
kfree(buf);
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index 53c9e76473ba..f03f4d4d7d88 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -698,8 +698,8 @@ nfulnl_log_packet(struct net *net,
unsigned int plen = 0;
struct nfnl_log_net *log = nfnl_log_pernet(net);
const struct nfnl_ct_hook *nfnl_ct = NULL;
+ enum ip_conntrack_info ctinfo = 0;
struct nf_conn *ct = NULL;
- enum ip_conntrack_info ctinfo;
if (li_user && li_user->type == NF_LOG_TYPE_ULOG)
li = li_user;
diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c
index 28e2873ba24e..928312d01eb1 100644
--- a/net/netfilter/nft_inner.c
+++ b/net/netfilter/nft_inner.c
@@ -298,6 +298,7 @@ static int nft_inner_init(const struct nft_ctx *ctx,
int err;
if (!tb[NFTA_INNER_FLAGS] ||
+ !tb[NFTA_INNER_NUM] ||
!tb[NFTA_INNER_HDRSIZE] ||
!tb[NFTA_INNER_TYPE] ||
!tb[NFTA_INNER_EXPR])
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 120f6d395b98..0a689c8e0295 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -179,7 +179,7 @@ void nft_payload_eval(const struct nft_expr *expr,
switch (priv->base) {
case NFT_PAYLOAD_LL_HEADER:
- if (!skb_mac_header_was_set(skb))
+ if (!skb_mac_header_was_set(skb) || skb_mac_header_len(skb) == 0)
goto err;
if (skb_vlan_tag_present(skb) &&
diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
index 25a75591583e..2e164a319945 100644
--- a/net/netfilter/nft_set_pipapo.h
+++ b/net/netfilter/nft_set_pipapo.h
@@ -147,7 +147,7 @@ struct nft_pipapo_match {
unsigned long * __percpu *scratch;
size_t bsize_max;
struct rcu_head rcu;
- struct nft_pipapo_field f[];
+ struct nft_pipapo_field f[] __counted_by(field_count);
};
/**
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 2660ceab3759..e34662f4a71e 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -568,6 +568,8 @@ static void *nft_rbtree_deactivate(const struct net *net,
nft_rbtree_interval_end(this)) {
parent = parent->rb_right;
continue;
+ } else if (nft_set_elem_expired(&rbe->ext)) {
+ break;
} else if (!nft_set_elem_active(&rbe->ext, genmask)) {
parent = parent->rb_left;
continue;
diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c
index 0935527d1d12..b68150c971d0 100644
--- a/net/nfc/nci/spi.c
+++ b/net/nfc/nci/spi.c
@@ -151,6 +151,8 @@ static int send_acknowledge(struct nci_spi *nspi, u8 acknowledge)
int ret;
skb = nci_skb_alloc(nspi->ndev, 0, GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
/* add the NCI SPI header to the start of the buffer */
hdr = skb_push(skb, NCI_SPI_HDR_LEN);
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index 08630896b6c8..14cc8fe8584b 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -1180,7 +1180,6 @@ static int rfkill_fop_open(struct inode *inode, struct file *file)
init_waitqueue_head(&data->read_wait);
mutex_lock(&rfkill_global_mutex);
- mutex_lock(&data->mtx);
/*
* start getting events from elsewhere but hold mtx to get
* startup events added first
@@ -1192,10 +1191,11 @@ static int rfkill_fop_open(struct inode *inode, struct file *file)
goto free;
rfkill_sync(rfkill);
rfkill_fill_event(&ev->ev, rfkill, RFKILL_OP_ADD);
+ mutex_lock(&data->mtx);
list_add_tail(&ev->list, &data->events);
+ mutex_unlock(&data->mtx);
}
list_add(&data->list, &rfkill_fds);
- mutex_unlock(&data->mtx);
mutex_unlock(&rfkill_global_mutex);
file->private_data = data;
@@ -1203,7 +1203,6 @@ static int rfkill_fop_open(struct inode *inode, struct file *file)
return stream_open(inode, file);
free:
- mutex_unlock(&data->mtx);
mutex_unlock(&rfkill_global_mutex);
mutex_destroy(&data->mtx);
list_for_each_entry_safe(ev, tmp, &data->events, list)
diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c
index e9d1b2f2ff0a..5a81505fba9a 100644
--- a/net/rfkill/rfkill-gpio.c
+++ b/net/rfkill/rfkill-gpio.c
@@ -108,13 +108,13 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
rfkill->clk = devm_clk_get(&pdev->dev, NULL);
- gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_OUT_LOW);
+ gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_ASIS);
if (IS_ERR(gpio))
return PTR_ERR(gpio);
rfkill->reset_gpio = gpio;
- gpio = devm_gpiod_get_optional(&pdev->dev, "shutdown", GPIOD_OUT_LOW);
+ gpio = devm_gpiod_get_optional(&pdev->dev, "shutdown", GPIOD_ASIS);
if (IS_ERR(gpio))
return PTR_ERR(gpio);
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 3554085bc2be..880c5f16b29c 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -902,6 +902,14 @@ hfsc_change_usc(struct hfsc_class *cl, struct tc_service_curve *usc,
cl->cl_flags |= HFSC_USC;
}
+static void
+hfsc_upgrade_rt(struct hfsc_class *cl)
+{
+ cl->cl_fsc = cl->cl_rsc;
+ rtsc_init(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vt, cl->cl_total);
+ cl->cl_flags |= HFSC_FSC;
+}
+
static const struct nla_policy hfsc_policy[TCA_HFSC_MAX + 1] = {
[TCA_HFSC_RSC] = { .len = sizeof(struct tc_service_curve) },
[TCA_HFSC_FSC] = { .len = sizeof(struct tc_service_curve) },
@@ -1011,10 +1019,6 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
if (parent == NULL)
return -ENOENT;
}
- if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) {
- NL_SET_ERR_MSG(extack, "Invalid parent - parent class must have FSC");
- return -EINVAL;
- }
if (classid == 0 || TC_H_MAJ(classid ^ sch->handle) != 0)
return -EINVAL;
@@ -1065,6 +1069,12 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
cl->cf_tree = RB_ROOT;
sch_tree_lock(sch);
+ /* Check if the inner class is a misconfigured 'rt' */
+ if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) {
+ NL_SET_ERR_MSG(extack,
+ "Forced curve change on parent 'rt' to 'sc'");
+ hfsc_upgrade_rt(parent);
+ }
qdisc_class_hash_insert(&q->clhash, &cl->cl_common);
list_add_tail(&cl->siblings, &parent->children);
if (parent->level == 0)
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index bacdd971615e..35ddebae8894 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1201,6 +1201,7 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc,
(struct smc_clc_msg_accept_confirm_v2 *)aclc;
struct smc_clc_first_contact_ext *fce =
smc_get_clc_first_contact_ext(clc_v2, false);
+ struct net *net = sock_net(&smc->sk);
int rc;
if (!ini->first_contact_peer || aclc->hdr.version == SMC_V1)
@@ -1210,7 +1211,7 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc,
memcpy(ini->smcrv2.nexthop_mac, &aclc->r0.lcl.mac, ETH_ALEN);
ini->smcrv2.uses_gateway = false;
} else {
- if (smc_ib_find_route(smc->clcsock->sk->sk_rcv_saddr,
+ if (smc_ib_find_route(net, smc->clcsock->sk->sk_rcv_saddr,
smc_ib_gid_to_ipv4(aclc->r0.lcl.gid),
ini->smcrv2.nexthop_mac,
&ini->smcrv2.uses_gateway))
@@ -2361,7 +2362,7 @@ static int smc_listen_find_device(struct smc_sock *new_smc,
smc_find_ism_store_rc(rc, ini);
return (!rc) ? 0 : ini->rc;
}
- return SMC_CLC_DECL_NOSMCDEV;
+ return prfx_rc;
}
/* listen worker: finish RDMA setup */
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 9b66d6aeeb1a..89981dbe46c9 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -193,7 +193,7 @@ bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport)
return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE;
}
-int smc_ib_find_route(__be32 saddr, __be32 daddr,
+int smc_ib_find_route(struct net *net, __be32 saddr, __be32 daddr,
u8 nexthop_mac[], u8 *uses_gateway)
{
struct neighbour *neigh = NULL;
@@ -205,7 +205,7 @@ int smc_ib_find_route(__be32 saddr, __be32 daddr,
if (daddr == cpu_to_be32(INADDR_NONE))
goto out;
- rt = ip_route_output_flow(&init_net, &fl4, NULL);
+ rt = ip_route_output_flow(net, &fl4, NULL);
if (IS_ERR(rt))
goto out;
if (rt->rt_uses_gateway && rt->rt_gw_family != AF_INET)
@@ -235,6 +235,7 @@ static int smc_ib_determine_gid_rcu(const struct net_device *ndev,
if (smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP &&
smc_ib_gid_to_ipv4((u8 *)&attr->gid) != cpu_to_be32(INADDR_NONE)) {
struct in_device *in_dev = __in_dev_get_rcu(ndev);
+ struct net *net = dev_net(ndev);
const struct in_ifaddr *ifa;
bool subnet_match = false;
@@ -248,7 +249,7 @@ static int smc_ib_determine_gid_rcu(const struct net_device *ndev,
}
if (!subnet_match)
goto out;
- if (smcrv2->daddr && smc_ib_find_route(smcrv2->saddr,
+ if (smcrv2->daddr && smc_ib_find_route(net, smcrv2->saddr,
smcrv2->daddr,
smcrv2->nexthop_mac,
&smcrv2->uses_gateway))
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index 4df5f8c8a0a1..ef8ac2b7546d 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -112,7 +112,7 @@ void smc_ib_sync_sg_for_device(struct smc_link *lnk,
int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
unsigned short vlan_id, u8 gid[], u8 *sgid_index,
struct smc_init_info_smcrv2 *smcrv2);
-int smc_ib_find_route(__be32 saddr, __be32 daddr,
+int smc_ib_find_route(struct net *net, __be32 saddr, __be32 daddr,
u8 nexthop_mac[], u8 *uses_gateway);
bool smc_ib_is_valid_local_systemid(void);
int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb);
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 02f583ff9239..002483e60c19 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -139,8 +139,8 @@ void update_sk_prot(struct sock *sk, struct tls_context *ctx)
int wait_on_pending_writer(struct sock *sk, long *timeo)
{
- int rc = 0;
DEFINE_WAIT_FUNC(wait, woken_wake_function);
+ int ret, rc = 0;
add_wait_queue(sk_sleep(sk), &wait);
while (1) {
@@ -154,9 +154,13 @@ int wait_on_pending_writer(struct sock *sk, long *timeo)
break;
}
- if (sk_wait_event(sk, timeo,
- !READ_ONCE(sk->sk_write_pending), &wait))
+ ret = sk_wait_event(sk, timeo,
+ !READ_ONCE(sk->sk_write_pending), &wait);
+ if (ret) {
+ if (ret < 0)
+ rc = ret;
break;
+ }
}
remove_wait_queue(sk_sleep(sk), &wait);
return rc;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index d1fc295b83b5..e9d1e83a859d 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1291,6 +1291,7 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock,
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
DEFINE_WAIT_FUNC(wait, woken_wake_function);
+ int ret = 0;
long timeo;
timeo = sock_rcvtimeo(sk, nonblock);
@@ -1302,6 +1303,9 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock,
if (sk->sk_err)
return sock_error(sk);
+ if (ret < 0)
+ return ret;
+
if (!skb_queue_empty(&sk->sk_receive_queue)) {
tls_strp_check_rcv(&ctx->strp);
if (tls_strp_msg_ready(ctx))
@@ -1320,10 +1324,10 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock,
released = true;
add_wait_queue(sk_sleep(sk), &wait);
sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
- sk_wait_event(sk, &timeo,
- tls_strp_msg_ready(ctx) ||
- !sk_psock_queue_empty(psock),
- &wait);
+ ret = sk_wait_event(sk, &timeo,
+ tls_strp_msg_ready(ctx) ||
+ !sk_psock_queue_empty(psock),
+ &wait);
sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
remove_wait_queue(sk_sleep(sk), &wait);
@@ -1852,6 +1856,7 @@ static int tls_rx_reader_acquire(struct sock *sk, struct tls_sw_context_rx *ctx,
bool nonblock)
{
long timeo;
+ int ret;
timeo = sock_rcvtimeo(sk, nonblock);
@@ -1861,14 +1866,16 @@ static int tls_rx_reader_acquire(struct sock *sk, struct tls_sw_context_rx *ctx,
ctx->reader_contended = 1;
add_wait_queue(&ctx->wq, &wait);
- sk_wait_event(sk, &timeo,
- !READ_ONCE(ctx->reader_present), &wait);
+ ret = sk_wait_event(sk, &timeo,
+ !READ_ONCE(ctx->reader_present), &wait);
remove_wait_queue(&ctx->wq, &wait);
if (timeo <= 0)
return -EAGAIN;
if (signal_pending(current))
return sock_intr_errno(timeo);
+ if (ret < 0)
+ return ret;
}
WRITE_ONCE(ctx->reader_present, 1);
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 64e861617110..acec41c1809a 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1622,7 +1622,7 @@ void wiphy_work_queue(struct wiphy *wiphy, struct wiphy_work *work)
list_add_tail(&work->entry, &rdev->wiphy_work_list);
spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags);
- schedule_work(&rdev->wiphy_work);
+ queue_work(system_unbound_wq, &rdev->wiphy_work);
}
EXPORT_SYMBOL_GPL(wiphy_work_queue);
diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
index b86474084690..e21cc71095bb 100644
--- a/net/xfrm/xfrm_interface_core.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -380,8 +380,8 @@ static int xfrmi_rcv_cb(struct sk_buff *skb, int err)
skb->dev = dev;
if (err) {
- dev->stats.rx_errors++;
- dev->stats.rx_dropped++;
+ DEV_STATS_INC(dev, rx_errors);
+ DEV_STATS_INC(dev, rx_dropped);
return 0;
}
@@ -426,7 +426,6 @@ static int
xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
{
struct xfrm_if *xi = netdev_priv(dev);
- struct net_device_stats *stats = &xi->dev->stats;
struct dst_entry *dst = skb_dst(skb);
unsigned int length = skb->len;
struct net_device *tdev;
@@ -473,7 +472,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
tdev = dst->dev;
if (tdev == dev) {
- stats->collisions++;
+ DEV_STATS_INC(dev, collisions);
net_warn_ratelimited("%s: Local routing loop detected!\n",
dev->name);
goto tx_err_dst_release;
@@ -512,13 +511,13 @@ xmit:
if (net_xmit_eval(err) == 0) {
dev_sw_netstats_tx_add(dev, 1, length);
} else {
- stats->tx_errors++;
- stats->tx_aborted_errors++;
+ DEV_STATS_INC(dev, tx_errors);
+ DEV_STATS_INC(dev, tx_aborted_errors);
}
return 0;
tx_err_link_failure:
- stats->tx_carrier_errors++;
+ DEV_STATS_INC(dev, tx_carrier_errors);
dst_link_failure(skb);
tx_err_dst_release:
dst_release(dst);
@@ -528,7 +527,6 @@ tx_err_dst_release:
static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct xfrm_if *xi = netdev_priv(dev);
- struct net_device_stats *stats = &xi->dev->stats;
struct dst_entry *dst = skb_dst(skb);
struct flowi fl;
int ret;
@@ -545,7 +543,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
dst = ip6_route_output(dev_net(dev), NULL, &fl.u.ip6);
if (dst->error) {
dst_release(dst);
- stats->tx_carrier_errors++;
+ DEV_STATS_INC(dev, tx_carrier_errors);
goto tx_err;
}
skb_dst_set(skb, dst);
@@ -561,7 +559,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
fl.u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC;
rt = __ip_route_output_key(dev_net(dev), &fl.u.ip4);
if (IS_ERR(rt)) {
- stats->tx_carrier_errors++;
+ DEV_STATS_INC(dev, tx_carrier_errors);
goto tx_err;
}
skb_dst_set(skb, &rt->dst);
@@ -580,8 +578,8 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
tx_err:
- stats->tx_errors++;
- stats->tx_dropped++;
+ DEV_STATS_INC(dev, tx_errors);
+ DEV_STATS_INC(dev, tx_dropped);
kfree_skb(skb);
return NETDEV_TX_OK;
}
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index d6b405782b63..d24b4d4f620e 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -851,7 +851,7 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net,
struct hlist_node *newpos = NULL;
bool matches_s, matches_d;
- if (!policy->bydst_reinsert)
+ if (policy->walk.dead || !policy->bydst_reinsert)
continue;
WARN_ON_ONCE(policy->family != family);
@@ -1256,8 +1256,11 @@ static void xfrm_hash_rebuild(struct work_struct *work)
struct xfrm_pol_inexact_bin *bin;
u8 dbits, sbits;
+ if (policy->walk.dead)
+ continue;
+
dir = xfrm_policy_id2dir(policy->index);
- if (policy->walk.dead || dir >= XFRM_POLICY_MAX)
+ if (dir >= XFRM_POLICY_MAX)
continue;
if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) {
@@ -1372,8 +1375,6 @@ EXPORT_SYMBOL(xfrm_policy_hash_rebuild);
* of an absolute inpredictability of ordering of rules. This will not pass. */
static u32 xfrm_gen_index(struct net *net, int dir, u32 index)
{
- static u32 idx_generator;
-
for (;;) {
struct hlist_head *list;
struct xfrm_policy *p;
@@ -1381,8 +1382,8 @@ static u32 xfrm_gen_index(struct net *net, int dir, u32 index)
int found;
if (!index) {
- idx = (idx_generator | dir);
- idx_generator += 8;
+ idx = (net->xfrm.idx_generator | dir);
+ net->xfrm.idx_generator += 8;
} else {
idx = index;
index = 0;
@@ -1823,9 +1824,11 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid)
again:
list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
+ if (pol->walk.dead)
+ continue;
+
dir = xfrm_policy_id2dir(pol->index);
- if (pol->walk.dead ||
- dir >= XFRM_POLICY_MAX ||
+ if (dir >= XFRM_POLICY_MAX ||
pol->type != type)
continue;
@@ -1862,9 +1865,11 @@ int xfrm_dev_policy_flush(struct net *net, struct net_device *dev,
again:
list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) {
+ if (pol->walk.dead)
+ continue;
+
dir = xfrm_policy_id2dir(pol->index);
- if (pol->walk.dead ||
- dir >= XFRM_POLICY_MAX ||
+ if (dir >= XFRM_POLICY_MAX ||
pol->xdo.dev != dev)
continue;
@@ -3215,7 +3220,7 @@ no_transform:
}
for (i = 0; i < num_pols; i++)
- pols[i]->curlft.use_time = ktime_get_real_seconds();
+ WRITE_ONCE(pols[i]->curlft.use_time, ktime_get_real_seconds());
if (num_xfrms < 0) {
/* Prohibit the flow */
diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h
index 4798f9d18fe8..9de35df1afc3 100644
--- a/tools/arch/x86/include/uapi/asm/unistd_32.h
+++ b/tools/arch/x86/include/uapi/asm/unistd_32.h
@@ -26,6 +26,6 @@
#ifndef __NR_setns
#define __NR_setns 346
#endif
-#ifdef __NR_seccomp
+#ifndef __NR_seccomp
#define __NR_seccomp 354
#endif
diff --git a/tools/net/ynl/generated/devlink-user.c b/tools/net/ynl/generated/devlink-user.c
index 3a8d8499fab6..2cb2518500cb 100644
--- a/tools/net/ynl/generated/devlink-user.c
+++ b/tools/net/ynl/generated/devlink-user.c
@@ -16,19 +16,19 @@
static const char * const devlink_op_strmap[] = {
[3] = "get",
[7] = "port-get",
- [DEVLINK_CMD_SB_GET] = "sb-get",
- [DEVLINK_CMD_SB_POOL_GET] = "sb-pool-get",
- [DEVLINK_CMD_SB_PORT_POOL_GET] = "sb-port-pool-get",
- [DEVLINK_CMD_SB_TC_POOL_BIND_GET] = "sb-tc-pool-bind-get",
+ [13] = "sb-get",
+ [17] = "sb-pool-get",
+ [21] = "sb-port-pool-get",
+ [25] = "sb-tc-pool-bind-get",
[DEVLINK_CMD_PARAM_GET] = "param-get",
[DEVLINK_CMD_REGION_GET] = "region-get",
[DEVLINK_CMD_INFO_GET] = "info-get",
[DEVLINK_CMD_HEALTH_REPORTER_GET] = "health-reporter-get",
- [DEVLINK_CMD_TRAP_GET] = "trap-get",
- [DEVLINK_CMD_TRAP_GROUP_GET] = "trap-group-get",
- [DEVLINK_CMD_TRAP_POLICER_GET] = "trap-policer-get",
- [DEVLINK_CMD_RATE_GET] = "rate-get",
- [DEVLINK_CMD_LINECARD_GET] = "linecard-get",
+ [63] = "trap-get",
+ [67] = "trap-group-get",
+ [71] = "trap-policer-get",
+ [76] = "rate-get",
+ [80] = "linecard-get",
[DEVLINK_CMD_SELFTESTS_GET] = "selftests-get",
};
@@ -838,7 +838,7 @@ devlink_sb_get(struct ynl_sock *ys, struct devlink_sb_get_req *req)
rsp = calloc(1, sizeof(*rsp));
yrs.yarg.data = rsp;
yrs.cb = devlink_sb_get_rsp_parse;
- yrs.rsp_cmd = DEVLINK_CMD_SB_GET;
+ yrs.rsp_cmd = 13;
err = ynl_exec(ys, nlh, &yrs);
if (err < 0)
@@ -876,7 +876,7 @@ devlink_sb_get_dump(struct ynl_sock *ys, struct devlink_sb_get_req_dump *req)
yds.ys = ys;
yds.alloc_sz = sizeof(struct devlink_sb_get_list);
yds.cb = devlink_sb_get_rsp_parse;
- yds.rsp_cmd = DEVLINK_CMD_SB_GET;
+ yds.rsp_cmd = 13;
yds.rsp_policy = &devlink_nest;
nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_GET, 1);
@@ -987,7 +987,7 @@ devlink_sb_pool_get(struct ynl_sock *ys, struct devlink_sb_pool_get_req *req)
rsp = calloc(1, sizeof(*rsp));
yrs.yarg.data = rsp;
yrs.cb = devlink_sb_pool_get_rsp_parse;
- yrs.rsp_cmd = DEVLINK_CMD_SB_POOL_GET;
+ yrs.rsp_cmd = 17;
err = ynl_exec(ys, nlh, &yrs);
if (err < 0)
@@ -1026,7 +1026,7 @@ devlink_sb_pool_get_dump(struct ynl_sock *ys,
yds.ys = ys;
yds.alloc_sz = sizeof(struct devlink_sb_pool_get_list);
yds.cb = devlink_sb_pool_get_rsp_parse;
- yds.rsp_cmd = DEVLINK_CMD_SB_POOL_GET;
+ yds.rsp_cmd = 17;
yds.rsp_policy = &devlink_nest;
nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_POOL_GET, 1);
@@ -1147,7 +1147,7 @@ devlink_sb_port_pool_get(struct ynl_sock *ys,
rsp = calloc(1, sizeof(*rsp));
yrs.yarg.data = rsp;
yrs.cb = devlink_sb_port_pool_get_rsp_parse;
- yrs.rsp_cmd = DEVLINK_CMD_SB_PORT_POOL_GET;
+ yrs.rsp_cmd = 21;
err = ynl_exec(ys, nlh, &yrs);
if (err < 0)
@@ -1187,7 +1187,7 @@ devlink_sb_port_pool_get_dump(struct ynl_sock *ys,
yds.ys = ys;
yds.alloc_sz = sizeof(struct devlink_sb_port_pool_get_list);
yds.cb = devlink_sb_port_pool_get_rsp_parse;
- yds.rsp_cmd = DEVLINK_CMD_SB_PORT_POOL_GET;
+ yds.rsp_cmd = 21;
yds.rsp_policy = &devlink_nest;
nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_GET, 1);
@@ -1316,7 +1316,7 @@ devlink_sb_tc_pool_bind_get(struct ynl_sock *ys,
rsp = calloc(1, sizeof(*rsp));
yrs.yarg.data = rsp;
yrs.cb = devlink_sb_tc_pool_bind_get_rsp_parse;
- yrs.rsp_cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET;
+ yrs.rsp_cmd = 25;
err = ynl_exec(ys, nlh, &yrs);
if (err < 0)
@@ -1356,7 +1356,7 @@ devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys,
yds.ys = ys;
yds.alloc_sz = sizeof(struct devlink_sb_tc_pool_bind_get_list);
yds.cb = devlink_sb_tc_pool_bind_get_rsp_parse;
- yds.rsp_cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET;
+ yds.rsp_cmd = 25;
yds.rsp_policy = &devlink_nest;
nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_GET, 1);
@@ -2183,7 +2183,7 @@ devlink_trap_get(struct ynl_sock *ys, struct devlink_trap_get_req *req)
rsp = calloc(1, sizeof(*rsp));
yrs.yarg.data = rsp;
yrs.cb = devlink_trap_get_rsp_parse;
- yrs.rsp_cmd = DEVLINK_CMD_TRAP_GET;
+ yrs.rsp_cmd = 63;
err = ynl_exec(ys, nlh, &yrs);
if (err < 0)
@@ -2223,7 +2223,7 @@ devlink_trap_get_dump(struct ynl_sock *ys,
yds.ys = ys;
yds.alloc_sz = sizeof(struct devlink_trap_get_list);
yds.cb = devlink_trap_get_rsp_parse;
- yds.rsp_cmd = DEVLINK_CMD_TRAP_GET;
+ yds.rsp_cmd = 63;
yds.rsp_policy = &devlink_nest;
nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_GET, 1);
@@ -2336,7 +2336,7 @@ devlink_trap_group_get(struct ynl_sock *ys,
rsp = calloc(1, sizeof(*rsp));
yrs.yarg.data = rsp;
yrs.cb = devlink_trap_group_get_rsp_parse;
- yrs.rsp_cmd = DEVLINK_CMD_TRAP_GROUP_GET;
+ yrs.rsp_cmd = 67;
err = ynl_exec(ys, nlh, &yrs);
if (err < 0)
@@ -2376,7 +2376,7 @@ devlink_trap_group_get_dump(struct ynl_sock *ys,
yds.ys = ys;
yds.alloc_sz = sizeof(struct devlink_trap_group_get_list);
yds.cb = devlink_trap_group_get_rsp_parse;
- yds.rsp_cmd = DEVLINK_CMD_TRAP_GROUP_GET;
+ yds.rsp_cmd = 67;
yds.rsp_policy = &devlink_nest;
nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_GROUP_GET, 1);
@@ -2483,7 +2483,7 @@ devlink_trap_policer_get(struct ynl_sock *ys,
rsp = calloc(1, sizeof(*rsp));
yrs.yarg.data = rsp;
yrs.cb = devlink_trap_policer_get_rsp_parse;
- yrs.rsp_cmd = DEVLINK_CMD_TRAP_POLICER_GET;
+ yrs.rsp_cmd = 71;
err = ynl_exec(ys, nlh, &yrs);
if (err < 0)
@@ -2523,7 +2523,7 @@ devlink_trap_policer_get_dump(struct ynl_sock *ys,
yds.ys = ys;
yds.alloc_sz = sizeof(struct devlink_trap_policer_get_list);
yds.cb = devlink_trap_policer_get_rsp_parse;
- yds.rsp_cmd = DEVLINK_CMD_TRAP_POLICER_GET;
+ yds.rsp_cmd = 71;
yds.rsp_policy = &devlink_nest;
nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_POLICER_GET, 1);
@@ -2642,7 +2642,7 @@ devlink_rate_get(struct ynl_sock *ys, struct devlink_rate_get_req *req)
rsp = calloc(1, sizeof(*rsp));
yrs.yarg.data = rsp;
yrs.cb = devlink_rate_get_rsp_parse;
- yrs.rsp_cmd = DEVLINK_CMD_RATE_GET;
+ yrs.rsp_cmd = 76;
err = ynl_exec(ys, nlh, &yrs);
if (err < 0)
@@ -2682,7 +2682,7 @@ devlink_rate_get_dump(struct ynl_sock *ys,
yds.ys = ys;
yds.alloc_sz = sizeof(struct devlink_rate_get_list);
yds.cb = devlink_rate_get_rsp_parse;
- yds.rsp_cmd = DEVLINK_CMD_RATE_GET;
+ yds.rsp_cmd = 76;
yds.rsp_policy = &devlink_nest;
nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_RATE_GET, 1);
@@ -2786,7 +2786,7 @@ devlink_linecard_get(struct ynl_sock *ys, struct devlink_linecard_get_req *req)
rsp = calloc(1, sizeof(*rsp));
yrs.yarg.data = rsp;
yrs.cb = devlink_linecard_get_rsp_parse;
- yrs.rsp_cmd = DEVLINK_CMD_LINECARD_GET;
+ yrs.rsp_cmd = 80;
err = ynl_exec(ys, nlh, &yrs);
if (err < 0)
@@ -2825,7 +2825,7 @@ devlink_linecard_get_dump(struct ynl_sock *ys,
yds.ys = ys;
yds.alloc_sz = sizeof(struct devlink_linecard_get_list);
yds.cb = devlink_linecard_get_rsp_parse;
- yds.rsp_cmd = DEVLINK_CMD_LINECARD_GET;
+ yds.rsp_cmd = 80;
yds.rsp_policy = &devlink_nest;
nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_LINECARD_GET, 1);
diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h
index 112bc1da732a..ce33d306c2cb 100644
--- a/tools/testing/selftests/kvm/include/ucall_common.h
+++ b/tools/testing/selftests/kvm/include/ucall_common.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-only */
/*
- * tools/testing/selftests/kvm/include/kvm_util.h
- *
* Copyright (C) 2018, Google LLC.
*/
#ifndef SELFTEST_KVM_UCALL_COMMON_H
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 4fd042112526..25bc61dac5fb 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -68,6 +68,12 @@ struct xstate {
#define XFEATURE_MASK_OPMASK BIT_ULL(5)
#define XFEATURE_MASK_ZMM_Hi256 BIT_ULL(6)
#define XFEATURE_MASK_Hi16_ZMM BIT_ULL(7)
+#define XFEATURE_MASK_PT BIT_ULL(8)
+#define XFEATURE_MASK_PKRU BIT_ULL(9)
+#define XFEATURE_MASK_PASID BIT_ULL(10)
+#define XFEATURE_MASK_CET_USER BIT_ULL(11)
+#define XFEATURE_MASK_CET_KERNEL BIT_ULL(12)
+#define XFEATURE_MASK_LBR BIT_ULL(15)
#define XFEATURE_MASK_XTILE_CFG BIT_ULL(17)
#define XFEATURE_MASK_XTILE_DATA BIT_ULL(18)
@@ -147,6 +153,7 @@ struct kvm_x86_cpu_feature {
#define X86_FEATURE_CLWB KVM_X86_CPU_FEATURE(0x7, 0, EBX, 24)
#define X86_FEATURE_UMIP KVM_X86_CPU_FEATURE(0x7, 0, ECX, 2)
#define X86_FEATURE_PKU KVM_X86_CPU_FEATURE(0x7, 0, ECX, 3)
+#define X86_FEATURE_OSPKE KVM_X86_CPU_FEATURE(0x7, 0, ECX, 4)
#define X86_FEATURE_LA57 KVM_X86_CPU_FEATURE(0x7, 0, ECX, 16)
#define X86_FEATURE_RDPID KVM_X86_CPU_FEATURE(0x7, 0, ECX, 22)
#define X86_FEATURE_SGX_LC KVM_X86_CPU_FEATURE(0x7, 0, ECX, 30)
@@ -553,6 +560,13 @@ static inline void xsetbv(u32 index, u64 value)
__asm__ __volatile__("xsetbv" :: "a" (eax), "d" (edx), "c" (index));
}
+static inline void wrpkru(u32 pkru)
+{
+ /* Note, ECX and EDX are architecturally required to be '0'. */
+ asm volatile(".byte 0x0f,0x01,0xef\n\t"
+ : : "a" (pkru), "c"(0), "d"(0));
+}
+
static inline struct desc_ptr get_gdt(void)
{
struct desc_ptr gdt;
@@ -908,6 +922,15 @@ static inline bool kvm_pmu_has(struct kvm_x86_pmu_feature feature)
!kvm_cpu_has(feature.anti_feature);
}
+static __always_inline uint64_t kvm_cpu_supported_xcr0(void)
+{
+ if (!kvm_cpu_has_p(X86_PROPERTY_SUPPORTED_XCR0_LO))
+ return 0;
+
+ return kvm_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_LO) |
+ ((uint64_t)kvm_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_HI) << 32);
+}
+
static inline size_t kvm_cpuid2_size(int nr_entries)
{
return sizeof(struct kvm_cpuid2) +
diff --git a/tools/testing/selftests/kvm/lib/guest_sprintf.c b/tools/testing/selftests/kvm/lib/guest_sprintf.c
index c4a69d8aeb68..74627514c4d4 100644
--- a/tools/testing/selftests/kvm/lib/guest_sprintf.c
+++ b/tools/testing/selftests/kvm/lib/guest_sprintf.c
@@ -200,6 +200,13 @@ repeat:
++fmt;
}
+ /*
+ * Play nice with %llu, %llx, etc. KVM selftests only support
+ * 64-bit builds, so just treat %ll* the same as %l*.
+ */
+ if (qualifier == 'l' && *fmt == 'l')
+ ++fmt;
+
/* default base */
base = 10;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/apic.c b/tools/testing/selftests/kvm/lib/x86_64/apic.c
index 7168e25c194e..89153a333e83 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/apic.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/apic.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * tools/testing/selftests/kvm/lib/x86_64/processor.c
- *
* Copyright (C) 2021, Google LLC.
*/
diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c
index 20eb2e730800..8698d1ab60d0 100644
--- a/tools/testing/selftests/kvm/memslot_perf_test.c
+++ b/tools/testing/selftests/kvm/memslot_perf_test.c
@@ -1033,9 +1033,8 @@ static bool test_loop(const struct test_data *data,
struct test_result *rbestruntime)
{
uint64_t maxslots;
- struct test_result result;
+ struct test_result result = {};
- result.nloops = 0;
if (!test_execute(targs->nslots, &maxslots, targs->seconds, data,
&result.nloops,
&result.slot_runtime, &result.guest_runtime)) {
@@ -1089,7 +1088,7 @@ int main(int argc, char *argv[])
.seconds = 5,
.runs = 1,
};
- struct test_result rbestslottime;
+ struct test_result rbestslottime = {};
int tctr;
if (!check_memory_sizes())
@@ -1098,11 +1097,10 @@ int main(int argc, char *argv[])
if (!parse_args(argc, argv, &targs))
return -1;
- rbestslottime.slottimens = 0;
for (tctr = targs.tfirst; tctr <= targs.tlast; tctr++) {
const struct test_data *data = &tests[tctr];
unsigned int runctr;
- struct test_result rbestruntime;
+ struct test_result rbestruntime = {};
if (tctr > targs.tfirst)
pr_info("\n");
@@ -1110,7 +1108,6 @@ int main(int argc, char *argv[])
pr_info("Testing %s performance with %i runs, %d seconds each\n",
data->name, targs.runs, targs.seconds);
- rbestruntime.runtimens = 0;
for (runctr = 0; runctr < targs.runs; runctr++)
if (!test_loop(data, &targs,
&rbestslottime, &rbestruntime))
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
index e446d76d1c0c..6c1278562090 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * KVM_GET/SET_* tests
- *
* Copyright (C) 2022, Red Hat, Inc.
*
* Tests for Hyper-V extensions to SVM.
diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
index 7f36c32fa760..18ac5c1952a3 100644
--- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
+++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * tools/testing/selftests/kvm/nx_huge_page_test.c
- *
* Usage: to be run via nx_huge_page_test.sh, which does the necessary
* environment setup and teardown
*
diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh
index 0560149e66ed..7cbb409801ee 100755
--- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh
+++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh
@@ -4,7 +4,6 @@
# Wrapper script which performs setup and cleanup for nx_huge_pages_test.
# Makes use of root privileges to set up huge pages and KVM module parameters.
#
-# tools/testing/selftests/kvm/nx_huge_page_test.sh
# Copyright (C) 2022, Google LLC.
set -e
diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c
index 4c4925a8ab45..88b58aab7207 100644
--- a/tools/testing/selftests/kvm/x86_64/state_test.c
+++ b/tools/testing/selftests/kvm/x86_64/state_test.c
@@ -139,6 +139,83 @@ static void vmx_l1_guest_code(struct vmx_pages *vmx_pages)
static void __attribute__((__flatten__)) guest_code(void *arg)
{
GUEST_SYNC(1);
+
+ if (this_cpu_has(X86_FEATURE_XSAVE)) {
+ uint64_t supported_xcr0 = this_cpu_supported_xcr0();
+ uint8_t buffer[4096];
+
+ memset(buffer, 0xcc, sizeof(buffer));
+
+ set_cr4(get_cr4() | X86_CR4_OSXSAVE);
+ GUEST_ASSERT(this_cpu_has(X86_FEATURE_OSXSAVE));
+
+ xsetbv(0, xgetbv(0) | supported_xcr0);
+
+ /*
+ * Modify state for all supported xfeatures to take them out of
+ * their "init" state, i.e. to make them show up in XSTATE_BV.
+ *
+ * Note off-by-default features, e.g. AMX, are out of scope for
+ * this particular testcase as they have a different ABI.
+ */
+ GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_FP);
+ asm volatile ("fincstp");
+
+ GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_SSE);
+ asm volatile ("vmovdqu %0, %%xmm0" :: "m" (buffer));
+
+ if (supported_xcr0 & XFEATURE_MASK_YMM)
+ asm volatile ("vmovdqu %0, %%ymm0" :: "m" (buffer));
+
+ if (supported_xcr0 & XFEATURE_MASK_AVX512) {
+ asm volatile ("kmovq %0, %%k1" :: "r" (-1ull));
+ asm volatile ("vmovupd %0, %%zmm0" :: "m" (buffer));
+ asm volatile ("vmovupd %0, %%zmm16" :: "m" (buffer));
+ }
+
+ if (this_cpu_has(X86_FEATURE_MPX)) {
+ uint64_t bounds[2] = { 10, 0xffffffffull };
+ uint64_t output[2] = { };
+
+ GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_BNDREGS);
+ GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_BNDCSR);
+
+ /*
+ * Don't bother trying to get BNDCSR into the INUSE
+ * state. MSR_IA32_BNDCFGS doesn't count as it isn't
+ * managed via XSAVE/XRSTOR, and BNDCFGU can only be
+ * modified by XRSTOR. Stuffing XSTATE_BV in the host
+ * is simpler than doing XRSTOR here in the guest.
+ *
+ * However, temporarily enable MPX in BNDCFGS so that
+ * BNDMOV actually loads BND1. If MPX isn't *fully*
+ * enabled, all MPX instructions are treated as NOPs.
+ *
+ * Hand encode "bndmov (%rax),%bnd1" as support for MPX
+ * mnemonics/registers has been removed from gcc and
+ * clang (and was never fully supported by clang).
+ */
+ wrmsr(MSR_IA32_BNDCFGS, BIT_ULL(0));
+ asm volatile (".byte 0x66,0x0f,0x1a,0x08" :: "a" (bounds));
+ /*
+ * Hand encode "bndmov %bnd1, (%rax)" to sanity check
+ * that BND1 actually got loaded.
+ */
+ asm volatile (".byte 0x66,0x0f,0x1b,0x08" :: "a" (output));
+ wrmsr(MSR_IA32_BNDCFGS, 0);
+
+ GUEST_ASSERT_EQ(bounds[0], output[0]);
+ GUEST_ASSERT_EQ(bounds[1], output[1]);
+ }
+ if (this_cpu_has(X86_FEATURE_PKU)) {
+ GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_PKRU);
+ set_cr4(get_cr4() | X86_CR4_PKE);
+ GUEST_ASSERT(this_cpu_has(X86_FEATURE_OSPKE));
+
+ wrpkru(-1u);
+ }
+ }
+
GUEST_SYNC(2);
if (arg) {
@@ -153,10 +230,11 @@ static void __attribute__((__flatten__)) guest_code(void *arg)
int main(int argc, char *argv[])
{
+ uint64_t *xstate_bv, saved_xstate_bv;
vm_vaddr_t nested_gva = 0;
-
+ struct kvm_cpuid2 empty_cpuid = {};
struct kvm_regs regs1, regs2;
- struct kvm_vcpu *vcpu;
+ struct kvm_vcpu *vcpu, *vcpuN;
struct kvm_vm *vm;
struct kvm_x86_state *state;
struct ucall uc;
@@ -209,6 +287,34 @@ int main(int argc, char *argv[])
/* Restore state in a new VM. */
vcpu = vm_recreate_with_one_vcpu(vm);
vcpu_load_state(vcpu, state);
+
+ /*
+ * Restore XSAVE state in a dummy vCPU, first without doing
+ * KVM_SET_CPUID2, and then with an empty guest CPUID. Except
+ * for off-by-default xfeatures, e.g. AMX, KVM is supposed to
+ * allow KVM_SET_XSAVE regardless of guest CPUID. Manually
+ * load only XSAVE state, MSRs in particular have a much more
+ * convoluted ABI.
+ *
+ * Load two versions of XSAVE state: one with the actual guest
+ * XSAVE state, and one with all supported features forced "on"
+ * in xstate_bv, e.g. to ensure that KVM allows loading all
+ * supported features, even if something goes awry in saving
+ * the original snapshot.
+ */
+ xstate_bv = (void *)&((uint8_t *)state->xsave->region)[512];
+ saved_xstate_bv = *xstate_bv;
+
+ vcpuN = __vm_vcpu_add(vm, vcpu->id + 1);
+ vcpu_xsave_set(vcpuN, state->xsave);
+ *xstate_bv = kvm_cpu_supported_xcr0();
+ vcpu_xsave_set(vcpuN, state->xsave);
+
+ vcpu_init_cpuid(vcpuN, &empty_cpuid);
+ vcpu_xsave_set(vcpuN, state->xsave);
+ *xstate_bv = saved_xstate_bv;
+ vcpu_xsave_set(vcpuN, state->xsave);
+
kvm_x86_state_cleanup(state);
memset(&regs2, 0, sizeof(regs2));
diff --git a/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c b/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c
index 5b669818e39a..59c7304f805e 100644
--- a/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c
+++ b/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c
@@ -1,10 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * svm_vmcall_test
- *
* Copyright © 2021 Amazon.com, Inc. or its affiliates.
- *
- * Xen shared_info / pvclock testing
*/
#include "test_util.h"
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index 05898ad9f4d9..9ec9ab60b63e 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -1,10 +1,6 @@
// SPDX-License-Identifier: GPL-2.0-only
/*
- * svm_vmcall_test
- *
* Copyright © 2021 Amazon.com, Inc. or its affiliates.
- *
- * Xen shared_info / pvclock testing
*/
#include "test_util.h"
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 8b017070960d..4a2881d43989 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -34,6 +34,7 @@ TEST_PROGS += gro.sh
TEST_PROGS += gre_gso.sh
TEST_PROGS += cmsg_so_mark.sh
TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh
+TEST_PROGS += netns-name.sh
TEST_PROGS += srv6_end_dt46_l3vpn_test.sh
TEST_PROGS += srv6_end_dt4_l3vpn_test.sh
TEST_PROGS += srv6_end_dt6_l3vpn_test.sh
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index e7d2a530618a..66d0db7a2614 100755
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -2437,6 +2437,9 @@ ipv4_mpath_list_test()
run_cmd "ip -n ns2 route add 203.0.113.0/24
nexthop via 172.16.201.2 nexthop via 172.16.202.2"
run_cmd "ip netns exec ns2 sysctl -qw net.ipv4.fib_multipath_hash_policy=1"
+ run_cmd "ip netns exec ns2 sysctl -qw net.ipv4.conf.veth2.rp_filter=0"
+ run_cmd "ip netns exec ns2 sysctl -qw net.ipv4.conf.all.rp_filter=0"
+ run_cmd "ip netns exec ns2 sysctl -qw net.ipv4.conf.default.rp_filter=0"
set +e
local dmac=$(ip -n ns2 -j link show dev veth2 | jq -r '.[]["address"]')
@@ -2449,7 +2452,7 @@ ipv4_mpath_list_test()
# words, the FIB lookup tracepoint needs to be triggered for every
# packet.
local t0_rx_pkts=$(link_stats_get ns2 veth2 rx packets)
- run_cmd "perf stat -e fib:fib_table_lookup --filter 'err == 0' -j -o $tmp_file -- $cmd"
+ run_cmd "perf stat -a -e fib:fib_table_lookup --filter 'err == 0' -j -o $tmp_file -- $cmd"
local t1_rx_pkts=$(link_stats_get ns2 veth2 rx packets)
local diff=$(echo $t1_rx_pkts - $t0_rx_pkts | bc -l)
list_rcv_eval $tmp_file $diff
@@ -2494,7 +2497,7 @@ ipv6_mpath_list_test()
# words, the FIB lookup tracepoint needs to be triggered for every
# packet.
local t0_rx_pkts=$(link_stats_get ns2 veth2 rx packets)
- run_cmd "perf stat -e fib6:fib6_table_lookup --filter 'err == 0' -j -o $tmp_file -- $cmd"
+ run_cmd "perf stat -a -e fib6:fib6_table_lookup --filter 'err == 0' -j -o $tmp_file -- $cmd"
local t1_rx_pkts=$(link_stats_get ns2 veth2 rx packets)
local diff=$(echo $t1_rx_pkts - $t0_rx_pkts | bc -l)
list_rcv_eval $tmp_file $diff
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index ee1f89a872b3..dc895b7b94e1 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -1432,7 +1432,9 @@ chk_rst_nr()
count=$(get_counter ${ns_tx} "MPTcpExtMPRstTx")
if [ -z "$count" ]; then
print_skip
- elif [ $count -lt $rst_tx ]; then
+ # accept more rst than expected except if we don't expect any
+ elif { [ $rst_tx -ne 0 ] && [ $count -lt $rst_tx ]; } ||
+ { [ $rst_tx -eq 0 ] && [ $count -ne 0 ]; }; then
fail_test "got $count MP_RST[s] TX expected $rst_tx"
else
print_ok
@@ -1442,7 +1444,9 @@ chk_rst_nr()
count=$(get_counter ${ns_rx} "MPTcpExtMPRstRx")
if [ -z "$count" ]; then
print_skip
- elif [ "$count" -lt "$rst_rx" ]; then
+ # accept more rst than expected except if we don't expect any
+ elif { [ $rst_rx -ne 0 ] && [ $count -lt $rst_rx ]; } ||
+ { [ $rst_rx -eq 0 ] && [ $count -ne 0 ]; }; then
fail_test "got $count MP_RST[s] RX expected $rst_rx"
else
print_ok
@@ -2305,6 +2309,7 @@ remove_tests()
chk_join_nr 1 1 1
chk_rm_tx_nr 1
chk_rm_nr 1 1
+ chk_rst_nr 0 0
fi
# multiple subflows, remove
@@ -2317,6 +2322,7 @@ remove_tests()
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 2 2 2
chk_rm_nr 2 2
+ chk_rst_nr 0 0
fi
# single address, remove
@@ -2329,6 +2335,7 @@ remove_tests()
chk_join_nr 1 1 1
chk_add_nr 1 1
chk_rm_nr 1 1 invert
+ chk_rst_nr 0 0
fi
# subflow and signal, remove
@@ -2342,6 +2349,7 @@ remove_tests()
chk_join_nr 2 2 2
chk_add_nr 1 1
chk_rm_nr 1 1
+ chk_rst_nr 0 0
fi
# subflows and signal, remove
@@ -2356,6 +2364,7 @@ remove_tests()
chk_join_nr 3 3 3
chk_add_nr 1 1
chk_rm_nr 2 2
+ chk_rst_nr 0 0
fi
# addresses remove
@@ -2370,6 +2379,7 @@ remove_tests()
chk_join_nr 3 3 3
chk_add_nr 3 3
chk_rm_nr 3 3 invert
+ chk_rst_nr 0 0
fi
# invalid addresses remove
@@ -2384,6 +2394,7 @@ remove_tests()
chk_join_nr 1 1 1
chk_add_nr 3 3
chk_rm_nr 3 1 invert
+ chk_rst_nr 0 0
fi
# subflows and signal, flush
@@ -2398,6 +2409,7 @@ remove_tests()
chk_join_nr 3 3 3
chk_add_nr 1 1
chk_rm_nr 1 3 invert simult
+ chk_rst_nr 0 0
fi
# subflows flush
@@ -2417,6 +2429,7 @@ remove_tests()
else
chk_rm_nr 3 3
fi
+ chk_rst_nr 0 0
fi
# addresses flush
@@ -2431,6 +2444,7 @@ remove_tests()
chk_join_nr 3 3 3
chk_add_nr 3 3
chk_rm_nr 3 3 invert simult
+ chk_rst_nr 0 0
fi
# invalid addresses flush
@@ -2445,6 +2459,7 @@ remove_tests()
chk_join_nr 1 1 1
chk_add_nr 3 3
chk_rm_nr 3 1 invert
+ chk_rst_nr 0 0
fi
# remove id 0 subflow
@@ -2456,6 +2471,7 @@ remove_tests()
run_tests $ns1 $ns2 10.0.1.1
chk_join_nr 1 1 1
chk_rm_nr 1 1
+ chk_rst_nr 0 0
fi
# remove id 0 address
@@ -2468,6 +2484,7 @@ remove_tests()
chk_join_nr 1 1 1
chk_add_nr 1 1
chk_rm_nr 1 1 invert
+ chk_rst_nr 0 0 invert
fi
}
diff --git a/tools/testing/selftests/net/netns-name.sh b/tools/testing/selftests/net/netns-name.sh
new file mode 100755
index 000000000000..7d3d3fc99461
--- /dev/null
+++ b/tools/testing/selftests/net/netns-name.sh
@@ -0,0 +1,87 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+set -o pipefail
+
+NS=netns-name-test
+DEV=dummy-dev0
+DEV2=dummy-dev1
+ALT_NAME=some-alt-name
+
+RET_CODE=0
+
+cleanup() {
+ ip netns del $NS
+}
+
+trap cleanup EXIT
+
+fail() {
+ echo "ERROR: ${1:-unexpected return code} (ret: $_)" >&2
+ RET_CODE=1
+}
+
+ip netns add $NS
+
+#
+# Test basic move without a rename
+#
+ip -netns $NS link add name $DEV type dummy || fail
+ip -netns $NS link set dev $DEV netns 1 ||
+ fail "Can't perform a netns move"
+ip link show dev $DEV >> /dev/null || fail "Device not found after move"
+ip link del $DEV || fail
+
+#
+# Test move with a conflict
+#
+ip link add name $DEV type dummy
+ip -netns $NS link add name $DEV type dummy || fail
+ip -netns $NS link set dev $DEV netns 1 2> /dev/null &&
+ fail "Performed a netns move with a name conflict"
+ip link show dev $DEV >> /dev/null || fail "Device not found after move"
+ip -netns $NS link del $DEV || fail
+ip link del $DEV || fail
+
+#
+# Test move with a conflict and rename
+#
+ip link add name $DEV type dummy
+ip -netns $NS link add name $DEV type dummy || fail
+ip -netns $NS link set dev $DEV netns 1 name $DEV2 ||
+ fail "Can't perform a netns move with rename"
+ip link del $DEV2 || fail
+ip link del $DEV || fail
+
+#
+# Test dup alt-name with netns move
+#
+ip link add name $DEV type dummy || fail
+ip link property add dev $DEV altname $ALT_NAME || fail
+ip -netns $NS link add name $DEV2 type dummy || fail
+ip -netns $NS link property add dev $DEV2 altname $ALT_NAME || fail
+
+ip -netns $NS link set dev $DEV2 netns 1 2> /dev/null &&
+ fail "Moved with alt-name dup"
+
+ip link del $DEV || fail
+ip -netns $NS link del $DEV2 || fail
+
+#
+# Test creating alt-name in one net-ns and using in another
+#
+ip -netns $NS link add name $DEV type dummy || fail
+ip -netns $NS link property add dev $DEV altname $ALT_NAME || fail
+ip -netns $NS link set dev $DEV netns 1 || fail
+ip link show dev $ALT_NAME >> /dev/null || fail "Can't find alt-name after move"
+ip -netns $NS link show dev $ALT_NAME 2> /dev/null &&
+ fail "Can still find alt-name after move"
+ip link del $DEV || fail
+
+echo -ne "$(basename $0) \t\t\t\t"
+if [ $RET_CODE -eq 0 ]; then
+ echo "[ OK ]"
+else
+ echo "[ FAIL ]"
+fi
+exit $RET_CODE
diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index 9c2012d70b08..f8499d4c87f3 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -3,6 +3,8 @@
#
# OVS kernel module self tests
+trap ovs_exit_sig EXIT TERM INT ERR
+
# Kselftest framework requirement - SKIP code is 4.
ksft_skip=4
@@ -142,6 +144,12 @@ ovs_add_flow () {
return 0
}
+ovs_del_flows () {
+ info "Deleting all flows from DP: sbx:$1 br:$2"
+ ovs_sbx "$1" python3 $ovs_base/ovs-dpctl.py del-flows "$2"
+ return 0
+}
+
ovs_drop_record_and_run () {
local sbx=$1
shift
@@ -198,6 +206,17 @@ test_drop_reason() {
ip netns exec server ip addr add 172.31.110.20/24 dev s1
ip netns exec server ip link set s1 up
+ # Check if drop reasons can be sent
+ ovs_add_flow "test_drop_reason" dropreason \
+ 'in_port(1),eth(),eth_type(0x0806),arp()' 'drop(10)' 2>/dev/null
+ if [ $? == 1 ]; then
+ info "no support for drop reasons - skipping"
+ ovs_exit_sig
+ return $ksft_skip
+ fi
+
+ ovs_del_flows "test_drop_reason" dropreason
+
# Allow ARP
ovs_add_flow "test_drop_reason" dropreason \
'in_port(1),eth(),eth_type(0x0806),arp()' '2' || return 1
@@ -525,7 +544,7 @@ run_test() {
fi
if python3 ovs-dpctl.py -h 2>&1 | \
- grep "Need to install the python" >/dev/null 2>&1; then
+ grep -E "Need to (install|upgrade) the python" >/dev/null 2>&1; then
stdbuf -o0 printf "TEST: %-60s [PYLIB]\n" "${tdesc}"
return $ksft_skip
fi
diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
index 912dc8c49085..b97e621face9 100644
--- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
+++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py
@@ -28,8 +28,10 @@ try:
from pyroute2.netlink import nlmsg_atoms
from pyroute2.netlink.exceptions import NetlinkError
from pyroute2.netlink.generic import GenericNetlinkSocket
+ import pyroute2
+
except ModuleNotFoundError:
- print("Need to install the python pyroute2 package.")
+ print("Need to install the python pyroute2 package >= 0.6.")
sys.exit(0)
@@ -1117,12 +1119,14 @@ class ovskey(nla):
"src",
lambda x: str(ipaddress.IPv4Address(x)),
int,
+ convert_ipv4,
),
(
"dst",
"dst",
- lambda x: str(ipaddress.IPv6Address(x)),
+ lambda x: str(ipaddress.IPv4Address(x)),
int,
+ convert_ipv4,
),
("tp_src", "tp_src", "%d", int),
("tp_dst", "tp_dst", "%d", int),
@@ -1904,6 +1908,32 @@ class OvsFlow(GenericNetlinkSocket):
raise ne
return reply
+ def del_flows(self, dpifindex):
+ """
+ Send a del message to the kernel that will drop all flows.
+
+ dpifindex should be a valid datapath obtained by calling
+ into the OvsDatapath lookup
+ """
+
+ flowmsg = OvsFlow.ovs_flow_msg()
+ flowmsg["cmd"] = OVS_FLOW_CMD_DEL
+ flowmsg["version"] = OVS_DATAPATH_VERSION
+ flowmsg["reserved"] = 0
+ flowmsg["dpifindex"] = dpifindex
+
+ try:
+ reply = self.nlm_request(
+ flowmsg,
+ msg_type=self.prid,
+ msg_flags=NLM_F_REQUEST | NLM_F_ACK,
+ )
+ reply = reply[0]
+ except NetlinkError as ne:
+ print(flowmsg)
+ raise ne
+ return reply
+
def dump(self, dpifindex, flowspec=None):
"""
Returns a list of messages containing flows.
@@ -1998,6 +2028,12 @@ def main(argv):
nlmsg_atoms.ovskey = ovskey
nlmsg_atoms.ovsactions = ovsactions
+ # version check for pyroute2
+ prverscheck = pyroute2.__version__.split(".")
+ if int(prverscheck[0]) == 0 and int(prverscheck[1]) < 6:
+ print("Need to upgrade the python pyroute2 package to >= 0.6.")
+ sys.exit(0)
+
parser = argparse.ArgumentParser()
parser.add_argument(
"-v",
@@ -2060,6 +2096,9 @@ def main(argv):
addflcmd.add_argument("flow", help="Flow specification")
addflcmd.add_argument("acts", help="Flow actions")
+ delfscmd = subparsers.add_parser("del-flows")
+ delfscmd.add_argument("flsbr", help="Datapath name")
+
args = parser.parse_args()
if args.verbose > 0:
@@ -2143,6 +2182,11 @@ def main(argv):
flow = OvsFlow.ovs_flow_msg()
flow.parse(args.flow, args.acts, rep["dpifindex"])
ovsflow.add_flow(rep["dpifindex"], flow)
+ elif hasattr(args, "flsbr"):
+ rep = ovsdp.info(args.flsbr, 0)
+ if rep is None:
+ print("DP '%s' not found." % args.flsbr)
+ ovsflow.del_flows(rep["dpifindex"])
return 0
diff --git a/tools/testing/selftests/netfilter/nft_audit.sh b/tools/testing/selftests/netfilter/nft_audit.sh
index bb34329e02a7..99ed5bd6e840 100755
--- a/tools/testing/selftests/netfilter/nft_audit.sh
+++ b/tools/testing/selftests/netfilter/nft_audit.sh
@@ -11,6 +11,12 @@ nft --version >/dev/null 2>&1 || {
exit $SKIP_RC
}
+# Run everything in a separate network namespace
+[ "${1}" != "run" ] && { unshare -n "${0}" run; exit $?; }
+
+# give other scripts a chance to finish - audit_logread sees all activity
+sleep 1
+
logfile=$(mktemp)
rulefile=$(mktemp)
echo "logging into $logfile"
@@ -93,6 +99,12 @@ do_test 'nft add counter t1 c1' \
do_test 'nft add counter t2 c1; add counter t2 c2' \
'table=t2 family=2 entries=2 op=nft_register_obj'
+for ((i = 3; i <= 500; i++)); do
+ echo "add counter t2 c$i"
+done >$rulefile
+do_test "nft -f $rulefile" \
+'table=t2 family=2 entries=498 op=nft_register_obj'
+
# adding/updating quotas
do_test 'nft add quota t1 q1 { 10 bytes }' \
@@ -101,6 +113,12 @@ do_test 'nft add quota t1 q1 { 10 bytes }' \
do_test 'nft add quota t2 q1 { 10 bytes }; add quota t2 q2 { 10 bytes }' \
'table=t2 family=2 entries=2 op=nft_register_obj'
+for ((i = 3; i <= 500; i++)); do
+ echo "add quota t2 q$i { 10 bytes }"
+done >$rulefile
+do_test "nft -f $rulefile" \
+'table=t2 family=2 entries=498 op=nft_register_obj'
+
# changing the quota value triggers obj update path
do_test 'nft add quota t1 q1 { 20 bytes }' \
'table=t1 family=2 entries=1 op=nft_register_obj'
@@ -150,6 +168,40 @@ done
do_test 'nft reset set t1 s' \
'table=t1 family=2 entries=3 op=nft_reset_setelem'
+# resetting counters
+
+do_test 'nft reset counter t1 c1' \
+'table=t1 family=2 entries=1 op=nft_reset_obj'
+
+do_test 'nft reset counters t1' \
+'table=t1 family=2 entries=1 op=nft_reset_obj'
+
+do_test 'nft reset counters t2' \
+'table=t2 family=2 entries=342 op=nft_reset_obj
+table=t2 family=2 entries=158 op=nft_reset_obj'
+
+do_test 'nft reset counters' \
+'table=t1 family=2 entries=1 op=nft_reset_obj
+table=t2 family=2 entries=341 op=nft_reset_obj
+table=t2 family=2 entries=159 op=nft_reset_obj'
+
+# resetting quotas
+
+do_test 'nft reset quota t1 q1' \
+'table=t1 family=2 entries=1 op=nft_reset_obj'
+
+do_test 'nft reset quotas t1' \
+'table=t1 family=2 entries=1 op=nft_reset_obj'
+
+do_test 'nft reset quotas t2' \
+'table=t2 family=2 entries=315 op=nft_reset_obj
+table=t2 family=2 entries=185 op=nft_reset_obj'
+
+do_test 'nft reset quotas' \
+'table=t1 family=2 entries=1 op=nft_reset_obj
+table=t2 family=2 entries=314 op=nft_reset_obj
+table=t2 family=2 entries=186 op=nft_reset_obj'
+
# deleting rules
readarray -t handles < <(nft -a list chain t1 c1 | \