frequency adjustment value (a positive integer) in
parts per billion.
+What: /sys/class/ptp/ptpN/max_vclocks
+Date: May 2021
+Contact: Yangbo Lu <yangbo.lu@nxp.com>
+Description:
+ This file contains the maximum number of ptp vclocks.
+ Write integer to re-configure it.
+
What: /sys/class/ptp/ptpN/n_alarms
Date: September 2010
Contact: Richard Cochran <richardcochran@gmail.com>
This file contains the number of programmable pins
offered by the PTP hardware clock.
+What: /sys/class/ptp/ptpN/n_vclocks
+Date: May 2021
+Contact: Yangbo Lu <yangbo.lu@nxp.com>
+Description:
+ This file contains the number of virtual PTP clocks in
+ use. By default, the value is 0 meaning that only the
+ physical clock is in use. Setting the value creates
+ the corresponding number of virtual clocks and causes
+ the physical clock to become free running. Setting the
+ value back to 0 deletes the virtual clocks and
+ switches the physical clock back to normal, adjustable
+ operation.
+
What: /sys/class/ptp/ptpN/pins
Date: March 2014
Contact: Richard Cochran <richardcochran@gmail.com>
For the properties relevant to the ethernet controller connected to the GPMC
refer to the binding documentation of the device. For example, the documentation
-for the SMSC 911x is Documentation/devicetree/bindings/net/smsc911x.txt
+for the SMSC 911x is Documentation/devicetree/bindings/net/smsc,lan9115.yaml
Child nodes need to specify the GPMC bus address width using the "bank-width"
property but is possible that an ethernet controller also has a property to
--- /dev/null
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/smsc,lan9115.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Smart Mixed-Signal Connectivity (SMSC) LAN911x/912x Controller
+
+maintainers:
+ - Shawn Guo <shawnguo@kernel.org>
+
+allOf:
+ - $ref: ethernet-controller.yaml#
+
+properties:
+ compatible:
+ oneOf:
+ - const: smsc,lan9115
+ - items:
+ - enum:
+ - smsc,lan89218
+ - smsc,lan9117
+ - smsc,lan9118
+ - smsc,lan9220
+ - smsc,lan9221
+ - const: smsc,lan9115
+
+ reg:
+ maxItems: 1
+
+ reg-shift: true
+
+ reg-io-width:
+ enum: [ 2, 4 ]
+ default: 2
+
+ interrupts:
+ minItems: 1
+ items:
+ - description:
+ LAN interrupt line
+ - description:
+ Optional PME (power management event) interrupt that is able to wake
+ up the host system with a 50ms pulse on network activity
+
+ clocks:
+ maxItems: 1
+
+ phy-mode: true
+
+ smsc,irq-active-high:
+ type: boolean
+ description: Indicates the IRQ polarity is active-high
+
+ smsc,irq-push-pull:
+ type: boolean
+ description: Indicates the IRQ type is push-pull
+
+ smsc,force-internal-phy:
+ type: boolean
+ description: Forces SMSC LAN controller to use internal PHY
+
+ smsc,force-external-phy:
+ type: boolean
+ description: Forces SMSC LAN controller to use external PHY
+
+ smsc,save-mac-address:
+ type: boolean
+ description:
+ Indicates that MAC address needs to be saved before resetting the
+ controller
+
+ reset-gpios:
+ maxItems: 1
+ description:
+ A GPIO line connected to the RESET (active low) signal of the device.
+ On many systems this is wired high so the device goes out of reset at
+ power-on, but if it is under program control, this optional GPIO can
+ wake up in response to it.
+
+ vdd33a-supply:
+ description: 3.3V analog power supply
+
+ vddvario-supply:
+ description: IO logic power supply
+
+required:
+ - compatible
+ - reg
+ - interrupts
+
+# There are lots of bus-specific properties ("qcom,*", "samsung,*", "fsl,*",
+# "gpmc,*", ...) to be found, that actually depend on the compatible value of
+# the parent node.
+additionalProperties: true
+
+examples:
+ - |
+ #include <dt-bindings/gpio/gpio.h>
+
+ ethernet@f4000000 {
+ compatible = "smsc,lan9220", "smsc,lan9115";
+ reg = <0xf4000000 0x2000000>;
+ phy-mode = "mii";
+ interrupt-parent = <&gpio1>;
+ interrupts = <31>, <32>;
+ reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>;
+ reg-io-width = <4>;
+ smsc,irq-push-pull;
+ };
+++ /dev/null
-* Smart Mixed-Signal Connectivity (SMSC) LAN911x/912x Controller
-
-Required properties:
-- compatible : Should be "smsc,lan<model>", "smsc,lan9115"
-- reg : Address and length of the io space for SMSC LAN
-- interrupts : one or two interrupt specifiers
- - The first interrupt is the SMSC LAN interrupt line
- - The second interrupt (if present) is the PME (power
- management event) interrupt that is able to wake up the host
- system with a 50ms pulse on network activity
-- phy-mode : See ethernet.txt file in the same directory
-
-Optional properties:
-- reg-shift : Specify the quantity to shift the register offsets by
-- reg-io-width : Specify the size (in bytes) of the IO accesses that
- should be performed on the device. Valid value for SMSC LAN is
- 2 or 4. If it's omitted or invalid, the size would be 2.
-- smsc,irq-active-high : Indicates the IRQ polarity is active-high
-- smsc,irq-push-pull : Indicates the IRQ type is push-pull
-- smsc,force-internal-phy : Forces SMSC LAN controller to use
- internal PHY
-- smsc,force-external-phy : Forces SMSC LAN controller to use
- external PHY
-- smsc,save-mac-address : Indicates that mac address needs to be saved
- before resetting the controller
-- reset-gpios : a GPIO line connected to the RESET (active low) signal
- of the device. On many systems this is wired high so the device goes
- out of reset at power-on, but if it is under program control, this
- optional GPIO can wake up in response to it.
-- vdd33a-supply, vddvario-supply : 3.3V analog and IO logic power supplies
-
-Examples:
-
-lan9220@f4000000 {
- compatible = "smsc,lan9220", "smsc,lan9115";
- reg = <0xf4000000 0x2000000>;
- phy-mode = "mii";
- interrupt-parent = <&gpio1>;
- interrupts = <31>, <32>;
- reset-gpios = <&gpio1 30 GPIO_ACTIVE_LOW>;
- reg-io-width = <4>;
- smsc,irq-push-pull;
-};
``ETHTOOL_MSG_FEC_SET`` set FEC settings
``ETHTOOL_MSG_MODULE_EEPROM_GET`` read SFP module EEPROM
``ETHTOOL_MSG_STATS_GET`` get standard statistics
+ ``ETHTOOL_MSG_PHC_VCLOCKS_GET`` get PHC virtual clocks info
===================================== ================================
Kernel to userspace:
``ETHTOOL_MSG_FEC_NTF`` FEC settings
``ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY`` read SFP module EEPROM
``ETHTOOL_MSG_STATS_GET_REPLY`` standard statistics
+ ``ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY`` PHC virtual clocks info
======================================== =================================
``GET`` requests are sent by userspace applications to retrieve device
etherStatsPkts512to1023Octets 512 1023
============================= ==== ====
+PHC_VCLOCKS_GET
+===============
+
+Query device PHC virtual clocks information.
+
+Request contents:
+
+ ==================================== ====== ==========================
+ ``ETHTOOL_A_PHC_VCLOCKS_HEADER`` nested request header
+ ==================================== ====== ==========================
+
+Kernel response contents:
+
+ ==================================== ====== ==========================
+ ``ETHTOOL_A_PHC_VCLOCKS_HEADER`` nested reply header
+ ``ETHTOOL_A_PHC_VCLOCKS_NUM`` u32 PHC virtual clocks number
+ ``ETHTOOL_A_PHC_VCLOCKS_INDEX`` s32 PHC index array
+ ==================================== ====== ==========================
+
Request translation
===================
n/a ``ETHTOOL_MSG_CABLE_TEST_ACT``
n/a ``ETHTOOL_MSG_CABLE_TEST_TDR_ACT``
n/a ``ETHTOOL_MSG_TUNNEL_INFO_GET``
+ n/a ``ETHTOOL_MSG_PHC_VCLOCKS_GET``
=================================== =====================================
Be conservative in what you do, be liberal in what you accept from others.
If it's non-zero, we mark only out of window RST segments as INVALID.
+nf_conntrack_tcp_ignore_invalid_rst - BOOLEAN
+ - 0 - disabled (default)
+ - 1 - enabled
+
+ If it's 1, we don't mark out of window RST segments as INVALID.
+
nf_conntrack_tcp_loose - BOOLEAN
- 0 - disabled
- not 0 - enabled (default)
Linux Kernel TIPC
=================
-TIPC (Transparent Inter Process Communication) is a protocol that is
-specially designed for intra-cluster communication.
+Introduction
+============
-For more information about TIPC, see http://tipc.sourceforge.net.
+TIPC (Transparent Inter Process Communication) is a protocol that is specially
+designed for intra-cluster communication. It can be configured to transmit
+messages either on UDP or directly across Ethernet. Message delivery is
+sequence guaranteed, loss free and flow controlled. Latency times are shorter
+than with any other known protocol, while maximal throughput is comparable to
+that of TCP.
+
+TIPC Features
+-------------
+
+- Cluster wide IPC service
+
+ Have you ever wished you had the convenience of Unix Domain Sockets even when
+ transmitting data between cluster nodes? Where you yourself determine the
+ addresses you want to bind to and use? Where you don't have to perform DNS
+ lookups and worry about IP addresses? Where you don't have to start timers
+ to monitor the continuous existence of peer sockets? And yet without the
+ downsides of that socket type, such as the risk of lingering inodes?
+
+ Welcome to the Transparent Inter Process Communication service, TIPC in short,
+ which gives you all of this, and a lot more.
+
+- Service Addressing
+
+ A fundamental concept in TIPC is that of Service Addressing which makes it
+ possible for a programmer to chose his own address, bind it to a server
+ socket and let client programs use only that address for sending messages.
+
+- Service Tracking
+
+ A client wanting to wait for the availability of a server, uses the Service
+ Tracking mechanism to subscribe for binding and unbinding/close events for
+ sockets with the associated service address.
+
+ The service tracking mechanism can also be used for Cluster Topology Tracking,
+ i.e., subscribing for availability/non-availability of cluster nodes.
+
+ Likewise, the service tracking mechanism can be used for Cluster Connectivity
+ Tracking, i.e., subscribing for up/down events for individual links between
+ cluster nodes.
+
+- Transmission Modes
+
+ Using a service address, a client can send datagram messages to a server socket.
+
+ Using the same address type, it can establish a connection towards an accepting
+ server socket.
+
+ It can also use a service address to create and join a Communication Group,
+ which is the TIPC manifestation of a brokerless message bus.
+
+ Multicast with very good performance and scalability is available both in
+ datagram mode and in communication group mode.
+
+- Inter Node Links
+
+ Communication between any two nodes in a cluster is maintained by one or two
+ Inter Node Links, which both guarantee data traffic integrity and monitor
+ the peer node's availability.
+
+- Cluster Scalability
+
+ By applying the Overlapping Ring Monitoring algorithm on the inter node links
+ it is possible to scale TIPC clusters up to 1000 nodes with a maintained
+ neighbor failure discovery time of 1-2 seconds. For smaller clusters this
+ time can be made much shorter.
+
+- Neighbor Discovery
+
+ Neighbor Node Discovery in the cluster is done by Ethernet broadcast or UDP
+ multicast, when any of those services are available. If not, configured peer
+ IP addresses can be used.
+
+- Configuration
+
+ When running TIPC in single node mode no configuration whatsoever is needed.
+ When running in cluster mode TIPC must as a minimum be given a node address
+ (before Linux 4.17) and told which interface to attach to. The "tipc"
+ configuration tool makes is possible to add and maintain many more
+ configuration parameters.
+
+- Performance
+
+ TIPC message transfer latency times are better than in any other known protocol.
+ Maximal byte throughput for inter-node connections is still somewhat lower than
+ for TCP, while they are superior for intra-node and inter-container throughput
+ on the same host.
+
+- Language Support
+
+ The TIPC user API has support for C, Python, Perl, Ruby, D and Go.
+
+More Information
+----------------
+
+- How to set up TIPC:
+
+ http://tipc.io/getting_started.html
+
+- How to program with TIPC:
+
+ http://tipc.io/programming.html
+
+- How to contribute to TIPC:
+
+- http://tipc.io/contacts.html
+
+- More details about TIPC specification:
+
+ http://tipc.io/protocol.html
+
+
+Implementation
+==============
+
+TIPC is implemented as a kernel module in net/tipc/ directory.
TIPC Base Types
---------------
AMD IOMMU (AMD-VI)
M: Joerg Roedel <joro@8bytes.org>
+R: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
L: iommu@lists.linux-foundation.org
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu.git
F: drivers/ptp/*
F: include/linux/ptp_cl*
+PTP VIRTUAL CLOCK SUPPORT
+M: Yangbo Lu <yangbo.lu@nxp.com>
+L: netdev@vger.kernel.org
+S: Maintained
+F: drivers/ptp/ptp_vclock.c
+F: net/ethtool/phc_vclocks.c
+
PTRACE SUPPORT
M: Oleg Nesterov <oleg@redhat.com>
S: Maintained
# Warn about unmarked fall-throughs in switch statement.
# Disabled for clang while comment to attribute conversion happens and
# https://github.com/ClangBuiltLinux/linux/issues/636 is discussed.
-KBUILD_CFLAGS += $(call cc-option,-Wimplicit-fallthrough,)
+KBUILD_CFLAGS += $(call cc-option,-Wimplicit-fallthrough=5,)
endif
# These warnings generated too much noise in a regular build.
* EBI2. This has a 25MHz chrystal next to it, so no
* clocking is needed.
*/
- ethernet-ebi2@2,0 {
+ ethernet@2,0 {
compatible = "smsc,lan9221", "smsc,lan9115";
reg = <2 0x0 0x100>;
/*
phy-mode = "mii";
reg-io-width = <2>;
smsc,force-external-phy;
- /* IRQ on edge falling = active low */
- smsc,irq-active-low;
smsc,irq-push-pull;
/*
/* we only have a 32-bit FPU */
return SIGFPE;
#endif
- fallthrough;
+ /* fallthrough */
case FPU_32BIT:
if (cpu_has_fre) {
/* clear FRE */
switch (boot_cpu_type()) {
default:
if (sizeof(long) == 4) {
+ fallthrough;
case CPU_LOONGSON2EF:
/* Loongson2 ebase is different than r4k, we have more space */
if ((p - tlb_handler) > 64)
default:
if (cpu_has_mips_r2_exec_hazard) {
uasm_i_ehb(&p);
+ fallthrough;
case CPU_CAVIUM_OCTEON:
case CPU_CAVIUM_OCTEON_PLUS:
switch(psurge_type) {
case PSURGE_DUAL:
out_8(psurge_sec_intr, ~0);
+ break;
case PSURGE_NONE:
break;
default:
case DIE_SSTEP:
if (uprobe_post_sstep_notifier(regs))
return NOTIFY_STOP;
+ break;
default:
break;
}
edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS);
edx.split.bit_width_fixed = cap.bit_width_fixed;
- edx.split.anythread_deprecated = 1;
+ if (cap.version)
+ edx.split.anythread_deprecated = 1;
edx.split.reserved1 = 0;
edx.split.reserved2 = 0;
unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U);
unsigned phys_as = entry->eax & 0xff;
- if (!g_phys_as)
+ /*
+ * If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as
+ * the guest operates in the same PA space as the host, i.e.
+ * reductions in MAXPHYADDR for memory encryption affect shadow
+ * paging, too.
+ *
+ * If TDP is enabled but an explicit guest MAXPHYADDR is not
+ * provided, use the raw bare metal MAXPHYADDR as reductions to
+ * the HPAs do not affect GPAs.
+ */
+ if (!tdp_enabled)
+ g_phys_as = boot_cpu_data.x86_phys_bits;
+ else if (!g_phys_as)
g_phys_as = phys_as;
+
entry->eax = g_phys_as | (virt_as << 8);
entry->edx = 0;
cpuid_entry_override(entry, CPUID_8000_0008_EBX);
case 0x8000001a:
case 0x8000001e:
break;
- /* Support memory encryption cpuid if host supports it */
case 0x8000001F:
- if (!kvm_cpu_cap_has(X86_FEATURE_SEV))
+ if (!kvm_cpu_cap_has(X86_FEATURE_SEV)) {
entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
- else
+ } else {
cpuid_entry_override(entry, CPUID_8000_001F_EAX);
+
+ /*
+ * Enumerate '0' for "PA bits reduction", the adjusted
+ * MAXPHYADDR is enumerated directly (see 0x80000008).
+ */
+ entry->ebx &= ~GENMASK(11, 6);
+ }
break;
/*Add support for Centaur's CPUID instruction*/
case 0xC0000000:
#include <asm/kvm_page_track.h>
#include "trace.h"
+#include "paging.h"
+
extern bool itlb_multihit_kvm_mitigation;
int __read_mostly nx_huge_pages = -1;
--- /dev/null
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Shadow paging constants/helpers that don't need to be #undef'd. */
+#ifndef __KVM_X86_PAGING_H
+#define __KVM_X86_PAGING_H
+
+#define GUEST_PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
+#define PT64_LVL_ADDR_MASK(level) \
+ (GUEST_PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
+ * PT64_LEVEL_BITS))) - 1))
+#define PT64_LVL_OFFSET_MASK(level) \
+ (GUEST_PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
+ * PT64_LEVEL_BITS))) - 1))
+#endif /* __KVM_X86_PAGING_H */
+
#define pt_element_t u64
#define guest_walker guest_walker64
#define FNAME(name) paging##64_##name
- #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK
+ #define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK
#define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
#define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
#define pt_element_t u64
#define guest_walker guest_walkerEPT
#define FNAME(name) ept_##name
- #define PT_BASE_ADDR_MASK PT64_BASE_ADDR_MASK
+ #define PT_BASE_ADDR_MASK GUEST_PT64_BASE_ADDR_MASK
#define PT_LVL_ADDR_MASK(lvl) PT64_LVL_ADDR_MASK(lvl)
#define PT_LVL_OFFSET_MASK(lvl) PT64_LVL_OFFSET_MASK(lvl)
#define PT_INDEX(addr, level) PT64_INDEX(addr, level)
#else
#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
#endif
-#define PT64_LVL_ADDR_MASK(level) \
- (PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + (((level) - 1) \
- * PT64_LEVEL_BITS))) - 1))
-#define PT64_LVL_OFFSET_MASK(level) \
- (PT64_BASE_ADDR_MASK & ((1ULL << (PAGE_SHIFT + (((level) - 1) \
- * PT64_LEVEL_BITS))) - 1))
#define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \
| shadow_x_mask | shadow_nx_mask | shadow_me_mask)
for (i = 0; i < MAX_INTERCEPT; i++)
c->intercepts[i] |= g->intercepts[i];
+
+ /* If SMI is not intercepted, ignore guest SMI intercept as well */
+ if (!intercept_smi)
+ vmcb_clr_intercept(c, INTERCEPT_SMI);
}
static void copy_vmcb_control_area(struct vmcb_control_area *dst,
return true;
}
-static void nested_load_control_from_vmcb12(struct vcpu_svm *svm,
- struct vmcb_control_area *control)
+void nested_load_control_from_vmcb12(struct vcpu_svm *svm,
+ struct vmcb_control_area *control)
{
copy_vmcb_control_area(&svm->nested.ctl, control);
struct kvm_host_map map;
u64 vmcb12_gpa;
+ if (!svm->nested.hsave_msr) {
+ kvm_inject_gp(vcpu, 0);
+ return 1;
+ }
+
if (is_smm(vcpu)) {
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
return ret;
}
+/* Copy state save area fields which are handled by VMRUN */
+void svm_copy_vmrun_state(struct vmcb_save_area *from_save,
+ struct vmcb_save_area *to_save)
+{
+ to_save->es = from_save->es;
+ to_save->cs = from_save->cs;
+ to_save->ss = from_save->ss;
+ to_save->ds = from_save->ds;
+ to_save->gdtr = from_save->gdtr;
+ to_save->idtr = from_save->idtr;
+ to_save->rflags = from_save->rflags | X86_EFLAGS_FIXED;
+ to_save->efer = from_save->efer;
+ to_save->cr0 = from_save->cr0;
+ to_save->cr3 = from_save->cr3;
+ to_save->cr4 = from_save->cr4;
+ to_save->rax = from_save->rax;
+ to_save->rsp = from_save->rsp;
+ to_save->rip = from_save->rip;
+ to_save->cpl = 0;
+}
+
void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
{
to_vmcb->save.fs = from_vmcb->save.fs;
svm->nested.vmcb12_gpa = kvm_state->hdr.svm.vmcb_pa;
- svm->vmcb01.ptr->save.es = save->es;
- svm->vmcb01.ptr->save.cs = save->cs;
- svm->vmcb01.ptr->save.ss = save->ss;
- svm->vmcb01.ptr->save.ds = save->ds;
- svm->vmcb01.ptr->save.gdtr = save->gdtr;
- svm->vmcb01.ptr->save.idtr = save->idtr;
- svm->vmcb01.ptr->save.rflags = save->rflags | X86_EFLAGS_FIXED;
- svm->vmcb01.ptr->save.efer = save->efer;
- svm->vmcb01.ptr->save.cr0 = save->cr0;
- svm->vmcb01.ptr->save.cr3 = save->cr3;
- svm->vmcb01.ptr->save.cr4 = save->cr4;
- svm->vmcb01.ptr->save.rax = save->rax;
- svm->vmcb01.ptr->save.rsp = save->rsp;
- svm->vmcb01.ptr->save.rip = save->rip;
- svm->vmcb01.ptr->save.cpl = 0;
-
+ svm_copy_vmrun_state(save, &svm->vmcb01.ptr->save);
nested_load_control_from_vmcb12(svm, ctl);
svm_switch_vmcb(svm, &svm->nested.vmcb02);
-
nested_vmcb02_prepare_control(svm);
-
kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
ret = 0;
out_free:
/* Pin guest memory */
guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK,
PAGE_SIZE, &n, 0);
- if (!guest_page)
- return -EFAULT;
+ if (IS_ERR(guest_page))
+ return PTR_ERR(guest_page);
/* allocate memory for header and transport buffer */
ret = -ENOMEM;
}
/* Copy packet header to userspace. */
- ret = copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr,
- params.hdr_len);
+ if (copy_to_user((void __user *)(uintptr_t)params.hdr_uaddr, hdr,
+ params.hdr_len))
+ ret = -EFAULT;
e_free_trans_data:
kfree(trans_data);
data.trans_len = params.trans_len;
/* Pin guest memory */
- ret = -EFAULT;
guest_page = sev_pin_memory(kvm, params.guest_uaddr & PAGE_MASK,
PAGE_SIZE, &n, 0);
- if (!guest_page)
+ if (IS_ERR(guest_page)) {
+ ret = PTR_ERR(guest_page);
goto e_free_trans;
+ }
/* The RECEIVE_UPDATE_DATA command requires C-bit to be always set. */
data.guest_address = (page_to_pfn(guest_page[0]) << PAGE_SHIFT) + offset;
bool __read_mostly dump_invalid_vmcb;
module_param(dump_invalid_vmcb, bool, 0644);
+
+bool intercept_smi = true;
+module_param(intercept_smi, bool, 0444);
+
+
static bool svm_gp_erratum_intercept = true;
static u8 rsm_ins_bytes[] = "\x0f\xaa";
svm_set_intercept(svm, INTERCEPT_INTR);
svm_set_intercept(svm, INTERCEPT_NMI);
- svm_set_intercept(svm, INTERCEPT_SMI);
+
+ if (intercept_smi)
+ svm_set_intercept(svm, INTERCEPT_SMI);
+
svm_set_intercept(svm, INTERCEPT_SELECTIVE_CR0);
svm_set_intercept(svm, INTERCEPT_RDPMC);
svm_set_intercept(svm, INTERCEPT_CPUID);
{
struct vcpu_svm *svm = to_svm(vcpu);
- u64 fault_address = __sme_clr(svm->vmcb->control.exit_info_2);
+ u64 fault_address = svm->vmcb->control.exit_info_2;
u64 error_code = svm->vmcb->control.exit_info_1;
trace_kvm_page_fault(fault_address, error_code);
return 1;
}
+static int smi_interception(struct kvm_vcpu *vcpu)
+{
+ return 1;
+}
+
static int intr_interception(struct kvm_vcpu *vcpu)
{
++vcpu->stat.irq_exits;
svm_disable_lbrv(vcpu);
break;
case MSR_VM_HSAVE_PA:
- svm->nested.hsave_msr = data;
+ /*
+ * Old kernels did not validate the value written to
+ * MSR_VM_HSAVE_PA. Allow KVM_SET_MSR to set an invalid
+ * value to allow live migrating buggy or malicious guests
+ * originating from those kernels.
+ */
+ if (!msr->host_initiated && !page_address_valid(vcpu, data))
+ return 1;
+
+ svm->nested.hsave_msr = data & PAGE_MASK;
break;
case MSR_VM_CR:
return svm_set_vm_cr(vcpu, data);
[SVM_EXIT_EXCP_BASE + GP_VECTOR] = gp_interception,
[SVM_EXIT_INTR] = intr_interception,
[SVM_EXIT_NMI] = nmi_interception,
- [SVM_EXIT_SMI] = kvm_emulate_as_nop,
- [SVM_EXIT_INIT] = kvm_emulate_as_nop,
+ [SVM_EXIT_SMI] = smi_interception,
[SVM_EXIT_VINTR] = interrupt_window_interception,
[SVM_EXIT_RDPMC] = kvm_emulate_rdpmc,
[SVM_EXIT_CPUID] = kvm_emulate_cpuid,
static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ struct kvm_host_map map_save;
int ret;
if (is_guest_mode(vcpu)) {
ret = nested_svm_vmexit(svm);
if (ret)
return ret;
+
+ /*
+ * KVM uses VMCB01 to store L1 host state while L2 runs but
+ * VMCB01 is going to be used during SMM and thus the state will
+ * be lost. Temporary save non-VMLOAD/VMSAVE state to the host save
+ * area pointed to by MSR_VM_HSAVE_PA. APM guarantees that the
+ * format of the area is identical to guest save area offsetted
+ * by 0x400 (matches the offset of 'struct vmcb_save_area'
+ * within 'struct vmcb'). Note: HSAVE area may also be used by
+ * L1 hypervisor to save additional host context (e.g. KVM does
+ * that, see svm_prepare_guest_switch()) which must be
+ * preserved.
+ */
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
+ &map_save) == -EINVAL)
+ return 1;
+
+ BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400);
+
+ svm_copy_vmrun_state(&svm->vmcb01.ptr->save,
+ map_save.hva + 0x400);
+
+ kvm_vcpu_unmap(vcpu, &map_save, true);
}
return 0;
}
static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
{
struct vcpu_svm *svm = to_svm(vcpu);
- struct kvm_host_map map;
+ struct kvm_host_map map, map_save;
int ret = 0;
if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) {
u64 saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
u64 guest = GET_SMSTATE(u64, smstate, 0x7ed8);
u64 vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
+ struct vmcb *vmcb12;
if (guest) {
if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
if (svm_allocate_nested(svm))
return 1;
- ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, map.hva);
+ vmcb12 = map.hva;
+
+ nested_load_control_from_vmcb12(svm, &vmcb12->control);
+
+ ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12);
kvm_vcpu_unmap(vcpu, &map, true);
+
+ /*
+ * Restore L1 host state from L1 HSAVE area as VMCB01 was
+ * used during SMM (see svm_enter_smm())
+ */
+ if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr),
+ &map_save) == -EINVAL)
+ return 1;
+
+ svm_copy_vmrun_state(map_save.hva + 0x400,
+ &svm->vmcb01.ptr->save);
+
+ kvm_vcpu_unmap(vcpu, &map_save, true);
}
}
#define MSRPM_OFFSETS 16
extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
extern bool npt_enabled;
+extern bool intercept_smi;
/*
* Clean bits in VMCB.
void svm_free_nested(struct vcpu_svm *svm);
int svm_allocate_nested(struct vcpu_svm *svm);
int nested_svm_vmrun(struct kvm_vcpu *vcpu);
+void svm_copy_vmrun_state(struct vmcb_save_area *from_save,
+ struct vmcb_save_area *to_save);
void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb);
int nested_svm_vmexit(struct vcpu_svm *svm);
int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
bool has_error_code, u32 error_code);
int nested_svm_exit_special(struct vcpu_svm *svm);
+void nested_load_control_from_vmcb12(struct vcpu_svm *svm,
+ struct vmcb_control_area *control);
void nested_sync_control_from_vmcb02(struct vcpu_svm *svm);
void nested_vmcb02_compute_g_pat(struct vcpu_svm *svm);
void svm_switch_vmcb(struct vcpu_svm *svm, struct kvm_vmcb_info *target_vmcb);
#include "vmx_ops.h"
#include "cpuid.h"
-extern const u32 vmx_msr_index[];
-
#define MSR_TYPE_R 1
#define MSR_TYPE_W 2
#define MSR_TYPE_RW 3
set_debugreg(vcpu->arch.eff_db[3], 3);
set_debugreg(vcpu->arch.dr6, 6);
vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD;
+ } else if (unlikely(hw_breakpoint_active())) {
+ set_debugreg(0, 7);
}
for (;;) {
int r;
rdmsrl_safe(MSR_EFER, &host_efer);
- if (WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_NX) &&
- !(host_efer & EFER_NX)))
- return -EIO;
if (boot_cpu_has(X86_FEATURE_XSAVES))
rdmsrl(MSR_IA32_XSS, host_xss);
for (i = 0; i < prog->aux->size_poke_tab; i++) {
poke = &prog->aux->poke_tab[i];
+ if (poke->aux && poke->aux != prog->aux)
+ continue;
+
WARN_ON_ONCE(READ_ONCE(poke->tailcall_target_stable));
if (poke->reason != BPF_POKE_REASON_TAIL_CALL)
rc);
break;
}
+ break;
case OPAL_SUCCESS:
break;
default:
return cpufreq_register_driver(&longhaul_driver);
case 10:
pr_err("Use acpi-cpufreq driver for VIA C7\n");
- default:
- ;
}
return -ENODEV;
case IDMAC_SDC_1:
case IDMAC_IC_7:
ipu_channel_set_priority(ipu, channel, true);
+ break;
default:
break;
}
case IDMAC_SDC_0:
case IDMAC_SDC_1:
n_desc = 4;
+ break;
default:
break;
}
case 16:
if (is_mpc8308)
return false;
+ break;
case 1:
case 2:
case 4:
ud->tchan_cnt),
ud->rchan_cnt - bitmap_weight(ud->rchan_map,
ud->rchan_cnt));
+ break;
default:
break;
}
config EDAC_IGEN6
tristate "Intel client SoC Integrated MC"
depends on PCI && PCI_MMCONFIG && ARCH_HAVE_NMI_SAFE_CMPXCHG
- depends on X64_64 && X86_MCE_INTEL
+ depends on X86_64 && X86_MCE_INTEL
help
Support for error detection and correction on the Intel
client SoC Integrated Memory Controller using In-Band ECC IP.
switch (obj->mm.madv) {
case I915_MADV_DONTNEED:
i915_gem_object_truncate(obj);
+ return;
case __I915_MADV_PURGED:
return;
}
case MSM_BO_CACHED_COHERENT:
if (priv->has_cached_coherent)
break;
- /* fallthrough */
+ fallthrough;
default:
DRM_DEV_ERROR(dev->dev, "invalid cache flag: %x\n",
(flags & MSM_BO_CACHE_MASK));
switch (idx) {
case CMDQ_ERR_CERROR_ABT_IDX:
dev_err(smmu->dev, "retrying command fetch\n");
+ return;
case CMDQ_ERR_CERROR_NONE_IDX:
return;
case CMDQ_ERR_CERROR_ATC_INV_IDX:
ret = iommu_device_register(&qcom_iommu->iommu, &qcom_iommu_ops, dev);
if (ret) {
dev_err(dev, "Failed to register iommu\n");
- goto err_sysfs_remove;
+ return ret;
}
- ret = bus_set_iommu(&platform_bus_type, &qcom_iommu_ops);
- if (ret)
- goto err_unregister_device;
+ bus_set_iommu(&platform_bus_type, &qcom_iommu_ops);
if (qcom_iommu->local_base) {
pm_runtime_get_sync(dev);
}
return 0;
-
-err_unregister_device:
- iommu_device_unregister(&qcom_iommu->iommu);
-
-err_sysfs_remove:
- iommu_device_sysfs_remove(&qcom_iommu->iommu);
- return ret;
}
static int qcom_iommu_device_remove(struct platform_device *pdev)
return 0;
}
-static void domain_context_clear_one(struct intel_iommu *iommu, u8 bus, u8 devfn)
+static void domain_context_clear_one(struct device_domain_info *info, u8 bus, u8 devfn)
{
- unsigned long flags;
+ struct intel_iommu *iommu = info->iommu;
struct context_entry *context;
+ unsigned long flags;
u16 did_old;
if (!iommu)
spin_unlock_irqrestore(&iommu->lock, flags);
return;
}
- did_old = context_domain_id(context);
+
+ if (sm_supported(iommu)) {
+ if (hw_pass_through && domain_type_is_si(info->domain))
+ did_old = FLPT_DEFAULT_DID;
+ else
+ did_old = info->domain->iommu_did[iommu->seq_id];
+ } else {
+ did_old = context_domain_id(context);
+ }
+
context_clear_entry(context);
__iommu_flush_cache(iommu, context, sizeof(*context));
spin_unlock_irqrestore(&iommu->lock, flags);
0,
0,
DMA_TLB_DSI_FLUSH);
+
+ __iommu_flush_dev_iotlb(info, 0, MAX_AGAW_PFN_WIDTH);
}
static inline void unlink_domain_info(struct device_domain_info *info)
static int domain_context_clear_one_cb(struct pci_dev *pdev, u16 alias, void *opaque)
{
- struct intel_iommu *iommu = opaque;
+ struct device_domain_info *info = opaque;
- domain_context_clear_one(iommu, PCI_BUS_NUM(alias), alias & 0xff);
+ domain_context_clear_one(info, PCI_BUS_NUM(alias), alias & 0xff);
return 0;
}
* devices, unbinding the driver from any one of them will possibly leave
* the others unable to operate.
*/
-static void domain_context_clear(struct intel_iommu *iommu, struct device *dev)
+static void domain_context_clear(struct device_domain_info *info)
{
- if (!iommu || !dev || !dev_is_pci(dev))
+ if (!info->iommu || !info->dev || !dev_is_pci(info->dev))
return;
- pci_for_each_dma_alias(to_pci_dev(dev), &domain_context_clear_one_cb, iommu);
+ pci_for_each_dma_alias(to_pci_dev(info->dev),
+ &domain_context_clear_one_cb, info);
}
static void __dmar_remove_one_dev_info(struct device_domain_info *info)
iommu = info->iommu;
domain = info->domain;
- if (info->dev) {
+ if (info->dev && !dev_is_real_dma_subdevice(info->dev)) {
if (dev_is_pci(info->dev) && sm_supported(iommu))
intel_pasid_tear_down_entry(iommu, info->dev,
PASID_RID2PASID, false);
iommu_disable_dev_iotlb(info);
- if (!dev_is_real_dma_subdevice(info->dev))
- domain_context_clear(iommu, info->dev);
+ domain_context_clear(info);
intel_pasid_free_table(info->dev);
}
}
#define DT_HI_MASK GENMASK_ULL(39, 32)
+#define DTE_BASE_HI_MASK GENMASK(11, 4)
#define DT_SHIFT 28
static inline phys_addr_t rk_dte_addr_phys_v2(u32 addr)
{
- return (phys_addr_t)(addr & RK_DTE_PT_ADDRESS_MASK) |
- ((addr & DT_HI_MASK) << DT_SHIFT);
+ u64 addr64 = addr;
+ return (phys_addr_t)(addr64 & RK_DTE_PT_ADDRESS_MASK) |
+ ((addr64 & DTE_BASE_HI_MASK) << DT_SHIFT);
}
static inline u32 rk_dma_addr_dte_v2(dma_addr_t dt_dma)
break;
}
}
+ fallthrough;
+
case JZ4740_MMC_STATE_DONE:
break;
}
#if BITS_PER_LONG >= 64
case 8:
onecmd |= (onecmd << (chip_mode * 32));
-#endif
fallthrough;
+#endif
case 4:
onecmd |= (onecmd << (chip_mode * 16));
fallthrough;
#if BITS_PER_LONG >= 64
case 8:
res |= (onestat >> (chip_mode * 32));
-#endif
fallthrough;
+#endif
case 4:
res |= (onestat >> (chip_mode * 16));
fallthrough;
static int bond_ipsec_add_sa(struct xfrm_state *xs)
{
struct net_device *bond_dev = xs->xso.dev;
+ struct bond_ipsec *ipsec;
struct bonding *bond;
struct slave *slave;
+ int err;
if (!bond_dev)
return -EINVAL;
+ rcu_read_lock();
bond = netdev_priv(bond_dev);
slave = rcu_dereference(bond->curr_active_slave);
- xs->xso.real_dev = slave->dev;
- bond->xs = xs;
+ if (!slave) {
+ rcu_read_unlock();
+ return -ENODEV;
+ }
- if (!(slave->dev->xfrmdev_ops
- && slave->dev->xfrmdev_ops->xdo_dev_state_add)) {
+ if (!slave->dev->xfrmdev_ops ||
+ !slave->dev->xfrmdev_ops->xdo_dev_state_add ||
+ netif_is_bond_master(slave->dev)) {
slave_warn(bond_dev, slave->dev, "Slave does not support ipsec offload\n");
+ rcu_read_unlock();
return -EINVAL;
}
- return slave->dev->xfrmdev_ops->xdo_dev_state_add(xs);
+ ipsec = kmalloc(sizeof(*ipsec), GFP_ATOMIC);
+ if (!ipsec) {
+ rcu_read_unlock();
+ return -ENOMEM;
+ }
+ xs->xso.real_dev = slave->dev;
+
+ err = slave->dev->xfrmdev_ops->xdo_dev_state_add(xs);
+ if (!err) {
+ ipsec->xs = xs;
+ INIT_LIST_HEAD(&ipsec->list);
+ spin_lock_bh(&bond->ipsec_lock);
+ list_add(&ipsec->list, &bond->ipsec_list);
+ spin_unlock_bh(&bond->ipsec_lock);
+ } else {
+ kfree(ipsec);
+ }
+ rcu_read_unlock();
+ return err;
+}
+
+static void bond_ipsec_add_sa_all(struct bonding *bond)
+{
+ struct net_device *bond_dev = bond->dev;
+ struct bond_ipsec *ipsec;
+ struct slave *slave;
+
+ rcu_read_lock();
+ slave = rcu_dereference(bond->curr_active_slave);
+ if (!slave)
+ goto out;
+
+ if (!slave->dev->xfrmdev_ops ||
+ !slave->dev->xfrmdev_ops->xdo_dev_state_add ||
+ netif_is_bond_master(slave->dev)) {
+ spin_lock_bh(&bond->ipsec_lock);
+ if (!list_empty(&bond->ipsec_list))
+ slave_warn(bond_dev, slave->dev,
+ "%s: no slave xdo_dev_state_add\n",
+ __func__);
+ spin_unlock_bh(&bond->ipsec_lock);
+ goto out;
+ }
+
+ spin_lock_bh(&bond->ipsec_lock);
+ list_for_each_entry(ipsec, &bond->ipsec_list, list) {
+ ipsec->xs->xso.real_dev = slave->dev;
+ if (slave->dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs)) {
+ slave_warn(bond_dev, slave->dev, "%s: failed to add SA\n", __func__);
+ ipsec->xs->xso.real_dev = NULL;
+ }
+ }
+ spin_unlock_bh(&bond->ipsec_lock);
+out:
+ rcu_read_unlock();
}
/**
static void bond_ipsec_del_sa(struct xfrm_state *xs)
{
struct net_device *bond_dev = xs->xso.dev;
+ struct bond_ipsec *ipsec;
struct bonding *bond;
struct slave *slave;
if (!bond_dev)
return;
+ rcu_read_lock();
bond = netdev_priv(bond_dev);
slave = rcu_dereference(bond->curr_active_slave);
if (!slave)
- return;
+ goto out;
- xs->xso.real_dev = slave->dev;
+ if (!xs->xso.real_dev)
+ goto out;
+
+ WARN_ON(xs->xso.real_dev != slave->dev);
- if (!(slave->dev->xfrmdev_ops
- && slave->dev->xfrmdev_ops->xdo_dev_state_delete)) {
+ if (!slave->dev->xfrmdev_ops ||
+ !slave->dev->xfrmdev_ops->xdo_dev_state_delete ||
+ netif_is_bond_master(slave->dev)) {
slave_warn(bond_dev, slave->dev, "%s: no slave xdo_dev_state_delete\n", __func__);
- return;
+ goto out;
}
slave->dev->xfrmdev_ops->xdo_dev_state_delete(xs);
+out:
+ spin_lock_bh(&bond->ipsec_lock);
+ list_for_each_entry(ipsec, &bond->ipsec_list, list) {
+ if (ipsec->xs == xs) {
+ list_del(&ipsec->list);
+ kfree(ipsec);
+ break;
+ }
+ }
+ spin_unlock_bh(&bond->ipsec_lock);
+ rcu_read_unlock();
+}
+
+static void bond_ipsec_del_sa_all(struct bonding *bond)
+{
+ struct net_device *bond_dev = bond->dev;
+ struct bond_ipsec *ipsec;
+ struct slave *slave;
+
+ rcu_read_lock();
+ slave = rcu_dereference(bond->curr_active_slave);
+ if (!slave) {
+ rcu_read_unlock();
+ return;
+ }
+
+ spin_lock_bh(&bond->ipsec_lock);
+ list_for_each_entry(ipsec, &bond->ipsec_list, list) {
+ if (!ipsec->xs->xso.real_dev)
+ continue;
+
+ if (!slave->dev->xfrmdev_ops ||
+ !slave->dev->xfrmdev_ops->xdo_dev_state_delete ||
+ netif_is_bond_master(slave->dev)) {
+ slave_warn(bond_dev, slave->dev,
+ "%s: no slave xdo_dev_state_delete\n",
+ __func__);
+ } else {
+ slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
+ }
+ ipsec->xs->xso.real_dev = NULL;
+ }
+ spin_unlock_bh(&bond->ipsec_lock);
+ rcu_read_unlock();
}
/**
static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
{
struct net_device *bond_dev = xs->xso.dev;
- struct bonding *bond = netdev_priv(bond_dev);
- struct slave *curr_active = rcu_dereference(bond->curr_active_slave);
- struct net_device *slave_dev = curr_active->dev;
+ struct net_device *real_dev;
+ struct slave *curr_active;
+ struct bonding *bond;
+ int err;
- if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)
- return true;
+ bond = netdev_priv(bond_dev);
+ rcu_read_lock();
+ curr_active = rcu_dereference(bond->curr_active_slave);
+ real_dev = curr_active->dev;
- if (!(slave_dev->xfrmdev_ops
- && slave_dev->xfrmdev_ops->xdo_dev_offload_ok)) {
- slave_warn(bond_dev, slave_dev, "%s: no slave xdo_dev_offload_ok\n", __func__);
- return false;
+ if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
+ err = false;
+ goto out;
}
- xs->xso.real_dev = slave_dev;
- return slave_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
+ if (!xs->xso.real_dev) {
+ err = false;
+ goto out;
+ }
+
+ if (!real_dev->xfrmdev_ops ||
+ !real_dev->xfrmdev_ops->xdo_dev_offload_ok ||
+ netif_is_bond_master(real_dev)) {
+ err = false;
+ goto out;
+ }
+
+ err = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
+out:
+ rcu_read_unlock();
+ return err;
}
static const struct xfrmdev_ops bond_xfrmdev_ops = {
return;
#ifdef CONFIG_XFRM_OFFLOAD
- if (old_active && bond->xs)
- bond_ipsec_del_sa(bond->xs);
+ bond_ipsec_del_sa_all(bond);
#endif /* CONFIG_XFRM_OFFLOAD */
if (new_active) {
}
#ifdef CONFIG_XFRM_OFFLOAD
- if (new_active && bond->xs) {
- xfrm_dev_state_flush(dev_net(bond->dev), bond->dev, true);
- bond_ipsec_add_sa(bond->xs);
- }
+ bond_ipsec_add_sa_all(bond);
#endif /* CONFIG_XFRM_OFFLOAD */
/* resend IGMP joins since active slave has changed or
return bond_event_changename(event_bond);
case NETDEV_UNREGISTER:
bond_remove_proc_entry(event_bond);
+ xfrm_dev_state_flush(dev_net(bond_dev), bond_dev, true);
break;
case NETDEV_REGISTER:
bond_create_proc_entry(event_bond);
#ifdef CONFIG_XFRM_OFFLOAD
/* set up xfrm device ops (only supported in active-backup right now) */
bond_dev->xfrmdev_ops = &bond_xfrmdev_ops;
- bond->xs = NULL;
+ INIT_LIST_HEAD(&bond->ipsec_list);
+ spin_lock_init(&bond->ipsec_lock);
#endif /* CONFIG_XFRM_OFFLOAD */
/* don't acquire bond device's netif_tx_lock when transmitting */
identified as N_CAIF. When this ldisc is opened from user space
it will redirect the TTY's traffic into the CAIF stack.
-config CAIF_HSI
- tristate "CAIF HSI transport driver"
- depends on CAIF
- default n
- help
- The CAIF low level driver for CAIF over HSI.
- Be aware that if you enable this then you also need to
- enable a low-level HSI driver.
-
config CAIF_VIRTIO
tristate "CAIF virtio transport driver"
depends on CAIF && HAS_DMA
# Serial interface
obj-$(CONFIG_CAIF_TTY) += caif_serial.o
-# HSI interface
-obj-$(CONFIG_CAIF_HSI) += caif_hsi.o
-
# Virtio interface
obj-$(CONFIG_CAIF_VIRTIO) += caif_virtio.o
+++ /dev/null
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Copyright (C) ST-Ericsson AB 2010
- * Author: Daniel Martensson
- * Dmitry.Tarnyagin / dmitry.tarnyagin@lockless.no
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME fmt
-
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/device.h>
-#include <linux/netdevice.h>
-#include <linux/string.h>
-#include <linux/list.h>
-#include <linux/interrupt.h>
-#include <linux/delay.h>
-#include <linux/sched.h>
-#include <linux/if_arp.h>
-#include <linux/timer.h>
-#include <net/rtnetlink.h>
-#include <linux/pkt_sched.h>
-#include <net/caif/caif_layer.h>
-#include <net/caif/caif_hsi.h>
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Daniel Martensson");
-MODULE_DESCRIPTION("CAIF HSI driver");
-
-/* Returns the number of padding bytes for alignment. */
-#define PAD_POW2(x, pow) ((((x)&((pow)-1)) == 0) ? 0 :\
- (((pow)-((x)&((pow)-1)))))
-
-static const struct cfhsi_config hsi_default_config = {
-
- /* Inactivity timeout on HSI, ms */
- .inactivity_timeout = HZ,
-
- /* Aggregation timeout (ms) of zero means no aggregation is done*/
- .aggregation_timeout = 1,
-
- /*
- * HSI link layer flow-control thresholds.
- * Threshold values for the HSI packet queue. Flow-control will be
- * asserted when the number of packets exceeds q_high_mark. It will
- * not be de-asserted before the number of packets drops below
- * q_low_mark.
- * Warning: A high threshold value might increase throughput but it
- * will at the same time prevent channel prioritization and increase
- * the risk of flooding the modem. The high threshold should be above
- * the low.
- */
- .q_high_mark = 100,
- .q_low_mark = 50,
-
- /*
- * HSI padding options.
- * Warning: must be a base of 2 (& operation used) and can not be zero !
- */
- .head_align = 4,
- .tail_align = 4,
-};
-
-#define ON 1
-#define OFF 0
-
-static LIST_HEAD(cfhsi_list);
-
-static void cfhsi_inactivity_tout(struct timer_list *t)
-{
- struct cfhsi *cfhsi = from_timer(cfhsi, t, inactivity_timer);
-
- netdev_dbg(cfhsi->ndev, "%s.\n",
- __func__);
-
- /* Schedule power down work queue. */
- if (!test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- queue_work(cfhsi->wq, &cfhsi->wake_down_work);
-}
-
-static void cfhsi_update_aggregation_stats(struct cfhsi *cfhsi,
- const struct sk_buff *skb,
- int direction)
-{
- struct caif_payload_info *info;
- int hpad, tpad, len;
-
- info = (struct caif_payload_info *)&skb->cb;
- hpad = 1 + PAD_POW2((info->hdr_len + 1), cfhsi->cfg.head_align);
- tpad = PAD_POW2((skb->len + hpad), cfhsi->cfg.tail_align);
- len = skb->len + hpad + tpad;
-
- if (direction > 0)
- cfhsi->aggregation_len += len;
- else if (direction < 0)
- cfhsi->aggregation_len -= len;
-}
-
-static bool cfhsi_can_send_aggregate(struct cfhsi *cfhsi)
-{
- int i;
-
- if (cfhsi->cfg.aggregation_timeout == 0)
- return true;
-
- for (i = 0; i < CFHSI_PRIO_BEBK; ++i) {
- if (cfhsi->qhead[i].qlen)
- return true;
- }
-
- /* TODO: Use aggregation_len instead */
- if (cfhsi->qhead[CFHSI_PRIO_BEBK].qlen >= CFHSI_MAX_PKTS)
- return true;
-
- return false;
-}
-
-static struct sk_buff *cfhsi_dequeue(struct cfhsi *cfhsi)
-{
- struct sk_buff *skb;
- int i;
-
- for (i = 0; i < CFHSI_PRIO_LAST; ++i) {
- skb = skb_dequeue(&cfhsi->qhead[i]);
- if (skb)
- break;
- }
-
- return skb;
-}
-
-static int cfhsi_tx_queue_len(struct cfhsi *cfhsi)
-{
- int i, len = 0;
- for (i = 0; i < CFHSI_PRIO_LAST; ++i)
- len += skb_queue_len(&cfhsi->qhead[i]);
- return len;
-}
-
-static void cfhsi_abort_tx(struct cfhsi *cfhsi)
-{
- struct sk_buff *skb;
-
- for (;;) {
- spin_lock_bh(&cfhsi->lock);
- skb = cfhsi_dequeue(cfhsi);
- if (!skb)
- break;
-
- cfhsi->ndev->stats.tx_errors++;
- cfhsi->ndev->stats.tx_dropped++;
- cfhsi_update_aggregation_stats(cfhsi, skb, -1);
- spin_unlock_bh(&cfhsi->lock);
- kfree_skb(skb);
- }
- cfhsi->tx_state = CFHSI_TX_STATE_IDLE;
- if (!test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- mod_timer(&cfhsi->inactivity_timer,
- jiffies + cfhsi->cfg.inactivity_timeout);
- spin_unlock_bh(&cfhsi->lock);
-}
-
-static int cfhsi_flush_fifo(struct cfhsi *cfhsi)
-{
- char buffer[32]; /* Any reasonable value */
- size_t fifo_occupancy;
- int ret;
-
- netdev_dbg(cfhsi->ndev, "%s.\n",
- __func__);
-
- do {
- ret = cfhsi->ops->cfhsi_fifo_occupancy(cfhsi->ops,
- &fifo_occupancy);
- if (ret) {
- netdev_warn(cfhsi->ndev,
- "%s: can't get FIFO occupancy: %d.\n",
- __func__, ret);
- break;
- } else if (!fifo_occupancy)
- /* No more data, exitting normally */
- break;
-
- fifo_occupancy = min(sizeof(buffer), fifo_occupancy);
- set_bit(CFHSI_FLUSH_FIFO, &cfhsi->bits);
- ret = cfhsi->ops->cfhsi_rx(buffer, fifo_occupancy,
- cfhsi->ops);
- if (ret) {
- clear_bit(CFHSI_FLUSH_FIFO, &cfhsi->bits);
- netdev_warn(cfhsi->ndev,
- "%s: can't read data: %d.\n",
- __func__, ret);
- break;
- }
-
- ret = 5 * HZ;
- ret = wait_event_interruptible_timeout(cfhsi->flush_fifo_wait,
- !test_bit(CFHSI_FLUSH_FIFO, &cfhsi->bits), ret);
-
- if (ret < 0) {
- netdev_warn(cfhsi->ndev,
- "%s: can't wait for flush complete: %d.\n",
- __func__, ret);
- break;
- } else if (!ret) {
- ret = -ETIMEDOUT;
- netdev_warn(cfhsi->ndev,
- "%s: timeout waiting for flush complete.\n",
- __func__);
- break;
- }
- } while (1);
-
- return ret;
-}
-
-static int cfhsi_tx_frm(struct cfhsi_desc *desc, struct cfhsi *cfhsi)
-{
- int nfrms = 0;
- int pld_len = 0;
- struct sk_buff *skb;
- u8 *pfrm = desc->emb_frm + CFHSI_MAX_EMB_FRM_SZ;
-
- skb = cfhsi_dequeue(cfhsi);
- if (!skb)
- return 0;
-
- /* Clear offset. */
- desc->offset = 0;
-
- /* Check if we can embed a CAIF frame. */
- if (skb->len < CFHSI_MAX_EMB_FRM_SZ) {
- struct caif_payload_info *info;
- int hpad;
- int tpad;
-
- /* Calculate needed head alignment and tail alignment. */
- info = (struct caif_payload_info *)&skb->cb;
-
- hpad = 1 + PAD_POW2((info->hdr_len + 1), cfhsi->cfg.head_align);
- tpad = PAD_POW2((skb->len + hpad), cfhsi->cfg.tail_align);
-
- /* Check if frame still fits with added alignment. */
- if ((skb->len + hpad + tpad) <= CFHSI_MAX_EMB_FRM_SZ) {
- u8 *pemb = desc->emb_frm;
- desc->offset = CFHSI_DESC_SHORT_SZ;
- *pemb = (u8)(hpad - 1);
- pemb += hpad;
-
- /* Update network statistics. */
- spin_lock_bh(&cfhsi->lock);
- cfhsi->ndev->stats.tx_packets++;
- cfhsi->ndev->stats.tx_bytes += skb->len;
- cfhsi_update_aggregation_stats(cfhsi, skb, -1);
- spin_unlock_bh(&cfhsi->lock);
-
- /* Copy in embedded CAIF frame. */
- skb_copy_bits(skb, 0, pemb, skb->len);
-
- /* Consume the SKB */
- consume_skb(skb);
- skb = NULL;
- }
- }
-
- /* Create payload CAIF frames. */
- while (nfrms < CFHSI_MAX_PKTS) {
- struct caif_payload_info *info;
- int hpad;
- int tpad;
-
- if (!skb)
- skb = cfhsi_dequeue(cfhsi);
-
- if (!skb)
- break;
-
- /* Calculate needed head alignment and tail alignment. */
- info = (struct caif_payload_info *)&skb->cb;
-
- hpad = 1 + PAD_POW2((info->hdr_len + 1), cfhsi->cfg.head_align);
- tpad = PAD_POW2((skb->len + hpad), cfhsi->cfg.tail_align);
-
- /* Fill in CAIF frame length in descriptor. */
- desc->cffrm_len[nfrms] = hpad + skb->len + tpad;
-
- /* Fill head padding information. */
- *pfrm = (u8)(hpad - 1);
- pfrm += hpad;
-
- /* Update network statistics. */
- spin_lock_bh(&cfhsi->lock);
- cfhsi->ndev->stats.tx_packets++;
- cfhsi->ndev->stats.tx_bytes += skb->len;
- cfhsi_update_aggregation_stats(cfhsi, skb, -1);
- spin_unlock_bh(&cfhsi->lock);
-
- /* Copy in CAIF frame. */
- skb_copy_bits(skb, 0, pfrm, skb->len);
-
- /* Update payload length. */
- pld_len += desc->cffrm_len[nfrms];
-
- /* Update frame pointer. */
- pfrm += skb->len + tpad;
-
- /* Consume the SKB */
- consume_skb(skb);
- skb = NULL;
-
- /* Update number of frames. */
- nfrms++;
- }
-
- /* Unused length fields should be zero-filled (according to SPEC). */
- while (nfrms < CFHSI_MAX_PKTS) {
- desc->cffrm_len[nfrms] = 0x0000;
- nfrms++;
- }
-
- /* Check if we can piggy-back another descriptor. */
- if (cfhsi_can_send_aggregate(cfhsi))
- desc->header |= CFHSI_PIGGY_DESC;
- else
- desc->header &= ~CFHSI_PIGGY_DESC;
-
- return CFHSI_DESC_SZ + pld_len;
-}
-
-static void cfhsi_start_tx(struct cfhsi *cfhsi)
-{
- struct cfhsi_desc *desc = (struct cfhsi_desc *)cfhsi->tx_buf;
- int len, res;
-
- netdev_dbg(cfhsi->ndev, "%s.\n", __func__);
-
- if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- return;
-
- do {
- /* Create HSI frame. */
- len = cfhsi_tx_frm(desc, cfhsi);
- if (!len) {
- spin_lock_bh(&cfhsi->lock);
- if (unlikely(cfhsi_tx_queue_len(cfhsi))) {
- spin_unlock_bh(&cfhsi->lock);
- res = -EAGAIN;
- continue;
- }
- cfhsi->tx_state = CFHSI_TX_STATE_IDLE;
- /* Start inactivity timer. */
- mod_timer(&cfhsi->inactivity_timer,
- jiffies + cfhsi->cfg.inactivity_timeout);
- spin_unlock_bh(&cfhsi->lock);
- break;
- }
-
- /* Set up new transfer. */
- res = cfhsi->ops->cfhsi_tx(cfhsi->tx_buf, len, cfhsi->ops);
- if (WARN_ON(res < 0))
- netdev_err(cfhsi->ndev, "%s: TX error %d.\n",
- __func__, res);
- } while (res < 0);
-}
-
-static void cfhsi_tx_done(struct cfhsi *cfhsi)
-{
- netdev_dbg(cfhsi->ndev, "%s.\n", __func__);
-
- if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- return;
-
- /*
- * Send flow on if flow off has been previously signalled
- * and number of packets is below low water mark.
- */
- spin_lock_bh(&cfhsi->lock);
- if (cfhsi->flow_off_sent &&
- cfhsi_tx_queue_len(cfhsi) <= cfhsi->cfg.q_low_mark &&
- cfhsi->cfdev.flowctrl) {
-
- cfhsi->flow_off_sent = 0;
- cfhsi->cfdev.flowctrl(cfhsi->ndev, ON);
- }
-
- if (cfhsi_can_send_aggregate(cfhsi)) {
- spin_unlock_bh(&cfhsi->lock);
- cfhsi_start_tx(cfhsi);
- } else {
- mod_timer(&cfhsi->aggregation_timer,
- jiffies + cfhsi->cfg.aggregation_timeout);
- spin_unlock_bh(&cfhsi->lock);
- }
-
- return;
-}
-
-static void cfhsi_tx_done_cb(struct cfhsi_cb_ops *cb_ops)
-{
- struct cfhsi *cfhsi;
-
- cfhsi = container_of(cb_ops, struct cfhsi, cb_ops);
- netdev_dbg(cfhsi->ndev, "%s.\n",
- __func__);
-
- if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- return;
- cfhsi_tx_done(cfhsi);
-}
-
-static int cfhsi_rx_desc(struct cfhsi_desc *desc, struct cfhsi *cfhsi)
-{
- int xfer_sz = 0;
- int nfrms = 0;
- u16 *plen = NULL;
- u8 *pfrm = NULL;
-
- if ((desc->header & ~CFHSI_PIGGY_DESC) ||
- (desc->offset > CFHSI_MAX_EMB_FRM_SZ)) {
- netdev_err(cfhsi->ndev, "%s: Invalid descriptor.\n",
- __func__);
- return -EPROTO;
- }
-
- /* Check for embedded CAIF frame. */
- if (desc->offset) {
- struct sk_buff *skb;
- int len = 0;
- pfrm = ((u8 *)desc) + desc->offset;
-
- /* Remove offset padding. */
- pfrm += *pfrm + 1;
-
- /* Read length of CAIF frame (little endian). */
- len = *pfrm;
- len |= ((*(pfrm+1)) << 8) & 0xFF00;
- len += 2; /* Add FCS fields. */
-
- /* Sanity check length of CAIF frame. */
- if (unlikely(len > CFHSI_MAX_CAIF_FRAME_SZ)) {
- netdev_err(cfhsi->ndev, "%s: Invalid length.\n",
- __func__);
- return -EPROTO;
- }
-
- /* Allocate SKB (OK even in IRQ context). */
- skb = alloc_skb(len + 1, GFP_ATOMIC);
- if (!skb) {
- netdev_err(cfhsi->ndev, "%s: Out of memory !\n",
- __func__);
- return -ENOMEM;
- }
- caif_assert(skb != NULL);
-
- skb_put_data(skb, pfrm, len);
-
- skb->protocol = htons(ETH_P_CAIF);
- skb_reset_mac_header(skb);
- skb->dev = cfhsi->ndev;
-
- netif_rx_any_context(skb);
-
- /* Update network statistics. */
- cfhsi->ndev->stats.rx_packets++;
- cfhsi->ndev->stats.rx_bytes += len;
- }
-
- /* Calculate transfer length. */
- plen = desc->cffrm_len;
- while (nfrms < CFHSI_MAX_PKTS && *plen) {
- xfer_sz += *plen;
- plen++;
- nfrms++;
- }
-
- /* Check for piggy-backed descriptor. */
- if (desc->header & CFHSI_PIGGY_DESC)
- xfer_sz += CFHSI_DESC_SZ;
-
- if ((xfer_sz % 4) || (xfer_sz > (CFHSI_BUF_SZ_RX - CFHSI_DESC_SZ))) {
- netdev_err(cfhsi->ndev,
- "%s: Invalid payload len: %d, ignored.\n",
- __func__, xfer_sz);
- return -EPROTO;
- }
- return xfer_sz;
-}
-
-static int cfhsi_rx_desc_len(struct cfhsi_desc *desc)
-{
- int xfer_sz = 0;
- int nfrms = 0;
- u16 *plen;
-
- if ((desc->header & ~CFHSI_PIGGY_DESC) ||
- (desc->offset > CFHSI_MAX_EMB_FRM_SZ)) {
-
- pr_err("Invalid descriptor. %x %x\n", desc->header,
- desc->offset);
- return -EPROTO;
- }
-
- /* Calculate transfer length. */
- plen = desc->cffrm_len;
- while (nfrms < CFHSI_MAX_PKTS && *plen) {
- xfer_sz += *plen;
- plen++;
- nfrms++;
- }
-
- if (xfer_sz % 4) {
- pr_err("Invalid payload len: %d, ignored.\n", xfer_sz);
- return -EPROTO;
- }
- return xfer_sz;
-}
-
-static int cfhsi_rx_pld(struct cfhsi_desc *desc, struct cfhsi *cfhsi)
-{
- int rx_sz = 0;
- int nfrms = 0;
- u16 *plen = NULL;
- u8 *pfrm = NULL;
-
- /* Sanity check header and offset. */
- if (WARN_ON((desc->header & ~CFHSI_PIGGY_DESC) ||
- (desc->offset > CFHSI_MAX_EMB_FRM_SZ))) {
- netdev_err(cfhsi->ndev, "%s: Invalid descriptor.\n",
- __func__);
- return -EPROTO;
- }
-
- /* Set frame pointer to start of payload. */
- pfrm = desc->emb_frm + CFHSI_MAX_EMB_FRM_SZ;
- plen = desc->cffrm_len;
-
- /* Skip already processed frames. */
- while (nfrms < cfhsi->rx_state.nfrms) {
- pfrm += *plen;
- rx_sz += *plen;
- plen++;
- nfrms++;
- }
-
- /* Parse payload. */
- while (nfrms < CFHSI_MAX_PKTS && *plen) {
- struct sk_buff *skb;
- u8 *pcffrm = NULL;
- int len;
-
- /* CAIF frame starts after head padding. */
- pcffrm = pfrm + *pfrm + 1;
-
- /* Read length of CAIF frame (little endian). */
- len = *pcffrm;
- len |= ((*(pcffrm + 1)) << 8) & 0xFF00;
- len += 2; /* Add FCS fields. */
-
- /* Sanity check length of CAIF frames. */
- if (unlikely(len > CFHSI_MAX_CAIF_FRAME_SZ)) {
- netdev_err(cfhsi->ndev, "%s: Invalid length.\n",
- __func__);
- return -EPROTO;
- }
-
- /* Allocate SKB (OK even in IRQ context). */
- skb = alloc_skb(len + 1, GFP_ATOMIC);
- if (!skb) {
- netdev_err(cfhsi->ndev, "%s: Out of memory !\n",
- __func__);
- cfhsi->rx_state.nfrms = nfrms;
- return -ENOMEM;
- }
- caif_assert(skb != NULL);
-
- skb_put_data(skb, pcffrm, len);
-
- skb->protocol = htons(ETH_P_CAIF);
- skb_reset_mac_header(skb);
- skb->dev = cfhsi->ndev;
-
- netif_rx_any_context(skb);
-
- /* Update network statistics. */
- cfhsi->ndev->stats.rx_packets++;
- cfhsi->ndev->stats.rx_bytes += len;
-
- pfrm += *plen;
- rx_sz += *plen;
- plen++;
- nfrms++;
- }
-
- return rx_sz;
-}
-
-static void cfhsi_rx_done(struct cfhsi *cfhsi)
-{
- int res;
- int desc_pld_len = 0, rx_len, rx_state;
- struct cfhsi_desc *desc = NULL;
- u8 *rx_ptr, *rx_buf;
- struct cfhsi_desc *piggy_desc = NULL;
-
- desc = (struct cfhsi_desc *)cfhsi->rx_buf;
-
- netdev_dbg(cfhsi->ndev, "%s\n", __func__);
-
- if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- return;
-
- /* Update inactivity timer if pending. */
- spin_lock_bh(&cfhsi->lock);
- mod_timer_pending(&cfhsi->inactivity_timer,
- jiffies + cfhsi->cfg.inactivity_timeout);
- spin_unlock_bh(&cfhsi->lock);
-
- if (cfhsi->rx_state.state == CFHSI_RX_STATE_DESC) {
- desc_pld_len = cfhsi_rx_desc_len(desc);
-
- if (desc_pld_len < 0)
- goto out_of_sync;
-
- rx_buf = cfhsi->rx_buf;
- rx_len = desc_pld_len;
- if (desc_pld_len > 0 && (desc->header & CFHSI_PIGGY_DESC))
- rx_len += CFHSI_DESC_SZ;
- if (desc_pld_len == 0)
- rx_buf = cfhsi->rx_flip_buf;
- } else {
- rx_buf = cfhsi->rx_flip_buf;
-
- rx_len = CFHSI_DESC_SZ;
- if (cfhsi->rx_state.pld_len > 0 &&
- (desc->header & CFHSI_PIGGY_DESC)) {
-
- piggy_desc = (struct cfhsi_desc *)
- (desc->emb_frm + CFHSI_MAX_EMB_FRM_SZ +
- cfhsi->rx_state.pld_len);
-
- cfhsi->rx_state.piggy_desc = true;
-
- /* Extract payload len from piggy-backed descriptor. */
- desc_pld_len = cfhsi_rx_desc_len(piggy_desc);
- if (desc_pld_len < 0)
- goto out_of_sync;
-
- if (desc_pld_len > 0) {
- rx_len = desc_pld_len;
- if (piggy_desc->header & CFHSI_PIGGY_DESC)
- rx_len += CFHSI_DESC_SZ;
- }
-
- /*
- * Copy needed information from the piggy-backed
- * descriptor to the descriptor in the start.
- */
- memcpy(rx_buf, (u8 *)piggy_desc,
- CFHSI_DESC_SHORT_SZ);
- }
- }
-
- if (desc_pld_len) {
- rx_state = CFHSI_RX_STATE_PAYLOAD;
- rx_ptr = rx_buf + CFHSI_DESC_SZ;
- } else {
- rx_state = CFHSI_RX_STATE_DESC;
- rx_ptr = rx_buf;
- rx_len = CFHSI_DESC_SZ;
- }
-
- /* Initiate next read */
- if (test_bit(CFHSI_AWAKE, &cfhsi->bits)) {
- /* Set up new transfer. */
- netdev_dbg(cfhsi->ndev, "%s: Start RX.\n",
- __func__);
-
- res = cfhsi->ops->cfhsi_rx(rx_ptr, rx_len,
- cfhsi->ops);
- if (WARN_ON(res < 0)) {
- netdev_err(cfhsi->ndev, "%s: RX error %d.\n",
- __func__, res);
- cfhsi->ndev->stats.rx_errors++;
- cfhsi->ndev->stats.rx_dropped++;
- }
- }
-
- if (cfhsi->rx_state.state == CFHSI_RX_STATE_DESC) {
- /* Extract payload from descriptor */
- if (cfhsi_rx_desc(desc, cfhsi) < 0)
- goto out_of_sync;
- } else {
- /* Extract payload */
- if (cfhsi_rx_pld(desc, cfhsi) < 0)
- goto out_of_sync;
- if (piggy_desc) {
- /* Extract any payload in piggyback descriptor. */
- if (cfhsi_rx_desc(piggy_desc, cfhsi) < 0)
- goto out_of_sync;
- /* Mark no embedded frame after extracting it */
- piggy_desc->offset = 0;
- }
- }
-
- /* Update state info */
- memset(&cfhsi->rx_state, 0, sizeof(cfhsi->rx_state));
- cfhsi->rx_state.state = rx_state;
- cfhsi->rx_ptr = rx_ptr;
- cfhsi->rx_len = rx_len;
- cfhsi->rx_state.pld_len = desc_pld_len;
- cfhsi->rx_state.piggy_desc = desc->header & CFHSI_PIGGY_DESC;
-
- if (rx_buf != cfhsi->rx_buf)
- swap(cfhsi->rx_buf, cfhsi->rx_flip_buf);
- return;
-
-out_of_sync:
- netdev_err(cfhsi->ndev, "%s: Out of sync.\n", __func__);
- print_hex_dump_bytes("--> ", DUMP_PREFIX_NONE,
- cfhsi->rx_buf, CFHSI_DESC_SZ);
- schedule_work(&cfhsi->out_of_sync_work);
-}
-
-static void cfhsi_rx_slowpath(struct timer_list *t)
-{
- struct cfhsi *cfhsi = from_timer(cfhsi, t, rx_slowpath_timer);
-
- netdev_dbg(cfhsi->ndev, "%s.\n",
- __func__);
-
- cfhsi_rx_done(cfhsi);
-}
-
-static void cfhsi_rx_done_cb(struct cfhsi_cb_ops *cb_ops)
-{
- struct cfhsi *cfhsi;
-
- cfhsi = container_of(cb_ops, struct cfhsi, cb_ops);
- netdev_dbg(cfhsi->ndev, "%s.\n",
- __func__);
-
- if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- return;
-
- if (test_and_clear_bit(CFHSI_FLUSH_FIFO, &cfhsi->bits))
- wake_up_interruptible(&cfhsi->flush_fifo_wait);
- else
- cfhsi_rx_done(cfhsi);
-}
-
-static void cfhsi_wake_up(struct work_struct *work)
-{
- struct cfhsi *cfhsi = NULL;
- int res;
- int len;
- long ret;
-
- cfhsi = container_of(work, struct cfhsi, wake_up_work);
-
- if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- return;
-
- if (unlikely(test_bit(CFHSI_AWAKE, &cfhsi->bits))) {
- /* It happenes when wakeup is requested by
- * both ends at the same time. */
- clear_bit(CFHSI_WAKE_UP, &cfhsi->bits);
- clear_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits);
- return;
- }
-
- /* Activate wake line. */
- cfhsi->ops->cfhsi_wake_up(cfhsi->ops);
-
- netdev_dbg(cfhsi->ndev, "%s: Start waiting.\n",
- __func__);
-
- /* Wait for acknowledge. */
- ret = CFHSI_WAKE_TOUT;
- ret = wait_event_interruptible_timeout(cfhsi->wake_up_wait,
- test_and_clear_bit(CFHSI_WAKE_UP_ACK,
- &cfhsi->bits), ret);
- if (unlikely(ret < 0)) {
- /* Interrupted by signal. */
- netdev_err(cfhsi->ndev, "%s: Signalled: %ld.\n",
- __func__, ret);
-
- clear_bit(CFHSI_WAKE_UP, &cfhsi->bits);
- cfhsi->ops->cfhsi_wake_down(cfhsi->ops);
- return;
- } else if (!ret) {
- bool ca_wake = false;
- size_t fifo_occupancy = 0;
-
- /* Wakeup timeout */
- netdev_dbg(cfhsi->ndev, "%s: Timeout.\n",
- __func__);
-
- /* Check FIFO to check if modem has sent something. */
- WARN_ON(cfhsi->ops->cfhsi_fifo_occupancy(cfhsi->ops,
- &fifo_occupancy));
-
- netdev_dbg(cfhsi->ndev, "%s: Bytes in FIFO: %u.\n",
- __func__, (unsigned) fifo_occupancy);
-
- /* Check if we misssed the interrupt. */
- WARN_ON(cfhsi->ops->cfhsi_get_peer_wake(cfhsi->ops,
- &ca_wake));
-
- if (ca_wake) {
- netdev_err(cfhsi->ndev, "%s: CA Wake missed !.\n",
- __func__);
-
- /* Clear the CFHSI_WAKE_UP_ACK bit to prevent race. */
- clear_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits);
-
- /* Continue execution. */
- goto wake_ack;
- }
-
- clear_bit(CFHSI_WAKE_UP, &cfhsi->bits);
- cfhsi->ops->cfhsi_wake_down(cfhsi->ops);
- return;
- }
-wake_ack:
- netdev_dbg(cfhsi->ndev, "%s: Woken.\n",
- __func__);
-
- /* Clear power up bit. */
- set_bit(CFHSI_AWAKE, &cfhsi->bits);
- clear_bit(CFHSI_WAKE_UP, &cfhsi->bits);
-
- /* Resume read operation. */
- netdev_dbg(cfhsi->ndev, "%s: Start RX.\n", __func__);
- res = cfhsi->ops->cfhsi_rx(cfhsi->rx_ptr, cfhsi->rx_len, cfhsi->ops);
-
- if (WARN_ON(res < 0))
- netdev_err(cfhsi->ndev, "%s: RX err %d.\n", __func__, res);
-
- /* Clear power up acknowledment. */
- clear_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits);
-
- spin_lock_bh(&cfhsi->lock);
-
- /* Resume transmit if queues are not empty. */
- if (!cfhsi_tx_queue_len(cfhsi)) {
- netdev_dbg(cfhsi->ndev, "%s: Peer wake, start timer.\n",
- __func__);
- /* Start inactivity timer. */
- mod_timer(&cfhsi->inactivity_timer,
- jiffies + cfhsi->cfg.inactivity_timeout);
- spin_unlock_bh(&cfhsi->lock);
- return;
- }
-
- netdev_dbg(cfhsi->ndev, "%s: Host wake.\n",
- __func__);
-
- spin_unlock_bh(&cfhsi->lock);
-
- /* Create HSI frame. */
- len = cfhsi_tx_frm((struct cfhsi_desc *)cfhsi->tx_buf, cfhsi);
-
- if (likely(len > 0)) {
- /* Set up new transfer. */
- res = cfhsi->ops->cfhsi_tx(cfhsi->tx_buf, len, cfhsi->ops);
- if (WARN_ON(res < 0)) {
- netdev_err(cfhsi->ndev, "%s: TX error %d.\n",
- __func__, res);
- cfhsi_abort_tx(cfhsi);
- }
- } else {
- netdev_err(cfhsi->ndev,
- "%s: Failed to create HSI frame: %d.\n",
- __func__, len);
- }
-}
-
-static void cfhsi_wake_down(struct work_struct *work)
-{
- long ret;
- struct cfhsi *cfhsi = NULL;
- size_t fifo_occupancy = 0;
- int retry = CFHSI_WAKE_TOUT;
-
- cfhsi = container_of(work, struct cfhsi, wake_down_work);
- netdev_dbg(cfhsi->ndev, "%s.\n", __func__);
-
- if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- return;
-
- /* Deactivate wake line. */
- cfhsi->ops->cfhsi_wake_down(cfhsi->ops);
-
- /* Wait for acknowledge. */
- ret = CFHSI_WAKE_TOUT;
- ret = wait_event_interruptible_timeout(cfhsi->wake_down_wait,
- test_and_clear_bit(CFHSI_WAKE_DOWN_ACK,
- &cfhsi->bits), ret);
- if (ret < 0) {
- /* Interrupted by signal. */
- netdev_err(cfhsi->ndev, "%s: Signalled: %ld.\n",
- __func__, ret);
- return;
- } else if (!ret) {
- bool ca_wake = true;
-
- /* Timeout */
- netdev_err(cfhsi->ndev, "%s: Timeout.\n", __func__);
-
- /* Check if we misssed the interrupt. */
- WARN_ON(cfhsi->ops->cfhsi_get_peer_wake(cfhsi->ops,
- &ca_wake));
- if (!ca_wake)
- netdev_err(cfhsi->ndev, "%s: CA Wake missed !.\n",
- __func__);
- }
-
- /* Check FIFO occupancy. */
- while (retry) {
- WARN_ON(cfhsi->ops->cfhsi_fifo_occupancy(cfhsi->ops,
- &fifo_occupancy));
-
- if (!fifo_occupancy)
- break;
-
- set_current_state(TASK_INTERRUPTIBLE);
- schedule_timeout(1);
- retry--;
- }
-
- if (!retry)
- netdev_err(cfhsi->ndev, "%s: FIFO Timeout.\n", __func__);
-
- /* Clear AWAKE condition. */
- clear_bit(CFHSI_AWAKE, &cfhsi->bits);
-
- /* Cancel pending RX requests. */
- cfhsi->ops->cfhsi_rx_cancel(cfhsi->ops);
-}
-
-static void cfhsi_out_of_sync(struct work_struct *work)
-{
- struct cfhsi *cfhsi = NULL;
-
- cfhsi = container_of(work, struct cfhsi, out_of_sync_work);
-
- rtnl_lock();
- dev_close(cfhsi->ndev);
- rtnl_unlock();
-}
-
-static void cfhsi_wake_up_cb(struct cfhsi_cb_ops *cb_ops)
-{
- struct cfhsi *cfhsi = NULL;
-
- cfhsi = container_of(cb_ops, struct cfhsi, cb_ops);
- netdev_dbg(cfhsi->ndev, "%s.\n",
- __func__);
-
- set_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits);
- wake_up_interruptible(&cfhsi->wake_up_wait);
-
- if (test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))
- return;
-
- /* Schedule wake up work queue if the peer initiates. */
- if (!test_and_set_bit(CFHSI_WAKE_UP, &cfhsi->bits))
- queue_work(cfhsi->wq, &cfhsi->wake_up_work);
-}
-
-static void cfhsi_wake_down_cb(struct cfhsi_cb_ops *cb_ops)
-{
- struct cfhsi *cfhsi = NULL;
-
- cfhsi = container_of(cb_ops, struct cfhsi, cb_ops);
- netdev_dbg(cfhsi->ndev, "%s.\n",
- __func__);
-
- /* Initiating low power is only permitted by the host (us). */
- set_bit(CFHSI_WAKE_DOWN_ACK, &cfhsi->bits);
- wake_up_interruptible(&cfhsi->wake_down_wait);
-}
-
-static void cfhsi_aggregation_tout(struct timer_list *t)
-{
- struct cfhsi *cfhsi = from_timer(cfhsi, t, aggregation_timer);
-
- netdev_dbg(cfhsi->ndev, "%s.\n",
- __func__);
-
- cfhsi_start_tx(cfhsi);
-}
-
-static netdev_tx_t cfhsi_xmit(struct sk_buff *skb, struct net_device *dev)
-{
- struct cfhsi *cfhsi = NULL;
- int start_xfer = 0;
- int timer_active;
- int prio;
-
- if (!dev)
- return -EINVAL;
-
- cfhsi = netdev_priv(dev);
-
- switch (skb->priority) {
- case TC_PRIO_BESTEFFORT:
- case TC_PRIO_FILLER:
- case TC_PRIO_BULK:
- prio = CFHSI_PRIO_BEBK;
- break;
- case TC_PRIO_INTERACTIVE_BULK:
- prio = CFHSI_PRIO_VI;
- break;
- case TC_PRIO_INTERACTIVE:
- prio = CFHSI_PRIO_VO;
- break;
- case TC_PRIO_CONTROL:
- default:
- prio = CFHSI_PRIO_CTL;
- break;
- }
-
- spin_lock_bh(&cfhsi->lock);
-
- /* Update aggregation statistics */
- cfhsi_update_aggregation_stats(cfhsi, skb, 1);
-
- /* Queue the SKB */
- skb_queue_tail(&cfhsi->qhead[prio], skb);
-
- /* Sanity check; xmit should not be called after unregister_netdev */
- if (WARN_ON(test_bit(CFHSI_SHUTDOWN, &cfhsi->bits))) {
- spin_unlock_bh(&cfhsi->lock);
- cfhsi_abort_tx(cfhsi);
- return -EINVAL;
- }
-
- /* Send flow off if number of packets is above high water mark. */
- if (!cfhsi->flow_off_sent &&
- cfhsi_tx_queue_len(cfhsi) > cfhsi->cfg.q_high_mark &&
- cfhsi->cfdev.flowctrl) {
- cfhsi->flow_off_sent = 1;
- cfhsi->cfdev.flowctrl(cfhsi->ndev, OFF);
- }
-
- if (cfhsi->tx_state == CFHSI_TX_STATE_IDLE) {
- cfhsi->tx_state = CFHSI_TX_STATE_XFER;
- start_xfer = 1;
- }
-
- if (!start_xfer) {
- /* Send aggregate if it is possible */
- bool aggregate_ready =
- cfhsi_can_send_aggregate(cfhsi) &&
- del_timer(&cfhsi->aggregation_timer) > 0;
- spin_unlock_bh(&cfhsi->lock);
- if (aggregate_ready)
- cfhsi_start_tx(cfhsi);
- return NETDEV_TX_OK;
- }
-
- /* Delete inactivity timer if started. */
- timer_active = del_timer_sync(&cfhsi->inactivity_timer);
-
- spin_unlock_bh(&cfhsi->lock);
-
- if (timer_active) {
- struct cfhsi_desc *desc = (struct cfhsi_desc *)cfhsi->tx_buf;
- int len;
- int res;
-
- /* Create HSI frame. */
- len = cfhsi_tx_frm(desc, cfhsi);
- WARN_ON(!len);
-
- /* Set up new transfer. */
- res = cfhsi->ops->cfhsi_tx(cfhsi->tx_buf, len, cfhsi->ops);
- if (WARN_ON(res < 0)) {
- netdev_err(cfhsi->ndev, "%s: TX error %d.\n",
- __func__, res);
- cfhsi_abort_tx(cfhsi);
- }
- } else {
- /* Schedule wake up work queue if the we initiate. */
- if (!test_and_set_bit(CFHSI_WAKE_UP, &cfhsi->bits))
- queue_work(cfhsi->wq, &cfhsi->wake_up_work);
- }
-
- return NETDEV_TX_OK;
-}
-
-static const struct net_device_ops cfhsi_netdevops;
-
-static void cfhsi_setup(struct net_device *dev)
-{
- int i;
- struct cfhsi *cfhsi = netdev_priv(dev);
- dev->features = 0;
- dev->type = ARPHRD_CAIF;
- dev->flags = IFF_POINTOPOINT | IFF_NOARP;
- dev->mtu = CFHSI_MAX_CAIF_FRAME_SZ;
- dev->priv_flags |= IFF_NO_QUEUE;
- dev->needs_free_netdev = true;
- dev->netdev_ops = &cfhsi_netdevops;
- for (i = 0; i < CFHSI_PRIO_LAST; ++i)
- skb_queue_head_init(&cfhsi->qhead[i]);
- cfhsi->cfdev.link_select = CAIF_LINK_HIGH_BANDW;
- cfhsi->cfdev.use_frag = false;
- cfhsi->cfdev.use_stx = false;
- cfhsi->cfdev.use_fcs = false;
- cfhsi->ndev = dev;
- cfhsi->cfg = hsi_default_config;
-}
-
-static int cfhsi_open(struct net_device *ndev)
-{
- struct cfhsi *cfhsi = netdev_priv(ndev);
- int res;
-
- clear_bit(CFHSI_SHUTDOWN, &cfhsi->bits);
-
- /* Initialize state vaiables. */
- cfhsi->tx_state = CFHSI_TX_STATE_IDLE;
- cfhsi->rx_state.state = CFHSI_RX_STATE_DESC;
-
- /* Set flow info */
- cfhsi->flow_off_sent = 0;
-
- /*
- * Allocate a TX buffer with the size of a HSI packet descriptors
- * and the necessary room for CAIF payload frames.
- */
- cfhsi->tx_buf = kzalloc(CFHSI_BUF_SZ_TX, GFP_KERNEL);
- if (!cfhsi->tx_buf) {
- res = -ENODEV;
- goto err_alloc_tx;
- }
-
- /*
- * Allocate a RX buffer with the size of two HSI packet descriptors and
- * the necessary room for CAIF payload frames.
- */
- cfhsi->rx_buf = kzalloc(CFHSI_BUF_SZ_RX, GFP_KERNEL);
- if (!cfhsi->rx_buf) {
- res = -ENODEV;
- goto err_alloc_rx;
- }
-
- cfhsi->rx_flip_buf = kzalloc(CFHSI_BUF_SZ_RX, GFP_KERNEL);
- if (!cfhsi->rx_flip_buf) {
- res = -ENODEV;
- goto err_alloc_rx_flip;
- }
-
- /* Initialize aggregation timeout */
- cfhsi->cfg.aggregation_timeout = hsi_default_config.aggregation_timeout;
-
- /* Initialize recieve vaiables. */
- cfhsi->rx_ptr = cfhsi->rx_buf;
- cfhsi->rx_len = CFHSI_DESC_SZ;
-
- /* Initialize spin locks. */
- spin_lock_init(&cfhsi->lock);
-
- /* Set up the driver. */
- cfhsi->cb_ops.tx_done_cb = cfhsi_tx_done_cb;
- cfhsi->cb_ops.rx_done_cb = cfhsi_rx_done_cb;
- cfhsi->cb_ops.wake_up_cb = cfhsi_wake_up_cb;
- cfhsi->cb_ops.wake_down_cb = cfhsi_wake_down_cb;
-
- /* Initialize the work queues. */
- INIT_WORK(&cfhsi->wake_up_work, cfhsi_wake_up);
- INIT_WORK(&cfhsi->wake_down_work, cfhsi_wake_down);
- INIT_WORK(&cfhsi->out_of_sync_work, cfhsi_out_of_sync);
-
- /* Clear all bit fields. */
- clear_bit(CFHSI_WAKE_UP_ACK, &cfhsi->bits);
- clear_bit(CFHSI_WAKE_DOWN_ACK, &cfhsi->bits);
- clear_bit(CFHSI_WAKE_UP, &cfhsi->bits);
- clear_bit(CFHSI_AWAKE, &cfhsi->bits);
-
- /* Create work thread. */
- cfhsi->wq = alloc_ordered_workqueue(cfhsi->ndev->name, WQ_MEM_RECLAIM);
- if (!cfhsi->wq) {
- netdev_err(cfhsi->ndev, "%s: Failed to create work queue.\n",
- __func__);
- res = -ENODEV;
- goto err_create_wq;
- }
-
- /* Initialize wait queues. */
- init_waitqueue_head(&cfhsi->wake_up_wait);
- init_waitqueue_head(&cfhsi->wake_down_wait);
- init_waitqueue_head(&cfhsi->flush_fifo_wait);
-
- /* Setup the inactivity timer. */
- timer_setup(&cfhsi->inactivity_timer, cfhsi_inactivity_tout, 0);
- /* Setup the slowpath RX timer. */
- timer_setup(&cfhsi->rx_slowpath_timer, cfhsi_rx_slowpath, 0);
- /* Setup the aggregation timer. */
- timer_setup(&cfhsi->aggregation_timer, cfhsi_aggregation_tout, 0);
-
- /* Activate HSI interface. */
- res = cfhsi->ops->cfhsi_up(cfhsi->ops);
- if (res) {
- netdev_err(cfhsi->ndev,
- "%s: can't activate HSI interface: %d.\n",
- __func__, res);
- goto err_activate;
- }
-
- /* Flush FIFO */
- res = cfhsi_flush_fifo(cfhsi);
- if (res) {
- netdev_err(cfhsi->ndev, "%s: Can't flush FIFO: %d.\n",
- __func__, res);
- goto err_net_reg;
- }
- return res;
-
- err_net_reg:
- cfhsi->ops->cfhsi_down(cfhsi->ops);
- err_activate:
- destroy_workqueue(cfhsi->wq);
- err_create_wq:
- kfree(cfhsi->rx_flip_buf);
- err_alloc_rx_flip:
- kfree(cfhsi->rx_buf);
- err_alloc_rx:
- kfree(cfhsi->tx_buf);
- err_alloc_tx:
- return res;
-}
-
-static int cfhsi_close(struct net_device *ndev)
-{
- struct cfhsi *cfhsi = netdev_priv(ndev);
- u8 *tx_buf, *rx_buf, *flip_buf;
-
- /* going to shutdown driver */
- set_bit(CFHSI_SHUTDOWN, &cfhsi->bits);
-
- /* Delete timers if pending */
- del_timer_sync(&cfhsi->inactivity_timer);
- del_timer_sync(&cfhsi->rx_slowpath_timer);
- del_timer_sync(&cfhsi->aggregation_timer);
-
- /* Cancel pending RX request (if any) */
- cfhsi->ops->cfhsi_rx_cancel(cfhsi->ops);
-
- /* Destroy workqueue */
- destroy_workqueue(cfhsi->wq);
-
- /* Store bufferes: will be freed later. */
- tx_buf = cfhsi->tx_buf;
- rx_buf = cfhsi->rx_buf;
- flip_buf = cfhsi->rx_flip_buf;
- /* Flush transmit queues. */
- cfhsi_abort_tx(cfhsi);
-
- /* Deactivate interface */
- cfhsi->ops->cfhsi_down(cfhsi->ops);
-
- /* Free buffers. */
- kfree(tx_buf);
- kfree(rx_buf);
- kfree(flip_buf);
- return 0;
-}
-
-static void cfhsi_uninit(struct net_device *dev)
-{
- struct cfhsi *cfhsi = netdev_priv(dev);
- ASSERT_RTNL();
- symbol_put(cfhsi_get_device);
- list_del(&cfhsi->list);
-}
-
-static const struct net_device_ops cfhsi_netdevops = {
- .ndo_uninit = cfhsi_uninit,
- .ndo_open = cfhsi_open,
- .ndo_stop = cfhsi_close,
- .ndo_start_xmit = cfhsi_xmit
-};
-
-static void cfhsi_netlink_parms(struct nlattr *data[], struct cfhsi *cfhsi)
-{
- int i;
-
- if (!data) {
- pr_debug("no params data found\n");
- return;
- }
-
- i = __IFLA_CAIF_HSI_INACTIVITY_TOUT;
- /*
- * Inactivity timeout in millisecs. Lowest possible value is 1,
- * and highest possible is NEXT_TIMER_MAX_DELTA.
- */
- if (data[i]) {
- u32 inactivity_timeout = nla_get_u32(data[i]);
- /* Pre-calculate inactivity timeout. */
- cfhsi->cfg.inactivity_timeout = inactivity_timeout * HZ / 1000;
- if (cfhsi->cfg.inactivity_timeout == 0)
- cfhsi->cfg.inactivity_timeout = 1;
- else if (cfhsi->cfg.inactivity_timeout > NEXT_TIMER_MAX_DELTA)
- cfhsi->cfg.inactivity_timeout = NEXT_TIMER_MAX_DELTA;
- }
-
- i = __IFLA_CAIF_HSI_AGGREGATION_TOUT;
- if (data[i])
- cfhsi->cfg.aggregation_timeout = nla_get_u32(data[i]);
-
- i = __IFLA_CAIF_HSI_HEAD_ALIGN;
- if (data[i])
- cfhsi->cfg.head_align = nla_get_u32(data[i]);
-
- i = __IFLA_CAIF_HSI_TAIL_ALIGN;
- if (data[i])
- cfhsi->cfg.tail_align = nla_get_u32(data[i]);
-
- i = __IFLA_CAIF_HSI_QHIGH_WATERMARK;
- if (data[i])
- cfhsi->cfg.q_high_mark = nla_get_u32(data[i]);
-
- i = __IFLA_CAIF_HSI_QLOW_WATERMARK;
- if (data[i])
- cfhsi->cfg.q_low_mark = nla_get_u32(data[i]);
-}
-
-static int caif_hsi_changelink(struct net_device *dev, struct nlattr *tb[],
- struct nlattr *data[],
- struct netlink_ext_ack *extack)
-{
- cfhsi_netlink_parms(data, netdev_priv(dev));
- netdev_state_change(dev);
- return 0;
-}
-
-static const struct nla_policy caif_hsi_policy[__IFLA_CAIF_HSI_MAX + 1] = {
- [__IFLA_CAIF_HSI_INACTIVITY_TOUT] = { .type = NLA_U32, .len = 4 },
- [__IFLA_CAIF_HSI_AGGREGATION_TOUT] = { .type = NLA_U32, .len = 4 },
- [__IFLA_CAIF_HSI_HEAD_ALIGN] = { .type = NLA_U32, .len = 4 },
- [__IFLA_CAIF_HSI_TAIL_ALIGN] = { .type = NLA_U32, .len = 4 },
- [__IFLA_CAIF_HSI_QHIGH_WATERMARK] = { .type = NLA_U32, .len = 4 },
- [__IFLA_CAIF_HSI_QLOW_WATERMARK] = { .type = NLA_U32, .len = 4 },
-};
-
-static size_t caif_hsi_get_size(const struct net_device *dev)
-{
- int i;
- size_t s = 0;
- for (i = __IFLA_CAIF_HSI_UNSPEC + 1; i < __IFLA_CAIF_HSI_MAX; i++)
- s += nla_total_size(caif_hsi_policy[i].len);
- return s;
-}
-
-static int caif_hsi_fill_info(struct sk_buff *skb, const struct net_device *dev)
-{
- struct cfhsi *cfhsi = netdev_priv(dev);
-
- if (nla_put_u32(skb, __IFLA_CAIF_HSI_INACTIVITY_TOUT,
- cfhsi->cfg.inactivity_timeout) ||
- nla_put_u32(skb, __IFLA_CAIF_HSI_AGGREGATION_TOUT,
- cfhsi->cfg.aggregation_timeout) ||
- nla_put_u32(skb, __IFLA_CAIF_HSI_HEAD_ALIGN,
- cfhsi->cfg.head_align) ||
- nla_put_u32(skb, __IFLA_CAIF_HSI_TAIL_ALIGN,
- cfhsi->cfg.tail_align) ||
- nla_put_u32(skb, __IFLA_CAIF_HSI_QHIGH_WATERMARK,
- cfhsi->cfg.q_high_mark) ||
- nla_put_u32(skb, __IFLA_CAIF_HSI_QLOW_WATERMARK,
- cfhsi->cfg.q_low_mark))
- return -EMSGSIZE;
-
- return 0;
-}
-
-static int caif_hsi_newlink(struct net *src_net, struct net_device *dev,
- struct nlattr *tb[], struct nlattr *data[],
- struct netlink_ext_ack *extack)
-{
- struct cfhsi *cfhsi = NULL;
- struct cfhsi_ops *(*get_ops)(void);
-
- ASSERT_RTNL();
-
- cfhsi = netdev_priv(dev);
- cfhsi_netlink_parms(data, cfhsi);
-
- get_ops = symbol_get(cfhsi_get_ops);
- if (!get_ops) {
- pr_err("%s: failed to get the cfhsi_ops\n", __func__);
- return -ENODEV;
- }
-
- /* Assign the HSI device. */
- cfhsi->ops = (*get_ops)();
- if (!cfhsi->ops) {
- pr_err("%s: failed to get the cfhsi_ops\n", __func__);
- goto err;
- }
-
- /* Assign the driver to this HSI device. */
- cfhsi->ops->cb_ops = &cfhsi->cb_ops;
- if (register_netdevice(dev)) {
- pr_warn("%s: caif_hsi device registration failed\n", __func__);
- goto err;
- }
- /* Add CAIF HSI device to list. */
- list_add_tail(&cfhsi->list, &cfhsi_list);
-
- return 0;
-err:
- symbol_put(cfhsi_get_ops);
- return -ENODEV;
-}
-
-static struct rtnl_link_ops caif_hsi_link_ops __read_mostly = {
- .kind = "cfhsi",
- .priv_size = sizeof(struct cfhsi),
- .setup = cfhsi_setup,
- .maxtype = __IFLA_CAIF_HSI_MAX,
- .policy = caif_hsi_policy,
- .newlink = caif_hsi_newlink,
- .changelink = caif_hsi_changelink,
- .get_size = caif_hsi_get_size,
- .fill_info = caif_hsi_fill_info,
-};
-
-static void __exit cfhsi_exit_module(void)
-{
- struct list_head *list_node;
- struct list_head *n;
- struct cfhsi *cfhsi;
-
- rtnl_link_unregister(&caif_hsi_link_ops);
-
- rtnl_lock();
- list_for_each_safe(list_node, n, &cfhsi_list) {
- cfhsi = list_entry(list_node, struct cfhsi, list);
- unregister_netdevice(cfhsi->ndev);
- }
- rtnl_unlock();
-}
-
-static int __init cfhsi_init_module(void)
-{
- return rtnl_link_register(&caif_hsi_link_ops);
-}
-
-module_init(cfhsi_init_module);
-module_exit(cfhsi_exit_module);
if (of_property_read_u32(port, "reg",
&port_num))
continue;
- if (!(dev->port_mask & BIT(port_num)))
+ if (!(dev->port_mask & BIT(port_num))) {
+ of_node_put(port);
return -EINVAL;
+ }
of_get_phy_mode(port,
&dev->ports[port_num].interface);
}
.port_set_speed_duplex = mv88e6341_port_set_speed_duplex,
.port_max_speed_mode = mv88e6341_port_max_speed_mode,
.port_tag_remap = mv88e6095_port_tag_remap,
+ .port_set_policy = mv88e6352_port_set_policy,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
.port_set_ucast_flood = mv88e6352_port_set_ucast_flood,
.port_set_mcast_flood = mv88e6352_port_set_mcast_flood,
.port_set_cmode = mv88e6341_port_set_cmode,
.port_setup_message_port = mv88e6xxx_setup_message_port,
.stats_snapshot = mv88e6390_g1_stats_snapshot,
- .stats_set_histogram = mv88e6095_g1_stats_set_histogram,
+ .stats_set_histogram = mv88e6390_g1_stats_set_histogram,
.stats_get_sset_count = mv88e6320_stats_get_sset_count,
.stats_get_strings = mv88e6320_stats_get_strings,
.stats_get_stats = mv88e6390_stats_get_stats,
.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
.pot_clear = mv88e6xxx_g2_pot_clear,
.reset = mv88e6352_g1_reset,
+ .rmu_disable = mv88e6390_g1_rmu_disable,
+ .atu_get_hash = mv88e6165_g1_atu_get_hash,
+ .atu_set_hash = mv88e6165_g1_atu_set_hash,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
.serdes_power = mv88e6390_serdes_power,
.serdes_irq_enable = mv88e6390_serdes_irq_enable,
.serdes_irq_status = mv88e6390_serdes_irq_status,
.gpio_ops = &mv88e6352_gpio_ops,
+ .serdes_get_sset_count = mv88e6390_serdes_get_sset_count,
+ .serdes_get_strings = mv88e6390_serdes_get_strings,
+ .serdes_get_stats = mv88e6390_serdes_get_stats,
+ .serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
+ .serdes_get_regs = mv88e6390_serdes_get_regs,
.phylink_validate = mv88e6341_phylink_validate,
};
.port_set_speed_duplex = mv88e6341_port_set_speed_duplex,
.port_max_speed_mode = mv88e6341_port_max_speed_mode,
.port_tag_remap = mv88e6095_port_tag_remap,
+ .port_set_policy = mv88e6352_port_set_policy,
.port_set_frame_mode = mv88e6351_port_set_frame_mode,
.port_set_ucast_flood = mv88e6352_port_set_ucast_flood,
.port_set_mcast_flood = mv88e6352_port_set_mcast_flood,
.port_set_cmode = mv88e6341_port_set_cmode,
.port_setup_message_port = mv88e6xxx_setup_message_port,
.stats_snapshot = mv88e6390_g1_stats_snapshot,
- .stats_set_histogram = mv88e6095_g1_stats_set_histogram,
+ .stats_set_histogram = mv88e6390_g1_stats_set_histogram,
.stats_get_sset_count = mv88e6320_stats_get_sset_count,
.stats_get_strings = mv88e6320_stats_get_strings,
.stats_get_stats = mv88e6390_stats_get_stats,
.mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu,
.pot_clear = mv88e6xxx_g2_pot_clear,
.reset = mv88e6352_g1_reset,
+ .rmu_disable = mv88e6390_g1_rmu_disable,
+ .atu_get_hash = mv88e6165_g1_atu_get_hash,
+ .atu_set_hash = mv88e6165_g1_atu_set_hash,
.vtu_getnext = mv88e6352_g1_vtu_getnext,
.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
.serdes_power = mv88e6390_serdes_power,
.gpio_ops = &mv88e6352_gpio_ops,
.avb_ops = &mv88e6390_avb_ops,
.ptp_ops = &mv88e6352_ptp_ops,
+ .serdes_get_sset_count = mv88e6390_serdes_get_sset_count,
+ .serdes_get_strings = mv88e6390_serdes_get_strings,
+ .serdes_get_stats = mv88e6390_serdes_get_stats,
+ .serdes_get_regs_len = mv88e6390_serdes_get_regs_len,
+ .serdes_get_regs = mv88e6390_serdes_get_regs,
.phylink_validate = mv88e6341_phylink_validate,
};
int mv88e6390_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port)
{
- if (mv88e6390_serdes_get_lane(chip, port) < 0)
+ if (mv88e6xxx_serdes_get_lane(chip, port) < 0)
return 0;
return ARRAY_SIZE(mv88e6390_serdes_hw_stats);
struct mv88e6390_serdes_hw_stat *stat;
int i;
- if (mv88e6390_serdes_get_lane(chip, port) < 0)
+ if (mv88e6xxx_serdes_get_lane(chip, port) < 0)
return 0;
for (i = 0; i < ARRAY_SIZE(mv88e6390_serdes_hw_stats); i++) {
int lane;
int i;
- lane = mv88e6390_serdes_get_lane(chip, port);
+ lane = mv88e6xxx_serdes_get_lane(chip, port);
if (lane < 0)
return 0;
for (i = 0; i < ds->num_ports; i++) {
mac[i] = default_mac;
- if (i == dsa_upstream_port(priv->ds, i)) {
- /* STP doesn't get called for CPU port, so we need to
- * set the I/O parameters statically.
- */
- mac[i].dyn_learn = true;
- mac[i].ingress = true;
- mac[i].egress = true;
- }
+
+ /* Let sja1105_bridge_stp_state_set() keep address learning
+ * enabled for the CPU port.
+ */
+ if (dsa_is_cpu_port(ds, i))
+ priv->learn_ena |= BIT(i);
}
return 0;
int ret_val;
u16 mii_bmcr_data = BMCR_RESET;
+ if (hw->nic_type == athr_mt) {
+ hw->phy_configured = true;
+ return 0;
+ }
+
if ((atl1c_read_phy_reg(hw, MII_PHYSID1, &hw->phy_id1) != 0) ||
(atl1c_read_phy_reg(hw, MII_PHYSID2, &hw->phy_id2) != 0)) {
dev_err(&pdev->dev, "Error get phy ID\n");
switch (mode) {
case GENET_POWER_PASSIVE:
- reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS);
+ reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS |
+ EXT_ENERGY_DET_MASK);
if (GENET_IS_V5(priv)) {
reg &= ~(EXT_PWR_DOWN_PHY_EN |
EXT_PWR_DOWN_PHY_RD |
/* Returns a reusable dma control register value */
static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv)
{
+ unsigned int i;
u32 reg;
u32 dma_ctrl;
/* disable DMA */
dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN;
+ for (i = 0; i < priv->hw_params->tx_queues; i++)
+ dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
reg &= ~dma_ctrl;
bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
+ dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN;
+ for (i = 0; i < priv->hw_params->rx_queues; i++)
+ dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
reg &= ~dma_ctrl;
bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
{
struct bcmgenet_priv *priv = netdev_priv(dev);
unsigned long dma_ctrl;
- u32 reg;
int ret;
netif_dbg(priv, ifup, dev, "bcmgenet_open\n");
bcmgenet_set_hw_addr(priv, dev->dev_addr);
- if (priv->internal_phy) {
- reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
- reg |= EXT_ENERGY_DET_MASK;
- bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
- }
-
/* Disable RX/TX DMA and flush TX queues */
dma_ctrl = bcmgenet_dma_disable(priv);
struct bcmgenet_priv *priv = netdev_priv(dev);
struct bcmgenet_rxnfc_rule *rule;
unsigned long dma_ctrl;
- u32 reg;
int ret;
if (!netif_running(dev))
if (rule->state != BCMGENET_RXNFC_STATE_UNUSED)
bcmgenet_hfb_create_rxnfc_filter(priv, rule);
- if (priv->internal_phy) {
- reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
- reg |= EXT_ENERGY_DET_MASK;
- bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
- }
-
/* Disable RX/TX DMA and flush TX queues */
dma_ctrl = bcmgenet_dma_disable(priv);
reg |= CMD_RX_EN;
bcmgenet_umac_writel(priv, reg, UMAC_CMD);
- if (priv->hw_params->flags & GENET_HAS_EXT) {
- reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
- reg &= ~EXT_ENERGY_DET_MASK;
- bcmgenet_ext_writel(priv, reg, EXT_EXT_PWR_MGMT);
- }
-
reg = UMAC_IRQ_MPD_R;
if (hfb_enable)
reg |= UMAC_IRQ_HFB_SM | UMAC_IRQ_HFB_MM;
{
unsigned int i;
+ if (!is_uld(adap))
+ return;
+
mutex_lock(&uld_mutex);
list_del(&adap->list_node);
*/
destroy_workqueue(adapter->workq);
- if (is_uld(adapter)) {
- detach_ulds(adapter);
- t4_uld_clean_up(adapter);
- }
+ detach_ulds(adapter);
+
+ for_each_port(adapter, i)
+ if (adapter->port[i]->reg_state == NETREG_REGISTERED)
+ unregister_netdev(adapter->port[i]);
+
+ t4_uld_clean_up(adapter);
adap_free_hma_mem(adapter);
cxgb4_free_mps_ref_entries(adapter);
- for_each_port(adapter, i)
- if (adapter->port[i]->reg_state == NETREG_REGISTERED)
- unregister_netdev(adapter->port[i]);
-
debugfs_remove_recursive(adapter->debugfs_root);
if (!is_t4(adapter->params.chip))
{
unsigned int i;
+ if (!is_uld(adap))
+ return;
+
mutex_lock(&uld_mutex);
for (i = 0; i < CXGB4_ULD_MAX; i++) {
if (!adap->uld[i].handle)
err = pci_enable_device(pdev);
if (err)
- return -ENXIO;
+ return err;
err = pci_request_regions(pdev, "gvnic-cfg");
if (err)
pci_set_master(pdev);
- err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+ err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
if (err) {
dev_err(&pdev->dev, "Failed to set dma mask: err=%d\n", err);
goto abort_with_pci_region;
}
- err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
- if (err) {
- dev_err(&pdev->dev,
- "Failed to set consistent dma mask: err=%d\n", err);
- goto abort_with_pci_region;
- }
-
reg_bar = pci_iomap(pdev, GVE_REGISTER_BAR, 0);
if (!reg_bar) {
dev_err(&pdev->dev, "Failed to map pci bar!\n");
dev = alloc_etherdev_mqs(sizeof(*priv), max_tx_queues, max_rx_queues);
if (!dev) {
dev_err(&pdev->dev, "could not allocate netdev\n");
+ err = -ENOMEM;
goto abort_with_db_bar;
}
SET_NETDEV_DEV(dev, &pdev->dev);
err = register_netdev(dev);
if (err)
- goto abort_with_wq;
+ goto abort_with_gve_init;
dev_info(&pdev->dev, "GVE version %s\n", gve_version_str);
dev_info(&pdev->dev, "GVE queue format %d\n", (int)priv->queue_format);
queue_work(priv->gve_wq, &priv->service_task);
return 0;
+abort_with_gve_init:
+ gve_teardown_priv_resources(priv);
+
abort_with_wq:
destroy_workqueue(priv->gve_wq);
abort_with_enabled:
pci_disable_device(pdev);
- return -ENXIO;
+ return err;
}
static void gve_remove(struct pci_dev *pdev)
return 0;
}
- /* Prefetch the payload header. */
- prefetch((char *)buf_state->addr + buf_state->page_info.page_offset);
-#if L1_CACHE_BYTES < 128
- prefetch((char *)buf_state->addr + buf_state->page_info.page_offset +
- L1_CACHE_BYTES);
-#endif
-
if (eop && buf_len <= priv->rx_copybreak) {
rx->skb_head = gve_rx_copy(priv->dev, napi,
&buf_state->page_info, buf_len, 0);
static void __ibmvnic_reset(struct work_struct *work)
{
- struct ibmvnic_rwi *rwi;
struct ibmvnic_adapter *adapter;
bool saved_state = false;
+ struct ibmvnic_rwi *tmprwi;
+ struct ibmvnic_rwi *rwi;
unsigned long flags;
u32 reset_state;
int rc = 0;
} else {
rc = do_reset(adapter, rwi, reset_state);
}
- kfree(rwi);
+ tmprwi = rwi;
adapter->last_reset_time = jiffies;
if (rc)
rwi = get_next_rwi(adapter);
+ /*
+ * If there is another reset queued, free the previous rwi
+ * and process the new reset even if previous reset failed
+ * (the previous reset could have failed because of a fail
+ * over for instance, so process the fail over).
+ *
+ * If there are no resets queued and the previous reset failed,
+ * the adapter would be in an undefined state. So retry the
+ * previous reset as a hard reset.
+ */
+ if (rwi)
+ kfree(tmprwi);
+ else if (rc)
+ rwi = tmprwi;
+
if (rwi && (rwi->reset_reason == VNIC_RESET_FAILOVER ||
- rwi->reset_reason == VNIC_RESET_MOBILITY))
+ rwi->reset_reason == VNIC_RESET_MOBILITY || rc))
adapter->force_reset_recovery = true;
}
err_ioremap:
free_netdev(netdev);
err_alloc_etherdev:
+ pci_disable_pcie_error_reporting(pdev);
pci_release_mem_regions(pdev);
err_pci_reg:
err_dma:
err_ioremap:
free_netdev(netdev);
err_alloc_netdev:
+ pci_disable_pcie_error_reporting(pdev);
pci_release_mem_regions(pdev);
err_pci_reg:
err_dma:
err_ioremap:
free_netdev(netdev);
err_alloc_etherdev:
+ pci_disable_pcie_error_reporting(pdev);
pci_release_regions(pdev);
err_pci_reg:
err_dma:
**/
static int igb_request_msix(struct igb_adapter *adapter)
{
+ unsigned int num_q_vectors = adapter->num_q_vectors;
struct net_device *netdev = adapter->netdev;
int i, err = 0, vector = 0, free_vector = 0;
if (err)
goto err_out;
- for (i = 0; i < adapter->num_q_vectors; i++) {
+ if (num_q_vectors > MAX_Q_VECTORS) {
+ num_q_vectors = MAX_Q_VECTORS;
+ dev_warn(&adapter->pdev->dev,
+ "The number of queue vectors (%d) is higher than max allowed (%d)\n",
+ adapter->num_q_vectors, MAX_Q_VECTORS);
+ }
+ for (i = 0; i < num_q_vectors; i++) {
struct igb_q_vector *q_vector = adapter->q_vector[i];
vector++;
**/
static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
{
- struct igb_ring *ring = adapter->tx_ring[queue];
struct net_device *netdev = adapter->netdev;
struct e1000_hw *hw = &adapter->hw;
+ struct igb_ring *ring;
u32 tqavcc, tqavctrl;
u16 value;
WARN_ON(hw->mac.type != e1000_i210);
WARN_ON(queue < 0 || queue > 1);
+ ring = adapter->tx_ring[queue];
/* If any of the Qav features is enabled, configure queues as SR and
* with HIGH PRIO. If none is, then configure them with LOW PRIO and
err_ioremap:
free_netdev(netdev);
err_alloc_etherdev:
+ pci_disable_pcie_error_reporting(pdev);
pci_release_mem_regions(pdev);
err_pci_reg:
err_dma:
DMA_TO_DEVICE);
}
+ tx_buffer->next_to_watch = NULL;
+
/* move us one more past the eop_desc for start of next pkt */
tx_buffer++;
i++;
if (hw->phy.ops.read_reg)
return hw->phy.ops.read_reg(hw, offset, data);
- return 0;
+ return -EOPNOTSUPP;
}
void igc_reinit_locked(struct igc_adapter *);
igc_unmap_tx_buffer(tx_ring->dev, tx_buffer);
}
+ tx_buffer->next_to_watch = NULL;
+
/* move us one more past the eop_desc for start of next pkt */
tx_buffer++;
i++;
err_ioremap:
free_netdev(netdev);
err_alloc_etherdev:
+ pci_disable_pcie_error_reporting(pdev);
pci_release_mem_regions(pdev);
err_pci_reg:
err_dma:
disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
free_netdev(netdev);
err_alloc_etherdev:
+ pci_disable_pcie_error_reporting(pdev);
pci_release_mem_regions(pdev);
err_pci_reg:
err_dma:
static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs,
u32 *mykey, u32 *mysalt)
{
- struct net_device *dev = xs->xso.dev;
+ struct net_device *dev = xs->xso.real_dev;
unsigned char *key_data;
char *alg_name = NULL;
int key_len;
**/
static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs)
{
- struct net_device *dev = xs->xso.dev;
- struct ixgbevf_adapter *adapter = netdev_priv(dev);
- struct ixgbevf_ipsec *ipsec = adapter->ipsec;
+ struct net_device *dev = xs->xso.real_dev;
+ struct ixgbevf_adapter *adapter;
+ struct ixgbevf_ipsec *ipsec;
u16 sa_idx;
int ret;
+ adapter = netdev_priv(dev);
+ ipsec = adapter->ipsec;
+
if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) {
netdev_err(dev, "Unsupported protocol 0x%04x for IPsec offload\n",
xs->id.proto);
**/
static void ixgbevf_ipsec_del_sa(struct xfrm_state *xs)
{
- struct net_device *dev = xs->xso.dev;
- struct ixgbevf_adapter *adapter = netdev_priv(dev);
- struct ixgbevf_ipsec *ipsec = adapter->ipsec;
+ struct net_device *dev = xs->xso.real_dev;
+ struct ixgbevf_adapter *adapter;
+ struct ixgbevf_ipsec *ipsec;
u16 sa_idx;
+ adapter = netdev_priv(dev);
+ ipsec = adapter->ipsec;
+
if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) {
sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_RX_INDEX;
skb_frag_off_set(frag, pp->rx_offset_correction);
skb_frag_size_set(frag, data_len);
__skb_frag_set_page(frag, page);
-
- /* last fragment */
- if (len == *size) {
- struct skb_shared_info *sinfo;
-
- sinfo = xdp_get_shared_info_from_buff(xdp);
- sinfo->nr_frags = xdp_sinfo->nr_frags;
- memcpy(sinfo->frags, xdp_sinfo->frags,
- sinfo->nr_frags * sizeof(skb_frag_t));
- }
} else {
page_pool_put_full_page(rxq->page_pool, page, true);
}
+
+ /* last fragment */
+ if (len == *size) {
+ struct skb_shared_info *sinfo;
+
+ sinfo = xdp_get_shared_info_from_buff(xdp);
+ sinfo->nr_frags = xdp_sinfo->nr_frags;
+ memcpy(sinfo->frags, xdp_sinfo->frags,
+ sinfo->nr_frags * sizeof(skb_frag_t));
+ }
*size -= len;
}
return test_bit(lmac_id, &cgx->lmac_bmap);
}
+/* Helper function to get sequential index
+ * given the enabled LMAC of a CGX
+ */
+static int get_sequence_id_of_lmac(struct cgx *cgx, int lmac_id)
+{
+ int tmp, id = 0;
+
+ for_each_set_bit(tmp, &cgx->lmac_bmap, MAX_LMAC_PER_CGX) {
+ if (tmp == lmac_id)
+ break;
+ id++;
+ }
+
+ return id;
+}
+
struct mac_ops *get_mac_ops(void *cgxd)
{
if (!cgxd)
return mac;
}
+static void cfg2mac(u64 cfg, u8 *mac_addr)
+{
+ int i, index = 0;
+
+ for (i = ETH_ALEN - 1; i >= 0; i--, index++)
+ mac_addr[i] = (cfg >> (8 * index)) & 0xFF;
+}
+
int cgx_lmac_addr_set(u8 cgx_id, u8 lmac_id, u8 *mac_addr)
{
struct cgx *cgx_dev = cgx_get_pdata(cgx_id);
+ struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev);
struct mac_ops *mac_ops;
+ int index, id;
u64 cfg;
+ /* access mac_ops to know csr_offset */
mac_ops = cgx_dev->mac_ops;
+
/* copy 6bytes from macaddr */
/* memcpy(&cfg, mac_addr, 6); */
cfg = mac2u64 (mac_addr);
- cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (lmac_id * 0x8)),
+ id = get_sequence_id_of_lmac(cgx_dev, lmac_id);
+
+ index = id * lmac->mac_to_index_bmap.max;
+
+ cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)),
cfg | CGX_DMAC_CAM_ADDR_ENABLE | ((u64)lmac_id << 49));
cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0);
- cfg |= CGX_DMAC_CTL0_CAM_ENABLE;
+ cfg |= (CGX_DMAC_CTL0_CAM_ENABLE | CGX_DMAC_BCAST_MODE |
+ CGX_DMAC_MCAST_MODE);
cgx_write(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg);
return 0;
}
+u64 cgx_read_dmac_ctrl(void *cgxd, int lmac_id)
+{
+ struct mac_ops *mac_ops;
+ struct cgx *cgx = cgxd;
+
+ if (!cgxd || !is_lmac_valid(cgxd, lmac_id))
+ return 0;
+
+ cgx = cgxd;
+ /* Get mac_ops to know csr offset */
+ mac_ops = cgx->mac_ops;
+
+ return cgx_read(cgxd, lmac_id, CGXX_CMRX_RX_DMAC_CTL0);
+}
+
+u64 cgx_read_dmac_entry(void *cgxd, int index)
+{
+ struct mac_ops *mac_ops;
+ struct cgx *cgx;
+
+ if (!cgxd)
+ return 0;
+
+ cgx = cgxd;
+ mac_ops = cgx->mac_ops;
+ return cgx_read(cgx, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 8)));
+}
+
+int cgx_lmac_addr_add(u8 cgx_id, u8 lmac_id, u8 *mac_addr)
+{
+ struct cgx *cgx_dev = cgx_get_pdata(cgx_id);
+ struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev);
+ struct mac_ops *mac_ops;
+ int index, idx;
+ u64 cfg = 0;
+ int id;
+
+ if (!lmac)
+ return -ENODEV;
+
+ mac_ops = cgx_dev->mac_ops;
+ /* Get available index where entry is to be installed */
+ idx = rvu_alloc_rsrc(&lmac->mac_to_index_bmap);
+ if (idx < 0)
+ return idx;
+
+ id = get_sequence_id_of_lmac(cgx_dev, lmac_id);
+
+ index = id * lmac->mac_to_index_bmap.max + idx;
+
+ cfg = mac2u64 (mac_addr);
+ cfg |= CGX_DMAC_CAM_ADDR_ENABLE;
+ cfg |= ((u64)lmac_id << 49);
+ cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), cfg);
+
+ cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0);
+ cfg |= (CGX_DMAC_BCAST_MODE | CGX_DMAC_CAM_ACCEPT);
+
+ if (is_multicast_ether_addr(mac_addr)) {
+ cfg &= ~GENMASK_ULL(2, 1);
+ cfg |= CGX_DMAC_MCAST_MODE_CAM;
+ lmac->mcast_filters_count++;
+ } else if (!lmac->mcast_filters_count) {
+ cfg |= CGX_DMAC_MCAST_MODE;
+ }
+
+ cgx_write(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg);
+
+ return idx;
+}
+
+int cgx_lmac_addr_reset(u8 cgx_id, u8 lmac_id)
+{
+ struct cgx *cgx_dev = cgx_get_pdata(cgx_id);
+ struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev);
+ struct mac_ops *mac_ops;
+ u8 index = 0, id;
+ u64 cfg;
+
+ if (!lmac)
+ return -ENODEV;
+
+ mac_ops = cgx_dev->mac_ops;
+ /* Restore index 0 to its default init value as done during
+ * cgx_lmac_init
+ */
+ set_bit(0, lmac->mac_to_index_bmap.bmap);
+
+ id = get_sequence_id_of_lmac(cgx_dev, lmac_id);
+
+ index = id * lmac->mac_to_index_bmap.max + index;
+ cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), 0);
+
+ /* Reset CGXX_CMRX_RX_DMAC_CTL0 register to default state */
+ cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0);
+ cfg &= ~CGX_DMAC_CAM_ACCEPT;
+ cfg |= (CGX_DMAC_BCAST_MODE | CGX_DMAC_MCAST_MODE);
+ cgx_write(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg);
+
+ return 0;
+}
+
+/* Allows caller to change macaddress associated with index
+ * in dmac filter table including index 0 reserved for
+ * interface mac address
+ */
+int cgx_lmac_addr_update(u8 cgx_id, u8 lmac_id, u8 *mac_addr, u8 index)
+{
+ struct cgx *cgx_dev = cgx_get_pdata(cgx_id);
+ struct mac_ops *mac_ops;
+ struct lmac *lmac;
+ u64 cfg;
+ int id;
+
+ lmac = lmac_pdata(lmac_id, cgx_dev);
+ if (!lmac)
+ return -ENODEV;
+
+ mac_ops = cgx_dev->mac_ops;
+ /* Validate the index */
+ if (index >= lmac->mac_to_index_bmap.max)
+ return -EINVAL;
+
+ /* ensure index is already set */
+ if (!test_bit(index, lmac->mac_to_index_bmap.bmap))
+ return -EINVAL;
+
+ id = get_sequence_id_of_lmac(cgx_dev, lmac_id);
+
+ index = id * lmac->mac_to_index_bmap.max + index;
+
+ cfg = cgx_read(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)));
+ cfg &= ~CGX_RX_DMAC_ADR_MASK;
+ cfg |= mac2u64 (mac_addr);
+
+ cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), cfg);
+ return 0;
+}
+
+int cgx_lmac_addr_del(u8 cgx_id, u8 lmac_id, u8 index)
+{
+ struct cgx *cgx_dev = cgx_get_pdata(cgx_id);
+ struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev);
+ struct mac_ops *mac_ops;
+ u8 mac[ETH_ALEN];
+ u64 cfg;
+ int id;
+
+ if (!lmac)
+ return -ENODEV;
+
+ mac_ops = cgx_dev->mac_ops;
+ /* Validate the index */
+ if (index >= lmac->mac_to_index_bmap.max)
+ return -EINVAL;
+
+ /* Skip deletion for reserved index i.e. index 0 */
+ if (index == 0)
+ return 0;
+
+ rvu_free_rsrc(&lmac->mac_to_index_bmap, index);
+
+ id = get_sequence_id_of_lmac(cgx_dev, lmac_id);
+
+ index = id * lmac->mac_to_index_bmap.max + index;
+
+ /* Read MAC address to check whether it is ucast or mcast */
+ cfg = cgx_read(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)));
+
+ cfg2mac(cfg, mac);
+ if (is_multicast_ether_addr(mac))
+ lmac->mcast_filters_count--;
+
+ if (!lmac->mcast_filters_count) {
+ cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0);
+ cfg &= ~GENMASK_ULL(2, 1);
+ cfg |= CGX_DMAC_MCAST_MODE;
+ cgx_write(cgx_dev, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg);
+ }
+
+ cgx_write(cgx_dev, 0, (CGXX_CMRX_RX_DMAC_CAM0 + (index * 0x8)), 0);
+
+ return 0;
+}
+
+int cgx_lmac_addr_max_entries_get(u8 cgx_id, u8 lmac_id)
+{
+ struct cgx *cgx_dev = cgx_get_pdata(cgx_id);
+ struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev);
+
+ if (lmac)
+ return lmac->mac_to_index_bmap.max;
+
+ return 0;
+}
+
u64 cgx_lmac_addr_get(u8 cgx_id, u8 lmac_id)
{
struct cgx *cgx_dev = cgx_get_pdata(cgx_id);
+ struct lmac *lmac = lmac_pdata(lmac_id, cgx_dev);
struct mac_ops *mac_ops;
+ int index;
u64 cfg;
+ int id;
mac_ops = cgx_dev->mac_ops;
- cfg = cgx_read(cgx_dev, 0, CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8);
+ id = get_sequence_id_of_lmac(cgx_dev, lmac_id);
+
+ index = id * lmac->mac_to_index_bmap.max;
+
+ cfg = cgx_read(cgx_dev, 0, CGXX_CMRX_RX_DMAC_CAM0 + index * 0x8);
return cfg & CGX_RX_DMAC_ADR_MASK;
}
void cgx_lmac_promisc_config(int cgx_id, int lmac_id, bool enable)
{
struct cgx *cgx = cgx_get_pdata(cgx_id);
+ struct lmac *lmac = lmac_pdata(lmac_id, cgx);
+ u16 max_dmac = lmac->mac_to_index_bmap.max;
struct mac_ops *mac_ops;
+ int index, i;
u64 cfg = 0;
+ int id;
if (!cgx)
return;
+ id = get_sequence_id_of_lmac(cgx, lmac_id);
+
mac_ops = cgx->mac_ops;
if (enable) {
/* Enable promiscuous mode on LMAC */
cfg = cgx_read(cgx, lmac_id, CGXX_CMRX_RX_DMAC_CTL0);
- cfg &= ~(CGX_DMAC_CAM_ACCEPT | CGX_DMAC_MCAST_MODE);
- cfg |= CGX_DMAC_BCAST_MODE;
+ cfg &= ~CGX_DMAC_CAM_ACCEPT;
+ cfg |= (CGX_DMAC_BCAST_MODE | CGX_DMAC_MCAST_MODE);
cgx_write(cgx, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg);
- cfg = cgx_read(cgx, 0,
- (CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8));
- cfg &= ~CGX_DMAC_CAM_ADDR_ENABLE;
- cgx_write(cgx, 0,
- (CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8), cfg);
+ for (i = 0; i < max_dmac; i++) {
+ index = id * max_dmac + i;
+ cfg = cgx_read(cgx, 0,
+ (CGXX_CMRX_RX_DMAC_CAM0 + index * 0x8));
+ cfg &= ~CGX_DMAC_CAM_ADDR_ENABLE;
+ cgx_write(cgx, 0,
+ (CGXX_CMRX_RX_DMAC_CAM0 + index * 0x8), cfg);
+ }
} else {
/* Disable promiscuous mode */
cfg = cgx_read(cgx, lmac_id, CGXX_CMRX_RX_DMAC_CTL0);
cfg |= CGX_DMAC_CAM_ACCEPT | CGX_DMAC_MCAST_MODE;
cgx_write(cgx, lmac_id, CGXX_CMRX_RX_DMAC_CTL0, cfg);
- cfg = cgx_read(cgx, 0,
- (CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8));
- cfg |= CGX_DMAC_CAM_ADDR_ENABLE;
- cgx_write(cgx, 0,
- (CGXX_CMRX_RX_DMAC_CAM0 + lmac_id * 0x8), cfg);
+ for (i = 0; i < max_dmac; i++) {
+ index = id * max_dmac + i;
+ cfg = cgx_read(cgx, 0,
+ (CGXX_CMRX_RX_DMAC_CAM0 + index * 0x8));
+ if ((cfg & CGX_RX_DMAC_ADR_MASK) != 0) {
+ cfg |= CGX_DMAC_CAM_ADDR_ENABLE;
+ cgx_write(cgx, 0,
+ (CGXX_CMRX_RX_DMAC_CAM0 +
+ index * 0x8),
+ cfg);
+ }
+ }
}
}
}
lmac->cgx = cgx;
+ lmac->mac_to_index_bmap.max =
+ MAX_DMAC_ENTRIES_PER_CGX / cgx->lmac_count;
+ err = rvu_alloc_bitmap(&lmac->mac_to_index_bmap);
+ if (err)
+ return err;
+
+ /* Reserve first entry for default MAC address */
+ set_bit(0, lmac->mac_to_index_bmap.bmap);
+
init_waitqueue_head(&lmac->wq_cmd_cmplt);
mutex_init(&lmac->cmd_lock);
spin_lock_init(&lmac->event_cb_lock);
continue;
cgx->mac_ops->mac_pause_frm_config(cgx, lmac->lmac_id, false);
cgx_configure_interrupt(cgx, lmac, lmac->lmac_id, true);
+ kfree(lmac->mac_to_index_bmap.bmap);
kfree(lmac->name);
kfree(lmac);
}
#define CGX_ID_MASK 0x7
#define MAX_LMAC_PER_CGX 4
+#define MAX_DMAC_ENTRIES_PER_CGX 32
#define CGX_FIFO_LEN 65536 /* 64K for both Rx & Tx */
#define CGX_OFFSET(x) ((x) * MAX_LMAC_PER_CGX)
#define CGXX_CMRX_RX_DMAC_CTL0 (0x1F8 + mac_ops->csr_offset)
#define CGX_DMAC_CTL0_CAM_ENABLE BIT_ULL(3)
#define CGX_DMAC_CAM_ACCEPT BIT_ULL(3)
+#define CGX_DMAC_MCAST_MODE_CAM BIT_ULL(2)
#define CGX_DMAC_MCAST_MODE BIT_ULL(1)
#define CGX_DMAC_BCAST_MODE BIT_ULL(0)
#define CGXX_CMRX_RX_DMAC_CAM0 (0x200 + mac_ops->csr_offset)
#define CGX_DMAC_CAM_ADDR_ENABLE BIT_ULL(48)
+#define CGX_DMAC_CAM_ENTRY_LMACID GENMASK_ULL(50, 49)
#define CGXX_CMRX_RX_DMAC_CAM1 0x400
#define CGX_RX_DMAC_ADR_MASK GENMASK_ULL(47, 0)
#define CGXX_CMRX_TX_STAT0 0x700
int cgx_lmac_rx_tx_enable(void *cgxd, int lmac_id, bool enable);
int cgx_lmac_tx_enable(void *cgxd, int lmac_id, bool enable);
int cgx_lmac_addr_set(u8 cgx_id, u8 lmac_id, u8 *mac_addr);
+int cgx_lmac_addr_reset(u8 cgx_id, u8 lmac_id);
u64 cgx_lmac_addr_get(u8 cgx_id, u8 lmac_id);
+int cgx_lmac_addr_add(u8 cgx_id, u8 lmac_id, u8 *mac_addr);
+int cgx_lmac_addr_del(u8 cgx_id, u8 lmac_id, u8 index);
+int cgx_lmac_addr_max_entries_get(u8 cgx_id, u8 lmac_id);
void cgx_lmac_promisc_config(int cgx_id, int lmac_id, bool enable);
void cgx_lmac_enadis_rx_pause_fwding(void *cgxd, int lmac_id, bool enable);
int cgx_lmac_internal_loopback(void *cgxd, int lmac_id, bool enable);
unsigned long cgx_get_lmac_bmap(void *cgxd);
void cgx_lmac_write(int cgx_id, int lmac_id, u64 offset, u64 val);
u64 cgx_lmac_read(int cgx_id, int lmac_id, u64 offset);
+int cgx_lmac_addr_update(u8 cgx_id, u8 lmac_id, u8 *mac_addr, u8 index);
+u64 cgx_read_dmac_ctrl(void *cgxd, int lmac_id);
+u64 cgx_read_dmac_entry(void *cgxd, int index);
#endif /* CGX_H */
#include "rvu.h"
#include "cgx.h"
/**
- * struct lmac
+ * struct lmac - per lmac locks and properties
* @wq_cmd_cmplt: waitq to keep the process blocked until cmd completion
* @cmd_lock: Lock to serialize the command interface
* @resp: command response
* @link_info: link related information
+ * @mac_to_index_bmap: Mac address to CGX table index mapping
* @event_cb: callback for linkchange events
* @event_cb_lock: lock for serializing callback with unregister
- * @cmd_pend: flag set before new command is started
- * flag cleared after command response is received
* @cgx: parent cgx port
+ * @mcast_filters_count: Number of multicast filters installed
* @lmac_id: lmac port id
+ * @cmd_pend: flag set before new command is started
+ * flag cleared after command response is received
* @name: lmac port name
*/
struct lmac {
struct mutex cmd_lock;
u64 resp;
struct cgx_link_user_info link_info;
+ struct rsrc_bmap mac_to_index_bmap;
struct cgx_event_cb event_cb;
/* lock for serializing callback with unregister */
spinlock_t event_cb_lock;
- bool cmd_pend;
struct cgx *cgx;
+ u8 mcast_filters_count;
u8 lmac_id;
+ bool cmd_pend;
char *name;
};
M(VF_FLR, 0x006, vf_flr, msg_req, msg_rsp) \
M(PTP_OP, 0x007, ptp_op, ptp_req, ptp_rsp) \
M(GET_HW_CAP, 0x008, get_hw_cap, msg_req, get_hw_cap_rsp) \
+M(LMTST_TBL_SETUP, 0x00a, lmtst_tbl_setup, lmtst_tbl_setup_req, \
+ msg_rsp) \
M(SET_VF_PERM, 0x00b, set_vf_perm, set_vf_perm, msg_rsp) \
/* CGX mbox IDs (range 0x200 - 0x3FF) */ \
M(CGX_START_RXTX, 0x200, cgx_start_rxtx, msg_req, msg_rsp) \
M(CGX_FEATURES_GET, 0x215, cgx_features_get, msg_req, \
cgx_features_info_msg) \
M(RPM_STATS, 0x216, rpm_stats, msg_req, rpm_stats_rsp) \
- /* NPA mbox IDs (range 0x400 - 0x5FF) */ \
+M(CGX_MAC_ADDR_ADD, 0x217, cgx_mac_addr_add, cgx_mac_addr_add_req, \
+ cgx_mac_addr_add_rsp) \
+M(CGX_MAC_ADDR_DEL, 0x218, cgx_mac_addr_del, cgx_mac_addr_del_req, \
+ msg_rsp) \
+M(CGX_MAC_MAX_ENTRIES_GET, 0x219, cgx_mac_max_entries_get, msg_req, \
+ cgx_max_dmac_entries_get_rsp) \
+M(CGX_MAC_ADDR_RESET, 0x21A, cgx_mac_addr_reset, msg_req, msg_rsp) \
+M(CGX_MAC_ADDR_UPDATE, 0x21B, cgx_mac_addr_update, cgx_mac_addr_update_req, \
+ msg_rsp) \
/* NPA mbox IDs (range 0x400 - 0x5FF) */ \
M(NPA_LF_ALLOC, 0x400, npa_lf_alloc, \
npa_lf_alloc_req, npa_lf_alloc_rsp) \
u8 mac_addr[ETH_ALEN];
};
+/* Structure for requesting the operation to
+ * add DMAC filter entry into CGX interface
+ */
+struct cgx_mac_addr_add_req {
+ struct mbox_msghdr hdr;
+ u8 mac_addr[ETH_ALEN];
+};
+
+/* Structure for response against the operation to
+ * add DMAC filter entry into CGX interface
+ */
+struct cgx_mac_addr_add_rsp {
+ struct mbox_msghdr hdr;
+ u8 index;
+};
+
+/* Structure for requesting the operation to
+ * delete DMAC filter entry from CGX interface
+ */
+struct cgx_mac_addr_del_req {
+ struct mbox_msghdr hdr;
+ u8 index;
+};
+
+/* Structure for response against the operation to
+ * get maximum supported DMAC filter entries
+ */
+struct cgx_max_dmac_entries_get_rsp {
+ struct mbox_msghdr hdr;
+ u8 max_dmac_filters;
+};
+
struct cgx_link_user_info {
uint64_t link_up:1;
uint64_t full_duplex:1;
int status;
};
+struct cgx_mac_addr_update_req {
+ struct mbox_msghdr hdr;
+ u8 mac_addr[ETH_ALEN];
+ u8 index;
+};
+
#define RVU_LMAC_FEAT_FC BIT_ULL(0) /* pause frames */
#define RVU_LMAC_FEAT_PTP BIT_ULL(1) /* precision time protocol */
#define RVU_MAC_VERSION BIT_ULL(2)
u64 flags;
};
+struct lmtst_tbl_setup_req {
+ struct mbox_msghdr hdr;
+ u16 base_pcifunc;
+ u8 use_local_lmt_region;
+ u64 lmt_iova;
+ u64 rsvd[4];
+};
+
/* CPT mailbox error codes
* Range 901 - 1000.
*/
rvu_blklf_teardown(rvu, pcifunc, BLKADDR_SSOW);
rvu_blklf_teardown(rvu, pcifunc, BLKADDR_SSO);
rvu_blklf_teardown(rvu, pcifunc, BLKADDR_NPA);
+ rvu_reset_lmt_map_tbl(rvu, pcifunc);
rvu_detach_rsrcs(rvu, NULL, pcifunc);
mutex_unlock(&rvu->flr_lock);
}
u8 nix_blkaddr; /* BLKADDR_NIX0/1 assigned to this PF */
u8 nix_rx_intf; /* NIX0_RX/NIX1_RX interface to NPC */
u8 nix_tx_intf; /* NIX0_TX/NIX1_TX interface to NPC */
+ u64 lmt_base_addr; /* Preseving the pcifunc's lmtst base addr*/
unsigned long flags;
};
int rvu_cgx_start_stop_io(struct rvu *rvu, u16 pcifunc, bool start);
int rvu_cgx_nix_cuml_stats(struct rvu *rvu, void *cgxd, int lmac_id, int index,
int rxtxflag, u64 *stat);
+void rvu_cgx_disable_dmac_entries(struct rvu *rvu, u16 pcifunc);
+
/* NPA APIs */
int rvu_npa_init(struct rvu *rvu);
void rvu_npa_freemem(struct rvu *rvu);
bool is_mac_feature_supported(struct rvu *rvu, int pf, int feature);
u32 rvu_cgx_get_fifolen(struct rvu *rvu);
void *rvu_first_cgx_pdata(struct rvu *rvu);
+int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id);
int npc_get_nixlf_mcam_index(struct npc_mcam *mcam, u16 pcifunc, int nixlf,
int type);
int rvu_set_channels_base(struct rvu *rvu);
void rvu_program_channels(struct rvu *rvu);
+/* CN10K RVU - LMT*/
+void rvu_reset_lmt_map_tbl(struct rvu *rvu, u16 pcifunc);
+
#ifdef CONFIG_DEBUG_FS
void rvu_dbg_init(struct rvu *rvu);
void rvu_dbg_exit(struct rvu *rvu);
return rvu->cgxlmac2pf_map[CGX_OFFSET(cgx_id) + lmac_id];
}
-static int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id)
+int cgxlmac_to_pf(struct rvu *rvu, int cgx_id, int lmac_id)
{
unsigned long pfmap;
return 0;
}
+void rvu_cgx_disable_dmac_entries(struct rvu *rvu, u16 pcifunc)
+{
+ int pf = rvu_get_pf(pcifunc);
+ int i = 0, lmac_count = 0;
+ u8 max_dmac_filters;
+ u8 cgx_id, lmac_id;
+ void *cgx_dev;
+
+ if (!is_cgx_config_permitted(rvu, pcifunc))
+ return;
+
+ rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
+ cgx_dev = cgx_get_pdata(cgx_id);
+ lmac_count = cgx_get_lmac_cnt(cgx_dev);
+ max_dmac_filters = MAX_DMAC_ENTRIES_PER_CGX / lmac_count;
+
+ for (i = 0; i < max_dmac_filters; i++)
+ cgx_lmac_addr_del(cgx_id, lmac_id, i);
+
+ /* As cgx_lmac_addr_del does not clear entry for index 0
+ * so it needs to be done explicitly
+ */
+ cgx_lmac_addr_reset(cgx_id, lmac_id);
+}
+
int rvu_mbox_handler_cgx_start_rxtx(struct rvu *rvu, struct msg_req *req,
struct msg_rsp *rsp)
{
return 0;
}
+int rvu_mbox_handler_cgx_mac_addr_add(struct rvu *rvu,
+ struct cgx_mac_addr_add_req *req,
+ struct cgx_mac_addr_add_rsp *rsp)
+{
+ int pf = rvu_get_pf(req->hdr.pcifunc);
+ u8 cgx_id, lmac_id;
+ int rc = 0;
+
+ if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
+ return -EPERM;
+
+ rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
+ rc = cgx_lmac_addr_add(cgx_id, lmac_id, req->mac_addr);
+ if (rc >= 0) {
+ rsp->index = rc;
+ return 0;
+ }
+
+ return rc;
+}
+
+int rvu_mbox_handler_cgx_mac_addr_del(struct rvu *rvu,
+ struct cgx_mac_addr_del_req *req,
+ struct msg_rsp *rsp)
+{
+ int pf = rvu_get_pf(req->hdr.pcifunc);
+ u8 cgx_id, lmac_id;
+
+ if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
+ return -EPERM;
+
+ rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
+ return cgx_lmac_addr_del(cgx_id, lmac_id, req->index);
+}
+
+int rvu_mbox_handler_cgx_mac_max_entries_get(struct rvu *rvu,
+ struct msg_req *req,
+ struct cgx_max_dmac_entries_get_rsp
+ *rsp)
+{
+ int pf = rvu_get_pf(req->hdr.pcifunc);
+ u8 cgx_id, lmac_id;
+
+ /* If msg is received from PFs(which are not mapped to CGX LMACs)
+ * or VF then no entries are allocated for DMAC filters at CGX level.
+ * So returning zero.
+ */
+ if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc)) {
+ rsp->max_dmac_filters = 0;
+ return 0;
+ }
+
+ rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
+ rsp->max_dmac_filters = cgx_lmac_addr_max_entries_get(cgx_id, lmac_id);
+ return 0;
+}
+
int rvu_mbox_handler_cgx_mac_addr_get(struct rvu *rvu,
struct cgx_mac_addr_set_or_get *req,
struct cgx_mac_addr_set_or_get *rsp)
rsp->status = cgx_set_link_mode(cgxd, req->args, cgx_idx, lmac);
return 0;
}
+
+int rvu_mbox_handler_cgx_mac_addr_reset(struct rvu *rvu, struct msg_req *req,
+ struct msg_rsp *rsp)
+{
+ int pf = rvu_get_pf(req->hdr.pcifunc);
+ u8 cgx_id, lmac_id;
+
+ if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
+ return -EPERM;
+
+ rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
+ return cgx_lmac_addr_reset(cgx_id, lmac_id);
+}
+
+int rvu_mbox_handler_cgx_mac_addr_update(struct rvu *rvu,
+ struct cgx_mac_addr_update_req *req,
+ struct msg_rsp *rsp)
+{
+ int pf = rvu_get_pf(req->hdr.pcifunc);
+ u8 cgx_id, lmac_id;
+
+ if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
+ return -EPERM;
+
+ rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, &lmac_id);
+ return cgx_lmac_addr_update(cgx_id, lmac_id, req->mac_addr, req->index);
+}
#include "cgx.h"
#include "rvu_reg.h"
+/* RVU LMTST */
+#define LMT_TBL_OP_READ 0
+#define LMT_TBL_OP_WRITE 1
+#define LMT_MAP_TABLE_SIZE (128 * 1024)
+#define LMT_MAPTBL_ENTRY_SIZE 16
+
+/* Function to perform operations (read/write) on lmtst map table */
+static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
+ int lmt_tbl_op)
+{
+ void __iomem *lmt_map_base;
+ u64 tbl_base;
+
+ tbl_base = rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_MAP_BASE);
+
+ lmt_map_base = ioremap_wc(tbl_base, LMT_MAP_TABLE_SIZE);
+ if (!lmt_map_base) {
+ dev_err(rvu->dev, "Failed to setup lmt map table mapping!!\n");
+ return -ENOMEM;
+ }
+
+ if (lmt_tbl_op == LMT_TBL_OP_READ) {
+ *val = readq(lmt_map_base + index);
+ } else {
+ writeq((*val), (lmt_map_base + index));
+ /* Flushing the AP interceptor cache to make APR_LMT_MAP_ENTRY_S
+ * changes effective. Write 1 for flush and read is being used as a
+ * barrier and sets up a data dependency. Write to 0 after a write
+ * to 1 to complete the flush.
+ */
+ rvu_write64(rvu, BLKADDR_APR, APR_AF_LMT_CTL, BIT_ULL(0));
+ rvu_read64(rvu, BLKADDR_APR, APR_AF_LMT_CTL);
+ rvu_write64(rvu, BLKADDR_APR, APR_AF_LMT_CTL, 0x00);
+ }
+
+ iounmap(lmt_map_base);
+ return 0;
+}
+
+static u32 rvu_get_lmtst_tbl_index(struct rvu *rvu, u16 pcifunc)
+{
+ return ((rvu_get_pf(pcifunc) * rvu->hw->total_vfs) +
+ (pcifunc & RVU_PFVF_FUNC_MASK)) * LMT_MAPTBL_ENTRY_SIZE;
+}
+
+static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc,
+ u64 iova, u64 *lmt_addr)
+{
+ u64 pa, val, pf;
+ int err;
+
+ if (!iova) {
+ dev_err(rvu->dev, "%s Requested Null address for transulation\n", __func__);
+ return -EINVAL;
+ }
+
+ rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_REQ, iova);
+ pf = rvu_get_pf(pcifunc) & 0x1F;
+ val = BIT_ULL(63) | BIT_ULL(14) | BIT_ULL(13) | pf << 8 |
+ ((pcifunc & RVU_PFVF_FUNC_MASK) & 0xFF);
+ rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TXN_REQ, val);
+
+ err = rvu_poll_reg(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_RSP_STS, BIT_ULL(0), false);
+ if (err) {
+ dev_err(rvu->dev, "%s LMTLINE iova transulation failed\n", __func__);
+ return err;
+ }
+ val = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_RSP_STS);
+ if (val & ~0x1ULL) {
+ dev_err(rvu->dev, "%s LMTLINE iova transulation failed err:%llx\n", __func__, val);
+ return -EIO;
+ }
+ /* PA[51:12] = RVU_AF_SMMU_TLN_FLIT1[60:21]
+ * PA[11:0] = IOVA[11:0]
+ */
+ pa = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TLN_FLIT1) >> 21;
+ pa &= GENMASK_ULL(39, 0);
+ *lmt_addr = (pa << 12) | (iova & 0xFFF);
+
+ return 0;
+}
+
+static int rvu_update_lmtaddr(struct rvu *rvu, u16 pcifunc, u64 lmt_addr)
+{
+ struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+ u32 tbl_idx;
+ int err = 0;
+ u64 val;
+
+ /* Read the current lmt addr of pcifunc */
+ tbl_idx = rvu_get_lmtst_tbl_index(rvu, pcifunc);
+ err = lmtst_map_table_ops(rvu, tbl_idx, &val, LMT_TBL_OP_READ);
+ if (err) {
+ dev_err(rvu->dev,
+ "Failed to read LMT map table: index 0x%x err %d\n",
+ tbl_idx, err);
+ return err;
+ }
+
+ /* Storing the seondary's lmt base address as this needs to be
+ * reverted in FLR. Also making sure this default value doesn't
+ * get overwritten on multiple calls to this mailbox.
+ */
+ if (!pfvf->lmt_base_addr)
+ pfvf->lmt_base_addr = val;
+
+ /* Update the LMT table with new addr */
+ err = lmtst_map_table_ops(rvu, tbl_idx, &lmt_addr, LMT_TBL_OP_WRITE);
+ if (err) {
+ dev_err(rvu->dev,
+ "Failed to update LMT map table: index 0x%x err %d\n",
+ tbl_idx, err);
+ return err;
+ }
+ return 0;
+}
+
+int rvu_mbox_handler_lmtst_tbl_setup(struct rvu *rvu,
+ struct lmtst_tbl_setup_req *req,
+ struct msg_rsp *rsp)
+{
+ u64 lmt_addr, val;
+ u32 pri_tbl_idx;
+ int err = 0;
+
+ /* Check if PF_FUNC wants to use it's own local memory as LMTLINE
+ * region, if so, convert that IOVA to physical address and
+ * populate LMT table with that address
+ */
+ if (req->use_local_lmt_region) {
+ err = rvu_get_lmtaddr(rvu, req->hdr.pcifunc,
+ req->lmt_iova, &lmt_addr);
+ if (err < 0)
+ return err;
+
+ /* Update the lmt addr for this PFFUNC in the LMT table */
+ err = rvu_update_lmtaddr(rvu, req->hdr.pcifunc, lmt_addr);
+ if (err)
+ return err;
+ }
+
+ /* Reconfiguring lmtst map table in lmt region shared mode i.e. make
+ * multiple PF_FUNCs to share an LMTLINE region, so primary/base
+ * pcifunc (which is passed as an argument to mailbox) is the one
+ * whose lmt base address will be shared among other secondary
+ * pcifunc (will be the one who is calling this mailbox).
+ */
+ if (req->base_pcifunc) {
+ /* Calculating the LMT table index equivalent to primary
+ * pcifunc.
+ */
+ pri_tbl_idx = rvu_get_lmtst_tbl_index(rvu, req->base_pcifunc);
+
+ /* Read the base lmt addr of the primary pcifunc */
+ err = lmtst_map_table_ops(rvu, pri_tbl_idx, &val,
+ LMT_TBL_OP_READ);
+ if (err) {
+ dev_err(rvu->dev,
+ "Failed to read LMT map table: index 0x%x err %d\n",
+ pri_tbl_idx, err);
+ return err;
+ }
+
+ /* Update the base lmt addr of secondary with primary's base
+ * lmt addr.
+ */
+ err = rvu_update_lmtaddr(rvu, req->hdr.pcifunc, val);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+/* Resetting the lmtst map table to original base addresses */
+void rvu_reset_lmt_map_tbl(struct rvu *rvu, u16 pcifunc)
+{
+ struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+ u32 tbl_idx;
+ int err;
+
+ if (is_rvu_otx2(rvu))
+ return;
+
+ if (pfvf->lmt_base_addr) {
+ /* This corresponds to lmt map table index */
+ tbl_idx = rvu_get_lmtst_tbl_index(rvu, pcifunc);
+ /* Reverting back original lmt base addr for respective
+ * pcifunc.
+ */
+ err = lmtst_map_table_ops(rvu, tbl_idx, &pfvf->lmt_base_addr,
+ LMT_TBL_OP_WRITE);
+ if (err)
+ dev_err(rvu->dev,
+ "Failed to update LMT map table: index 0x%x err %d\n",
+ tbl_idx, err);
+ pfvf->lmt_base_addr = 0;
+ }
+}
+
int rvu_set_channels_base(struct rvu *rvu)
{
struct rvu_hwinfo *hw = rvu->hw;
return err;
}
-static int rvu_dbg_cgx_stat_display(struct seq_file *filp, void *unused)
+static int rvu_dbg_derive_lmacid(struct seq_file *filp, int *lmac_id)
{
struct dentry *current_dir;
- int err, lmac_id;
char *buf;
current_dir = filp->file->f_path.dentry->d_parent;
if (!buf)
return -EINVAL;
- err = kstrtoint(buf + 1, 10, &lmac_id);
- if (!err) {
- err = cgx_print_stats(filp, lmac_id);
- if (err)
- return err;
- }
+ return kstrtoint(buf + 1, 10, lmac_id);
+}
+
+static int rvu_dbg_cgx_stat_display(struct seq_file *filp, void *unused)
+{
+ int lmac_id, err;
+
+ err = rvu_dbg_derive_lmacid(filp, &lmac_id);
+ if (!err)
+ return cgx_print_stats(filp, lmac_id);
+
return err;
}
RVU_DEBUG_SEQ_FOPS(cgx_stat, cgx_stat_display, NULL);
+static int cgx_print_dmac_flt(struct seq_file *s, int lmac_id)
+{
+ struct pci_dev *pdev = NULL;
+ void *cgxd = s->private;
+ char *bcast, *mcast;
+ u16 index, domain;
+ u8 dmac[ETH_ALEN];
+ struct rvu *rvu;
+ u64 cfg, mac;
+ int pf;
+
+ rvu = pci_get_drvdata(pci_get_device(PCI_VENDOR_ID_CAVIUM,
+ PCI_DEVID_OCTEONTX2_RVU_AF, NULL));
+ if (!rvu)
+ return -ENODEV;
+
+ pf = cgxlmac_to_pf(rvu, cgx_get_cgxid(cgxd), lmac_id);
+ domain = 2;
+
+ pdev = pci_get_domain_bus_and_slot(domain, pf + 1, 0);
+ if (!pdev)
+ return 0;
+
+ cfg = cgx_read_dmac_ctrl(cgxd, lmac_id);
+ bcast = cfg & CGX_DMAC_BCAST_MODE ? "ACCEPT" : "REJECT";
+ mcast = cfg & CGX_DMAC_MCAST_MODE ? "ACCEPT" : "REJECT";
+
+ seq_puts(s,
+ "PCI dev RVUPF BROADCAST MULTICAST FILTER-MODE\n");
+ seq_printf(s, "%s PF%d %9s %9s",
+ dev_name(&pdev->dev), pf, bcast, mcast);
+ if (cfg & CGX_DMAC_CAM_ACCEPT)
+ seq_printf(s, "%12s\n\n", "UNICAST");
+ else
+ seq_printf(s, "%16s\n\n", "PROMISCUOUS");
+
+ seq_puts(s, "\nDMAC-INDEX ADDRESS\n");
+
+ for (index = 0 ; index < 32 ; index++) {
+ cfg = cgx_read_dmac_entry(cgxd, index);
+ /* Display enabled dmac entries associated with current lmac */
+ if (lmac_id == FIELD_GET(CGX_DMAC_CAM_ENTRY_LMACID, cfg) &&
+ FIELD_GET(CGX_DMAC_CAM_ADDR_ENABLE, cfg)) {
+ mac = FIELD_GET(CGX_RX_DMAC_ADR_MASK, cfg);
+ u64_to_ether_addr(mac, dmac);
+ seq_printf(s, "%7d %pM\n", index, dmac);
+ }
+ }
+
+ return 0;
+}
+
+static int rvu_dbg_cgx_dmac_flt_display(struct seq_file *filp, void *unused)
+{
+ int err, lmac_id;
+
+ err = rvu_dbg_derive_lmacid(filp, &lmac_id);
+ if (!err)
+ return cgx_print_dmac_flt(filp, lmac_id);
+
+ return err;
+}
+
+RVU_DEBUG_SEQ_FOPS(cgx_dmac_flt, cgx_dmac_flt_display, NULL);
+
static void rvu_dbg_cgx_init(struct rvu *rvu)
{
struct mac_ops *mac_ops;
debugfs_create_file("stats", 0600, rvu->rvu_dbg.lmac,
cgx, &rvu_dbg_cgx_stat_fops);
+ debugfs_create_file("mac_filter", 0600,
+ rvu->rvu_dbg.lmac, cgx,
+ &rvu_dbg_cgx_dmac_flt_fops);
}
}
}
/* Free and disable any MCAM entries used by this NIX LF */
rvu_npc_disable_mcam_entries(rvu, pcifunc, nixlf);
+
+ /* Disable DMAC filters used */
+ rvu_cgx_disable_dmac_entries(rvu, pcifunc);
}
int rvu_mbox_handler_nix_bp_disable(struct rvu *rvu,
#define RVU_AF_PFX_VF_BAR4_ADDR (0x5400 | (a) << 4)
#define RVU_AF_PFX_VF_BAR4_CFG (0x5600 | (a) << 4)
#define RVU_AF_PFX_LMTLINE_ADDR (0x5800 | (a) << 4)
+#define RVU_AF_SMMU_ADDR_REQ (0x6000)
+#define RVU_AF_SMMU_TXN_REQ (0x6008)
+#define RVU_AF_SMMU_ADDR_RSP_STS (0x6010)
+#define RVU_AF_SMMU_ADDR_TLN (0x6018)
+#define RVU_AF_SMMU_TLN_FLIT1 (0x6030)
/* Admin function's privileged PF/VF registers */
#define RVU_PRIV_CONST (0x8000000)
#define LBK_LINK_CFG_ID_MASK GENMASK_ULL(11, 6)
#define LBK_LINK_CFG_BASE_MASK GENMASK_ULL(5, 0)
+/* APR */
+#define APR_AF_LMT_CFG (0x000ull)
+#define APR_AF_LMT_MAP_BASE (0x008ull)
+#define APR_AF_LMT_CTL (0x010ull)
+
#endif /* RVU_REG_H */
BLKADDR_NDC_NPA0 = 0xeULL,
BLKADDR_NDC_NIX1_RX = 0x10ULL,
BLKADDR_NDC_NIX1_TX = 0x11ULL,
- BLK_COUNT = 0x12ULL,
+ BLKADDR_APR = 0x16ULL,
+ BLK_COUNT = 0x17ULL,
};
/* RVU Block Type Enumeration */
obj-$(CONFIG_OCTEONTX2_VF) += rvu_nicvf.o
rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \
- otx2_ptp.o otx2_flows.o otx2_tc.o cn10k.o
+ otx2_ptp.o otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o
rvu_nicvf-y := otx2_vf.o
ccflags-y += -I$(srctree)/drivers/net/ethernet/marvell/octeontx2/af
.refill_pool_ptrs = cn10k_refill_pool_ptrs,
};
-int cn10k_pf_lmtst_init(struct otx2_nic *pf)
+int cn10k_lmtst_init(struct otx2_nic *pfvf)
{
- int size, num_lines;
- u64 base;
- if (!test_bit(CN10K_LMTST, &pf->hw.cap_flag)) {
- pf->hw_ops = &otx2_hw_ops;
+ struct lmtst_tbl_setup_req *req;
+ int qcount, err;
+
+ if (!test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) {
+ pfvf->hw_ops = &otx2_hw_ops;
return 0;
}
- pf->hw_ops = &cn10k_hw_ops;
- base = pci_resource_start(pf->pdev, PCI_MBOX_BAR_NUM) +
- (MBOX_SIZE * (pf->total_vfs + 1));
-
- size = pci_resource_len(pf->pdev, PCI_MBOX_BAR_NUM) -
- (MBOX_SIZE * (pf->total_vfs + 1));
-
- pf->hw.lmt_base = ioremap(base, size);
+ pfvf->hw_ops = &cn10k_hw_ops;
+ qcount = pfvf->hw.max_queues;
+ /* LMTST lines allocation
+ * qcount = num_online_cpus();
+ * NPA = TX + RX + XDP.
+ * NIX = TX * 32 (For Burst SQE flush).
+ */
+ pfvf->tot_lmt_lines = (qcount * 3) + (qcount * 32);
+ pfvf->npa_lmt_lines = qcount * 3;
+ pfvf->nix_lmt_size = LMT_BURST_SIZE * LMT_LINE_SIZE;
- if (!pf->hw.lmt_base) {
- dev_err(pf->dev, "Unable to map PF LMTST region\n");
+ mutex_lock(&pfvf->mbox.lock);
+ req = otx2_mbox_alloc_msg_lmtst_tbl_setup(&pfvf->mbox);
+ if (!req) {
+ mutex_unlock(&pfvf->mbox.lock);
return -ENOMEM;
}
- /* FIXME: Get the num of LMTST lines from LMT table */
- pf->tot_lmt_lines = size / LMT_LINE_SIZE;
- num_lines = (pf->tot_lmt_lines - NIX_LMTID_BASE) /
- pf->hw.tx_queues;
- /* Number of LMT lines per SQ queues */
- pf->nix_lmt_lines = num_lines > 32 ? 32 : num_lines;
-
- pf->nix_lmt_size = pf->nix_lmt_lines * LMT_LINE_SIZE;
- return 0;
-}
+ req->use_local_lmt_region = true;
-int cn10k_vf_lmtst_init(struct otx2_nic *vf)
-{
- int size, num_lines;
-
- if (!test_bit(CN10K_LMTST, &vf->hw.cap_flag)) {
- vf->hw_ops = &otx2_hw_ops;
- return 0;
+ err = qmem_alloc(pfvf->dev, &pfvf->dync_lmt, pfvf->tot_lmt_lines,
+ LMT_LINE_SIZE);
+ if (err) {
+ mutex_unlock(&pfvf->mbox.lock);
+ return err;
}
+ pfvf->hw.lmt_base = (u64 *)pfvf->dync_lmt->base;
+ req->lmt_iova = (u64)pfvf->dync_lmt->iova;
- vf->hw_ops = &cn10k_hw_ops;
- size = pci_resource_len(vf->pdev, PCI_MBOX_BAR_NUM);
- vf->hw.lmt_base = ioremap_wc(pci_resource_start(vf->pdev,
- PCI_MBOX_BAR_NUM),
- size);
- if (!vf->hw.lmt_base) {
- dev_err(vf->dev, "Unable to map VF LMTST region\n");
- return -ENOMEM;
- }
+ err = otx2_sync_mbox_msg(&pfvf->mbox);
+ mutex_unlock(&pfvf->mbox.lock);
- vf->tot_lmt_lines = size / LMT_LINE_SIZE;
- /* LMTST lines per SQ */
- num_lines = (vf->tot_lmt_lines - NIX_LMTID_BASE) /
- vf->hw.tx_queues;
- vf->nix_lmt_lines = num_lines > 32 ? 32 : num_lines;
- vf->nix_lmt_size = vf->nix_lmt_lines * LMT_LINE_SIZE;
return 0;
}
-EXPORT_SYMBOL(cn10k_vf_lmtst_init);
+EXPORT_SYMBOL(cn10k_lmtst_init);
int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura)
{
struct otx2_snd_queue *sq;
sq = &pfvf->qset.sq[qidx];
- sq->lmt_addr = (__force u64 *)((u64)pfvf->hw.nix_lmt_base +
+ sq->lmt_addr = (u64 *)((u64)pfvf->hw.nix_lmt_base +
(qidx * pfvf->nix_lmt_size));
+ sq->lmt_id = pfvf->npa_lmt_lines + (qidx * LMT_BURST_SIZE);
+
/* Get memory to put this msg */
aq = otx2_mbox_alloc_msg_nix_cn10k_aq_enq(&pfvf->mbox);
if (!aq)
void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx)
{
- struct otx2_nic *pfvf = dev;
- int lmt_id = NIX_LMTID_BASE + (qidx * pfvf->nix_lmt_lines);
u64 val = 0, tar_addr = 0;
/* FIXME: val[0:10] LMT_ID.
* [12:15] no of LMTST - 1 in the burst.
* [19:63] data size of each LMTST in the burst except first.
*/
- val = (lmt_id & 0x7FF);
+ val = (sq->lmt_id & 0x7FF);
/* Target address for LMTST flush tells HW how many 128bit
* words are present.
* tar_addr[6:4] size of first LMTST - 1 in units of 128b.
void cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq);
void cn10k_sqe_flush(void *dev, struct otx2_snd_queue *sq, int size, int qidx);
int cn10k_sq_aq_init(void *dev, u16 qidx, u16 sqb_aura);
-int cn10k_pf_lmtst_init(struct otx2_nic *pf);
-int cn10k_vf_lmtst_init(struct otx2_nic *vf);
+int cn10k_lmtst_init(struct otx2_nic *pfvf);
int cn10k_free_all_ipolicers(struct otx2_nic *pfvf);
int cn10k_alloc_matchall_ipolicer(struct otx2_nic *pfvf);
int cn10k_free_matchall_ipolicer(struct otx2_nic *pfvf);
/* update dmac field in vlan offload rule */
if (pfvf->flags & OTX2_FLAG_RX_VLAN_SUPPORT)
otx2_install_rxvlan_offload_flow(pfvf);
+ /* update dmac address in ntuple and DMAC filter list */
+ if (pfvf->flags & OTX2_FLAG_DMACFLTR_SUPPORT)
+ otx2_dmacflt_update_pfmac_flow(pfvf);
} else {
return -EPERM;
}
unsigned long cap_flag;
#define LMT_LINE_SIZE 128
-#define NIX_LMTID_BASE 72 /* RX + TX + XDP */
- void __iomem *lmt_base;
+#define LMT_BURST_SIZE 32 /* 32 LMTST lines for burst SQE flush */
+ u64 *lmt_base;
u64 *npa_lmt_base;
u64 *nix_lmt_base;
};
u16 tc_flower_offset;
u16 ntuple_max_flows;
u16 tc_max_flows;
+ u8 dmacflt_max_flows;
+ u8 *bmap_to_dmacindex;
+ unsigned long dmacflt_bmap;
struct list_head flow_list;
};
#define OTX2_FLAG_TC_FLOWER_SUPPORT BIT_ULL(11)
#define OTX2_FLAG_TC_MATCHALL_EGRESS_ENABLED BIT_ULL(12)
#define OTX2_FLAG_TC_MATCHALL_INGRESS_ENABLED BIT_ULL(13)
+#define OTX2_FLAG_DMACFLTR_SUPPORT BIT_ULL(14)
u64 flags;
struct otx2_qset qset;
/* Block address of NIX either BLKADDR_NIX0 or BLKADDR_NIX1 */
int nix_blkaddr;
/* LMTST Lines info */
+ struct qmem *dync_lmt;
u16 tot_lmt_lines;
- u16 nix_lmt_lines;
+ u16 npa_lmt_lines;
u32 nix_lmt_size;
struct otx2_ptp *ptp;
void otx2_shutdown_tc(struct otx2_nic *nic);
int otx2_setup_tc(struct net_device *netdev, enum tc_setup_type type,
void *type_data);
+/* CGX/RPM DMAC filters support */
+int otx2_dmacflt_get_max_cnt(struct otx2_nic *pf);
+int otx2_dmacflt_add(struct otx2_nic *pf, const u8 *mac, u8 bit_pos);
+int otx2_dmacflt_remove(struct otx2_nic *pf, const u8 *mac, u8 bit_pos);
+int otx2_dmacflt_update(struct otx2_nic *pf, u8 *mac, u8 bit_pos);
+void otx2_dmacflt_reinstall_flows(struct otx2_nic *pf);
+void otx2_dmacflt_update_pfmac_flow(struct otx2_nic *pfvf);
#endif /* OTX2_COMMON_H */
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell OcteonTx2 RVU Physcial Function ethernet driver
+ *
+ * Copyright (C) 2021 Marvell.
+ */
+
+#include "otx2_common.h"
+
+static int otx2_dmacflt_do_add(struct otx2_nic *pf, const u8 *mac,
+ u8 *dmac_index)
+{
+ struct cgx_mac_addr_add_req *req;
+ struct cgx_mac_addr_add_rsp *rsp;
+ int err;
+
+ mutex_lock(&pf->mbox.lock);
+
+ req = otx2_mbox_alloc_msg_cgx_mac_addr_add(&pf->mbox);
+ if (!req) {
+ mutex_unlock(&pf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ ether_addr_copy(req->mac_addr, mac);
+ err = otx2_sync_mbox_msg(&pf->mbox);
+
+ if (!err) {
+ rsp = (struct cgx_mac_addr_add_rsp *)
+ otx2_mbox_get_rsp(&pf->mbox.mbox, 0, &req->hdr);
+ *dmac_index = rsp->index;
+ }
+
+ mutex_unlock(&pf->mbox.lock);
+ return err;
+}
+
+static int otx2_dmacflt_add_pfmac(struct otx2_nic *pf)
+{
+ struct cgx_mac_addr_set_or_get *req;
+ int err;
+
+ mutex_lock(&pf->mbox.lock);
+
+ req = otx2_mbox_alloc_msg_cgx_mac_addr_set(&pf->mbox);
+ if (!req) {
+ mutex_unlock(&pf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ ether_addr_copy(req->mac_addr, pf->netdev->dev_addr);
+ err = otx2_sync_mbox_msg(&pf->mbox);
+
+ mutex_unlock(&pf->mbox.lock);
+ return err;
+}
+
+int otx2_dmacflt_add(struct otx2_nic *pf, const u8 *mac, u8 bit_pos)
+{
+ u8 *dmacindex;
+
+ /* Store dmacindex returned by CGX/RPM driver which will
+ * be used for macaddr update/remove
+ */
+ dmacindex = &pf->flow_cfg->bmap_to_dmacindex[bit_pos];
+
+ if (ether_addr_equal(mac, pf->netdev->dev_addr))
+ return otx2_dmacflt_add_pfmac(pf);
+ else
+ return otx2_dmacflt_do_add(pf, mac, dmacindex);
+}
+
+static int otx2_dmacflt_do_remove(struct otx2_nic *pfvf, const u8 *mac,
+ u8 dmac_index)
+{
+ struct cgx_mac_addr_del_req *req;
+ int err;
+
+ mutex_lock(&pfvf->mbox.lock);
+ req = otx2_mbox_alloc_msg_cgx_mac_addr_del(&pfvf->mbox);
+ if (!req) {
+ mutex_unlock(&pfvf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ req->index = dmac_index;
+
+ err = otx2_sync_mbox_msg(&pfvf->mbox);
+ mutex_unlock(&pfvf->mbox.lock);
+
+ return err;
+}
+
+static int otx2_dmacflt_remove_pfmac(struct otx2_nic *pf)
+{
+ struct msg_req *req;
+ int err;
+
+ mutex_lock(&pf->mbox.lock);
+ req = otx2_mbox_alloc_msg_cgx_mac_addr_reset(&pf->mbox);
+ if (!req) {
+ mutex_unlock(&pf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ err = otx2_sync_mbox_msg(&pf->mbox);
+
+ mutex_unlock(&pf->mbox.lock);
+ return err;
+}
+
+int otx2_dmacflt_remove(struct otx2_nic *pf, const u8 *mac,
+ u8 bit_pos)
+{
+ u8 dmacindex = pf->flow_cfg->bmap_to_dmacindex[bit_pos];
+
+ if (ether_addr_equal(mac, pf->netdev->dev_addr))
+ return otx2_dmacflt_remove_pfmac(pf);
+ else
+ return otx2_dmacflt_do_remove(pf, mac, dmacindex);
+}
+
+/* CGX/RPM blocks support max unicast entries of 32.
+ * on typical configuration MAC block associated
+ * with 4 lmacs, each lmac will have 8 dmac entries
+ */
+int otx2_dmacflt_get_max_cnt(struct otx2_nic *pf)
+{
+ struct cgx_max_dmac_entries_get_rsp *rsp;
+ struct msg_req *msg;
+ int err;
+
+ mutex_lock(&pf->mbox.lock);
+ msg = otx2_mbox_alloc_msg_cgx_mac_max_entries_get(&pf->mbox);
+
+ if (!msg) {
+ mutex_unlock(&pf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ err = otx2_sync_mbox_msg(&pf->mbox);
+ if (err)
+ goto out;
+
+ rsp = (struct cgx_max_dmac_entries_get_rsp *)
+ otx2_mbox_get_rsp(&pf->mbox.mbox, 0, &msg->hdr);
+ pf->flow_cfg->dmacflt_max_flows = rsp->max_dmac_filters;
+
+out:
+ mutex_unlock(&pf->mbox.lock);
+ return err;
+}
+
+int otx2_dmacflt_update(struct otx2_nic *pf, u8 *mac, u8 bit_pos)
+{
+ struct cgx_mac_addr_update_req *req;
+ int rc;
+
+ mutex_lock(&pf->mbox.lock);
+
+ req = otx2_mbox_alloc_msg_cgx_mac_addr_update(&pf->mbox);
+
+ if (!req) {
+ mutex_unlock(&pf->mbox.lock);
+ return -ENOMEM;
+ }
+
+ ether_addr_copy(req->mac_addr, mac);
+ req->index = pf->flow_cfg->bmap_to_dmacindex[bit_pos];
+ rc = otx2_sync_mbox_msg(&pf->mbox);
+
+ mutex_unlock(&pf->mbox.lock);
+ return rc;
+}
bool is_vf;
u8 rss_ctx_id;
int vf;
+ bool dmac_filter;
+};
+
+enum dmac_req {
+ DMAC_ADDR_UPDATE,
+ DMAC_ADDR_DEL
};
static void otx2_clear_ntuple_flow_info(struct otx2_nic *pfvf, struct otx2_flow_config *flow_cfg)
if (!pf->mac_table)
return -ENOMEM;
+ otx2_dmacflt_get_max_cnt(pf);
+
+ /* DMAC filters are not allocated */
+ if (!pf->flow_cfg->dmacflt_max_flows)
+ return 0;
+
+ pf->flow_cfg->bmap_to_dmacindex =
+ devm_kzalloc(pf->dev, sizeof(u8) *
+ pf->flow_cfg->dmacflt_max_flows,
+ GFP_KERNEL);
+
+ if (!pf->flow_cfg->bmap_to_dmacindex)
+ return -ENOMEM;
+
+ pf->flags |= OTX2_FLAG_DMACFLTR_SUPPORT;
+
return 0;
}
{
struct otx2_nic *pf = netdev_priv(netdev);
+ if (bitmap_weight(&pf->flow_cfg->dmacflt_bmap,
+ pf->flow_cfg->dmacflt_max_flows))
+ netdev_warn(netdev,
+ "Add %pM to CGX/RPM DMAC filters list as well\n",
+ mac);
+
return otx2_do_add_macfilter(pf, mac);
}
list_add(&flow->list, head);
}
+static int otx2_get_maxflows(struct otx2_flow_config *flow_cfg)
+{
+ if (flow_cfg->nr_flows == flow_cfg->ntuple_max_flows ||
+ bitmap_weight(&flow_cfg->dmacflt_bmap,
+ flow_cfg->dmacflt_max_flows))
+ return flow_cfg->ntuple_max_flows + flow_cfg->dmacflt_max_flows;
+ else
+ return flow_cfg->ntuple_max_flows;
+}
+
int otx2_get_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc,
u32 location)
{
struct otx2_flow *iter;
- if (location >= pfvf->flow_cfg->ntuple_max_flows)
+ if (location >= otx2_get_maxflows(pfvf->flow_cfg))
return -EINVAL;
list_for_each_entry(iter, &pfvf->flow_cfg->flow_list, list) {
int idx = 0;
int err = 0;
- nfc->data = pfvf->flow_cfg->ntuple_max_flows;
+ nfc->data = otx2_get_maxflows(pfvf->flow_cfg);
while ((!err || err == -ENOENT) && idx < rule_cnt) {
err = otx2_get_flow(pfvf, nfc, location);
if (!err)
return 0;
}
+static int otx2_is_flow_rule_dmacfilter(struct otx2_nic *pfvf,
+ struct ethtool_rx_flow_spec *fsp)
+{
+ struct ethhdr *eth_mask = &fsp->m_u.ether_spec;
+ struct ethhdr *eth_hdr = &fsp->h_u.ether_spec;
+ u64 ring_cookie = fsp->ring_cookie;
+ u32 flow_type;
+
+ if (!(pfvf->flags & OTX2_FLAG_DMACFLTR_SUPPORT))
+ return false;
+
+ flow_type = fsp->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS);
+
+ /* CGX/RPM block dmac filtering configured for white listing
+ * check for action other than DROP
+ */
+ if (flow_type == ETHER_FLOW && ring_cookie != RX_CLS_FLOW_DISC &&
+ !ethtool_get_flow_spec_ring_vf(ring_cookie)) {
+ if (is_zero_ether_addr(eth_mask->h_dest) &&
+ is_valid_ether_addr(eth_hdr->h_dest))
+ return true;
+ }
+
+ return false;
+}
+
static int otx2_add_flow_msg(struct otx2_nic *pfvf, struct otx2_flow *flow)
{
u64 ring_cookie = flow->flow_spec.ring_cookie;
return err;
}
+static int otx2_add_flow_with_pfmac(struct otx2_nic *pfvf,
+ struct otx2_flow *flow)
+{
+ struct otx2_flow *pf_mac;
+ struct ethhdr *eth_hdr;
+
+ pf_mac = kzalloc(sizeof(*pf_mac), GFP_KERNEL);
+ if (!pf_mac)
+ return -ENOMEM;
+
+ pf_mac->entry = 0;
+ pf_mac->dmac_filter = true;
+ pf_mac->location = pfvf->flow_cfg->ntuple_max_flows;
+ memcpy(&pf_mac->flow_spec, &flow->flow_spec,
+ sizeof(struct ethtool_rx_flow_spec));
+ pf_mac->flow_spec.location = pf_mac->location;
+
+ /* Copy PF mac address */
+ eth_hdr = &pf_mac->flow_spec.h_u.ether_spec;
+ ether_addr_copy(eth_hdr->h_dest, pfvf->netdev->dev_addr);
+
+ /* Install DMAC filter with PF mac address */
+ otx2_dmacflt_add(pfvf, eth_hdr->h_dest, 0);
+
+ otx2_add_flow_to_list(pfvf, pf_mac);
+ pfvf->flow_cfg->nr_flows++;
+ set_bit(0, &pfvf->flow_cfg->dmacflt_bmap);
+
+ return 0;
+}
+
int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc)
{
struct otx2_flow_config *flow_cfg = pfvf->flow_cfg;
struct ethtool_rx_flow_spec *fsp = &nfc->fs;
struct otx2_flow *flow;
+ struct ethhdr *eth_hdr;
bool new = false;
+ int err = 0;
u32 ring;
- int err;
ring = ethtool_get_flow_spec_ring(fsp->ring_cookie);
if (!(pfvf->flags & OTX2_FLAG_NTUPLE_SUPPORT))
if (ring >= pfvf->hw.rx_queues && fsp->ring_cookie != RX_CLS_FLOW_DISC)
return -EINVAL;
- if (fsp->location >= flow_cfg->ntuple_max_flows)
+ if (fsp->location >= otx2_get_maxflows(flow_cfg))
return -EINVAL;
flow = otx2_find_flow(pfvf, fsp->location);
if (!flow) {
- flow = kzalloc(sizeof(*flow), GFP_ATOMIC);
+ flow = kzalloc(sizeof(*flow), GFP_KERNEL);
if (!flow)
return -ENOMEM;
flow->location = fsp->location;
- flow->entry = flow_cfg->flow_ent[flow->location];
new = true;
}
/* struct copy */
if (fsp->flow_type & FLOW_RSS)
flow->rss_ctx_id = nfc->rss_context;
- err = otx2_add_flow_msg(pfvf, flow);
+ if (otx2_is_flow_rule_dmacfilter(pfvf, &flow->flow_spec)) {
+ eth_hdr = &flow->flow_spec.h_u.ether_spec;
+
+ /* Sync dmac filter table with updated fields */
+ if (flow->dmac_filter)
+ return otx2_dmacflt_update(pfvf, eth_hdr->h_dest,
+ flow->entry);
+
+ if (bitmap_full(&flow_cfg->dmacflt_bmap,
+ flow_cfg->dmacflt_max_flows)) {
+ netdev_warn(pfvf->netdev,
+ "Can't insert the rule %d as max allowed dmac filters are %d\n",
+ flow->location +
+ flow_cfg->dmacflt_max_flows,
+ flow_cfg->dmacflt_max_flows);
+ err = -EINVAL;
+ if (new)
+ kfree(flow);
+ return err;
+ }
+
+ /* Install PF mac address to DMAC filter list */
+ if (!test_bit(0, &flow_cfg->dmacflt_bmap))
+ otx2_add_flow_with_pfmac(pfvf, flow);
+
+ flow->dmac_filter = true;
+ flow->entry = find_first_zero_bit(&flow_cfg->dmacflt_bmap,
+ flow_cfg->dmacflt_max_flows);
+ fsp->location = flow_cfg->ntuple_max_flows + flow->entry;
+ flow->flow_spec.location = fsp->location;
+ flow->location = fsp->location;
+
+ set_bit(flow->entry, &flow_cfg->dmacflt_bmap);
+ otx2_dmacflt_add(pfvf, eth_hdr->h_dest, flow->entry);
+
+ } else {
+ if (flow->location >= pfvf->flow_cfg->ntuple_max_flows) {
+ netdev_warn(pfvf->netdev,
+ "Can't insert non dmac ntuple rule at %d, allowed range %d-0\n",
+ flow->location,
+ flow_cfg->ntuple_max_flows - 1);
+ err = -EINVAL;
+ } else {
+ flow->entry = flow_cfg->flow_ent[flow->location];
+ err = otx2_add_flow_msg(pfvf, flow);
+ }
+ }
+
if (err) {
if (new)
kfree(flow);
return err;
}
+static void otx2_update_rem_pfmac(struct otx2_nic *pfvf, int req)
+{
+ struct otx2_flow *iter;
+ struct ethhdr *eth_hdr;
+ bool found = false;
+
+ list_for_each_entry(iter, &pfvf->flow_cfg->flow_list, list) {
+ if (iter->dmac_filter && iter->entry == 0) {
+ eth_hdr = &iter->flow_spec.h_u.ether_spec;
+ if (req == DMAC_ADDR_DEL) {
+ otx2_dmacflt_remove(pfvf, eth_hdr->h_dest,
+ 0);
+ clear_bit(0, &pfvf->flow_cfg->dmacflt_bmap);
+ found = true;
+ } else {
+ ether_addr_copy(eth_hdr->h_dest,
+ pfvf->netdev->dev_addr);
+ otx2_dmacflt_update(pfvf, eth_hdr->h_dest, 0);
+ }
+ break;
+ }
+ }
+
+ if (found) {
+ list_del(&iter->list);
+ kfree(iter);
+ pfvf->flow_cfg->nr_flows--;
+ }
+}
+
int otx2_remove_flow(struct otx2_nic *pfvf, u32 location)
{
struct otx2_flow_config *flow_cfg = pfvf->flow_cfg;
struct otx2_flow *flow;
int err;
- if (location >= flow_cfg->ntuple_max_flows)
+ if (location >= otx2_get_maxflows(flow_cfg))
return -EINVAL;
flow = otx2_find_flow(pfvf, location);
if (!flow)
return -ENOENT;
- err = otx2_remove_flow_msg(pfvf, flow->entry, false);
+ if (flow->dmac_filter) {
+ struct ethhdr *eth_hdr = &flow->flow_spec.h_u.ether_spec;
+
+ /* user not allowed to remove dmac filter with interface mac */
+ if (ether_addr_equal(pfvf->netdev->dev_addr, eth_hdr->h_dest))
+ return -EPERM;
+
+ err = otx2_dmacflt_remove(pfvf, eth_hdr->h_dest,
+ flow->entry);
+ clear_bit(flow->entry, &flow_cfg->dmacflt_bmap);
+ /* If all dmac filters are removed delete macfilter with
+ * interface mac address and configure CGX/RPM block in
+ * promiscuous mode
+ */
+ if (bitmap_weight(&flow_cfg->dmacflt_bmap,
+ flow_cfg->dmacflt_max_flows) == 1)
+ otx2_update_rem_pfmac(pfvf, DMAC_ADDR_DEL);
+ } else {
+ err = otx2_remove_flow_msg(pfvf, flow->entry, false);
+ }
+
if (err)
return err;
mutex_unlock(&pf->mbox.lock);
return rsp_hdr->rc;
}
+
+void otx2_dmacflt_reinstall_flows(struct otx2_nic *pf)
+{
+ struct otx2_flow *iter;
+ struct ethhdr *eth_hdr;
+
+ list_for_each_entry(iter, &pf->flow_cfg->flow_list, list) {
+ if (iter->dmac_filter) {
+ eth_hdr = &iter->flow_spec.h_u.ether_spec;
+ otx2_dmacflt_add(pf, eth_hdr->h_dest,
+ iter->entry);
+ }
+ }
+}
+
+void otx2_dmacflt_update_pfmac_flow(struct otx2_nic *pfvf)
+{
+ otx2_update_rem_pfmac(pfvf, DMAC_ADDR_UPDATE);
+}
struct msg_req *msg;
int err;
+ if (enable && bitmap_weight(&pf->flow_cfg->dmacflt_bmap,
+ pf->flow_cfg->dmacflt_max_flows))
+ netdev_warn(pf->netdev,
+ "CGX/RPM internal loopback might not work as DMAC filters are active\n");
+
mutex_lock(&pf->mbox.lock);
if (enable)
msg = otx2_mbox_alloc_msg_cgx_intlbk_enable(&pf->mbox);
if (test_bit(CN10K_LMTST, &pf->hw.cap_flag)) {
/* Reserve LMT lines for NPA AURA batch free */
- pf->hw.npa_lmt_base = (__force u64 *)pf->hw.lmt_base;
+ pf->hw.npa_lmt_base = pf->hw.lmt_base;
/* Reserve LMT lines for NIX TX */
- pf->hw.nix_lmt_base = (__force u64 *)((u64)pf->hw.npa_lmt_base +
- (NIX_LMTID_BASE * LMT_LINE_SIZE));
+ pf->hw.nix_lmt_base = (u64 *)((u64)pf->hw.npa_lmt_base +
+ (pf->npa_lmt_lines * LMT_LINE_SIZE));
}
err = otx2_init_hw_resources(pf);
/* Restore pause frame settings */
otx2_config_pause_frm(pf);
+ /* Install DMAC Filters */
+ if (pf->flags & OTX2_FLAG_DMACFLTR_SUPPORT)
+ otx2_dmacflt_reinstall_flows(pf);
+
err = otx2_rxtx_enable(pf, true);
if (err)
goto err_tx_stop_queues;
if (err)
goto err_detach_rsrc;
- err = cn10k_pf_lmtst_init(pf);
+ err = cn10k_lmtst_init(pf);
if (err)
goto err_detach_rsrc;
err_ptp_destroy:
otx2_ptp_destroy(pf);
err_detach_rsrc:
- if (hw->lmt_base)
- iounmap(hw->lmt_base);
+ if (test_bit(CN10K_LMTST, &pf->hw.cap_flag))
+ qmem_free(pf->dev, pf->dync_lmt);
otx2_detach_resources(&pf->mbox);
err_disable_mbox_intr:
otx2_disable_mbox_intr(pf);
otx2_mcam_flow_del(pf);
otx2_shutdown_tc(pf);
otx2_detach_resources(&pf->mbox);
- if (pf->hw.lmt_base)
- iounmap(pf->hw.lmt_base);
-
+ if (test_bit(CN10K_LMTST, &pf->hw.cap_flag))
+ qmem_free(pf->dev, pf->dync_lmt);
otx2_disable_mbox_intr(pf);
otx2_pfaf_mbox_destroy(pf);
pci_free_irq_vectors(pf->pdev);
struct otx2_nic *priv;
u32 burst, mark = 0;
u8 nr_police = 0;
- bool pps;
+ bool pps = false;
u64 rate;
int i;
u16 num_sqbs;
u16 sqe_thresh;
u8 sqe_per_sqb;
+ u32 lmt_id;
u64 io_addr;
u64 *aura_fc_addr;
u64 *lmt_addr;
if (err)
goto err_detach_rsrc;
- err = cn10k_vf_lmtst_init(vf);
+ err = cn10k_lmtst_init(vf);
if (err)
goto err_detach_rsrc;
err_unreg_netdev:
unregister_netdev(netdev);
err_detach_rsrc:
- if (hw->lmt_base)
- iounmap(hw->lmt_base);
+ if (test_bit(CN10K_LMTST, &vf->hw.cap_flag))
+ qmem_free(vf->dev, vf->dync_lmt);
otx2_detach_resources(&vf->mbox);
err_disable_mbox_intr:
otx2vf_disable_mbox_intr(vf);
destroy_workqueue(vf->otx2_wq);
otx2vf_disable_mbox_intr(vf);
otx2_detach_resources(&vf->mbox);
-
- if (vf->hw.lmt_base)
- iounmap(vf->hw.lmt_base);
-
+ if (test_bit(CN10K_LMTST, &vf->hw.cap_flag))
+ qmem_free(vf->dev, vf->dync_lmt);
otx2vf_vfaf_mbox_destroy(vf);
pci_free_irq_vectors(vf->pdev);
pci_set_drvdata(pdev, NULL);
tristate "Sparx5 switch driver"
depends on NET_SWITCHDEV
depends on HAS_IOMEM
+ depends on OF
select PHYLINK
select PHY_SPARX5_SERDES
select RESET_CONTROLLER
SET_NETDEV_DEV(ndev, &pdev->dev);
ret = register_netdev(ndev);
- if (ret) {
- free_netdev(ndev);
+ if (ret)
goto init_fail;
- }
netdev_dbg(ndev, "%s: IRQ=%d address=%pM\n",
__func__, ndev->irq, ndev->dev_addr);
}
static int ocelot_netdevice_changeupper(struct net_device *dev,
+ struct net_device *brport_dev,
struct netdev_notifier_changeupper_info *info)
{
struct netlink_ext_ack *extack;
if (netif_is_bridge_master(info->upper_dev)) {
if (info->linking)
- err = ocelot_netdevice_bridge_join(dev, dev,
+ err = ocelot_netdevice_bridge_join(dev, brport_dev,
info->upper_dev,
extack);
else
- err = ocelot_netdevice_bridge_leave(dev, dev,
+ err = ocelot_netdevice_bridge_leave(dev, brport_dev,
info->upper_dev);
}
if (netif_is_lag_master(info->upper_dev)) {
if (ocelot_port->bond != dev)
return NOTIFY_OK;
- err = ocelot_netdevice_changeupper(lower, info);
+ err = ocelot_netdevice_changeupper(lower, dev, info);
if (err)
return notifier_from_errno(err);
}
struct netdev_notifier_changeupper_info *info = ptr;
if (ocelot_netdevice_dev_check(dev))
- return ocelot_netdevice_changeupper(dev, info);
+ return ocelot_netdevice_changeupper(dev, dev, info);
if (netif_is_lag_master(dev))
return ocelot_netdevice_lag_changeupper(dev, info);
nfp_fl_ct_clean_flow_entry(ct_entry);
kfree(ct_map_ent);
- /* If this is the last pre_ct_rule it means that it is
- * very likely that the nft table will be cleaned up next,
- * as this happens on the removal of the last act_ct flow.
- * However we cannot deregister the callback on the removal
- * of the last nft flow as this runs into a deadlock situation.
- * So deregister the callback on removal of the last pre_ct flow
- * and remove any remaining nft flow entries. We also cannot
- * save this state and delete the callback later since the
- * nft table would already have been freed at that time.
- */
if (!zt->pre_ct_count) {
- nf_flow_table_offload_del_cb(zt->nft,
- nfp_fl_ct_handle_nft_flow,
- zt);
zt->nft = NULL;
nfp_fl_ct_clean_nft_entries(zt);
}
nfp_ct_map_params);
nfp_fl_ct_clean_flow_entry(ct_map_ent->ct_entry);
kfree(ct_map_ent);
+ break;
default:
break;
}
put_device(&adpt->phydev->mdio.dev);
mdiobus_unregister(adpt->mii_bus);
- free_netdev(netdev);
if (adpt->phy.digital)
iounmap(adpt->phy.digital);
iounmap(adpt->phy.base);
+ free_netdev(netdev);
+
return 0;
}
* maximum size.
*/
tx_per_ev = EFX_MAX_EVQ_SIZE / EFX_TXQ_MAX_ENT(efx);
+ tx_per_ev = min(tx_per_ev, EFX_MAX_TXQ_PER_CHANNEL);
n_xdp_tx = num_possible_cpus();
n_xdp_ev = DIV_ROUND_UP(n_xdp_tx, tx_per_ev);
netif_err(efx, drv, efx->net_dev,
"Insufficient resources for %d XDP event queues (%d other channels, max %d)\n",
n_xdp_ev, n_channels, max_channels);
+ netif_err(efx, drv, efx->net_dev,
+ "XDP_TX and XDP_REDIRECT will not work on this interface");
efx->n_xdp_channels = 0;
efx->xdp_tx_per_channel = 0;
efx->xdp_tx_queue_count = 0;
netif_err(efx, drv, efx->net_dev,
"Insufficient resources for %d XDP TX queues (%d other channels, max VIs %d)\n",
n_xdp_tx, n_channels, efx->max_vis);
+ netif_err(efx, drv, efx->net_dev,
+ "XDP_TX and XDP_REDIRECT will not work on this interface");
efx->n_xdp_channels = 0;
efx->xdp_tx_per_channel = 0;
efx->xdp_tx_queue_count = 0;
} else {
efx->n_xdp_channels = n_xdp_ev;
- efx->xdp_tx_per_channel = EFX_MAX_TXQ_PER_CHANNEL;
+ efx->xdp_tx_per_channel = tx_per_ev;
efx->xdp_tx_queue_count = n_xdp_tx;
n_channels += n_xdp_ev;
netif_dbg(efx, drv, efx->net_dev,
if (efx_channel_is_xdp_tx(channel)) {
efx_for_each_channel_tx_queue(tx_queue, channel) {
tx_queue->queue = next_queue++;
- netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n",
- channel->channel, tx_queue->label,
- xdp_queue_number, tx_queue->queue);
+
/* We may have a few left-over XDP TX
* queues owing to xdp_tx_queue_count
* not dividing evenly by EFX_MAX_TXQ_PER_CHANNEL.
* We still allocate and probe those
* TXQs, but never use them.
*/
- if (xdp_queue_number < efx->xdp_tx_queue_count)
+ if (xdp_queue_number < efx->xdp_tx_queue_count) {
+ netif_dbg(efx, drv, efx->net_dev, "Channel %u TXQ %u is XDP %u, HW %u\n",
+ channel->channel, tx_queue->label,
+ xdp_queue_number, tx_queue->queue);
efx->xdp_tx_queues[xdp_queue_number] = tx_queue;
- xdp_queue_number++;
+ xdp_queue_number++;
+ }
}
} else {
efx_for_each_channel_tx_queue(tx_queue, channel) {
}
}
}
- if (xdp_queue_number)
- efx->xdp_tx_queue_count = xdp_queue_number;
+ WARN_ON(xdp_queue_number != efx->xdp_tx_queue_count);
rc = netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels);
if (rc)
{
struct plat_stmmacenet_data *plat;
struct stmmac_resources res;
- bool mdio = false;
- int ret, i;
struct device_node *np;
+ int ret, i, phy_mode;
+ bool mdio = false;
np = dev_of_node(&pdev->dev);
if (plat->bus_id < 0)
plat->bus_id = pci_dev_id(pdev);
- plat->phy_interface = device_get_phy_mode(&pdev->dev);
- if (plat->phy_interface < 0)
+ phy_mode = device_get_phy_mode(&pdev->dev);
+ if (phy_mode < 0)
dev_err(&pdev->dev, "phy_mode not found\n");
+ plat->phy_interface = phy_mode;
plat->interface = PHY_INTERFACE_MODE_GMII;
pci_set_master(pdev);
void stmmac_disable_tx_queue(struct stmmac_priv *priv, u32 queue);
void stmmac_enable_tx_queue(struct stmmac_priv *priv, u32 queue);
int stmmac_xsk_wakeup(struct net_device *dev, u32 queue, u32 flags);
+struct timespec64 stmmac_calc_tas_basetime(ktime_t old_base_time,
+ ktime_t current_time,
+ u64 cycle_time);
#if IS_ENABLED(CONFIG_STMMAC_SELFTESTS)
void stmmac_selftest_run(struct net_device *dev,
priv->plat->rx_queues_to_use, false);
stmmac_fpe_handshake(priv, false);
+ stmmac_fpe_stop_wq(priv);
}
priv->speed = SPEED_UNKNOWN;
struct device_node *np = pdev->dev.of_node;
struct plat_stmmacenet_data *plat;
struct stmmac_dma_cfg *dma_cfg;
+ int phy_mode;
void *ret;
int rc;
eth_zero_addr(mac);
}
- plat->phy_interface = device_get_phy_mode(&pdev->dev);
- if (plat->phy_interface < 0)
- return ERR_PTR(plat->phy_interface);
+ phy_mode = device_get_phy_mode(&pdev->dev);
+ if (phy_mode < 0)
+ return ERR_PTR(phy_mode);
+ plat->phy_interface = phy_mode;
plat->interface = stmmac_of_get_mac_mode(np);
if (plat->interface < 0)
plat->interface = plat->phy_interface;
u32 sec, nsec;
u32 quotient, reminder;
int neg_adj = 0;
- bool xmac;
+ bool xmac, est_rst = false;
+ int ret;
xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
sec = quotient;
nsec = reminder;
+ /* If EST is enabled, disabled it before adjust ptp time. */
+ if (priv->plat->est && priv->plat->est->enable) {
+ est_rst = true;
+ mutex_lock(&priv->plat->est->lock);
+ priv->plat->est->enable = false;
+ stmmac_est_configure(priv, priv->ioaddr, priv->plat->est,
+ priv->plat->clk_ptp_rate);
+ mutex_unlock(&priv->plat->est->lock);
+ }
+
spin_lock_irqsave(&priv->ptp_lock, flags);
stmmac_adjust_systime(priv, priv->ptpaddr, sec, nsec, neg_adj, xmac);
spin_unlock_irqrestore(&priv->ptp_lock, flags);
+ /* Caculate new basetime and re-configured EST after PTP time adjust. */
+ if (est_rst) {
+ struct timespec64 current_time, time;
+ ktime_t current_time_ns, basetime;
+ u64 cycle_time;
+
+ mutex_lock(&priv->plat->est->lock);
+ priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, ¤t_time);
+ current_time_ns = timespec64_to_ktime(current_time);
+ time.tv_nsec = priv->plat->est->btr_reserve[0];
+ time.tv_sec = priv->plat->est->btr_reserve[1];
+ basetime = timespec64_to_ktime(time);
+ cycle_time = priv->plat->est->ctr[1] * NSEC_PER_SEC +
+ priv->plat->est->ctr[0];
+ time = stmmac_calc_tas_basetime(basetime,
+ current_time_ns,
+ cycle_time);
+
+ priv->plat->est->btr[0] = (u32)time.tv_nsec;
+ priv->plat->est->btr[1] = (u32)time.tv_sec;
+ priv->plat->est->enable = true;
+ ret = stmmac_est_configure(priv, priv->ioaddr, priv->plat->est,
+ priv->plat->clk_ptp_rate);
+ mutex_unlock(&priv->plat->est->lock);
+ if (ret)
+ netdev_err(priv->dev, "failed to configure EST\n");
+ }
+
return 0;
}
return ret;
}
+struct timespec64 stmmac_calc_tas_basetime(ktime_t old_base_time,
+ ktime_t current_time,
+ u64 cycle_time)
+{
+ struct timespec64 time;
+
+ if (ktime_after(old_base_time, current_time)) {
+ time = ktime_to_timespec64(old_base_time);
+ } else {
+ s64 n;
+ ktime_t base_time;
+
+ n = div64_s64(ktime_sub_ns(current_time, old_base_time),
+ cycle_time);
+ base_time = ktime_add_ns(old_base_time,
+ (n + 1) * cycle_time);
+
+ time = ktime_to_timespec64(base_time);
+ }
+
+ return time;
+}
+
static int tc_setup_taprio(struct stmmac_priv *priv,
struct tc_taprio_qopt_offload *qopt)
{
u32 size, wid = priv->dma_cap.estwid, dep = priv->dma_cap.estdep;
struct plat_stmmacenet_data *plat = priv->plat;
- struct timespec64 time, current_time;
+ struct timespec64 time, current_time, qopt_time;
ktime_t current_time_ns;
bool fpe = false;
int i, ret = 0;
GFP_KERNEL);
if (!plat->est)
return -ENOMEM;
+
+ mutex_init(&priv->plat->est->lock);
} else {
memset(plat->est, 0, sizeof(*plat->est));
}
size = qopt->num_entries;
+ mutex_lock(&priv->plat->est->lock);
priv->plat->est->gcl_size = size;
priv->plat->est->enable = qopt->enable;
+ mutex_unlock(&priv->plat->est->lock);
for (i = 0; i < size; i++) {
s64 delta_ns = qopt->entries[i].interval;
priv->plat->est->gcl[i] = delta_ns | (gates << wid);
}
+ mutex_lock(&priv->plat->est->lock);
/* Adjust for real system time */
priv->ptp_clock_ops.gettime64(&priv->ptp_clock_ops, ¤t_time);
current_time_ns = timespec64_to_ktime(current_time);
- if (ktime_after(qopt->base_time, current_time_ns)) {
- time = ktime_to_timespec64(qopt->base_time);
- } else {
- ktime_t base_time;
- s64 n;
-
- n = div64_s64(ktime_sub_ns(current_time_ns, qopt->base_time),
- qopt->cycle_time);
- base_time = ktime_add_ns(qopt->base_time,
- (n + 1) * qopt->cycle_time);
-
- time = ktime_to_timespec64(base_time);
- }
+ time = stmmac_calc_tas_basetime(qopt->base_time, current_time_ns,
+ qopt->cycle_time);
priv->plat->est->btr[0] = (u32)time.tv_nsec;
priv->plat->est->btr[1] = (u32)time.tv_sec;
+ qopt_time = ktime_to_timespec64(qopt->base_time);
+ priv->plat->est->btr_reserve[0] = (u32)qopt_time.tv_nsec;
+ priv->plat->est->btr_reserve[1] = (u32)qopt_time.tv_sec;
+
ctr = qopt->cycle_time;
priv->plat->est->ctr[0] = do_div(ctr, NSEC_PER_SEC);
priv->plat->est->ctr[1] = (u32)ctr;
- if (fpe && !priv->dma_cap.fpesel)
+ if (fpe && !priv->dma_cap.fpesel) {
+ mutex_unlock(&priv->plat->est->lock);
return -EOPNOTSUPP;
+ }
/* Actual FPE register configuration will be done after FPE handshake
* is success.
ret = stmmac_est_configure(priv, priv->ioaddr, priv->plat->est,
priv->plat->clk_ptp_rate);
+ mutex_unlock(&priv->plat->est->lock);
if (ret) {
netdev_err(priv->dev, "failed to configure EST\n");
goto disable;
return 0;
disable:
+ mutex_lock(&priv->plat->est->lock);
priv->plat->est->enable = false;
stmmac_est_configure(priv, priv->ioaddr, priv->plat->est,
priv->plat->clk_ptp_rate);
+ mutex_unlock(&priv->plat->est->lock);
priv->plat->fpe_cfg->enable = false;
stmmac_fpe_configure(priv, priv->ioaddr,
pci_release_regions(pdev);
#endif
- free_netdev(dev);
-
cancel_work_sync(&priv->tlan_tqueue);
+ free_netdev(dev);
}
static void tlan_start(struct net_device *dev)
release_mem_region(start, len);
err_out_kfree:
- free_netdev(dev);
-
pr_err("%s: initialization failure, aborting!\n", fp->name);
+ free_netdev(dev);
return ret;
}
u32 *mykey, u32 *mysalt)
{
const char aes_gcm_name[] = "rfc4106(gcm(aes))";
- struct net_device *dev = xs->xso.dev;
+ struct net_device *dev = xs->xso.real_dev;
unsigned char *key_data;
char *alg_name = NULL;
int key_len;
u16 sa_idx;
int ret;
- dev = xs->xso.dev;
+ dev = xs->xso.real_dev;
ns = netdev_priv(dev);
ipsec = &ns->ipsec;
static void nsim_ipsec_del_sa(struct xfrm_state *xs)
{
- struct netdevsim *ns = netdev_priv(xs->xso.dev);
+ struct netdevsim *ns = netdev_priv(xs->xso.real_dev);
struct nsim_ipsec *ipsec = &ns->ipsec;
u16 sa_idx;
static bool nsim_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
{
- struct netdevsim *ns = netdev_priv(xs->xso.dev);
+ struct netdevsim *ns = netdev_priv(xs->xso.real_dev);
struct nsim_ipsec *ipsec = &ns->ipsec;
ipsec->ok++;
/* Temperature read register (88E2110 only) */
MV_PCS_TEMP = 0x8042,
+ /* Number of ports on the device */
+ MV_PCS_PORT_INFO = 0xd00d,
+ MV_PCS_PORT_INFO_NPORTS_MASK = 0x0380,
+ MV_PCS_PORT_INFO_NPORTS_SHIFT = 7,
+
/* These registers appear at 0x800X and 0xa00X - the 0xa00X control
* registers appear to set themselves to the 0x800X when AN is
* restarted, but status registers appear readable from either.
#endif
};
+static int mv3310_get_number_of_ports(struct phy_device *phydev)
+{
+ int ret;
+
+ ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MV_PCS_PORT_INFO);
+ if (ret < 0)
+ return ret;
+
+ ret &= MV_PCS_PORT_INFO_NPORTS_MASK;
+ ret >>= MV_PCS_PORT_INFO_NPORTS_SHIFT;
+
+ return ret + 1;
+}
+
+static int mv3310_match_phy_device(struct phy_device *phydev)
+{
+ return mv3310_get_number_of_ports(phydev) == 1;
+}
+
+static int mv3340_match_phy_device(struct phy_device *phydev)
+{
+ return mv3310_get_number_of_ports(phydev) == 4;
+}
+
static int mv211x_match_phy_device(struct phy_device *phydev, bool has_5g)
{
int val;
static struct phy_driver mv3310_drivers[] = {
{
.phy_id = MARVELL_PHY_ID_88X3310,
- .phy_id_mask = MARVELL_PHY_ID_88X33X0_MASK,
+ .phy_id_mask = MARVELL_PHY_ID_MASK,
+ .match_phy_device = mv3310_match_phy_device,
.name = "mv88x3310",
.driver_data = &mv3310_type,
.get_features = mv3310_get_features,
.set_loopback = genphy_c45_loopback,
},
{
- .phy_id = MARVELL_PHY_ID_88X3340,
- .phy_id_mask = MARVELL_PHY_ID_88X33X0_MASK,
+ .phy_id = MARVELL_PHY_ID_88X3310,
+ .phy_id_mask = MARVELL_PHY_ID_MASK,
+ .match_phy_device = mv3340_match_phy_device,
.name = "mv88x3340",
.driver_data = &mv3340_type,
.get_features = mv3310_get_features,
module_phy_driver(mv3310_drivers);
static struct mdio_device_id __maybe_unused mv3310_tbl[] = {
- { MARVELL_PHY_ID_88X3310, MARVELL_PHY_ID_88X33X0_MASK },
- { MARVELL_PHY_ID_88X3340, MARVELL_PHY_ID_88X33X0_MASK },
+ { MARVELL_PHY_ID_88X3310, MARVELL_PHY_ID_MASK },
{ MARVELL_PHY_ID_88E2110, MARVELL_PHY_ID_MASK },
{ },
};
return ret;
}
+ phy_suspend(priv->phydev);
priv->phydev->mac_managed_pm = 1;
phy_attached_info(priv->phydev);
{
struct scatterlist *sgs[4], hdr, stat;
unsigned out_num = 0, tmp;
+ int ret;
/* Caller should know better */
BUG_ON(!virtio_has_feature(vi->vdev, VIRTIO_NET_F_CTRL_VQ));
sgs[out_num] = &stat;
BUG_ON(out_num + 1 > ARRAY_SIZE(sgs));
- virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC);
+ ret = virtqueue_add_sgs(vi->cvq, sgs, out_num, 1, vi, GFP_ATOMIC);
+ if (ret < 0) {
+ dev_warn(&vi->vdev->dev,
+ "Failed to add sgs for command vq: %d\n.", ret);
+ return false;
+ }
if (unlikely(!virtqueue_kick(vi->cvq)))
return vi->ctrl->status == VIRTIO_NET_OK;
/*
* Linux driver for VMware's vmxnet3 ethernet NIC.
*
- * Copyright (C) 2008-2020, VMware, Inc. All Rights Reserved.
+ * Copyright (C) 2008-2021, VMware, Inc. All Rights Reserved.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
#include "vmxnet3_int.h"
+#include <net/vxlan.h>
+#include <net/geneve.h>
+
+#define VXLAN_UDP_PORT 8472
struct vmxnet3_stat_desc {
char desc[ETH_GSTRING_LEN];
if (VMXNET3_VERSION_GE_4(adapter) &&
skb->encapsulation && skb->ip_summed == CHECKSUM_PARTIAL) {
u8 l4_proto = 0;
+ u16 port;
+ struct udphdr *udph;
switch (vlan_get_protocol(skb)) {
case htons(ETH_P_IP):
return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
}
- if (l4_proto != IPPROTO_UDP)
+ switch (l4_proto) {
+ case IPPROTO_UDP:
+ udph = udp_hdr(skb);
+ port = be16_to_cpu(udph->dest);
+ /* Check if offloaded port is supported */
+ if (port != GENEVE_UDP_PORT &&
+ port != IANA_VXLAN_UDP_PORT &&
+ port != VXLAN_UDP_PORT) {
+ return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+ }
+ break;
+ default:
return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
+ }
}
return features;
}
return -EINVAL;
}
-static int __init mod_init(void)
+static int __init hdlc_cisco_init(void)
{
register_hdlc_protocol(&proto);
return 0;
}
-static void __exit mod_exit(void)
+static void __exit hdlc_cisco_exit(void)
{
unregister_hdlc_protocol(&proto);
}
-module_init(mod_init);
-module_exit(mod_exit);
+module_init(hdlc_cisco_init);
+module_exit(hdlc_cisco_exit);
MODULE_AUTHOR("Krzysztof Halasa <khc@pm.waw.pl>");
MODULE_DESCRIPTION("Cisco HDLC protocol support for generic HDLC");
return -EINVAL;
}
-static int __init mod_init(void)
+static int __init hdlc_fr_init(void)
{
register_hdlc_protocol(&proto);
return 0;
}
-static void __exit mod_exit(void)
+static void __exit hdlc_fr_exit(void)
{
unregister_hdlc_protocol(&proto);
}
-module_init(mod_init);
-module_exit(mod_exit);
+module_init(hdlc_fr_init);
+module_exit(hdlc_fr_exit);
MODULE_AUTHOR("Krzysztof Halasa <khc@pm.waw.pl>");
MODULE_DESCRIPTION("Frame-Relay protocol support for generic HDLC");
return -EINVAL;
}
-static int __init mod_init(void)
+static int __init hdlc_ppp_init(void)
{
skb_queue_head_init(&tx_queue);
register_hdlc_protocol(&proto);
return 0;
}
-static void __exit mod_exit(void)
+static void __exit hdlc_ppp_exit(void)
{
unregister_hdlc_protocol(&proto);
}
-module_init(mod_init);
-module_exit(mod_exit);
+module_init(hdlc_ppp_init);
+module_exit(hdlc_ppp_exit);
MODULE_AUTHOR("Krzysztof Halasa <khc@pm.waw.pl>");
MODULE_DESCRIPTION("PPP protocol support for generic HDLC");
}
-static int __init mod_init(void)
+static int __init hdlc_raw_init(void)
{
register_hdlc_protocol(&proto);
return 0;
-static void __exit mod_exit(void)
+static void __exit hdlc_raw_exit(void)
{
unregister_hdlc_protocol(&proto);
}
-module_init(mod_init);
-module_exit(mod_exit);
+module_init(hdlc_raw_init);
+module_exit(hdlc_raw_exit);
MODULE_AUTHOR("Krzysztof Halasa <khc@pm.waw.pl>");
MODULE_DESCRIPTION("Raw HDLC protocol support for generic HDLC");
}
-static int __init mod_init(void)
+static int __init hdlc_eth_init(void)
{
register_hdlc_protocol(&proto);
return 0;
-static void __exit mod_exit(void)
+static void __exit hdlc_eth_exit(void)
{
unregister_hdlc_protocol(&proto);
}
-module_init(mod_init);
-module_exit(mod_exit);
+module_init(hdlc_eth_init);
+module_exit(hdlc_eth_exit);
MODULE_AUTHOR("Krzysztof Halasa <khc@pm.waw.pl>");
MODULE_DESCRIPTION("Ethernet encapsulation support for generic HDLC");
return -EINVAL;
}
-static int __init mod_init(void)
+static int __init hdlc_x25_init(void)
{
register_hdlc_protocol(&proto);
return 0;
}
-static void __exit mod_exit(void)
+static void __exit hdlc_x25_exit(void)
{
unregister_hdlc_protocol(&proto);
}
-module_init(mod_init);
-module_exit(mod_exit);
+module_init(hdlc_x25_init);
+module_exit(hdlc_x25_exit);
MODULE_AUTHOR("Krzysztof Halasa <khc@pm.waw.pl>");
MODULE_DESCRIPTION("X.25 protocol support for generic HDLC");
case WLAN_CIPHER_SUITE_WEP104:
if (!mvif->wep_sta)
return -EOPNOTSUPP;
+ break;
case WLAN_CIPHER_SUITE_TKIP:
case WLAN_CIPHER_SUITE_CCMP:
case WLAN_CIPHER_SUITE_CCMP_256:
ret = mt76_get_field(dev, MT_CONN_ON_MISC, MT_TOP_MISC2_FW_N9_RDY);
if (ret) {
dev_dbg(dev->mt76.dev, "Firmware is already download\n");
- return -EIO;
+ goto fw_loaded;
}
ret = mt7921_load_patch(dev);
return -EIO;
}
+fw_loaded:
mt76_queue_tx_cleanup(dev, dev->mt76.q_mcu[MT_MCUQ_FWDL], false);
#ifdef CONFIG_PM
return -EIO;
}
- /* check for the interafce id
- * if if_id 1 to 8 then create IP MUX channel sessions.
- * To start MUX session from 0 as network interface id would start
- * from 1 so map it to if_id = if_id - 1
- */
- if (if_id >= IP_MUX_SESSION_START && if_id <= IP_MUX_SESSION_END)
- return ipc_mux_open_session(ipc_imem->mux, if_id - 1);
-
- return -EINVAL;
+ return ipc_mux_open_session(ipc_imem->mux, if_id);
}
/* Release a net link to CP. */
{
if (ipc_imem->mux && if_id >= IP_MUX_SESSION_START &&
if_id <= IP_MUX_SESSION_END)
- ipc_mux_close_session(ipc_imem->mux, if_id - 1);
+ ipc_mux_close_session(ipc_imem->mux, if_id);
}
/* Tasklet call to do uplink transfer. */
goto out;
}
- if (if_id >= IP_MUX_SESSION_START && if_id <= IP_MUX_SESSION_END)
- /* Route the UL packet through IP MUX Layer */
- ret = ipc_mux_ul_trigger_encode(ipc_imem->mux,
- if_id - 1, skb);
- else
- dev_err(ipc_imem->dev,
- "invalid if_id %d: ", if_id);
+ /* Route the UL packet through IP MUX Layer */
+ ret = ipc_mux_ul_trigger_encode(ipc_imem->mux, if_id, skb);
out:
return ret;
}
#define BOOT_CHECK_DEFAULT_TIMEOUT 400
/* IP MUX channel range */
-#define IP_MUX_SESSION_START 1
-#define IP_MUX_SESSION_END 8
+#define IP_MUX_SESSION_START 0
+#define IP_MUX_SESSION_END 7
/* Default IP MUX channel */
-#define IP_MUX_SESSION_DEFAULT 1
+#define IP_MUX_SESSION_DEFAULT 0
/**
* ipc_imem_sys_port_open - Open a port link to CP.
/* Pass the packet to the netif layer. */
dest_skb->priority = service_class;
- return ipc_wwan_receive(wwan, dest_skb, false, if_id + 1);
+ return ipc_wwan_receive(wwan, dest_skb, false, if_id);
}
/* Decode Flow Credit Table in the block */
/* Store the device and event information */
info->dev = dev;
- snprintf(info->uevent, MAX_UEVENT_LEN, "%s: %s", dev_name(dev), uevent);
+ snprintf(info->uevent, MAX_UEVENT_LEN, "IOSM_EVENT=%s", uevent);
/* Schedule uevent in process context using work queue */
schedule_work(&info->work);
{
struct iosm_netdev_priv *priv = wwan_netdev_drvpriv(netdev);
struct iosm_wwan *ipc_wwan = priv->ipc_wwan;
+ unsigned int len = skb->len;
int if_id = priv->if_id;
int ret;
/* Return code of zero is success */
if (ret == 0) {
+ netdev->stats.tx_packets++;
+ netdev->stats.tx_bytes += len;
ret = NETDEV_TX_OK;
} else if (ret == -EBUSY) {
ret = NETDEV_TX_BUSY;
ret);
dev_kfree_skb_any(skb);
- return ret;
+ netdev->stats.tx_dropped++;
+ return NETDEV_TX_OK;
}
/* Ops structure for wwan net link */
iosm_dev->priv_flags |= IFF_NO_QUEUE;
iosm_dev->type = ARPHRD_NONE;
+ iosm_dev->mtu = ETH_DATA_LEN;
iosm_dev->min_mtu = ETH_MIN_MTU;
iosm_dev->max_mtu = ETH_MAX_MTU;
skb->pkt_type = PACKET_HOST;
- if (if_id < (IP_MUX_SESSION_START - 1) ||
- if_id > (IP_MUX_SESSION_END - 1)) {
+ if (if_id < IP_MUX_SESSION_START ||
+ if_id > IP_MUX_SESSION_END) {
ret = -EINVAL;
goto free;
}
break;
}
/* If arch decided it can't, fall through... */
-#endif /* HAVE_PCI_MMAP */
fallthrough;
+#endif /* HAVE_PCI_MMAP */
default:
ret = -EINVAL;
break;
break;
case AB8500_FG_CALIB_WAIT:
dev_dbg(di->dev, "Calibration WFI\n");
+ break;
default:
break;
}
queue_work(di->fg_wq, &di->fg_work);
break;
}
+ break;
default:
break;
}
default:
break;
}
+ break;
default:
break;
}
# Makefile for PTP 1588 clock support.
#
-ptp-y := ptp_clock.o ptp_chardev.o ptp_sysfs.o
+ptp-y := ptp_clock.o ptp_chardev.o ptp_sysfs.o ptp_vclock.o
ptp_kvm-$(CONFIG_X86) := ptp_kvm_x86.o ptp_kvm_common.o
ptp_kvm-$(CONFIG_HAVE_ARM_SMCCC) := ptp_kvm_arm.o ptp_kvm_common.o
obj-$(CONFIG_PTP_1588_CLOCK) += ptp.o
#define PTP_PPS_EVENT PPS_CAPTUREASSERT
#define PTP_PPS_MODE (PTP_PPS_DEFAULTS | PPS_CANWAIT | PPS_TSFMT_TSPEC)
+struct class *ptp_class;
+
/* private globals */
static dev_t ptp_devt;
-static struct class *ptp_class;
static DEFINE_IDA(ptp_clocks_map);
{
struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
+ if (ptp_vclock_in_use(ptp)) {
+ pr_err("ptp: virtual clock in use\n");
+ return -EBUSY;
+ }
+
return ptp->info->settime64(ptp->info, tp);
}
struct ptp_clock_info *ops;
int err = -EOPNOTSUPP;
+ if (ptp_vclock_in_use(ptp)) {
+ pr_err("ptp: virtual clock in use\n");
+ return -EBUSY;
+ }
+
ops = ptp->info;
if (tx->modes & ADJ_SETOFFSET) {
ptp_cleanup_pin_groups(ptp);
mutex_destroy(&ptp->tsevq_mux);
mutex_destroy(&ptp->pincfg_mux);
+ mutex_destroy(&ptp->n_vclocks_mux);
ida_simple_remove(&ptp_clocks_map, ptp->index);
kfree(ptp);
}
{
struct ptp_clock *ptp;
int err = 0, index, major = MAJOR(ptp_devt);
+ size_t size;
if (info->n_alarm > PTP_MAX_ALARMS)
return ERR_PTR(-EINVAL);
spin_lock_init(&ptp->tsevq.lock);
mutex_init(&ptp->tsevq_mux);
mutex_init(&ptp->pincfg_mux);
+ mutex_init(&ptp->n_vclocks_mux);
init_waitqueue_head(&ptp->tsev_wq);
if (ptp->info->do_aux_work) {
pr_err("failed to create ptp aux_worker %d\n", err);
goto kworker_err;
}
- ptp->pps_source->lookup_cookie = ptp;
+ }
+
+ /* PTP virtual clock is being registered under physical clock */
+ if (parent && parent->class && parent->class->name &&
+ strcmp(parent->class->name, "ptp") == 0)
+ ptp->is_virtual_clock = true;
+
+ if (!ptp->is_virtual_clock) {
+ ptp->max_vclocks = PTP_DEFAULT_MAX_VCLOCKS;
+
+ size = sizeof(int) * ptp->max_vclocks;
+ ptp->vclock_index = kzalloc(size, GFP_KERNEL);
+ if (!ptp->vclock_index) {
+ err = -ENOMEM;
+ goto no_mem_for_vclocks;
+ }
}
err = ptp_populate_pin_groups(ptp);
pr_err("failed to register pps source\n");
goto no_pps;
}
+ ptp->pps_source->lookup_cookie = ptp;
}
/* Initialize a new device of our class in our clock structure. */
no_pps:
ptp_cleanup_pin_groups(ptp);
no_pin_groups:
+ kfree(ptp->vclock_index);
+no_mem_for_vclocks:
if (ptp->kworker)
kthread_destroy_worker(ptp->kworker);
kworker_err:
mutex_destroy(&ptp->tsevq_mux);
mutex_destroy(&ptp->pincfg_mux);
+ mutex_destroy(&ptp->n_vclocks_mux);
ida_simple_remove(&ptp_clocks_map, index);
no_slot:
kfree(ptp);
int ptp_clock_unregister(struct ptp_clock *ptp)
{
+ if (ptp_vclock_in_use(ptp)) {
+ pr_err("ptp: virtual clock in use\n");
+ return -EBUSY;
+ }
+
ptp->defunct = 1;
wake_up_interruptible(&ptp->tsev_wq);
+ kfree(ptp->vclock_index);
+
if (ptp->kworker) {
kthread_cancel_delayed_work_sync(&ptp->aux_work);
kthread_destroy_worker(ptp->kworker);
#define PTP_MAX_TIMESTAMPS 128
#define PTP_BUF_TIMESTAMPS 30
+#define PTP_DEFAULT_MAX_VCLOCKS 20
struct timestamp_event_queue {
struct ptp_extts_event buf[PTP_MAX_TIMESTAMPS];
const struct attribute_group *pin_attr_groups[2];
struct kthread_worker *kworker;
struct kthread_delayed_work aux_work;
+ unsigned int max_vclocks;
+ unsigned int n_vclocks;
+ int *vclock_index;
+ struct mutex n_vclocks_mux; /* protect concurrent n_vclocks access */
+ bool is_virtual_clock;
+};
+
+#define info_to_vclock(d) container_of((d), struct ptp_vclock, info)
+#define cc_to_vclock(d) container_of((d), struct ptp_vclock, cc)
+#define dw_to_vclock(d) container_of((d), struct ptp_vclock, refresh_work)
+
+struct ptp_vclock {
+ struct ptp_clock *pclock;
+ struct ptp_clock_info info;
+ struct ptp_clock *clock;
+ struct cyclecounter cc;
+ struct timecounter tc;
+ spinlock_t lock; /* protects tc/cc */
};
/*
return cnt < 0 ? PTP_MAX_TIMESTAMPS + cnt : cnt;
}
+/* Check if ptp virtual clock is in use */
+static inline bool ptp_vclock_in_use(struct ptp_clock *ptp)
+{
+ bool in_use = false;
+
+ if (mutex_lock_interruptible(&ptp->n_vclocks_mux))
+ return true;
+
+ if (!ptp->is_virtual_clock && ptp->n_vclocks)
+ in_use = true;
+
+ mutex_unlock(&ptp->n_vclocks_mux);
+
+ return in_use;
+}
+
+extern struct class *ptp_class;
+
/*
* see ptp_chardev.c
*/
int ptp_populate_pin_groups(struct ptp_clock *ptp);
void ptp_cleanup_pin_groups(struct ptp_clock *ptp);
+struct ptp_vclock *ptp_vclock_register(struct ptp_clock *pclock);
+void ptp_vclock_unregister(struct ptp_vclock *vclock);
#endif
* PTP 1588 clock support - sysfs interface.
*
* Copyright (C) 2010 OMICRON electronics GmbH
+ * Copyright 2021 NXP
*/
#include <linux/capability.h>
#include <linux/slab.h>
}
static DEVICE_ATTR(pps_enable, 0220, NULL, pps_enable_store);
+static int unregister_vclock(struct device *dev, void *data)
+{
+ struct ptp_clock *ptp = dev_get_drvdata(dev);
+ struct ptp_clock_info *info = ptp->info;
+ struct ptp_vclock *vclock;
+ u8 *num = data;
+
+ vclock = info_to_vclock(info);
+ dev_info(dev->parent, "delete virtual clock ptp%d\n",
+ vclock->clock->index);
+
+ ptp_vclock_unregister(vclock);
+ (*num)--;
+
+ /* For break. Not error. */
+ if (*num == 0)
+ return -EINVAL;
+
+ return 0;
+}
+
+static ssize_t n_vclocks_show(struct device *dev,
+ struct device_attribute *attr, char *page)
+{
+ struct ptp_clock *ptp = dev_get_drvdata(dev);
+ ssize_t size;
+
+ if (mutex_lock_interruptible(&ptp->n_vclocks_mux))
+ return -ERESTARTSYS;
+
+ size = snprintf(page, PAGE_SIZE - 1, "%u\n", ptp->n_vclocks);
+
+ mutex_unlock(&ptp->n_vclocks_mux);
+
+ return size;
+}
+
+static ssize_t n_vclocks_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct ptp_clock *ptp = dev_get_drvdata(dev);
+ struct ptp_vclock *vclock;
+ int err = -EINVAL;
+ u32 num, i;
+
+ if (kstrtou32(buf, 0, &num))
+ return err;
+
+ if (mutex_lock_interruptible(&ptp->n_vclocks_mux))
+ return -ERESTARTSYS;
+
+ if (num > ptp->max_vclocks) {
+ dev_err(dev, "max value is %d\n", ptp->max_vclocks);
+ goto out;
+ }
+
+ /* Need to create more vclocks */
+ if (num > ptp->n_vclocks) {
+ for (i = 0; i < num - ptp->n_vclocks; i++) {
+ vclock = ptp_vclock_register(ptp);
+ if (!vclock)
+ goto out;
+
+ *(ptp->vclock_index + ptp->n_vclocks + i) =
+ vclock->clock->index;
+
+ dev_info(dev, "new virtual clock ptp%d\n",
+ vclock->clock->index);
+ }
+ }
+
+ /* Need to delete vclocks */
+ if (num < ptp->n_vclocks) {
+ i = ptp->n_vclocks - num;
+ device_for_each_child_reverse(dev, &i,
+ unregister_vclock);
+
+ for (i = 1; i <= ptp->n_vclocks - num; i++)
+ *(ptp->vclock_index + ptp->n_vclocks - i) = -1;
+ }
+
+ if (num == 0)
+ dev_info(dev, "only physical clock in use now\n");
+ else
+ dev_info(dev, "guarantee physical clock free running\n");
+
+ ptp->n_vclocks = num;
+ mutex_unlock(&ptp->n_vclocks_mux);
+
+ return count;
+out:
+ mutex_unlock(&ptp->n_vclocks_mux);
+ return err;
+}
+static DEVICE_ATTR_RW(n_vclocks);
+
+static ssize_t max_vclocks_show(struct device *dev,
+ struct device_attribute *attr, char *page)
+{
+ struct ptp_clock *ptp = dev_get_drvdata(dev);
+ ssize_t size;
+
+ size = snprintf(page, PAGE_SIZE - 1, "%u\n", ptp->max_vclocks);
+
+ return size;
+}
+
+static ssize_t max_vclocks_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct ptp_clock *ptp = dev_get_drvdata(dev);
+ unsigned int *vclock_index;
+ int err = -EINVAL;
+ size_t size;
+ u32 max;
+
+ if (kstrtou32(buf, 0, &max) || max == 0)
+ return -EINVAL;
+
+ if (max == ptp->max_vclocks)
+ return count;
+
+ if (mutex_lock_interruptible(&ptp->n_vclocks_mux))
+ return -ERESTARTSYS;
+
+ if (max < ptp->n_vclocks)
+ goto out;
+
+ size = sizeof(int) * max;
+ vclock_index = kzalloc(size, GFP_KERNEL);
+ if (!vclock_index) {
+ err = -ENOMEM;
+ goto out;
+ }
+
+ size = sizeof(int) * ptp->n_vclocks;
+ memcpy(vclock_index, ptp->vclock_index, size);
+
+ kfree(ptp->vclock_index);
+ ptp->vclock_index = vclock_index;
+ ptp->max_vclocks = max;
+
+ mutex_unlock(&ptp->n_vclocks_mux);
+
+ return count;
+out:
+ mutex_unlock(&ptp->n_vclocks_mux);
+ return err;
+}
+static DEVICE_ATTR_RW(max_vclocks);
+
static struct attribute *ptp_attrs[] = {
&dev_attr_clock_name.attr,
&dev_attr_fifo.attr,
&dev_attr_period.attr,
&dev_attr_pps_enable.attr,
+ &dev_attr_n_vclocks.attr,
+ &dev_attr_max_vclocks.attr,
NULL
};
} else if (attr == &dev_attr_pps_enable.attr) {
if (!info->pps)
mode = 0;
+ } else if (attr == &dev_attr_n_vclocks.attr ||
+ attr == &dev_attr_max_vclocks.attr) {
+ if (ptp->is_virtual_clock)
+ mode = 0;
}
return mode;
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * PTP virtual clock driver
+ *
+ * Copyright 2021 NXP
+ */
+#include <linux/slab.h>
+#include "ptp_private.h"
+
+#define PTP_VCLOCK_CC_SHIFT 31
+#define PTP_VCLOCK_CC_MULT (1 << PTP_VCLOCK_CC_SHIFT)
+#define PTP_VCLOCK_FADJ_SHIFT 9
+#define PTP_VCLOCK_FADJ_DENOMINATOR 15625ULL
+#define PTP_VCLOCK_REFRESH_INTERVAL (HZ * 2)
+
+static int ptp_vclock_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
+{
+ struct ptp_vclock *vclock = info_to_vclock(ptp);
+ unsigned long flags;
+ s64 adj;
+
+ adj = (s64)scaled_ppm << PTP_VCLOCK_FADJ_SHIFT;
+ adj = div_s64(adj, PTP_VCLOCK_FADJ_DENOMINATOR);
+
+ spin_lock_irqsave(&vclock->lock, flags);
+ timecounter_read(&vclock->tc);
+ vclock->cc.mult = PTP_VCLOCK_CC_MULT + adj;
+ spin_unlock_irqrestore(&vclock->lock, flags);
+
+ return 0;
+}
+
+static int ptp_vclock_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+ struct ptp_vclock *vclock = info_to_vclock(ptp);
+ unsigned long flags;
+
+ spin_lock_irqsave(&vclock->lock, flags);
+ timecounter_adjtime(&vclock->tc, delta);
+ spin_unlock_irqrestore(&vclock->lock, flags);
+
+ return 0;
+}
+
+static int ptp_vclock_gettime(struct ptp_clock_info *ptp,
+ struct timespec64 *ts)
+{
+ struct ptp_vclock *vclock = info_to_vclock(ptp);
+ unsigned long flags;
+ u64 ns;
+
+ spin_lock_irqsave(&vclock->lock, flags);
+ ns = timecounter_read(&vclock->tc);
+ spin_unlock_irqrestore(&vclock->lock, flags);
+ *ts = ns_to_timespec64(ns);
+
+ return 0;
+}
+
+static int ptp_vclock_settime(struct ptp_clock_info *ptp,
+ const struct timespec64 *ts)
+{
+ struct ptp_vclock *vclock = info_to_vclock(ptp);
+ u64 ns = timespec64_to_ns(ts);
+ unsigned long flags;
+
+ spin_lock_irqsave(&vclock->lock, flags);
+ timecounter_init(&vclock->tc, &vclock->cc, ns);
+ spin_unlock_irqrestore(&vclock->lock, flags);
+
+ return 0;
+}
+
+static long ptp_vclock_refresh(struct ptp_clock_info *ptp)
+{
+ struct ptp_vclock *vclock = info_to_vclock(ptp);
+ struct timespec64 ts;
+
+ ptp_vclock_gettime(&vclock->info, &ts);
+
+ return PTP_VCLOCK_REFRESH_INTERVAL;
+}
+
+static const struct ptp_clock_info ptp_vclock_info = {
+ .owner = THIS_MODULE,
+ .name = "ptp virtual clock",
+ /* The maximum ppb value that long scaled_ppm can support */
+ .max_adj = 32767999,
+ .adjfine = ptp_vclock_adjfine,
+ .adjtime = ptp_vclock_adjtime,
+ .gettime64 = ptp_vclock_gettime,
+ .settime64 = ptp_vclock_settime,
+ .do_aux_work = ptp_vclock_refresh,
+};
+
+static u64 ptp_vclock_read(const struct cyclecounter *cc)
+{
+ struct ptp_vclock *vclock = cc_to_vclock(cc);
+ struct ptp_clock *ptp = vclock->pclock;
+ struct timespec64 ts = {};
+
+ if (ptp->info->gettimex64)
+ ptp->info->gettimex64(ptp->info, &ts, NULL);
+ else
+ ptp->info->gettime64(ptp->info, &ts);
+
+ return timespec64_to_ns(&ts);
+}
+
+static const struct cyclecounter ptp_vclock_cc = {
+ .read = ptp_vclock_read,
+ .mask = CYCLECOUNTER_MASK(32),
+ .mult = PTP_VCLOCK_CC_MULT,
+ .shift = PTP_VCLOCK_CC_SHIFT,
+};
+
+struct ptp_vclock *ptp_vclock_register(struct ptp_clock *pclock)
+{
+ struct ptp_vclock *vclock;
+
+ vclock = kzalloc(sizeof(*vclock), GFP_KERNEL);
+ if (!vclock)
+ return NULL;
+
+ vclock->pclock = pclock;
+ vclock->info = ptp_vclock_info;
+ vclock->cc = ptp_vclock_cc;
+
+ snprintf(vclock->info.name, PTP_CLOCK_NAME_LEN, "ptp%d_virt",
+ pclock->index);
+
+ spin_lock_init(&vclock->lock);
+
+ vclock->clock = ptp_clock_register(&vclock->info, &pclock->dev);
+ if (IS_ERR_OR_NULL(vclock->clock)) {
+ kfree(vclock);
+ return NULL;
+ }
+
+ timecounter_init(&vclock->tc, &vclock->cc, 0);
+ ptp_schedule_worker(vclock->clock, PTP_VCLOCK_REFRESH_INTERVAL);
+
+ return vclock;
+}
+
+void ptp_vclock_unregister(struct ptp_vclock *vclock)
+{
+ ptp_clock_unregister(vclock->clock);
+ kfree(vclock);
+}
+
+int ptp_get_vclocks_index(int pclock_index, int **vclock_index)
+{
+ char name[PTP_CLOCK_NAME_LEN] = "";
+ struct ptp_clock *ptp;
+ struct device *dev;
+ int num = 0;
+
+ if (pclock_index < 0)
+ return num;
+
+ snprintf(name, PTP_CLOCK_NAME_LEN, "ptp%d", pclock_index);
+ dev = class_find_device_by_name(ptp_class, name);
+ if (!dev)
+ return num;
+
+ ptp = dev_get_drvdata(dev);
+
+ if (mutex_lock_interruptible(&ptp->n_vclocks_mux)) {
+ put_device(dev);
+ return num;
+ }
+
+ *vclock_index = kzalloc(sizeof(int) * ptp->n_vclocks, GFP_KERNEL);
+ if (!(*vclock_index))
+ goto out;
+
+ memcpy(*vclock_index, ptp->vclock_index, sizeof(int) * ptp->n_vclocks);
+ num = ptp->n_vclocks;
+out:
+ mutex_unlock(&ptp->n_vclocks_mux);
+ put_device(dev);
+ return num;
+}
+EXPORT_SYMBOL(ptp_get_vclocks_index);
+
+void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps,
+ int vclock_index)
+{
+ char name[PTP_CLOCK_NAME_LEN] = "";
+ struct ptp_vclock *vclock;
+ struct ptp_clock *ptp;
+ unsigned long flags;
+ struct device *dev;
+ u64 ns;
+
+ snprintf(name, PTP_CLOCK_NAME_LEN, "ptp%d", vclock_index);
+ dev = class_find_device_by_name(ptp_class, name);
+ if (!dev)
+ return;
+
+ ptp = dev_get_drvdata(dev);
+ if (!ptp->is_virtual_clock) {
+ put_device(dev);
+ return;
+ }
+
+ vclock = info_to_vclock(ptp->info);
+
+ ns = ktime_to_ns(hwtstamps->hwtstamp);
+
+ spin_lock_irqsave(&vclock->lock, flags);
+ ns = timecounter_cyc2time(&vclock->tc, ns);
+ spin_unlock_irqrestore(&vclock->lock, flags);
+
+ put_device(dev);
+ hwtstamps->hwtstamp = ns_to_ktime(ns);
+}
+EXPORT_SYMBOL(ptp_convert_timestamp);
return 0;
}
- if (state->period != pwm->state.period ||
- state->duty_cycle != pwm->state.duty_cycle) {
- err = berlin_pwm_config(chip, pwm, state->duty_cycle, state->period);
- if (err)
- return err;
- }
+ err = berlin_pwm_config(chip, pwm, state->duty_cycle, state->period);
+ if (err)
+ return err;
if (!enabled)
return berlin_pwm_enable(chip, pwm);
int ret;
struct ep93xx_pwm *ep93xx_pwm = to_ep93xx_pwm(chip);
bool enabled = state->enabled;
+ void __iomem *base = ep93xx_pwm->base;
+ unsigned long long c;
+ unsigned long period_cycles;
+ unsigned long duty_cycles;
+ unsigned long term;
if (state->polarity != pwm->state.polarity) {
if (enabled) {
return 0;
}
- if (state->period != pwm->state.period ||
- state->duty_cycle != pwm->state.duty_cycle) {
- struct ep93xx_pwm *ep93xx_pwm = to_ep93xx_pwm(chip);
- void __iomem *base = ep93xx_pwm->base;
- unsigned long long c;
- unsigned long period_cycles;
- unsigned long duty_cycles;
- unsigned long term;
+ /*
+ * The clock needs to be enabled to access the PWM registers.
+ * Configuration can be changed at any time.
+ */
+ if (!pwm_is_enabled(pwm)) {
+ ret = clk_prepare_enable(ep93xx_pwm->clk);
+ if (ret)
+ return ret;
+ }
- /*
- * The clock needs to be enabled to access the PWM registers.
- * Configuration can be changed at any time.
- */
- if (!pwm_is_enabled(pwm)) {
- ret = clk_prepare_enable(ep93xx_pwm->clk);
- if (ret)
- return ret;
- }
+ c = clk_get_rate(ep93xx_pwm->clk);
+ c *= state->period;
+ do_div(c, 1000000000);
+ period_cycles = c;
+
+ c = period_cycles;
+ c *= state->duty_cycle;
+ do_div(c, state->period);
+ duty_cycles = c;
- c = clk_get_rate(ep93xx_pwm->clk);
- c *= state->period;
- do_div(c, 1000000000);
- period_cycles = c;
-
- c = period_cycles;
- c *= state->duty_cycle;
- do_div(c, state->period);
- duty_cycles = c;
-
- if (period_cycles < 0x10000 && duty_cycles < 0x10000) {
- term = readw(base + EP93XX_PWMx_TERM_COUNT);
-
- /* Order is important if PWM is running */
- if (period_cycles > term) {
- writew(period_cycles, base + EP93XX_PWMx_TERM_COUNT);
- writew(duty_cycles, base + EP93XX_PWMx_DUTY_CYCLE);
- } else {
- writew(duty_cycles, base + EP93XX_PWMx_DUTY_CYCLE);
- writew(period_cycles, base + EP93XX_PWMx_TERM_COUNT);
- }
- ret = 0;
+ if (period_cycles < 0x10000 && duty_cycles < 0x10000) {
+ term = readw(base + EP93XX_PWMx_TERM_COUNT);
+
+ /* Order is important if PWM is running */
+ if (period_cycles > term) {
+ writew(period_cycles, base + EP93XX_PWMx_TERM_COUNT);
+ writew(duty_cycles, base + EP93XX_PWMx_DUTY_CYCLE);
} else {
- ret = -EINVAL;
+ writew(duty_cycles, base + EP93XX_PWMx_DUTY_CYCLE);
+ writew(period_cycles, base + EP93XX_PWMx_TERM_COUNT);
}
+ ret = 0;
+ } else {
+ ret = -EINVAL;
+ }
- if (!pwm_is_enabled(pwm))
- clk_disable_unprepare(ep93xx_pwm->clk);
+ if (!pwm_is_enabled(pwm))
+ clk_disable_unprepare(ep93xx_pwm->clk);
- if (ret)
- return ret;
- }
+ if (ret)
+ return ret;
if (!enabled) {
ret = clk_prepare_enable(ep93xx_pwm->clk);
return 0;
}
- if (state->period != pwm->state.period ||
- state->duty_cycle != pwm->state.duty_cycle) {
- err = spear_pwm_config(chip, pwm, state->duty_cycle, state->period);
- if (err)
- return err;
- }
+ err = spear_pwm_config(chip, pwm, state->duty_cycle, state->period);
+ if (err)
+ return err;
if (!pwm->state.enabled)
return spear_pwm_enable(chip, pwm);
}
}
- if (state->period != cstate->period ||
- state->duty_cycle != cstate->duty_cycle) {
- ret = sprd_pwm_config(spc, pwm, state->duty_cycle,
- state->period);
- if (ret)
- return ret;
- }
+ ret = sprd_pwm_config(spc, pwm, state->duty_cycle,
+ state->period);
+ if (ret)
+ return ret;
sprd_pwm_write(spc, pwm->hwpwm, SPRD_PWM_ENABLE, 1);
} else if (cstate->enabled) {
return 0;
}
- if (state->period != pwm->state.period ||
- state->duty_cycle != pwm->state.duty_cycle) {
- if (state->period > NSEC_PER_SEC)
- return -ERANGE;
+ if (state->period > NSEC_PER_SEC)
+ return -ERANGE;
- err = ecap_pwm_config(chip, pwm, state->duty_cycle,
- state->period, enabled);
- if (err)
- return err;
- }
+ err = ecap_pwm_config(chip, pwm, state->duty_cycle,
+ state->period, enabled);
+ if (err)
+ return err;
if (!enabled)
return ecap_pwm_enable(chip, pwm);
case MTSEEK:
if (device->required_tapemarks)
tape_std_terminate_write(device);
- default:
- ;
}
rc = tape_mtop(device, op.mt_op, op.mt_count);
get_ccwdev_lock(ch->cdev), saveflags);
if (rc != 0)
ctcm_ccw_check_rc(ch, rc, "normal RX");
+ break;
default:
break;
}
if (qeth_is_ipafunc_supported(card, prot,
IPA_OSA_MC_ROUTER))
return 0;
+ goto out_inval;
default:
goto out_inval;
}
break;
#else
pr_notice("ATA device seen but CONFIG_SCSI_SAS_ATA=N so cannot attach\n");
- /* Fall through */
+ fallthrough;
#endif
/* Fall through - only for the #else condition above. */
default:
MODULE_ALIAS_SCSI_DEVICE(TYPE_RBC);
MODULE_ALIAS_SCSI_DEVICE(TYPE_ZBC);
-#if !defined(CONFIG_DEBUG_BLOCK_EXT_DEVT)
#define SD_MINORS 16
-#else
-#define SD_MINORS 0
-#endif
static void sd_config_discard(struct scsi_disk *, unsigned int);
static void sd_config_write_same(struct scsi_disk *);
case USB_SPEED_FULL:
if (max <= 1023)
break;
+ fallthrough;
default:
goto en_done;
}
case FB_BLANK_POWERDOWN:
/* turn off panel */
xilinx_fb_out32(drvdata, REG_CTRL, 0);
+ break;
+
default:
break;
}
if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE))
return;
- mutex_lock(&fs_info->reclaim_bgs_lock);
+ /*
+ * Long running balances can keep us blocked here for eternity, so
+ * simply skip reclaim if we're unable to get the mutex.
+ */
+ if (!mutex_trylock(&fs_info->reclaim_bgs_lock)) {
+ btrfs_exclop_finish(fs_info);
+ return;
+ }
+
spin_lock(&fs_info->unused_bgs_lock);
while (!list_empty(&fs_info->reclaim_bgs)) {
+ u64 zone_unusable;
int ret = 0;
bg = list_first_entry(&fs_info->reclaim_bgs,
goto next;
}
+ /*
+ * Cache the zone_unusable value before turning the block group
+ * to read only. As soon as the blog group is read only it's
+ * zone_unusable value gets moved to the block group's read-only
+ * bytes and isn't available for calculations anymore.
+ */
+ zone_unusable = bg->zone_unusable;
ret = inc_block_group_ro(bg, 0);
up_write(&space_info->groups_sem);
if (ret < 0)
goto next;
- btrfs_info(fs_info, "reclaiming chunk %llu with %llu%% used",
- bg->start, div_u64(bg->used * 100, bg->length));
+ btrfs_info(fs_info,
+ "reclaiming chunk %llu with %llu%% used %llu%% unusable",
+ bg->start, div_u64(bg->used * 100, bg->length),
+ div64_u64(zone_unusable * 100, bg->length));
trace_btrfs_reclaim_block_group(bg);
ret = btrfs_relocate_chunk(fs_info, bg->start);
if (ret)
return ret;
}
+/*
+ * This function, insert_block_group_item(), belongs to the phase 2 of chunk
+ * allocation.
+ *
+ * See the comment at btrfs_chunk_alloc() for details about the chunk allocation
+ * phases.
+ */
static int insert_block_group_item(struct btrfs_trans_handle *trans,
struct btrfs_block_group *block_group)
{
return btrfs_insert_item(trans, root, &key, &bgi, sizeof(bgi));
}
+/*
+ * This function, btrfs_create_pending_block_groups(), belongs to the phase 2 of
+ * chunk allocation.
+ *
+ * See the comment at btrfs_chunk_alloc() for details about the chunk allocation
+ * phases.
+ */
void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_block_group *block_group;
int ret = 0;
- if (!trans->can_flush_pending_bgs)
- return;
-
while (!list_empty(&trans->new_bgs)) {
int index;
ret = insert_block_group_item(trans, block_group);
if (ret)
btrfs_abort_transaction(trans, ret);
+ if (!block_group->chunk_item_inserted) {
+ mutex_lock(&fs_info->chunk_mutex);
+ ret = btrfs_chunk_alloc_add_chunk_item(trans, block_group);
+ mutex_unlock(&fs_info->chunk_mutex);
+ if (ret)
+ btrfs_abort_transaction(trans, ret);
+ }
ret = btrfs_finish_chunk_alloc(trans, block_group->start,
block_group->length);
if (ret)
btrfs_trans_release_chunk_metadata(trans);
}
-int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
- u64 type, u64 chunk_offset, u64 size)
+struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *trans,
+ u64 bytes_used, u64 type,
+ u64 chunk_offset, u64 size)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_block_group *cache;
cache = btrfs_create_block_group_cache(fs_info, chunk_offset);
if (!cache)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
cache->length = size;
set_free_space_tree_thresholds(cache);
ret = btrfs_load_block_group_zone_info(cache, true);
if (ret) {
btrfs_put_block_group(cache);
- return ret;
+ return ERR_PTR(ret);
}
ret = exclude_super_stripes(cache);
/* We may have excluded something, so call this just in case */
btrfs_free_excluded_extents(cache);
btrfs_put_block_group(cache);
- return ret;
+ return ERR_PTR(ret);
}
add_new_free_space(cache, chunk_offset, chunk_offset + size);
if (ret) {
btrfs_remove_free_space_cache(cache);
btrfs_put_block_group(cache);
- return ret;
+ return ERR_PTR(ret);
}
/*
btrfs_update_delayed_refs_rsv(trans);
set_avail_alloc_bits(fs_info, type);
- return 0;
+ return cache;
}
/*
return btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
}
+static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags)
+{
+ struct btrfs_block_group *bg;
+ int ret;
+
+ /*
+ * Check if we have enough space in the system space info because we
+ * will need to update device items in the chunk btree and insert a new
+ * chunk item in the chunk btree as well. This will allocate a new
+ * system block group if needed.
+ */
+ check_system_chunk(trans, flags);
+
+ bg = btrfs_alloc_chunk(trans, flags);
+ if (IS_ERR(bg)) {
+ ret = PTR_ERR(bg);
+ goto out;
+ }
+
+ /*
+ * If this is a system chunk allocation then stop right here and do not
+ * add the chunk item to the chunk btree. This is to prevent a deadlock
+ * because this system chunk allocation can be triggered while COWing
+ * some extent buffer of the chunk btree and while holding a lock on a
+ * parent extent buffer, in which case attempting to insert the chunk
+ * item (or update the device item) would result in a deadlock on that
+ * parent extent buffer. In this case defer the chunk btree updates to
+ * the second phase of chunk allocation and keep our reservation until
+ * the second phase completes.
+ *
+ * This is a rare case and can only be triggered by the very few cases
+ * we have where we need to touch the chunk btree outside chunk allocation
+ * and chunk removal. These cases are basically adding a device, removing
+ * a device or resizing a device.
+ */
+ if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
+ return 0;
+
+ ret = btrfs_chunk_alloc_add_chunk_item(trans, bg);
+ /*
+ * Normally we are not expected to fail with -ENOSPC here, since we have
+ * previously reserved space in the system space_info and allocated one
+ * new system chunk if necessary. However there are two exceptions:
+ *
+ * 1) We may have enough free space in the system space_info but all the
+ * existing system block groups have a profile which can not be used
+ * for extent allocation.
+ *
+ * This happens when mounting in degraded mode. For example we have a
+ * RAID1 filesystem with 2 devices, lose one device and mount the fs
+ * using the other device in degraded mode. If we then allocate a chunk,
+ * we may have enough free space in the existing system space_info, but
+ * none of the block groups can be used for extent allocation since they
+ * have a RAID1 profile, and because we are in degraded mode with a
+ * single device, we are forced to allocate a new system chunk with a
+ * SINGLE profile. Making check_system_chunk() iterate over all system
+ * block groups and check if they have a usable profile and enough space
+ * can be slow on very large filesystems, so we tolerate the -ENOSPC and
+ * try again after forcing allocation of a new system chunk. Like this
+ * we avoid paying the cost of that search in normal circumstances, when
+ * we were not mounted in degraded mode;
+ *
+ * 2) We had enough free space info the system space_info, and one suitable
+ * block group to allocate from when we called check_system_chunk()
+ * above. However right after we called it, the only system block group
+ * with enough free space got turned into RO mode by a running scrub,
+ * and in this case we have to allocate a new one and retry. We only
+ * need do this allocate and retry once, since we have a transaction
+ * handle and scrub uses the commit root to search for block groups.
+ */
+ if (ret == -ENOSPC) {
+ const u64 sys_flags = btrfs_system_alloc_profile(trans->fs_info);
+ struct btrfs_block_group *sys_bg;
+
+ sys_bg = btrfs_alloc_chunk(trans, sys_flags);
+ if (IS_ERR(sys_bg)) {
+ ret = PTR_ERR(sys_bg);
+ btrfs_abort_transaction(trans, ret);
+ goto out;
+ }
+
+ ret = btrfs_chunk_alloc_add_chunk_item(trans, sys_bg);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out;
+ }
+
+ ret = btrfs_chunk_alloc_add_chunk_item(trans, bg);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out;
+ }
+ } else if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out;
+ }
+out:
+ btrfs_trans_release_chunk_metadata(trans);
+
+ return ret;
+}
+
/*
- * If force is CHUNK_ALLOC_FORCE:
+ * Chunk allocation is done in 2 phases:
+ *
+ * 1) Phase 1 - through btrfs_chunk_alloc() we allocate device extents for
+ * the chunk, the chunk mapping, create its block group and add the items
+ * that belong in the chunk btree to it - more specifically, we need to
+ * update device items in the chunk btree and add a new chunk item to it.
+ *
+ * 2) Phase 2 - through btrfs_create_pending_block_groups(), we add the block
+ * group item to the extent btree and the device extent items to the devices
+ * btree.
+ *
+ * This is done to prevent deadlocks. For example when COWing a node from the
+ * extent btree we are holding a write lock on the node's parent and if we
+ * trigger chunk allocation and attempted to insert the new block group item
+ * in the extent btree right way, we could deadlock because the path for the
+ * insertion can include that parent node. At first glance it seems impossible
+ * to trigger chunk allocation after starting a transaction since tasks should
+ * reserve enough transaction units (metadata space), however while that is true
+ * most of the time, chunk allocation may still be triggered for several reasons:
+ *
+ * 1) When reserving metadata, we check if there is enough free space in the
+ * metadata space_info and therefore don't trigger allocation of a new chunk.
+ * However later when the task actually tries to COW an extent buffer from
+ * the extent btree or from the device btree for example, it is forced to
+ * allocate a new block group (chunk) because the only one that had enough
+ * free space was just turned to RO mode by a running scrub for example (or
+ * device replace, block group reclaim thread, etc), so we can not use it
+ * for allocating an extent and end up being forced to allocate a new one;
+ *
+ * 2) Because we only check that the metadata space_info has enough free bytes,
+ * we end up not allocating a new metadata chunk in that case. However if
+ * the filesystem was mounted in degraded mode, none of the existing block
+ * groups might be suitable for extent allocation due to their incompatible
+ * profile (for e.g. mounting a 2 devices filesystem, where all block groups
+ * use a RAID1 profile, in degraded mode using a single device). In this case
+ * when the task attempts to COW some extent buffer of the extent btree for
+ * example, it will trigger allocation of a new metadata block group with a
+ * suitable profile (SINGLE profile in the example of the degraded mount of
+ * the RAID1 filesystem);
+ *
+ * 3) The task has reserved enough transaction units / metadata space, but when
+ * it attempts to COW an extent buffer from the extent or device btree for
+ * example, it does not find any free extent in any metadata block group,
+ * therefore forced to try to allocate a new metadata block group.
+ * This is because some other task allocated all available extents in the
+ * meanwhile - this typically happens with tasks that don't reserve space
+ * properly, either intentionally or as a bug. One example where this is
+ * done intentionally is fsync, as it does not reserve any transaction units
+ * and ends up allocating a variable number of metadata extents for log
+ * tree extent buffers.
+ *
+ * We also need this 2 phases setup when adding a device to a filesystem with
+ * a seed device - we must create new metadata and system chunks without adding
+ * any of the block group items to the chunk, extent and device btrees. If we
+ * did not do it this way, we would get ENOSPC when attempting to update those
+ * btrees, since all the chunks from the seed device are read-only.
+ *
+ * Phase 1 does the updates and insertions to the chunk btree because if we had
+ * it done in phase 2 and have a thundering herd of tasks allocating chunks in
+ * parallel, we risk having too many system chunks allocated by many tasks if
+ * many tasks reach phase 1 without the previous ones completing phase 2. In the
+ * extreme case this leads to exhaustion of the system chunk array in the
+ * superblock. This is easier to trigger if using a btree node/leaf size of 64K
+ * and with RAID filesystems (so we have more device items in the chunk btree).
+ * This has happened before and commit eafa4fd0ad0607 ("btrfs: fix exhaustion of
+ * the system chunk array due to concurrent allocations") provides more details.
+ *
+ * For allocation of system chunks, we defer the updates and insertions into the
+ * chunk btree to phase 2. This is to prevent deadlocks on extent buffers because
+ * if the chunk allocation is triggered while COWing an extent buffer of the
+ * chunk btree, we are holding a lock on the parent of that extent buffer and
+ * doing the chunk btree updates and insertions can require locking that parent.
+ * This is for the very few and rare cases where we update the chunk btree that
+ * are not chunk allocation or chunk removal: adding a device, removing a device
+ * or resizing a device.
+ *
+ * The reservation of system space, done through check_system_chunk(), as well
+ * as all the updates and insertions into the chunk btree must be done while
+ * holding fs_info->chunk_mutex. This is important to guarantee that while COWing
+ * an extent buffer from the chunks btree we never trigger allocation of a new
+ * system chunk, which would result in a deadlock (trying to lock twice an
+ * extent buffer of the chunk btree, first time before triggering the chunk
+ * allocation and the second time during chunk allocation while attempting to
+ * update the chunks btree). The system chunk array is also updated while holding
+ * that mutex. The same logic applies to removing chunks - we must reserve system
+ * space, update the chunk btree and the system chunk array in the superblock
+ * while holding fs_info->chunk_mutex.
+ *
+ * This function, btrfs_chunk_alloc(), belongs to phase 1.
+ *
+ * If @force is CHUNK_ALLOC_FORCE:
* - return 1 if it successfully allocates a chunk,
* - return errors including -ENOSPC otherwise.
- * If force is NOT CHUNK_ALLOC_FORCE:
+ * If @force is NOT CHUNK_ALLOC_FORCE:
* - return 0 if it doesn't need to allocate a new chunk,
* - return 1 if it successfully allocates a chunk,
* - return errors including -ENOSPC otherwise.
/* Don't re-enter if we're already allocating a chunk */
if (trans->allocating_chunk)
return -ENOSPC;
+ /*
+ * If we are removing a chunk, don't re-enter or we would deadlock.
+ * System space reservation and system chunk allocation is done by the
+ * chunk remove operation (btrfs_remove_chunk()).
+ */
+ if (trans->removing_chunk)
+ return -ENOSPC;
space_info = btrfs_find_space_info(fs_info, flags);
ASSERT(space_info);
force_metadata_allocation(fs_info);
}
- /*
- * Check if we have enough space in SYSTEM chunk because we may need
- * to update devices.
- */
- check_system_chunk(trans, flags);
-
- ret = btrfs_alloc_chunk(trans, flags);
+ ret = do_chunk_alloc(trans, flags);
trans->allocating_chunk = false;
spin_lock(&space_info->lock);
space_info->chunk_alloc = 0;
spin_unlock(&space_info->lock);
mutex_unlock(&fs_info->chunk_mutex);
- /*
- * When we allocate a new chunk we reserve space in the chunk block
- * reserve to make sure we can COW nodes/leafs in the chunk tree or
- * add new nodes/leafs to it if we end up needing to do it when
- * inserting the chunk item and updating device items as part of the
- * second phase of chunk allocation, performed by
- * btrfs_finish_chunk_alloc(). So make sure we don't accumulate a
- * large number of new block groups to create in our transaction
- * handle's new_bgs list to avoid exhausting the chunk block reserve
- * in extreme cases - like having a single transaction create many new
- * block groups when starting to write out the free space caches of all
- * the block groups that were made dirty during the lifetime of the
- * transaction.
- */
- if (trans->chunk_bytes_reserved >= (u64)SZ_2M)
- btrfs_create_pending_block_groups(trans);
return ret;
}
*/
void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
{
- struct btrfs_transaction *cur_trans = trans->transaction;
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_space_info *info;
u64 left;
lockdep_assert_held(&fs_info->chunk_mutex);
info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
-again:
spin_lock(&info->lock);
left = info->total_bytes - btrfs_space_info_used(info, true);
spin_unlock(&info->lock);
if (left < thresh) {
u64 flags = btrfs_system_alloc_profile(fs_info);
- u64 reserved = atomic64_read(&cur_trans->chunk_bytes_reserved);
-
- /*
- * If there's not available space for the chunk tree (system
- * space) and there are other tasks that reserved space for
- * creating a new system block group, wait for them to complete
- * the creation of their system block group and release excess
- * reserved space. We do this because:
- *
- * *) We can end up allocating more system chunks than necessary
- * when there are multiple tasks that are concurrently
- * allocating block groups, which can lead to exhaustion of
- * the system array in the superblock;
- *
- * *) If we allocate extra and unnecessary system block groups,
- * despite being empty for a long time, and possibly forever,
- * they end not being added to the list of unused block groups
- * because that typically happens only when deallocating the
- * last extent from a block group - which never happens since
- * we never allocate from them in the first place. The few
- * exceptions are when mounting a filesystem or running scrub,
- * which add unused block groups to the list of unused block
- * groups, to be deleted by the cleaner kthread.
- * And even when they are added to the list of unused block
- * groups, it can take a long time until they get deleted,
- * since the cleaner kthread might be sleeping or busy with
- * other work (deleting subvolumes, running delayed iputs,
- * defrag scheduling, etc);
- *
- * This is rare in practice, but can happen when too many tasks
- * are allocating blocks groups in parallel (via fallocate())
- * and before the one that reserved space for a new system block
- * group finishes the block group creation and releases the space
- * reserved in excess (at btrfs_create_pending_block_groups()),
- * other tasks end up here and see free system space temporarily
- * not enough for updating the chunk tree.
- *
- * We unlock the chunk mutex before waiting for such tasks and
- * lock it again after the wait, otherwise we would deadlock.
- * It is safe to do so because allocating a system chunk is the
- * first thing done while allocating a new block group.
- */
- if (reserved > trans->chunk_bytes_reserved) {
- const u64 min_needed = reserved - thresh;
-
- mutex_unlock(&fs_info->chunk_mutex);
- wait_event(cur_trans->chunk_reserve_wait,
- atomic64_read(&cur_trans->chunk_bytes_reserved) <=
- min_needed);
- mutex_lock(&fs_info->chunk_mutex);
- goto again;
- }
+ struct btrfs_block_group *bg;
/*
* Ignore failure to create system chunk. We might end up not
* needing it, as we might not need to COW all nodes/leafs from
* the paths we visit in the chunk tree (they were already COWed
* or created in the current transaction for example).
+ *
+ * Also, if our caller is allocating a system chunk, do not
+ * attempt to insert the chunk item in the chunk btree, as we
+ * could deadlock on an extent buffer since our caller may be
+ * COWing an extent buffer from the chunk btree.
*/
- ret = btrfs_alloc_chunk(trans, flags);
+ bg = btrfs_alloc_chunk(trans, flags);
+ if (IS_ERR(bg)) {
+ ret = PTR_ERR(bg);
+ } else if (!(type & BTRFS_BLOCK_GROUP_SYSTEM)) {
+ /*
+ * If we fail to add the chunk item here, we end up
+ * trying again at phase 2 of chunk allocation, at
+ * btrfs_create_pending_block_groups(). So ignore
+ * any error here.
+ */
+ btrfs_chunk_alloc_add_chunk_item(trans, bg);
+ }
}
if (!ret) {
ret = btrfs_block_rsv_add(fs_info->chunk_root,
&fs_info->chunk_block_rsv,
thresh, BTRFS_RESERVE_NO_FLUSH);
- if (!ret) {
- atomic64_add(thresh, &cur_trans->chunk_bytes_reserved);
+ if (!ret)
trans->chunk_bytes_reserved += thresh;
- }
}
}
unsigned int removed:1;
unsigned int to_copy:1;
unsigned int relocating_repair:1;
+ unsigned int chunk_item_inserted:1;
int disk_cache_state;
void btrfs_reclaim_bgs(struct btrfs_fs_info *fs_info);
void btrfs_mark_bg_to_reclaim(struct btrfs_block_group *bg);
int btrfs_read_block_groups(struct btrfs_fs_info *info);
-int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
- u64 type, u64 chunk_offset, u64 size);
+struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *trans,
+ u64 bytes_used, u64 type,
+ u64 chunk_offset, u64 size);
void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans);
int btrfs_inc_block_group_ro(struct btrfs_block_group *cache,
bool do_chunk_alloc);
return 0;
}
-static struct extent_buffer *alloc_tree_block_no_bg_flush(
- struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- u64 parent_start,
- const struct btrfs_disk_key *disk_key,
- int level,
- u64 hint,
- u64 empty_size,
- enum btrfs_lock_nesting nest)
-{
- struct btrfs_fs_info *fs_info = root->fs_info;
- struct extent_buffer *ret;
-
- /*
- * If we are COWing a node/leaf from the extent, chunk, device or free
- * space trees, make sure that we do not finish block group creation of
- * pending block groups. We do this to avoid a deadlock.
- * COWing can result in allocation of a new chunk, and flushing pending
- * block groups (btrfs_create_pending_block_groups()) can be triggered
- * when finishing allocation of a new chunk. Creation of a pending block
- * group modifies the extent, chunk, device and free space trees,
- * therefore we could deadlock with ourselves since we are holding a
- * lock on an extent buffer that btrfs_create_pending_block_groups() may
- * try to COW later.
- * For similar reasons, we also need to delay flushing pending block
- * groups when splitting a leaf or node, from one of those trees, since
- * we are holding a write lock on it and its parent or when inserting a
- * new root node for one of those trees.
- */
- if (root == fs_info->extent_root ||
- root == fs_info->chunk_root ||
- root == fs_info->dev_root ||
- root == fs_info->free_space_root)
- trans->can_flush_pending_bgs = false;
-
- ret = btrfs_alloc_tree_block(trans, root, parent_start,
- root->root_key.objectid, disk_key, level,
- hint, empty_size, nest);
- trans->can_flush_pending_bgs = true;
-
- return ret;
-}
-
/*
* does the dirty work in cow of a single block. The parent block (if
* supplied) is updated to point to the new cow copy. The new buffer is marked
if ((root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && parent)
parent_start = parent->start;
- cow = alloc_tree_block_no_bg_flush(trans, root, parent_start, &disk_key,
- level, search_start, empty_size, nest);
+ cow = btrfs_alloc_tree_block(trans, root, parent_start,
+ root->root_key.objectid, &disk_key, level,
+ search_start, empty_size, nest);
if (IS_ERR(cow))
return PTR_ERR(cow);
else
btrfs_node_key(lower, &lower_key, 0);
- c = alloc_tree_block_no_bg_flush(trans, root, 0, &lower_key, level,
- root->node->start, 0,
- BTRFS_NESTING_NEW_ROOT);
+ c = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
+ &lower_key, level, root->node->start, 0,
+ BTRFS_NESTING_NEW_ROOT);
if (IS_ERR(c))
return PTR_ERR(c);
mid = (c_nritems + 1) / 2;
btrfs_node_key(c, &disk_key, mid);
- split = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, level,
- c->start, 0, BTRFS_NESTING_SPLIT);
+ split = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
+ &disk_key, level, c->start, 0,
+ BTRFS_NESTING_SPLIT);
if (IS_ERR(split))
return PTR_ERR(split);
* BTRFS_NESTING_SPLIT_THE_SPLITTENING if we need to, but for now just
* use BTRFS_NESTING_NEW_ROOT.
*/
- right = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, 0,
- l->start, 0, num_doubles ?
- BTRFS_NESTING_NEW_ROOT :
- BTRFS_NESTING_SPLIT);
+ right = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
+ &disk_key, 0, l->start, 0,
+ num_doubles ? BTRFS_NESTING_NEW_ROOT :
+ BTRFS_NESTING_SPLIT);
if (IS_ERR(right))
return PTR_ERR(right);
return btrfs_csum_one_bio(BTRFS_I(inode), bio, 0, 0);
}
+/*
+ * Split an extent_map at [start, start + len]
+ *
+ * This function is intended to be used only for extract_ordered_extent().
+ */
+static int split_zoned_em(struct btrfs_inode *inode, u64 start, u64 len,
+ u64 pre, u64 post)
+{
+ struct extent_map_tree *em_tree = &inode->extent_tree;
+ struct extent_map *em;
+ struct extent_map *split_pre = NULL;
+ struct extent_map *split_mid = NULL;
+ struct extent_map *split_post = NULL;
+ int ret = 0;
+ int modified;
+ unsigned long flags;
+
+ /* Sanity check */
+ if (pre == 0 && post == 0)
+ return 0;
+
+ split_pre = alloc_extent_map();
+ if (pre)
+ split_mid = alloc_extent_map();
+ if (post)
+ split_post = alloc_extent_map();
+ if (!split_pre || (pre && !split_mid) || (post && !split_post)) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ASSERT(pre + post < len);
+
+ lock_extent(&inode->io_tree, start, start + len - 1);
+ write_lock(&em_tree->lock);
+ em = lookup_extent_mapping(em_tree, start, len);
+ if (!em) {
+ ret = -EIO;
+ goto out_unlock;
+ }
+
+ ASSERT(em->len == len);
+ ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags));
+ ASSERT(em->block_start < EXTENT_MAP_LAST_BYTE);
+
+ flags = em->flags;
+ clear_bit(EXTENT_FLAG_PINNED, &em->flags);
+ clear_bit(EXTENT_FLAG_LOGGING, &flags);
+ modified = !list_empty(&em->list);
+
+ /* First, replace the em with a new extent_map starting from * em->start */
+ split_pre->start = em->start;
+ split_pre->len = (pre ? pre : em->len - post);
+ split_pre->orig_start = split_pre->start;
+ split_pre->block_start = em->block_start;
+ split_pre->block_len = split_pre->len;
+ split_pre->orig_block_len = split_pre->block_len;
+ split_pre->ram_bytes = split_pre->len;
+ split_pre->flags = flags;
+ split_pre->compress_type = em->compress_type;
+ split_pre->generation = em->generation;
+
+ replace_extent_mapping(em_tree, em, split_pre, modified);
+
+ /*
+ * Now we only have an extent_map at:
+ * [em->start, em->start + pre] if pre != 0
+ * [em->start, em->start + em->len - post] if pre == 0
+ */
+
+ if (pre) {
+ /* Insert the middle extent_map */
+ split_mid->start = em->start + pre;
+ split_mid->len = em->len - pre - post;
+ split_mid->orig_start = split_mid->start;
+ split_mid->block_start = em->block_start + pre;
+ split_mid->block_len = split_mid->len;
+ split_mid->orig_block_len = split_mid->block_len;
+ split_mid->ram_bytes = split_mid->len;
+ split_mid->flags = flags;
+ split_mid->compress_type = em->compress_type;
+ split_mid->generation = em->generation;
+ add_extent_mapping(em_tree, split_mid, modified);
+ }
+
+ if (post) {
+ split_post->start = em->start + em->len - post;
+ split_post->len = post;
+ split_post->orig_start = split_post->start;
+ split_post->block_start = em->block_start + em->len - post;
+ split_post->block_len = split_post->len;
+ split_post->orig_block_len = split_post->block_len;
+ split_post->ram_bytes = split_post->len;
+ split_post->flags = flags;
+ split_post->compress_type = em->compress_type;
+ split_post->generation = em->generation;
+ add_extent_mapping(em_tree, split_post, modified);
+ }
+
+ /* Once for us */
+ free_extent_map(em);
+ /* Once for the tree */
+ free_extent_map(em);
+
+out_unlock:
+ write_unlock(&em_tree->lock);
+ unlock_extent(&inode->io_tree, start, start + len - 1);
+out:
+ free_extent_map(split_pre);
+ free_extent_map(split_mid);
+ free_extent_map(split_post);
+
+ return ret;
+}
+
static blk_status_t extract_ordered_extent(struct btrfs_inode *inode,
struct bio *bio, loff_t file_offset)
{
struct btrfs_ordered_extent *ordered;
- struct extent_map *em = NULL, *em_new = NULL;
- struct extent_map_tree *em_tree = &inode->extent_tree;
u64 start = (u64)bio->bi_iter.bi_sector << SECTOR_SHIFT;
+ u64 file_len;
u64 len = bio->bi_iter.bi_size;
u64 end = start + len;
u64 ordered_end;
goto out;
}
+ file_len = ordered->num_bytes;
pre = start - ordered->disk_bytenr;
post = ordered_end - end;
ret = btrfs_split_ordered_extent(ordered, pre, post);
if (ret)
goto out;
-
- read_lock(&em_tree->lock);
- em = lookup_extent_mapping(em_tree, ordered->file_offset, len);
- if (!em) {
- read_unlock(&em_tree->lock);
- ret = -EIO;
- goto out;
- }
- read_unlock(&em_tree->lock);
-
- ASSERT(!test_bit(EXTENT_FLAG_COMPRESSED, &em->flags));
- /*
- * We cannot reuse em_new here but have to create a new one, as
- * unpin_extent_cache() expects the start of the extent map to be the
- * logical offset of the file, which does not hold true anymore after
- * splitting.
- */
- em_new = create_io_em(inode, em->start + pre, len,
- em->start + pre, em->block_start + pre, len,
- len, len, BTRFS_COMPRESS_NONE,
- BTRFS_ORDERED_REGULAR);
- if (IS_ERR(em_new)) {
- ret = PTR_ERR(em_new);
- goto out;
- }
- free_extent_map(em_new);
+ ret = split_zoned_em(inode, file_offset, file_len, pre, post);
out:
- free_extent_map(em);
btrfs_put_ordered_extent(ordered);
return errno_to_blk_status(ret);
}
/*
- * To be called after all the new block groups attached to the transaction
- * handle have been created (btrfs_create_pending_block_groups()).
+ * To be called after doing the chunk btree updates right after allocating a new
+ * chunk (after btrfs_chunk_alloc_add_chunk_item() is called), when removing a
+ * chunk after all chunk btree updates and after finishing the second phase of
+ * chunk allocation (btrfs_create_pending_block_groups()) in case some block
+ * group had its chunk item insertion delayed to the second phase.
*/
void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_transaction *cur_trans = trans->transaction;
if (!trans->chunk_bytes_reserved)
return;
- WARN_ON_ONCE(!list_empty(&trans->new_bgs));
-
btrfs_block_rsv_release(fs_info, &fs_info->chunk_block_rsv,
trans->chunk_bytes_reserved, NULL);
- atomic64_sub(trans->chunk_bytes_reserved, &cur_trans->chunk_bytes_reserved);
- cond_wake_up(&cur_trans->chunk_reserve_wait);
trans->chunk_bytes_reserved = 0;
}
spin_lock_init(&cur_trans->dropped_roots_lock);
INIT_LIST_HEAD(&cur_trans->releasing_ebs);
spin_lock_init(&cur_trans->releasing_ebs_lock);
- atomic64_set(&cur_trans->chunk_bytes_reserved, 0);
- init_waitqueue_head(&cur_trans->chunk_reserve_wait);
list_add_tail(&cur_trans->list, &fs_info->trans_list);
extent_io_tree_init(fs_info, &cur_trans->dirty_pages,
IO_TREE_TRANS_DIRTY_PAGES, fs_info->btree_inode);
h->fs_info = root->fs_info;
h->type = type;
- h->can_flush_pending_bgs = true;
INIT_LIST_HEAD(&h->new_bgs);
smp_mb();
spinlock_t releasing_ebs_lock;
struct list_head releasing_ebs;
-
- /*
- * The number of bytes currently reserved, by all transaction handles
- * attached to this transaction, for metadata extents of the chunk tree.
- */
- atomic64_t chunk_bytes_reserved;
- wait_queue_head_t chunk_reserve_wait;
};
#define __TRANS_FREEZABLE (1U << 0)
short aborted;
bool adding_csums;
bool allocating_chunk;
- bool can_flush_pending_bgs;
+ bool removing_chunk;
bool reloc_reserved;
bool in_fsync;
struct btrfs_root *root;
if (!log_root_tree->node) {
ret = btrfs_alloc_log_tree_node(trans, log_root_tree);
if (ret) {
- mutex_unlock(&fs_info->tree_log_mutex);
+ mutex_unlock(&fs_info->tree_root->log_mutex);
goto out;
}
}
extent = btrfs_item_ptr(leaf, path->slots[0],
struct btrfs_dev_extent);
} else {
- btrfs_handle_fs_error(fs_info, ret, "Slot search failed");
goto out;
}
*dev_extent_len = btrfs_dev_extent_length(leaf, extent);
ret = btrfs_del_item(trans, root, path);
- if (ret) {
- btrfs_handle_fs_error(fs_info, ret,
- "Failed to remove dev extent item");
- } else {
+ if (ret == 0)
set_bit(BTRFS_TRANS_HAVE_FREE_BGS, &trans->transaction->flags);
- }
out:
btrfs_free_path(path);
return ret;
u32 cur;
struct btrfs_key key;
- mutex_lock(&fs_info->chunk_mutex);
+ lockdep_assert_held(&fs_info->chunk_mutex);
array_size = btrfs_super_sys_array_size(super_copy);
ptr = super_copy->sys_chunk_array;
cur += len;
}
}
- mutex_unlock(&fs_info->chunk_mutex);
return ret;
}
return em;
}
+static int remove_chunk_item(struct btrfs_trans_handle *trans,
+ struct map_lookup *map, u64 chunk_offset)
+{
+ int i;
+
+ /*
+ * Removing chunk items and updating the device items in the chunks btree
+ * requires holding the chunk_mutex.
+ * See the comment at btrfs_chunk_alloc() for the details.
+ */
+ lockdep_assert_held(&trans->fs_info->chunk_mutex);
+
+ for (i = 0; i < map->num_stripes; i++) {
+ int ret;
+
+ ret = btrfs_update_device(trans, map->stripes[i].dev);
+ if (ret)
+ return ret;
+ }
+
+ return btrfs_free_chunk(trans, chunk_offset);
+}
+
int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
return PTR_ERR(em);
}
map = em->map_lookup;
- mutex_lock(&fs_info->chunk_mutex);
- check_system_chunk(trans, map->type);
- mutex_unlock(&fs_info->chunk_mutex);
/*
- * Take the device list mutex to prevent races with the final phase of
- * a device replace operation that replaces the device object associated
- * with map stripes (dev-replace.c:btrfs_dev_replace_finishing()).
+ * First delete the device extent items from the devices btree.
+ * We take the device_list_mutex to avoid racing with the finishing phase
+ * of a device replace operation. See the comment below before acquiring
+ * fs_info->chunk_mutex. Note that here we do not acquire the chunk_mutex
+ * because that can result in a deadlock when deleting the device extent
+ * items from the devices btree - COWing an extent buffer from the btree
+ * may result in allocating a new metadata chunk, which would attempt to
+ * lock again fs_info->chunk_mutex.
*/
mutex_lock(&fs_devices->device_list_mutex);
for (i = 0; i < map->num_stripes; i++) {
btrfs_clear_space_info_full(fs_info);
mutex_unlock(&fs_info->chunk_mutex);
}
+ }
+ mutex_unlock(&fs_devices->device_list_mutex);
- ret = btrfs_update_device(trans, device);
+ /*
+ * We acquire fs_info->chunk_mutex for 2 reasons:
+ *
+ * 1) Just like with the first phase of the chunk allocation, we must
+ * reserve system space, do all chunk btree updates and deletions, and
+ * update the system chunk array in the superblock while holding this
+ * mutex. This is for similar reasons as explained on the comment at
+ * the top of btrfs_chunk_alloc();
+ *
+ * 2) Prevent races with the final phase of a device replace operation
+ * that replaces the device object associated with the map's stripes,
+ * because the device object's id can change at any time during that
+ * final phase of the device replace operation
+ * (dev-replace.c:btrfs_dev_replace_finishing()), so we could grab the
+ * replaced device and then see it with an ID of
+ * BTRFS_DEV_REPLACE_DEVID, which would cause a failure when updating
+ * the device item, which does not exists on the chunk btree.
+ * The finishing phase of device replace acquires both the
+ * device_list_mutex and the chunk_mutex, in that order, so we are
+ * safe by just acquiring the chunk_mutex.
+ */
+ trans->removing_chunk = true;
+ mutex_lock(&fs_info->chunk_mutex);
+
+ check_system_chunk(trans, map->type);
+
+ ret = remove_chunk_item(trans, map, chunk_offset);
+ /*
+ * Normally we should not get -ENOSPC since we reserved space before
+ * through the call to check_system_chunk().
+ *
+ * Despite our system space_info having enough free space, we may not
+ * be able to allocate extents from its block groups, because all have
+ * an incompatible profile, which will force us to allocate a new system
+ * block group with the right profile, or right after we called
+ * check_system_space() above, a scrub turned the only system block group
+ * with enough free space into RO mode.
+ * This is explained with more detail at do_chunk_alloc().
+ *
+ * So if we get -ENOSPC, allocate a new system chunk and retry once.
+ */
+ if (ret == -ENOSPC) {
+ const u64 sys_flags = btrfs_system_alloc_profile(fs_info);
+ struct btrfs_block_group *sys_bg;
+
+ sys_bg = btrfs_alloc_chunk(trans, sys_flags);
+ if (IS_ERR(sys_bg)) {
+ ret = PTR_ERR(sys_bg);
+ btrfs_abort_transaction(trans, ret);
+ goto out;
+ }
+
+ ret = btrfs_chunk_alloc_add_chunk_item(trans, sys_bg);
if (ret) {
- mutex_unlock(&fs_devices->device_list_mutex);
btrfs_abort_transaction(trans, ret);
goto out;
}
- }
- mutex_unlock(&fs_devices->device_list_mutex);
- ret = btrfs_free_chunk(trans, chunk_offset);
- if (ret) {
+ ret = remove_chunk_item(trans, map, chunk_offset);
+ if (ret) {
+ btrfs_abort_transaction(trans, ret);
+ goto out;
+ }
+ } else if (ret) {
btrfs_abort_transaction(trans, ret);
goto out;
}
}
}
+ mutex_unlock(&fs_info->chunk_mutex);
+ trans->removing_chunk = false;
+
+ /*
+ * We are done with chunk btree updates and deletions, so release the
+ * system space we previously reserved (with check_system_chunk()).
+ */
+ btrfs_trans_release_chunk_metadata(trans);
+
ret = btrfs_remove_block_group(trans, chunk_offset, em);
if (ret) {
btrfs_abort_transaction(trans, ret);
}
out:
+ if (trans->removing_chunk) {
+ mutex_unlock(&fs_info->chunk_mutex);
+ trans->removing_chunk = false;
+ }
/* once for us */
free_extent_map(em);
return ret;
u32 array_size;
u8 *ptr;
- mutex_lock(&fs_info->chunk_mutex);
+ lockdep_assert_held(&fs_info->chunk_mutex);
+
array_size = btrfs_super_sys_array_size(super_copy);
if (array_size + item_size + sizeof(disk_key)
- > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) {
- mutex_unlock(&fs_info->chunk_mutex);
+ > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE)
return -EFBIG;
- }
ptr = super_copy->sys_chunk_array + array_size;
btrfs_cpu_key_to_disk(&disk_key, key);
memcpy(ptr, chunk, item_size);
item_size += sizeof(disk_key);
btrfs_set_super_sys_array_size(super_copy, array_size + item_size);
- mutex_unlock(&fs_info->chunk_mutex);
return 0;
}
}
}
-static int create_chunk(struct btrfs_trans_handle *trans,
+static struct btrfs_block_group *create_chunk(struct btrfs_trans_handle *trans,
struct alloc_chunk_ctl *ctl,
struct btrfs_device_info *devices_info)
{
struct btrfs_fs_info *info = trans->fs_info;
struct map_lookup *map = NULL;
struct extent_map_tree *em_tree;
+ struct btrfs_block_group *block_group;
struct extent_map *em;
u64 start = ctl->start;
u64 type = ctl->type;
map = kmalloc(map_lookup_size(ctl->num_stripes), GFP_NOFS);
if (!map)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
map->num_stripes = ctl->num_stripes;
for (i = 0; i < ctl->ndevs; ++i) {
em = alloc_extent_map();
if (!em) {
kfree(map);
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
}
set_bit(EXTENT_FLAG_FS_MAPPING, &em->flags);
em->map_lookup = map;
if (ret) {
write_unlock(&em_tree->lock);
free_extent_map(em);
- return ret;
+ return ERR_PTR(ret);
}
write_unlock(&em_tree->lock);
- ret = btrfs_make_block_group(trans, 0, type, start, ctl->chunk_size);
- if (ret)
+ block_group = btrfs_make_block_group(trans, 0, type, start, ctl->chunk_size);
+ if (IS_ERR(block_group))
goto error_del_extent;
for (i = 0; i < map->num_stripes; i++) {
check_raid56_incompat_flag(info, type);
check_raid1c34_incompat_flag(info, type);
- return 0;
+ return block_group;
error_del_extent:
write_lock(&em_tree->lock);
/* One for the tree reference */
free_extent_map(em);
- return ret;
+ return block_group;
}
-int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type)
+struct btrfs_block_group *btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
+ u64 type)
{
struct btrfs_fs_info *info = trans->fs_info;
struct btrfs_fs_devices *fs_devices = info->fs_devices;
struct btrfs_device_info *devices_info = NULL;
struct alloc_chunk_ctl ctl;
+ struct btrfs_block_group *block_group;
int ret;
lockdep_assert_held(&info->chunk_mutex);
if (!alloc_profile_is_valid(type, 0)) {
ASSERT(0);
- return -EINVAL;
+ return ERR_PTR(-EINVAL);
}
if (list_empty(&fs_devices->alloc_list)) {
if (btrfs_test_opt(info, ENOSPC_DEBUG))
btrfs_debug(info, "%s: no writable device", __func__);
- return -ENOSPC;
+ return ERR_PTR(-ENOSPC);
}
if (!(type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
btrfs_err(info, "invalid chunk type 0x%llx requested", type);
ASSERT(0);
- return -EINVAL;
+ return ERR_PTR(-EINVAL);
}
ctl.start = find_next_chunk(info);
devices_info = kcalloc(fs_devices->rw_devices, sizeof(*devices_info),
GFP_NOFS);
if (!devices_info)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
ret = gather_device_info(fs_devices, &ctl, devices_info);
- if (ret < 0)
+ if (ret < 0) {
+ block_group = ERR_PTR(ret);
goto out;
+ }
ret = decide_stripe_size(fs_devices, &ctl, devices_info);
- if (ret < 0)
+ if (ret < 0) {
+ block_group = ERR_PTR(ret);
goto out;
+ }
- ret = create_chunk(trans, &ctl, devices_info);
+ block_group = create_chunk(trans, &ctl, devices_info);
out:
kfree(devices_info);
- return ret;
+ return block_group;
}
/*
- * Chunk allocation falls into two parts. The first part does work
- * that makes the new allocated chunk usable, but does not do any operation
- * that modifies the chunk tree. The second part does the work that
- * requires modifying the chunk tree. This division is important for the
- * bootstrap process of adding storage to a seed btrfs.
+ * This function, btrfs_finish_chunk_alloc(), belongs to phase 2.
+ *
+ * See the comment at btrfs_chunk_alloc() for details about the chunk allocation
+ * phases.
*/
int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
u64 chunk_offset, u64 chunk_size)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_root *extent_root = fs_info->extent_root;
- struct btrfs_root *chunk_root = fs_info->chunk_root;
- struct btrfs_key key;
struct btrfs_device *device;
- struct btrfs_chunk *chunk;
- struct btrfs_stripe *stripe;
struct extent_map *em;
struct map_lookup *map;
- size_t item_size;
u64 dev_offset;
u64 stripe_size;
- int i = 0;
+ int i;
int ret = 0;
em = btrfs_get_chunk_map(fs_info, chunk_offset, chunk_size);
return PTR_ERR(em);
map = em->map_lookup;
- item_size = btrfs_chunk_item_size(map->num_stripes);
stripe_size = em->orig_block_len;
- chunk = kzalloc(item_size, GFP_NOFS);
- if (!chunk) {
- ret = -ENOMEM;
- goto out;
- }
-
/*
* Take the device list mutex to prevent races with the final phase of
* a device replace operation that replaces the device object associated
* with the map's stripes, because the device object's id can change
* at any time during that final phase of the device replace operation
- * (dev-replace.c:btrfs_dev_replace_finishing()).
+ * (dev-replace.c:btrfs_dev_replace_finishing()), so we could grab the
+ * replaced device and then see it with an ID of BTRFS_DEV_REPLACE_DEVID,
+ * resulting in persisting a device extent item with such ID.
*/
mutex_lock(&fs_info->fs_devices->device_list_mutex);
for (i = 0; i < map->num_stripes; i++) {
device = map->stripes[i].dev;
dev_offset = map->stripes[i].physical;
- ret = btrfs_update_device(trans, device);
- if (ret)
- break;
ret = btrfs_alloc_dev_extent(trans, device, chunk_offset,
dev_offset, stripe_size);
if (ret)
break;
}
- if (ret) {
- mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+ mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+
+ free_extent_map(em);
+ return ret;
+}
+
+/*
+ * This function, btrfs_chunk_alloc_add_chunk_item(), typically belongs to the
+ * phase 1 of chunk allocation. It belongs to phase 2 only when allocating system
+ * chunks.
+ *
+ * See the comment at btrfs_chunk_alloc() for details about the chunk allocation
+ * phases.
+ */
+int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans,
+ struct btrfs_block_group *bg)
+{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
+ struct btrfs_root *extent_root = fs_info->extent_root;
+ struct btrfs_root *chunk_root = fs_info->chunk_root;
+ struct btrfs_key key;
+ struct btrfs_chunk *chunk;
+ struct btrfs_stripe *stripe;
+ struct extent_map *em;
+ struct map_lookup *map;
+ size_t item_size;
+ int i;
+ int ret;
+
+ /*
+ * We take the chunk_mutex for 2 reasons:
+ *
+ * 1) Updates and insertions in the chunk btree must be done while holding
+ * the chunk_mutex, as well as updating the system chunk array in the
+ * superblock. See the comment on top of btrfs_chunk_alloc() for the
+ * details;
+ *
+ * 2) To prevent races with the final phase of a device replace operation
+ * that replaces the device object associated with the map's stripes,
+ * because the device object's id can change at any time during that
+ * final phase of the device replace operation
+ * (dev-replace.c:btrfs_dev_replace_finishing()), so we could grab the
+ * replaced device and then see it with an ID of BTRFS_DEV_REPLACE_DEVID,
+ * which would cause a failure when updating the device item, which does
+ * not exists, or persisting a stripe of the chunk item with such ID.
+ * Here we can't use the device_list_mutex because our caller already
+ * has locked the chunk_mutex, and the final phase of device replace
+ * acquires both mutexes - first the device_list_mutex and then the
+ * chunk_mutex. Using any of those two mutexes protects us from a
+ * concurrent device replace.
+ */
+ lockdep_assert_held(&fs_info->chunk_mutex);
+
+ em = btrfs_get_chunk_map(fs_info, bg->start, bg->length);
+ if (IS_ERR(em)) {
+ ret = PTR_ERR(em);
+ btrfs_abort_transaction(trans, ret);
+ return ret;
+ }
+
+ map = em->map_lookup;
+ item_size = btrfs_chunk_item_size(map->num_stripes);
+
+ chunk = kzalloc(item_size, GFP_NOFS);
+ if (!chunk) {
+ ret = -ENOMEM;
+ btrfs_abort_transaction(trans, ret);
goto out;
}
+ for (i = 0; i < map->num_stripes; i++) {
+ struct btrfs_device *device = map->stripes[i].dev;
+
+ ret = btrfs_update_device(trans, device);
+ if (ret)
+ goto out;
+ }
+
stripe = &chunk->stripe;
for (i = 0; i < map->num_stripes; i++) {
- device = map->stripes[i].dev;
- dev_offset = map->stripes[i].physical;
+ struct btrfs_device *device = map->stripes[i].dev;
+ const u64 dev_offset = map->stripes[i].physical;
btrfs_set_stack_stripe_devid(stripe, device->devid);
btrfs_set_stack_stripe_offset(stripe, dev_offset);
memcpy(stripe->dev_uuid, device->uuid, BTRFS_UUID_SIZE);
stripe++;
}
- mutex_unlock(&fs_info->fs_devices->device_list_mutex);
- btrfs_set_stack_chunk_length(chunk, chunk_size);
+ btrfs_set_stack_chunk_length(chunk, bg->length);
btrfs_set_stack_chunk_owner(chunk, extent_root->root_key.objectid);
btrfs_set_stack_chunk_stripe_len(chunk, map->stripe_len);
btrfs_set_stack_chunk_type(chunk, map->type);
key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID;
key.type = BTRFS_CHUNK_ITEM_KEY;
- key.offset = chunk_offset;
+ key.offset = bg->start;
ret = btrfs_insert_item(trans, chunk_root, &key, chunk, item_size);
- if (ret == 0 && map->type & BTRFS_BLOCK_GROUP_SYSTEM) {
- /*
- * TODO: Cleanup of inserted chunk root in case of
- * failure.
- */
+ if (ret)
+ goto out;
+
+ bg->chunk_item_inserted = 1;
+
+ if (map->type & BTRFS_BLOCK_GROUP_SYSTEM) {
ret = btrfs_add_system_chunk(fs_info, &key, chunk, item_size);
+ if (ret)
+ goto out;
}
out:
{
struct btrfs_fs_info *fs_info = trans->fs_info;
u64 alloc_profile;
- int ret;
+ struct btrfs_block_group *meta_bg;
+ struct btrfs_block_group *sys_bg;
+
+ /*
+ * When adding a new device for sprouting, the seed device is read-only
+ * so we must first allocate a metadata and a system chunk. But before
+ * adding the block group items to the extent, device and chunk btrees,
+ * we must first:
+ *
+ * 1) Create both chunks without doing any changes to the btrees, as
+ * otherwise we would get -ENOSPC since the block groups from the
+ * seed device are read-only;
+ *
+ * 2) Add the device item for the new sprout device - finishing the setup
+ * of a new block group requires updating the device item in the chunk
+ * btree, so it must exist when we attempt to do it. The previous step
+ * ensures this does not fail with -ENOSPC.
+ *
+ * After that we can add the block group items to their btrees:
+ * update existing device item in the chunk btree, add a new block group
+ * item to the extent btree, add a new chunk item to the chunk btree and
+ * finally add the new device extent items to the devices btree.
+ */
alloc_profile = btrfs_metadata_alloc_profile(fs_info);
- ret = btrfs_alloc_chunk(trans, alloc_profile);
- if (ret)
- return ret;
+ meta_bg = btrfs_alloc_chunk(trans, alloc_profile);
+ if (IS_ERR(meta_bg))
+ return PTR_ERR(meta_bg);
alloc_profile = btrfs_system_alloc_profile(fs_info);
- ret = btrfs_alloc_chunk(trans, alloc_profile);
- return ret;
+ sys_bg = btrfs_alloc_chunk(trans, alloc_profile);
+ if (IS_ERR(sys_bg))
+ return PTR_ERR(sys_bg);
+
+ return 0;
}
static inline int btrfs_chunk_max_errors(struct map_lookup *map)
total_dev++;
} else if (found_key.type == BTRFS_CHUNK_ITEM_KEY) {
struct btrfs_chunk *chunk;
+
+ /*
+ * We are only called at mount time, so no need to take
+ * fs_info->chunk_mutex. Plus, to avoid lockdep warnings,
+ * we always lock first fs_info->chunk_mutex before
+ * acquiring any locks on the chunk tree. This is a
+ * requirement for chunk allocation, see the comment on
+ * top of btrfs_chunk_alloc() for details.
+ */
+ ASSERT(!test_bit(BTRFS_FS_OPEN, &fs_info->flags));
chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
- mutex_lock(&fs_info->chunk_mutex);
ret = read_one_chunk(&found_key, leaf, chunk);
- mutex_unlock(&fs_info->chunk_mutex);
if (ret)
goto error;
}
struct btrfs_io_geometry *io_geom);
int btrfs_read_sys_array(struct btrfs_fs_info *fs_info);
int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
-int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type);
+struct btrfs_block_group *btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
+ u64 type);
void btrfs_mapping_tree_free(struct extent_map_tree *tree);
blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
int mirror_num);
u64 logical);
int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
u64 chunk_offset, u64 chunk_size);
+int btrfs_chunk_alloc_add_chunk_item(struct btrfs_trans_handle *trans,
+ struct btrfs_block_group *bg);
int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset);
struct extent_map *btrfs_get_chunk_map(struct btrfs_fs_info *fs_info,
u64 logical, u64 length);
}
pr_debug("%s: count = %zd, pos = %lld, buf = %s\n",
__func__, iov_iter_count(to), iocb->ki_pos, buffer->page);
- retval = copy_to_iter(buffer->page, buffer->count, to);
+ if (iocb->ki_pos >= buffer->count)
+ goto out;
+ retval = copy_to_iter(buffer->page + iocb->ki_pos,
+ buffer->count - iocb->ki_pos, to);
iocb->ki_pos += retval;
if (retval == 0)
retval = -EFAULT;
buffer->needs_read_fill = 0;
}
- retval = copy_to_iter(buffer->bin_buffer, buffer->bin_buffer_size, to);
+ if (iocb->ki_pos >= buffer->bin_buffer_size)
+ goto out;
+ retval = copy_to_iter(buffer->bin_buffer + iocb->ki_pos,
+ buffer->bin_buffer_size - iocb->ki_pos, to);
iocb->ki_pos += retval;
if (retval == 0)
retval = -EFAULT;
return retval;
}
-static int fill_write_buffer(struct configfs_buffer *buffer,
+/* Fill [buffer, buffer + pos) with data coming from @from. */
+static int fill_write_buffer(struct configfs_buffer *buffer, loff_t pos,
struct iov_iter *from)
{
+ loff_t to_copy;
int copied;
+ u8 *to;
if (!buffer->page)
buffer->page = (char *)__get_free_pages(GFP_KERNEL, 0);
if (!buffer->page)
return -ENOMEM;
- copied = copy_from_iter(buffer->page, SIMPLE_ATTR_SIZE - 1, from);
+ to_copy = SIMPLE_ATTR_SIZE - 1 - pos;
+ if (to_copy <= 0)
+ return 0;
+ to = buffer->page + pos;
+ copied = copy_from_iter(to, to_copy, from);
buffer->needs_read_fill = 1;
/* if buf is assumed to contain a string, terminate it by \0,
* so e.g. sscanf() can scan the string easily */
- buffer->page[copied] = 0;
+ to[copied] = 0;
return copied ? : -EFAULT;
}
ssize_t len;
mutex_lock(&buffer->mutex);
- len = fill_write_buffer(buffer, from);
+ len = fill_write_buffer(buffer, iocb->ki_pos, from);
if (len > 0)
len = flush_write_buffer(file, buffer, len);
if (len > 0)
buffer->bin_buffer_size = end_offset;
}
- len = copy_from_iter(buffer->bin_buffer, buffer->bin_buffer_size, from);
+ len = copy_from_iter(buffer->bin_buffer + iocb->ki_pos,
+ buffer->bin_buffer_size - iocb->ki_pos, from);
+ iocb->ki_pos += len;
out:
mutex_unlock(&buffer->mutex);
return len ? : -EFAULT;
/* 32-bit arches must use fcntl64() */
case F_OFD_SETLK:
case F_OFD_SETLKW:
-#endif
fallthrough;
+#endif
case F_SETLK:
case F_SETLKW:
if (copy_from_user(&flock, argp, sizeof(flock)))
}
/**
+ * vfs_parse_fs_param_source - Handle setting "source" via parameter
+ * @fc: The filesystem context to modify
+ * @param: The parameter
+ *
+ * This is a simple helper for filesystems to verify that the "source" they
+ * accept is sane.
+ *
+ * Returns 0 on success, -ENOPARAM if this is not "source" parameter, and
+ * -EINVAL otherwise. In the event of failure, supplementary error information
+ * is logged.
+ */
+int vfs_parse_fs_param_source(struct fs_context *fc, struct fs_parameter *param)
+{
+ if (strcmp(param->key, "source") != 0)
+ return -ENOPARAM;
+
+ if (param->type != fs_value_is_string)
+ return invalf(fc, "Non-string source");
+
+ if (fc->source)
+ return invalf(fc, "Multiple sources");
+
+ fc->source = param->string;
+ param->string = NULL;
+ return 0;
+}
+EXPORT_SYMBOL(vfs_parse_fs_param_source);
+
+/**
* vfs_parse_fs_param - Add a single parameter to a superblock config
* @fc: The filesystem context to modify
* @param: The parameter
/* If the filesystem doesn't take any arguments, give it the
* default handling of source.
*/
- if (strcmp(param->key, "source") == 0) {
- if (param->type != fs_value_is_string)
- return invalf(fc, "VFS: Non-string source");
- if (fc->source)
- return invalf(fc, "VFS: Multiple sources");
- fc->source = param->string;
- param->string = NULL;
- return 0;
- }
+ ret = vfs_parse_fs_param_source(fc, param);
+ if (ret != -ENOPARAM)
+ return ret;
return invalf(fc, "%s: Unknown parameter '%s'",
fc->fs_type->name, param->key);
struct legacy_fs_context *ctx = fc->fs_private;
unsigned int size = ctx->data_size;
size_t len = 0;
+ int ret;
- if (strcmp(param->key, "source") == 0) {
- if (param->type != fs_value_is_string)
- return invalf(fc, "VFS: Legacy: Non-string source");
- if (fc->source)
- return invalf(fc, "VFS: Legacy: Multiple sources");
- fc->source = param->string;
- param->string = NULL;
- return 0;
- }
+ ret = vfs_parse_fs_param_source(fc, param);
+ if (ret != -ENOPARAM)
+ return ret;
if (ctx->param_type == LEGACY_FS_MONOLITHIC_PARAMS)
return invalf(fc, "VFS: Legacy: Can't mix monolithic and individual options");
fd->key = ptr + tree->max_key_len + 2;
hfs_dbg(BNODE_REFS, "find_init: %d (%p)\n",
tree->cnid, __builtin_return_address(0));
- mutex_lock(&tree->tree_lock);
+ switch (tree->cnid) {
+ case HFS_CAT_CNID:
+ mutex_lock_nested(&tree->tree_lock, CATALOG_BTREE_MUTEX);
+ break;
+ case HFS_EXT_CNID:
+ mutex_lock_nested(&tree->tree_lock, EXTENTS_BTREE_MUTEX);
+ break;
+ case HFS_ATTR_CNID:
+ mutex_lock_nested(&tree->tree_lock, ATTR_BTREE_MUTEX);
+ break;
+ default:
+ return -EINVAL;
+ }
return 0;
}
#include "btree.h"
-void hfs_bnode_read(struct hfs_bnode *node, void *buf,
- int off, int len)
+void hfs_bnode_read(struct hfs_bnode *node, void *buf, int off, int len)
{
struct page *page;
+ int pagenum;
+ int bytes_read;
+ int bytes_to_read;
+ void *vaddr;
off += node->page_offset;
- page = node->page[0];
+ pagenum = off >> PAGE_SHIFT;
+ off &= ~PAGE_MASK; /* compute page offset for the first page */
- memcpy(buf, kmap(page) + off, len);
- kunmap(page);
+ for (bytes_read = 0; bytes_read < len; bytes_read += bytes_to_read) {
+ if (pagenum >= node->tree->pages_per_bnode)
+ break;
+ page = node->page[pagenum];
+ bytes_to_read = min_t(int, len - bytes_read, PAGE_SIZE - off);
+
+ vaddr = kmap_atomic(page);
+ memcpy(buf + bytes_read, vaddr + off, bytes_to_read);
+ kunmap_atomic(vaddr);
+
+ pagenum++;
+ off = 0; /* page offset only applies to the first page */
+ }
}
u16 hfs_bnode_read_u16(struct hfs_bnode *node, int off)
#define NODE_HASH_SIZE 256
+/* B-tree mutex nested subclasses */
+enum hfs_btree_mutex_classes {
+ CATALOG_BTREE_MUTEX,
+ EXTENTS_BTREE_MUTEX,
+ ATTR_BTREE_MUTEX,
+};
+
/* A HFS BTree held in memory */
struct hfs_btree {
struct super_block *sb;
if (!res) {
if (fd.entrylength > sizeof(rec) || fd.entrylength < 0) {
res = -EIO;
- goto bail;
+ goto bail_hfs_find;
}
hfs_bnode_read(fd.bnode, &rec, fd.entryoffset, fd.entrylength);
}
- if (res) {
- hfs_find_exit(&fd);
- goto bail_no_root;
- }
+ if (res)
+ goto bail_hfs_find;
res = -EINVAL;
root_inode = hfs_iget(sb, &fd.search_key->cat, &rec);
hfs_find_exit(&fd);
/* everything's okay */
return 0;
+bail_hfs_find:
+ hfs_find_exit(&fd);
bail_no_root:
pr_err("get root inode failed\n");
bail:
}
static int vboxsf_dir_create(struct inode *parent, struct dentry *dentry,
- umode_t mode, int is_dir)
+ umode_t mode, bool is_dir, bool excl, u64 *handle_ret)
{
struct vboxsf_inode *sf_parent_i = VBOXSF_I(parent);
struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
int err;
params.handle = SHFL_HANDLE_NIL;
- params.create_flags = SHFL_CF_ACT_CREATE_IF_NEW |
- SHFL_CF_ACT_FAIL_IF_EXISTS |
- SHFL_CF_ACCESS_READWRITE |
- (is_dir ? SHFL_CF_DIRECTORY : 0);
+ params.create_flags = SHFL_CF_ACT_CREATE_IF_NEW | SHFL_CF_ACCESS_READWRITE;
+ if (is_dir)
+ params.create_flags |= SHFL_CF_DIRECTORY;
+ if (excl)
+ params.create_flags |= SHFL_CF_ACT_FAIL_IF_EXISTS;
+
params.info.attr.mode = (mode & 0777) |
(is_dir ? SHFL_TYPE_DIRECTORY : SHFL_TYPE_FILE);
params.info.attr.additional = SHFLFSOBJATTRADD_NOTHING;
if (params.result != SHFL_FILE_CREATED)
return -EPERM;
- vboxsf_close(sbi->root, params.handle);
-
err = vboxsf_dir_instantiate(parent, dentry, ¶ms.info);
if (err)
- return err;
+ goto out;
/* parent directory access/change time changed */
sf_parent_i->force_restat = 1;
- return 0;
+out:
+ if (err == 0 && handle_ret)
+ *handle_ret = params.handle;
+ else
+ vboxsf_close(sbi->root, params.handle);
+
+ return err;
}
static int vboxsf_dir_mkfile(struct user_namespace *mnt_userns,
struct inode *parent, struct dentry *dentry,
umode_t mode, bool excl)
{
- return vboxsf_dir_create(parent, dentry, mode, 0);
+ return vboxsf_dir_create(parent, dentry, mode, false, excl, NULL);
}
static int vboxsf_dir_mkdir(struct user_namespace *mnt_userns,
struct inode *parent, struct dentry *dentry,
umode_t mode)
{
- return vboxsf_dir_create(parent, dentry, mode, 1);
+ return vboxsf_dir_create(parent, dentry, mode, true, true, NULL);
+}
+
+static int vboxsf_dir_atomic_open(struct inode *parent, struct dentry *dentry,
+ struct file *file, unsigned int flags, umode_t mode)
+{
+ struct vboxsf_sbi *sbi = VBOXSF_SBI(parent->i_sb);
+ struct vboxsf_handle *sf_handle;
+ struct dentry *res = NULL;
+ u64 handle;
+ int err;
+
+ if (d_in_lookup(dentry)) {
+ res = vboxsf_dir_lookup(parent, dentry, 0);
+ if (IS_ERR(res))
+ return PTR_ERR(res);
+
+ if (res)
+ dentry = res;
+ }
+
+ /* Only creates */
+ if (!(flags & O_CREAT) || d_really_is_positive(dentry))
+ return finish_no_open(file, res);
+
+ err = vboxsf_dir_create(parent, dentry, mode, false, flags & O_EXCL, &handle);
+ if (err)
+ goto out;
+
+ sf_handle = vboxsf_create_sf_handle(d_inode(dentry), handle, SHFL_CF_ACCESS_READWRITE);
+ if (IS_ERR(sf_handle)) {
+ vboxsf_close(sbi->root, handle);
+ err = PTR_ERR(sf_handle);
+ goto out;
+ }
+
+ err = finish_open(file, dentry, generic_file_open);
+ if (err) {
+ /* This also closes the handle passed to vboxsf_create_sf_handle() */
+ vboxsf_release_sf_handle(d_inode(dentry), sf_handle);
+ goto out;
+ }
+
+ file->private_data = sf_handle;
+ file->f_mode |= FMODE_CREATED;
+out:
+ dput(res);
+ return err;
}
static int vboxsf_dir_unlink(struct inode *parent, struct dentry *dentry)
.lookup = vboxsf_dir_lookup,
.create = vboxsf_dir_mkfile,
.mkdir = vboxsf_dir_mkdir,
+ .atomic_open = vboxsf_dir_atomic_open,
.rmdir = vboxsf_dir_unlink,
.unlink = vboxsf_dir_unlink,
.rename = vboxsf_dir_rename,
struct list_head head;
};
-static int vboxsf_file_open(struct inode *inode, struct file *file)
+struct vboxsf_handle *vboxsf_create_sf_handle(struct inode *inode,
+ u64 handle, u32 access_flags)
{
struct vboxsf_inode *sf_i = VBOXSF_I(inode);
- struct shfl_createparms params = {};
struct vboxsf_handle *sf_handle;
- u32 access_flags = 0;
- int err;
sf_handle = kmalloc(sizeof(*sf_handle), GFP_KERNEL);
if (!sf_handle)
- return -ENOMEM;
+ return ERR_PTR(-ENOMEM);
+
+ /* the host may have given us different attr then requested */
+ sf_i->force_restat = 1;
+
+ /* init our handle struct and add it to the inode's handles list */
+ sf_handle->handle = handle;
+ sf_handle->root = VBOXSF_SBI(inode->i_sb)->root;
+ sf_handle->access_flags = access_flags;
+ kref_init(&sf_handle->refcount);
+
+ mutex_lock(&sf_i->handle_list_mutex);
+ list_add(&sf_handle->head, &sf_i->handle_list);
+ mutex_unlock(&sf_i->handle_list_mutex);
+
+ return sf_handle;
+}
+
+static int vboxsf_file_open(struct inode *inode, struct file *file)
+{
+ struct vboxsf_sbi *sbi = VBOXSF_SBI(inode->i_sb);
+ struct shfl_createparms params = {};
+ struct vboxsf_handle *sf_handle;
+ u32 access_flags = 0;
+ int err;
/*
* We check the value of params.handle afterwards to find out if
err = vboxsf_create_at_dentry(file_dentry(file), ¶ms);
if (err == 0 && params.handle == SHFL_HANDLE_NIL)
err = (params.result == SHFL_FILE_EXISTS) ? -EEXIST : -ENOENT;
- if (err) {
- kfree(sf_handle);
+ if (err)
return err;
- }
-
- /* the host may have given us different attr then requested */
- sf_i->force_restat = 1;
- /* init our handle struct and add it to the inode's handles list */
- sf_handle->handle = params.handle;
- sf_handle->root = VBOXSF_SBI(inode->i_sb)->root;
- sf_handle->access_flags = access_flags;
- kref_init(&sf_handle->refcount);
-
- mutex_lock(&sf_i->handle_list_mutex);
- list_add(&sf_handle->head, &sf_i->handle_list);
- mutex_unlock(&sf_i->handle_list_mutex);
+ sf_handle = vboxsf_create_sf_handle(inode, params.handle, access_flags);
+ if (IS_ERR(sf_handle)) {
+ vboxsf_close(sbi->root, params.handle);
+ return PTR_ERR(sf_handle);
+ }
file->private_data = sf_handle;
return 0;
kfree(sf_handle);
}
-static int vboxsf_file_release(struct inode *inode, struct file *file)
+void vboxsf_release_sf_handle(struct inode *inode, struct vboxsf_handle *sf_handle)
{
struct vboxsf_inode *sf_i = VBOXSF_I(inode);
- struct vboxsf_handle *sf_handle = file->private_data;
+ mutex_lock(&sf_i->handle_list_mutex);
+ list_del(&sf_handle->head);
+ mutex_unlock(&sf_i->handle_list_mutex);
+
+ kref_put(&sf_handle->refcount, vboxsf_handle_release);
+}
+
+static int vboxsf_file_release(struct inode *inode, struct file *file)
+{
/*
* When a file is closed on our (the guest) side, we want any subsequent
* accesses done on the host side to see all changes done from our side.
*/
filemap_write_and_wait(inode->i_mapping);
- mutex_lock(&sf_i->handle_list_mutex);
- list_del(&sf_handle->head);
- mutex_unlock(&sf_i->handle_list_mutex);
-
- kref_put(&sf_handle->refcount, vboxsf_handle_release);
+ vboxsf_release_sf_handle(inode, file->private_data);
return 0;
}
#define VBOXSF_SBI(sb) ((struct vboxsf_sbi *)(sb)->s_fs_info)
#define VBOXSF_I(i) container_of(i, struct vboxsf_inode, vfs_inode)
+struct vboxsf_handle;
+
struct vboxsf_options {
unsigned long ttl;
kuid_t uid;
extern const struct address_space_operations vboxsf_reg_aops;
extern const struct dentry_operations vboxsf_dentry_ops;
+/* from file.c */
+struct vboxsf_handle *vboxsf_create_sf_handle(struct inode *inode,
+ u64 handle, u32 access_flags);
+void vboxsf_release_sf_handle(struct inode *inode, struct vboxsf_handle *sf_handle);
+
/* from utils.c */
struct inode *vboxsf_new_inode(struct super_block *sb);
int vboxsf_init_inode(struct vboxsf_sbi *sbi, struct inode *inode,
if (error)
return error;
- /* fallthrough */
+ fallthrough;
case XFS_DAS_RM_LBLK:
/* Set state in case xfs_attr_rmtval_remove returns -EAGAIN */
dac->dela_state = XFS_DAS_RM_LBLK;
return -EAGAIN;
}
- /* fallthrough */
+ fallthrough;
case XFS_DAS_RD_LEAF:
/*
* This is the last step for leaf format. Read the block with
return error;
}
- /* fallthrough */
+ fallthrough;
case XFS_DAS_ALLOC_NODE:
/*
* If there was an out-of-line value, allocate the blocks we
if (error)
return error;
- /* fallthrough */
+ fallthrough;
case XFS_DAS_RM_NBLK:
/* Set state in case xfs_attr_rmtval_remove returns -EAGAIN */
dac->dela_state = XFS_DAS_RM_NBLK;
return -EAGAIN;
}
- /* fallthrough */
+ fallthrough;
case XFS_DAS_CLR_FLAG:
/*
* The last state for node format. Look up the old attr and
state = dac->da_state;
}
- /* fallthrough */
+ fallthrough;
case XFS_DAS_RMTBLK:
dac->dela_state = XFS_DAS_RMTBLK;
return -EAGAIN;
}
- /* fallthrough */
+ fallthrough;
case XFS_DAS_RM_NAME:
/*
* If we came here fresh from a transaction roll, reattach all
return -EAGAIN;
}
- /* fallthrough */
+ fallthrough;
case XFS_DAS_RM_SHRINK:
/*
* If the result is small enough, push it all into the inode.
void *tailcall_target;
void *tailcall_bypass;
void *bypass_addr;
+ void *aux;
union {
struct {
struct bpf_map *map;
enum ethtool_link_mode_bit_indices link_mode);
/**
+ * ethtool_get_phc_vclocks - Derive phc vclocks information, and caller
+ * is responsible to free memory of vclock_index
+ * @dev: pointer to net_device structure
+ * @vclock_index: pointer to pointer of vclock index
+ *
+ * Return number of phc vclocks
+ */
+int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index);
+
+/**
* ethtool_sprintf - Write formatted string to ethtool string data
* @data: Pointer to start of string to update
* @fmt: Format of string to write
extern int generic_parse_monolithic(struct fs_context *fc, void *data);
extern int vfs_get_tree(struct fs_context *fc);
extern void put_fs_context(struct fs_context *fc);
+extern int vfs_parse_fs_param_source(struct fs_context *fc,
+ struct fs_parameter *param);
/*
* sget() wrappers to be called from the ->get_tree() op.
#define _LINUX_KASAN_H
#include <linux/bug.h>
+#include <linux/kernel.h>
#include <linux/static_key.h>
#include <linux/types.h>
#define MARVELL_PHY_ID_88E1545 0x01410ea0
#define MARVELL_PHY_ID_88E1548P 0x01410ec0
#define MARVELL_PHY_ID_88E3016 0x01410e60
+#define MARVELL_PHY_ID_88X3310 0x002b09a0
#define MARVELL_PHY_ID_88E2110 0x002b09b0
#define MARVELL_PHY_ID_88X2222 0x01410f10
-/* PHY IDs and mask for Alaska 10G PHYs */
-#define MARVELL_PHY_ID_88X33X0_MASK 0xfffffff8
-#define MARVELL_PHY_ID_88X3310 0x002b09a0
-#define MARVELL_PHY_ID_88X3340 0x002b09a8
-
/* Marvel 88E1111 in Finisar SFP module with modified PHY ID */
#define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0
struct page *newpage, struct page *page);
extern int migrate_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page, int extra_count);
-extern void copy_huge_page(struct page *dst, struct page *src);
#else
static inline void putback_movable_pages(struct list_head *l) {}
{
return -ENOSYS;
}
-
-static inline void copy_huge_page(struct page *dst, struct page *src)
-{
-}
#endif /* CONFIG_MIGRATION */
#ifdef CONFIG_COMPACTION
void put_pages_list(struct list_head *pages);
void split_page(struct page *page, unsigned int order);
+void copy_huge_page(struct page *dst, struct page *src);
/*
* Compound pages have a destructor function. Provide a
#include <linux/device.h>
#include <linux/pps_kernel.h>
#include <linux/ptp_clock.h>
+#include <linux/timecounter.h>
+#include <linux/skbuff.h>
+#define PTP_CLOCK_NAME_LEN 32
/**
* struct ptp_clock_request - request PTP clock event
*
struct ptp_clock_info {
struct module *owner;
- char name[16];
+ char name[PTP_CLOCK_NAME_LEN];
s32 max_adj;
int n_alarm;
int n_ext_ts;
*/
void ptp_cancel_worker_sync(struct ptp_clock *ptp);
+/**
+ * ptp_get_vclocks_index() - get all vclocks index on pclock, and
+ * caller is responsible to free memory
+ * of vclock_index
+ *
+ * @pclock_index: phc index of ptp pclock.
+ * @vclock_index: pointer to pointer of vclock index.
+ *
+ * return number of vclocks.
+ */
+int ptp_get_vclocks_index(int pclock_index, int **vclock_index);
+
+/**
+ * ptp_convert_timestamp() - convert timestamp to a ptp vclock time
+ *
+ * @hwtstamps: skb_shared_hwtstamps structure pointer
+ * @vclock_index: phc index of ptp vclock.
+ */
+void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps,
+ int vclock_index);
+
#else
static inline struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info,
struct device *parent)
{ return -EOPNOTSUPP; }
static inline void ptp_cancel_worker_sync(struct ptp_clock *ptp)
{ }
+static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index)
+{ return 0; }
+static inline void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps,
+ int vclock_index)
+{ }
#endif
return 0;
}
-#define try_to_unmap(page, refs) false
+static inline void try_to_unmap(struct page *page, enum ttu_flags flags)
+{
+}
static inline int page_mkclean(struct page *page)
{
#define EST_GCL 1024
struct stmmac_est {
+ struct mutex lock;
int enable;
+ u32 btr_reserve[2];
u32 btr_offset[2];
u32 btr[2];
u32 ctr[2];
FP_SET_EXCEPTION(FP_EX_INVALID | FP_EX_INVALID_ISI); \
break; \
} \
- /* FALLTHRU */ \
+ fallthrough; \
\
case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_NORMAL): \
case _FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_ZERO): \
*/
#define BOND_LINK_NOCHANGE -1
+struct bond_ipsec {
+ struct list_head list;
+ struct xfrm_state *xs;
+};
+
/*
* Here are the locking policies for the two bonding locks:
* Get rcu_read_lock when reading or RTNL when writing slave list.
#endif /* CONFIG_DEBUG_FS */
struct rtnl_link_stats64 bond_stats;
#ifdef CONFIG_XFRM_OFFLOAD
- struct xfrm_state *xs;
+ struct list_head ipsec_list;
+ /* protecting ipsec_list */
+ spinlock_t ipsec_lock;
#endif /* CONFIG_XFRM_OFFLOAD */
};
static inline bool sk_can_busy_loop(const struct sock *sk)
{
- return sk->sk_ll_usec && !signal_pending(current);
+ return READ_ONCE(sk->sk_ll_usec) && !signal_pending(current);
}
bool sk_busy_loop_end(void *p, unsigned long start_time);
+++ /dev/null
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) ST-Ericsson AB 2010
- * Author: Daniel Martensson / daniel.martensson@stericsson.com
- * Dmitry.Tarnyagin / dmitry.tarnyagin@stericsson.com
- */
-
-#ifndef CAIF_HSI_H_
-#define CAIF_HSI_H_
-
-#include <net/caif/caif_layer.h>
-#include <net/caif/caif_device.h>
-#include <linux/atomic.h>
-
-/*
- * Maximum number of CAIF frames that can reside in the same HSI frame.
- */
-#define CFHSI_MAX_PKTS 15
-
-/*
- * Maximum number of bytes used for the frame that can be embedded in the
- * HSI descriptor.
- */
-#define CFHSI_MAX_EMB_FRM_SZ 96
-
-/*
- * Decides if HSI buffers should be prefilled with 0xFF pattern for easier
- * debugging. Both TX and RX buffers will be filled before the transfer.
- */
-#define CFHSI_DBG_PREFILL 0
-
-/* Structure describing a HSI packet descriptor. */
-#pragma pack(1) /* Byte alignment. */
-struct cfhsi_desc {
- u8 header;
- u8 offset;
- u16 cffrm_len[CFHSI_MAX_PKTS];
- u8 emb_frm[CFHSI_MAX_EMB_FRM_SZ];
-};
-#pragma pack() /* Default alignment. */
-
-/* Size of the complete HSI packet descriptor. */
-#define CFHSI_DESC_SZ (sizeof(struct cfhsi_desc))
-
-/*
- * Size of the complete HSI packet descriptor excluding the optional embedded
- * CAIF frame.
- */
-#define CFHSI_DESC_SHORT_SZ (CFHSI_DESC_SZ - CFHSI_MAX_EMB_FRM_SZ)
-
-/*
- * Maximum bytes transferred in one transfer.
- */
-#define CFHSI_MAX_CAIF_FRAME_SZ 4096
-
-#define CFHSI_MAX_PAYLOAD_SZ (CFHSI_MAX_PKTS * CFHSI_MAX_CAIF_FRAME_SZ)
-
-/* Size of the complete HSI TX buffer. */
-#define CFHSI_BUF_SZ_TX (CFHSI_DESC_SZ + CFHSI_MAX_PAYLOAD_SZ)
-
-/* Size of the complete HSI RX buffer. */
-#define CFHSI_BUF_SZ_RX ((2 * CFHSI_DESC_SZ) + CFHSI_MAX_PAYLOAD_SZ)
-
-/* Bitmasks for the HSI descriptor. */
-#define CFHSI_PIGGY_DESC (0x01 << 7)
-
-#define CFHSI_TX_STATE_IDLE 0
-#define CFHSI_TX_STATE_XFER 1
-
-#define CFHSI_RX_STATE_DESC 0
-#define CFHSI_RX_STATE_PAYLOAD 1
-
-/* Bitmasks for power management. */
-#define CFHSI_WAKE_UP 0
-#define CFHSI_WAKE_UP_ACK 1
-#define CFHSI_WAKE_DOWN_ACK 2
-#define CFHSI_AWAKE 3
-#define CFHSI_WAKELOCK_HELD 4
-#define CFHSI_SHUTDOWN 5
-#define CFHSI_FLUSH_FIFO 6
-
-#ifndef CFHSI_INACTIVITY_TOUT
-#define CFHSI_INACTIVITY_TOUT (1 * HZ)
-#endif /* CFHSI_INACTIVITY_TOUT */
-
-#ifndef CFHSI_WAKE_TOUT
-#define CFHSI_WAKE_TOUT (3 * HZ)
-#endif /* CFHSI_WAKE_TOUT */
-
-#ifndef CFHSI_MAX_RX_RETRIES
-#define CFHSI_MAX_RX_RETRIES (10 * HZ)
-#endif
-
-/* Structure implemented by the CAIF HSI driver. */
-struct cfhsi_cb_ops {
- void (*tx_done_cb) (struct cfhsi_cb_ops *drv);
- void (*rx_done_cb) (struct cfhsi_cb_ops *drv);
- void (*wake_up_cb) (struct cfhsi_cb_ops *drv);
- void (*wake_down_cb) (struct cfhsi_cb_ops *drv);
-};
-
-/* Structure implemented by HSI device. */
-struct cfhsi_ops {
- int (*cfhsi_up) (struct cfhsi_ops *dev);
- int (*cfhsi_down) (struct cfhsi_ops *dev);
- int (*cfhsi_tx) (u8 *ptr, int len, struct cfhsi_ops *dev);
- int (*cfhsi_rx) (u8 *ptr, int len, struct cfhsi_ops *dev);
- int (*cfhsi_wake_up) (struct cfhsi_ops *dev);
- int (*cfhsi_wake_down) (struct cfhsi_ops *dev);
- int (*cfhsi_get_peer_wake) (struct cfhsi_ops *dev, bool *status);
- int (*cfhsi_fifo_occupancy) (struct cfhsi_ops *dev, size_t *occupancy);
- int (*cfhsi_rx_cancel)(struct cfhsi_ops *dev);
- struct cfhsi_cb_ops *cb_ops;
-};
-
-/* Structure holds status of received CAIF frames processing */
-struct cfhsi_rx_state {
- int state;
- int nfrms;
- int pld_len;
- int retries;
- bool piggy_desc;
-};
-
-/* Priority mapping */
-enum {
- CFHSI_PRIO_CTL = 0,
- CFHSI_PRIO_VI,
- CFHSI_PRIO_VO,
- CFHSI_PRIO_BEBK,
- CFHSI_PRIO_LAST,
-};
-
-struct cfhsi_config {
- u32 inactivity_timeout;
- u32 aggregation_timeout;
- u32 head_align;
- u32 tail_align;
- u32 q_high_mark;
- u32 q_low_mark;
-};
-
-/* Structure implemented by CAIF HSI drivers. */
-struct cfhsi {
- struct caif_dev_common cfdev;
- struct net_device *ndev;
- struct platform_device *pdev;
- struct sk_buff_head qhead[CFHSI_PRIO_LAST];
- struct cfhsi_cb_ops cb_ops;
- struct cfhsi_ops *ops;
- int tx_state;
- struct cfhsi_rx_state rx_state;
- struct cfhsi_config cfg;
- int rx_len;
- u8 *rx_ptr;
- u8 *tx_buf;
- u8 *rx_buf;
- u8 *rx_flip_buf;
- spinlock_t lock;
- int flow_off_sent;
- struct list_head list;
- struct work_struct wake_up_work;
- struct work_struct wake_down_work;
- struct work_struct out_of_sync_work;
- struct workqueue_struct *wq;
- wait_queue_head_t wake_up_wait;
- wait_queue_head_t wake_down_wait;
- wait_queue_head_t flush_fifo_wait;
- struct timer_list inactivity_timer;
- struct timer_list rx_slowpath_timer;
-
- /* TX aggregation */
- int aggregation_len;
- struct timer_list aggregation_timer;
-
- unsigned long bits;
-};
-extern struct platform_driver cfhsi_driver;
-
-/**
- * enum ifla_caif_hsi - CAIF HSI NetlinkRT parameters.
- * @IFLA_CAIF_HSI_INACTIVITY_TOUT: Inactivity timeout before
- * taking the HSI wakeline down, in milliseconds.
- * When using RT Netlink to create, destroy or configure a CAIF HSI interface,
- * enum ifla_caif_hsi is used to specify the configuration attributes.
- */
-enum ifla_caif_hsi {
- __IFLA_CAIF_HSI_UNSPEC,
- __IFLA_CAIF_HSI_INACTIVITY_TOUT,
- __IFLA_CAIF_HSI_AGGREGATION_TOUT,
- __IFLA_CAIF_HSI_HEAD_ALIGN,
- __IFLA_CAIF_HSI_TAIL_ALIGN,
- __IFLA_CAIF_HSI_QHIGH_WATERMARK,
- __IFLA_CAIF_HSI_QLOW_WATERMARK,
- __IFLA_CAIF_HSI_MAX
-};
-
-struct cfhsi_ops *cfhsi_get_ops(void);
-
-#endif /* CAIF_HSI_H_ */
return &md_dst->u.tun_info;
dst = skb_dst(skb);
- if (dst && dst->lwtstate)
+ if (dst && dst->lwtstate &&
+ (dst->lwtstate->type == LWTUNNEL_ENCAP_IP ||
+ dst->lwtstate->type == LWTUNNEL_ENCAP_IP6))
return lwt_tun_info(dst->lwtstate);
return NULL;
int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
int (*output)(struct net *, struct sock *, struct sk_buff *));
-static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
+static inline unsigned int ip6_skb_dst_mtu(struct sk_buff *skb)
{
int mtu;
bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
unsigned int *size, unsigned int remaining,
struct mptcp_out_options *opts);
-void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb);
+bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb);
void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
struct mptcp_out_options *opts);
return false;
}
-static inline void mptcp_incoming_options(struct sock *sk,
+static inline bool mptcp_incoming_options(struct sock *sk,
struct sk_buff *skb)
{
+ return true;
}
static inline void mptcp_skb_ext_move(struct sk_buff *to,
void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list);
void nf_conntrack_proto_pernet_init(struct net *net);
-void nf_conntrack_proto_pernet_fini(struct net *net);
int nf_conntrack_proto_init(void);
void nf_conntrack_proto_fini(void);
u8 tcp_loose;
u8 tcp_be_liberal;
u8 tcp_max_retrans;
+ u8 tcp_ignore_invalid_rst;
#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
unsigned int offload_timeout;
unsigned int offload_pickup;
#define SCTP_SCOPE_POLICY_MAX SCTP_SCOPE_POLICY_LINK
/* Based on IPv4 scoping <draft-stewart-tsvwg-sctp-ipv4-00.txt>,
- * SCTP IPv4 unusable addresses: 0.0.0.0/8, 224.0.0.0/4, 198.18.0.0/24,
- * 192.88.99.0/24.
+ * SCTP IPv4 unusable addresses: 0.0.0.0/8, 224.0.0.0/4, 192.88.99.0/24.
* Also, RFC 8.4, non-unicast addresses are not considered valid SCTP
* addresses.
*/
((htonl(INADDR_BROADCAST) == a) || \
ipv4_is_multicast(a) || \
ipv4_is_zeronet(a) || \
- ipv4_is_test_198(a) || \
ipv4_is_anycast_6to4(a))
/* Flags used for the bind address copy functions. */
* @sk_timer: sock cleanup timer
* @sk_stamp: time stamp of last packet received
* @sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only
- * @sk_tsflags: SO_TIMESTAMPING socket options
+ * @sk_tsflags: SO_TIMESTAMPING flags
+ * @sk_bind_phc: SO_TIMESTAMPING bind PHC index of PTP virtual clock
+ * for timestamping
* @sk_tskey: counter to disambiguate concurrent tstamp requests
* @sk_zckey: counter to order MSG_ZEROCOPY notifications
* @sk_socket: Identd and reporting IO signals
seqlock_t sk_stamp_seq;
#endif
u16 sk_tsflags;
+ int sk_bind_phc;
u8 sk_shutdown;
u32 sk_tskey;
atomic_t sk_zckey;
int sock_bindtoindex(struct sock *sk, int ifindex, bool lock_sk);
void sock_set_timestamp(struct sock *sk, int optname, bool valbool);
-int sock_set_timestamping(struct sock *sk, int optname, int val);
+int sock_set_timestamping(struct sock *sk, int optname,
+ struct so_timestamping timestamping);
void sock_enable_timestamps(struct sock *sk);
void sock_no_linger(struct sock *sk);
static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
{
+ /* mptcp hooks are only on the slow path */
+ if (sk_is_mptcp((struct sock *)tp))
+ return;
+
tp->pred_flags = htonl((tp->tcp_header_len << 26) |
ntohl(TCP_FLAG_ACK) |
snd_wnd);
ETHTOOL_MSG_FEC_SET,
ETHTOOL_MSG_MODULE_EEPROM_GET,
ETHTOOL_MSG_STATS_GET,
+ ETHTOOL_MSG_PHC_VCLOCKS_GET,
/* add new constants above here */
__ETHTOOL_MSG_USER_CNT,
ETHTOOL_MSG_FEC_NTF,
ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY,
ETHTOOL_MSG_STATS_GET_REPLY,
+ ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY,
/* add new constants above here */
__ETHTOOL_MSG_KERNEL_CNT,
ETHTOOL_A_TSINFO_MAX = (__ETHTOOL_A_TSINFO_CNT - 1)
};
+/* PHC VCLOCKS */
+
+enum {
+ ETHTOOL_A_PHC_VCLOCKS_UNSPEC,
+ ETHTOOL_A_PHC_VCLOCKS_HEADER, /* nest - _A_HEADER_* */
+ ETHTOOL_A_PHC_VCLOCKS_NUM, /* u32 */
+ ETHTOOL_A_PHC_VCLOCKS_INDEX, /* array, s32 */
+
+ /* add new constants above here */
+ __ETHTOOL_A_PHC_VCLOCKS_CNT,
+ ETHTOOL_A_PHC_VCLOCKS_MAX = (__ETHTOOL_A_PHC_VCLOCKS_CNT - 1)
+};
+
/* CABLE TEST */
enum {
#include <linux/types.h>
#include <linux/socket.h> /* for SO_TIMESTAMPING */
-/* SO_TIMESTAMPING gets an integer bit field comprised of these values */
+/* SO_TIMESTAMPING flags */
enum {
SOF_TIMESTAMPING_TX_HARDWARE = (1<<0),
SOF_TIMESTAMPING_TX_SOFTWARE = (1<<1),
SOF_TIMESTAMPING_OPT_STATS = (1<<12),
SOF_TIMESTAMPING_OPT_PKTINFO = (1<<13),
SOF_TIMESTAMPING_OPT_TX_SWHW = (1<<14),
+ SOF_TIMESTAMPING_BIND_PHC = (1 << 15),
- SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_TX_SWHW,
+ SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_BIND_PHC,
SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) |
SOF_TIMESTAMPING_LAST
};
SOF_TIMESTAMPING_TX_ACK)
/**
+ * struct so_timestamping - SO_TIMESTAMPING parameter
+ *
+ * @flags: SO_TIMESTAMPING flags
+ * @bind_phc: Index of PTP virtual clock bound to sock. This is available
+ * if flag SOF_TIMESTAMPING_BIND_PHC is set.
+ */
+struct so_timestamping {
+ int flags;
+ int bind_phc;
+};
+
+/**
* struct hwtstamp_config - %SIOCGHWTSTAMP and %SIOCSHWTSTAMP parameter
*
* @flags: no flags defined right now, must be zero for %SIOCSHWTSTAMP
NFULA_HWTYPE, /* hardware type */
NFULA_HWHEADER, /* hardware header */
NFULA_HWLEN, /* hardware header length */
- NFULA_CT, /* nf_conntrack_netlink.h */
+ NFULA_CT, /* nfnetlink_conntrack.h */
NFULA_CT_INFO, /* enum ip_conntrack_info */
NFULA_VLAN, /* nested attribute: packet vlan info */
NFULA_L2HDR, /* full L2 header */
NFQA_IFINDEX_PHYSOUTDEV, /* __u32 ifindex */
NFQA_HWADDR, /* nfqnl_msg_packet_hw */
NFQA_PAYLOAD, /* opaque data payload */
- NFQA_CT, /* nf_conntrack_netlink.h */
+ NFQA_CT, /* nfnetlink_conntrack.h */
NFQA_CT_INFO, /* enum ip_conntrack_info */
NFQA_CAP_LEN, /* __u32 length of captured packet */
NFQA_SKB_INFO, /* __u32 skb meta information */
- NFQA_EXP, /* nf_conntrack_netlink.h */
+ NFQA_EXP, /* nfnetlink_conntrack.h */
NFQA_UID, /* __u32 sk uid */
NFQA_GID, /* __u32 sk gid */
NFQA_SECCTX, /* security context string */
#endif
if (aux->dst_trampoline)
bpf_trampoline_put(aux->dst_trampoline);
- for (i = 0; i < aux->func_cnt; i++)
+ for (i = 0; i < aux->func_cnt; i++) {
+ /* We can just unlink the subprog poke descriptor table as
+ * it was originally linked to the main program and is also
+ * released along with it.
+ */
+ aux->func[i]->aux->poke_tab = NULL;
bpf_jit_free(aux->func[i]);
+ }
if (aux->func_cnt) {
kfree(aux->func);
bpf_prog_unlock_free(aux->prog);
if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
for (i = 0; i < map->max_entries; i++) {
- dst = READ_ONCE(dtab->netdev_map[i]);
+ dst = rcu_dereference_check(dtab->netdev_map[i],
+ rcu_read_lock_bh_held());
if (!is_valid_dst(dst, xdp, exclude_ifindex))
continue;
if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
for (i = 0; i < map->max_entries; i++) {
- dst = READ_ONCE(dtab->netdev_map[i]);
+ dst = rcu_dereference_check(dtab->netdev_map[i],
+ rcu_read_lock_bh_held());
if (!dst || dst->dev->ifindex == exclude_ifindex)
continue;
goto out_free;
func[i]->is_func = 1;
func[i]->aux->func_idx = i;
- /* the btf and func_info will be freed only at prog->aux */
+ /* Below members will be freed only at prog->aux */
func[i]->aux->btf = prog->aux->btf;
func[i]->aux->func_info = prog->aux->func_info;
+ func[i]->aux->poke_tab = prog->aux->poke_tab;
+ func[i]->aux->size_poke_tab = prog->aux->size_poke_tab;
for (j = 0; j < prog->aux->size_poke_tab; j++) {
- u32 insn_idx = prog->aux->poke_tab[j].insn_idx;
- int ret;
+ struct bpf_jit_poke_descriptor *poke;
- if (!(insn_idx >= subprog_start &&
- insn_idx <= subprog_end))
- continue;
-
- ret = bpf_jit_add_poke_descriptor(func[i],
- &prog->aux->poke_tab[j]);
- if (ret < 0) {
- verbose(env, "adding tail call poke descriptor failed\n");
- goto out_free;
- }
-
- func[i]->insnsi[insn_idx - subprog_start].imm = ret + 1;
-
- map_ptr = func[i]->aux->poke_tab[ret].tail_call.map;
- ret = map_ptr->ops->map_poke_track(map_ptr, func[i]->aux);
- if (ret < 0) {
- verbose(env, "tracking tail call prog failed\n");
- goto out_free;
- }
+ poke = &prog->aux->poke_tab[j];
+ if (poke->insn_idx < subprog_end &&
+ poke->insn_idx >= subprog_start)
+ poke->aux = func[i]->aux;
}
/* Use bpf_prog_F_tag to indicate functions in stack traces.
cond_resched();
}
- /* Untrack main program's aux structs so that during map_poke_run()
- * we will not stumble upon the unfilled poke descriptors; each
- * of the main program's poke descs got distributed across subprogs
- * and got tracked onto map, so we are sure that none of them will
- * be missed after the operation below
- */
- for (i = 0; i < prog->aux->size_poke_tab; i++) {
- map_ptr = prog->aux->poke_tab[i].tail_call.map;
-
- map_ptr->ops->map_poke_untrack(map_ptr, prog->aux);
- }
-
/* at this point all bpf functions were successfully JITed
* now populate all bpf_calls with correct addresses and
* run last pass of JIT
bpf_prog_jit_attempt_done(prog);
return 0;
out_free:
+ /* We failed JIT'ing, so at this point we need to unregister poke
+ * descriptors from subprogs, so that kernel is not attempting to
+ * patch it anymore as we're freeing the subprog JIT memory.
+ */
+ for (i = 0; i < prog->aux->size_poke_tab; i++) {
+ map_ptr = prog->aux->poke_tab[i].tail_call.map;
+ map_ptr->ops->map_poke_untrack(map_ptr, prog->aux);
+ }
+ /* At this point we're guaranteed that poke descriptors are not
+ * live anymore. We can just unlink its descriptor table as it's
+ * released with the main prog.
+ */
for (i = 0; i < env->subprog_cnt; i++) {
if (!func[i])
continue;
-
- for (j = 0; j < func[i]->aux->size_poke_tab; j++) {
- map_ptr = func[i]->aux->poke_tab[j].tail_call.map;
- map_ptr->ops->map_poke_untrack(map_ptr, func[i]->aux);
- }
+ func[i]->aux->poke_tab = NULL;
bpf_jit_free(func[i]);
}
kfree(func);
opt = fs_parse(fc, cgroup1_fs_parameters, param, &result);
if (opt == -ENOPARAM) {
- if (strcmp(param->key, "source") == 0) {
- if (fc->source)
- return invalf(fc, "Multiple sources not supported");
- fc->source = param->string;
- param->string = NULL;
- return 0;
- }
+ int ret;
+
+ ret = vfs_parse_fs_param_source(fc, param);
+ if (ret != -ENOPARAM)
+ return ret;
for_each_subsys(ss, i) {
if (strcmp(param->key, ss->legacy_name))
continue;
gdb_cmd_detachkill(ks);
return DBG_PASS_EVENT;
}
-#endif
fallthrough;
+#endif
case 'C': /* Exception passing */
tmp = gdb_cmd_exception_pass(ks);
if (tmp > 0)
s64 duration;
VERBOSE_SCALEOUT_BATCH("ref_scale_reader %ld: task started", me);
- set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids));
+ WARN_ON_ONCE(set_cpus_allowed_ptr(current, cpumask_of(me % nr_cpu_ids)));
set_user_nice(current, MAX_NICE);
atomic_inc(&n_init);
if (holdoff)
schedule_timeout_interruptible(holdoff * HZ);
repeat:
- VERBOSE_SCALEOUT_BATCH("ref_scale_reader %ld: waiting to start next experiment on cpu %d", me, smp_processor_id());
+ VERBOSE_SCALEOUT_BATCH("ref_scale_reader %ld: waiting to start next experiment on cpu %d", me, raw_smp_processor_id());
// Wait for signal that this reader can start.
wait_event(rt->wq, (atomic_read(&nreaders_exp) && smp_load_acquire(&rt->start_reader)) ||
goto end;
// Make sure that the CPU is affinitized appropriately during testing.
- WARN_ON_ONCE(smp_processor_id() != me);
+ WARN_ON_ONCE(raw_smp_processor_id() != me);
WRITE_ONCE(rt->start_reader, 0);
if (!atomic_dec_return(&n_started))
in_qs = likely(!t->trc_reader_nesting);
}
- // Mark as checked. Because this is called from the grace-period
- // kthread, also remove the task from the holdout list.
+ // Mark as checked so that the grace-period kthread will
+ // remove it from the holdout list.
t->trc_reader_checked = true;
- trc_del_holdout(t);
if (in_qs)
return true; // Already in quiescent state, done!!!
// The current task had better be in a quiescent state.
if (t == current) {
t->trc_reader_checked = true;
- trc_del_holdout(t);
WARN_ON_ONCE(t->trc_reader_nesting);
return;
}
jr = j - data_race(rcu_state.gp_req_activity);
js = j - data_race(rcu_state.gp_start);
jw = j - data_race(rcu_state.gp_wake_time);
- pr_info("%s: wait state: %s(%d) ->state: %#lx ->rt_priority %u delta ->gp_start %lu ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_max %lu ->gp_flags %#x\n",
+ pr_info("%s: wait state: %s(%d) ->state: %#x ->rt_priority %u delta ->gp_start %lu ->gp_activity %lu ->gp_req_activity %lu ->gp_wake_time %lu ->gp_wake_seq %ld ->gp_seq %ld ->gp_seq_needed %ld ->gp_max %lu ->gp_flags %#x\n",
rcu_state.name, gp_state_getname(rcu_state.gp_state),
- rcu_state.gp_state, t ? t->__state : 0x1ffffL, t ? t->rt_priority : 0xffU,
+ rcu_state.gp_state, t ? t->__state : 0x1ffff, t ? t->rt_priority : 0xffU,
js, ja, jr, jw, (long)data_race(rcu_state.gp_wake_seq),
(long)data_race(rcu_state.gp_seq),
(long)data_race(rcu_get_root()->gp_seq_needed),
VERBOSE_SCFTORTOUT("scftorture_invoker %d: task started", scfp->cpu);
cpu = scfp->cpu % nr_cpu_ids;
- set_cpus_allowed_ptr(current, cpumask_of(cpu));
+ WARN_ON_ONCE(set_cpus_allowed_ptr(current, cpumask_of(cpu)));
set_user_nice(current, MAX_NICE);
if (holdoff)
schedule_timeout_interruptible(holdoff * HZ);
- VERBOSE_SCFTORTOUT("scftorture_invoker %d: Waiting for all SCF torturers from cpu %d", scfp->cpu, smp_processor_id());
+ VERBOSE_SCFTORTOUT("scftorture_invoker %d: Waiting for all SCF torturers from cpu %d", scfp->cpu, raw_smp_processor_id());
// Make sure that the CPU is affinitized appropriately during testing.
- curcpu = smp_processor_id();
+ curcpu = raw_smp_processor_id();
WARN_ONCE(curcpu != scfp->cpu % nr_cpu_ids,
"%s: Wanted CPU %d, running on %d, nr_cpu_ids = %d\n",
__func__, scfp->cpu, curcpu, nr_cpu_ids);
for (pfn = start >> PAGE_SHIFT; pfn < (end >> PAGE_SHIFT); pfn++) {
void *entry;
- struct page *page;
entry = xa_load(&dmirror->pt, pfn);
- page = xa_untag_pointer(entry);
if (xa_pointer_tag(entry) == DPT_XA_TAG_ATOMIC)
return -EPERM;
}
continue;
}
- refs = min3(pages_per_huge_page(h) - pfn_offset,
- (vma->vm_end - vaddr) >> PAGE_SHIFT, remainder);
+ /* vaddr may not be aligned to PAGE_SIZE */
+ refs = min3(pages_per_huge_page(h) - pfn_offset, remainder,
+ (vma->vm_end - ALIGN_DOWN(vaddr, PAGE_SIZE)) >> PAGE_SHIFT);
if (pages || vmas)
record_subpages_vmas(mem_map_offset(page, pfn_offset),
#ifdef CONFIG_KASAN_HW_TAGS
#include <linux/static_key.h>
+#include "../slab.h"
DECLARE_STATIC_KEY_FALSE(kasan_flag_stacktrace);
extern bool kasan_flag_async __ro_after_init;
if (WARN_ON((unsigned long)addr & KASAN_GRANULE_MASK))
return;
+ /*
+ * Explicitly initialize the memory with the precise object size to
+ * avoid overwriting the SLAB redzone. This disables initialization in
+ * the arch code and may thus lead to performance penalty. The penalty
+ * is accepted since SLAB redzones aren't enabled in production builds.
+ */
+ if (__slub_debug_enabled() &&
+ init && ((unsigned long)size & KASAN_GRANULE_MASK)) {
+ init = false;
+ memzero_explicit((void *)addr, size);
+ }
size = round_up(size, KASAN_GRANULE_SIZE);
hw_set_mem_tag_range((void *)addr, size, tag, init);
}
/*
- * Gigantic pages are so large that we do not guarantee that page++ pointer
- * arithmetic will work across the entire page. We need something more
- * specialized.
- */
-static void __copy_gigantic_page(struct page *dst, struct page *src,
- int nr_pages)
-{
- int i;
- struct page *dst_base = dst;
- struct page *src_base = src;
-
- for (i = 0; i < nr_pages; ) {
- cond_resched();
- copy_highpage(dst, src);
-
- i++;
- dst = mem_map_next(dst, dst_base, i);
- src = mem_map_next(src, src_base, i);
- }
-}
-
-void copy_huge_page(struct page *dst, struct page *src)
-{
- int i;
- int nr_pages;
-
- if (PageHuge(src)) {
- /* hugetlbfs page */
- struct hstate *h = page_hstate(src);
- nr_pages = pages_per_huge_page(h);
-
- if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) {
- __copy_gigantic_page(dst, src, nr_pages);
- return;
- }
- } else {
- /* thp page */
- BUG_ON(!PageTransHuge(src));
- nr_pages = thp_nr_pages(src);
- }
-
- for (i = 0; i < nr_pages; i++) {
- cond_resched();
- copy_highpage(dst + i, src + i);
- }
-}
-
-/*
* Copy the page to its new location
*/
void migrate_page_states(struct page *newpage, struct page *page)
#endif /* CONFIG_FAIL_PAGE_ALLOC */
-static noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
+noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
{
return __should_fail_alloc_page(gfp_mask, order);
}
unsigned int alloc_flags = ALLOC_WMARK_LOW;
int nr_populated = 0, nr_account = 0;
- if (unlikely(nr_pages <= 0))
- return 0;
-
/*
* Skip populated array elements to determine if any pages need
* to be allocated before disabling IRQs.
while (page_array && nr_populated < nr_pages && page_array[nr_populated])
nr_populated++;
+ /* No pages requested? */
+ if (unlikely(nr_pages <= 0))
+ goto out;
+
/* Already populated array? */
if (unlikely(page_array && nr_pages - nr_populated == 0))
- return nr_populated;
+ goto out;
/* Use the single page allocator for one page. */
if (nr_pages - nr_populated == 1)
goto failed;
+#ifdef CONFIG_PAGE_OWNER
+ /*
+ * PAGE_OWNER may recurse into the allocator to allocate space to
+ * save the stack with pagesets.lock held. Releasing/reacquiring
+ * removes much of the performance benefit of bulk allocation so
+ * force the caller to allocate one page at a time as it'll have
+ * similar performance to added complexity to the bulk allocator.
+ */
+ if (static_branch_unlikely(&page_owner_inited))
+ goto failed;
+#endif
+
/* May set ALLOC_NOFRAGMENT, fragmentation will return 1 page. */
gfp &= gfp_allowed_mask;
alloc_gfp = gfp;
if (!prepare_alloc_pages(gfp, 0, preferred_nid, nodemask, &ac, &alloc_gfp, &alloc_flags))
- return 0;
+ goto out;
gfp = alloc_gfp;
/* Find an allowed local zone that meets the low watermark. */
__count_zid_vm_events(PGALLOC, zone_idx(zone), nr_account);
zone_statistics(ac.preferred_zoneref->zone, zone, nr_account);
+out:
return nr_populated;
failed_irq:
nr_populated++;
}
- return nr_populated;
+ goto out;
}
EXPORT_SYMBOL_GPL(__alloc_pages_bulk);
/*
* If the page is mlock()d, we cannot swap it out.
*/
- if (!(flags & TTU_IGNORE_MLOCK)) {
- if (vma->vm_flags & VM_LOCKED) {
- /* PTE-mapped THP are never marked as mlocked */
- if (!PageTransCompound(page) ||
- (PageHead(page) && !PageDoubleMap(page))) {
- /*
- * Holding pte lock, we do *not* need
- * mmap_lock here
- */
- mlock_vma_page(page);
- }
- ret = false;
- page_vma_mapped_walk_done(&pvmw);
- break;
- }
+ if (!(flags & TTU_IGNORE_MLOCK) &&
+ (vma->vm_flags & VM_LOCKED)) {
+ /*
+ * PTE-mapped THP are never marked as mlocked: so do
+ * not set it on a DoubleMap THP, nor on an Anon THP
+ * (which may still be PTE-mapped after DoubleMap was
+ * cleared). But stop unmapping even in those cases.
+ */
+ if (!PageTransCompound(page) || (PageHead(page) &&
+ !PageDoubleMap(page) && !PageAnon(page)))
+ mlock_vma_page(page);
+ page_vma_mapped_walk_done(&pvmw);
+ ret = false;
+ break;
}
/* Unexpected PMD-mapped THP? */
*/
if (vma->vm_flags & VM_LOCKED) {
/*
- * PTE-mapped THP are never marked as mlocked, but
- * this function is never called when PageDoubleMap().
+ * PTE-mapped THP are never marked as mlocked; but
+ * this function is never called on a DoubleMap THP,
+ * nor on an Anon THP (which may still be PTE-mapped
+ * after DoubleMap was cleared).
*/
mlock_vma_page(page);
/*
VM_BUG_ON_PAGE(!PageLocked(page) || PageLRU(page), page);
VM_BUG_ON_PAGE(PageCompound(page) && PageDoubleMap(page), page);
+ /* Anon THP are only marked as mlocked when singly mapped */
+ if (PageTransCompound(page) && PageAnon(page))
+ return;
+
rmap_walk(page, &rwc);
}
#endif
extern void print_tracking(struct kmem_cache *s, void *object);
long validate_slab_cache(struct kmem_cache *s);
+static inline bool __slub_debug_enabled(void)
+{
+ return static_branch_unlikely(&slub_debug_enabled);
+}
#else
static inline void print_tracking(struct kmem_cache *s, void *object)
{
}
+static inline bool __slub_debug_enabled(void)
+{
+ return false;
+}
#endif
/*
*/
static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t flags)
{
-#ifdef CONFIG_SLUB_DEBUG
- VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS));
- if (static_branch_unlikely(&slub_debug_enabled))
+ if (IS_ENABLED(CONFIG_SLUB_DEBUG))
+ VM_WARN_ON_ONCE(!(flags & SLAB_DEBUG_FLAGS));
+ if (__slub_debug_enabled())
return s->flags & flags;
-#endif
return false;
}
*/
#ifdef CONFIG_SLUB_DEBUG
-
#ifdef CONFIG_SLUB_DEBUG_ON
DEFINE_STATIC_KEY_TRUE(slub_debug_enabled);
#else
DEFINE_STATIC_KEY_FALSE(slub_debug_enabled);
#endif
-
-static inline bool __slub_debug_enabled(void)
-{
- return static_branch_unlikely(&slub_debug_enabled);
-}
-
-#else /* CONFIG_SLUB_DEBUG */
-
-static inline bool __slub_debug_enabled(void)
-{
- return false;
-}
-
#endif /* CONFIG_SLUB_DEBUG */
static inline bool kmem_cache_debug(struct kmem_cache *s)
}
EXPORT_SYMBOL_GPL(__page_mapcount);
+void copy_huge_page(struct page *dst, struct page *src)
+{
+ unsigned i, nr = compound_nr(src);
+
+ for (i = 0; i < nr; i++) {
+ cond_resched();
+ copy_highpage(nth_page(dst, i), nth_page(src, i));
+ }
+}
+
int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;
int sysctl_overcommit_ratio __read_mostly = 50;
unsigned long sysctl_overcommit_kbytes __read_mostly;
kfree(attr);
}
+static void garp_attr_destroy_all(struct garp_applicant *app)
+{
+ struct rb_node *node, *next;
+ struct garp_attr *attr;
+
+ for (node = rb_first(&app->gid);
+ next = node ? rb_next(node) : NULL, node != NULL;
+ node = next) {
+ attr = rb_entry(node, struct garp_attr, node);
+ garp_attr_destroy(app, attr);
+ }
+}
+
static int garp_pdu_init(struct garp_applicant *app)
{
struct sk_buff *skb;
spin_lock_bh(&app->lock);
garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU);
+ garp_attr_destroy_all(app);
garp_pdu_queue(app);
spin_unlock_bh(&app->lock);
kfree(attr);
}
+static void mrp_attr_destroy_all(struct mrp_applicant *app)
+{
+ struct rb_node *node, *next;
+ struct mrp_attr *attr;
+
+ for (node = rb_first(&app->mad);
+ next = node ? rb_next(node) : NULL, node != NULL;
+ node = next) {
+ attr = rb_entry(node, struct mrp_attr, node);
+ mrp_attr_destroy(app, attr);
+ }
+}
+
static int mrp_pdu_init(struct mrp_applicant *app)
{
struct sk_buff *skb;
spin_lock_bh(&app->lock);
mrp_mad_event(app, MRP_EVENT_TX);
+ mrp_attr_destroy_all(app);
mrp_pdu_queue(app);
spin_unlock_bh(&app->lock);
struct net_bridge_port *p;
int err = 0;
unsigned br_hr, dev_hr;
- bool changed_addr;
+ bool changed_addr, fdb_synced = false;
/* Don't allow bridging non-ethernet like devices. */
if ((dev->flags & IFF_LOOPBACK) ||
list_add_rcu(&p->list, &br->port_list);
nbp_update_port_count(br);
+ if (!br_promisc_port(p) && (p->dev->priv_flags & IFF_UNICAST_FLT)) {
+ /* When updating the port count we also update all ports'
+ * promiscuous mode.
+ * A port leaving promiscuous mode normally gets the bridge's
+ * fdb synced to the unicast filter (if supported), however,
+ * `br_port_clear_promisc` does not distinguish between
+ * non-promiscuous ports and *new* ports, so we need to
+ * sync explicitly here.
+ */
+ fdb_synced = br_fdb_sync_static(br, p) == 0;
+ if (!fdb_synced)
+ netdev_err(dev, "failed to sync bridge static fdb addresses to this port\n");
+ }
netdev_update_features(br->dev);
return 0;
err7:
+ if (fdb_synced)
+ br_fdb_unsync_static(br, p);
list_del_rcu(&p->list);
br_fdb_delete_by_port(br, p, 0, 1);
nbp_update_port_count(br);
pim_hdr_type(pimhdr) != PIM_TYPE_HELLO)
return;
+ spin_lock(&br->multicast_lock);
br_ip4_multicast_mark_router(br, port);
+ spin_unlock(&br->multicast_lock);
}
static int br_ip4_multicast_mrd_rcv(struct net_bridge *br,
igmp_hdr(skb)->type != IGMP_MRDISC_ADV)
return -ENOMSG;
+ spin_lock(&br->multicast_lock);
br_ip4_multicast_mark_router(br, port);
+ spin_unlock(&br->multicast_lock);
return 0;
}
if (icmp6_hdr(skb)->icmp6_type != ICMPV6_MRDISC_ADV)
return;
+ spin_lock(&br->multicast_lock);
br_ip6_multicast_mark_router(br, port);
+ spin_unlock(&br->multicast_lock);
}
static int br_multicast_ipv6_rcv(struct net_bridge *br,
diffs = memcmp(skb_mac_header(p),
skb_mac_header(skb),
maclen);
+
+ diffs |= skb_get_nfct(p) ^ skb_get_nfct(skb);
+#if IS_ENABLED(CONFIG_SKB_EXTENSIONS) && IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
+ if (!diffs) {
+ struct tc_skb_ext *skb_ext = skb_ext_find(skb, TC_SKB_EXT);
+ struct tc_skb_ext *p_ext = skb_ext_find(p, TC_SKB_EXT);
+
+ diffs |= (!!p_ext) ^ (!!skb_ext);
+ if (!diffs && unlikely(skb_ext))
+ diffs |= p_ext->chain ^ skb_ext->chain;
+ }
+#endif
+
NAPI_GRO_CB(p)->same_flow = !diffs;
}
}
case GRO_MERGED_FREE:
if (NAPI_GRO_CB(skb)->free == NAPI_GRO_FREE_STOLEN_HEAD)
napi_skb_free_stolen_head(skb);
+ else if (skb->fclone != SKB_FCLONE_UNAVAILABLE)
+ __kfree_skb(skb);
else
__kfree_skb_defer(skb);
break;
skb_shinfo(skb)->gso_type = 0;
skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
skb_ext_reset(skb);
+ nf_reset_ct(skb);
napi->skb = skb;
}
void napi_skb_free_stolen_head(struct sk_buff *skb)
{
+ nf_reset_ct(skb);
skb_dst_drop(skb);
skb_ext_put(skb);
napi_skb_cache_put(skb);
#include <net/tcp.h>
#include <net/busy_poll.h>
+#include <linux/ethtool.h>
+
static DEFINE_MUTEX(proto_list_mutex);
static LIST_HEAD(proto_list);
}
}
-int sock_set_timestamping(struct sock *sk, int optname, int val)
+static int sock_timestamping_bind_phc(struct sock *sk, int phc_index)
+{
+ struct net *net = sock_net(sk);
+ struct net_device *dev = NULL;
+ bool match = false;
+ int *vclock_index;
+ int i, num;
+
+ if (sk->sk_bound_dev_if)
+ dev = dev_get_by_index(net, sk->sk_bound_dev_if);
+
+ if (!dev) {
+ pr_err("%s: sock not bind to device\n", __func__);
+ return -EOPNOTSUPP;
+ }
+
+ num = ethtool_get_phc_vclocks(dev, &vclock_index);
+ for (i = 0; i < num; i++) {
+ if (*(vclock_index + i) == phc_index) {
+ match = true;
+ break;
+ }
+ }
+
+ if (num > 0)
+ kfree(vclock_index);
+
+ if (!match)
+ return -EINVAL;
+
+ sk->sk_bind_phc = phc_index;
+
+ return 0;
+}
+
+int sock_set_timestamping(struct sock *sk, int optname,
+ struct so_timestamping timestamping)
{
+ int val = timestamping.flags;
+ int ret;
+
if (val & ~SOF_TIMESTAMPING_MASK)
return -EINVAL;
!(val & SOF_TIMESTAMPING_OPT_TSONLY))
return -EINVAL;
+ if (val & SOF_TIMESTAMPING_BIND_PHC) {
+ ret = sock_timestamping_bind_phc(sk, timestamping.bind_phc);
+ if (ret)
+ return ret;
+ }
+
sk->sk_tsflags = val;
sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW);
int sock_setsockopt(struct socket *sock, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
+ struct so_timestamping timestamping;
struct sock_txtime sk_txtime;
struct sock *sk = sock->sk;
int val;
case SO_TIMESTAMP_NEW:
case SO_TIMESTAMPNS_OLD:
case SO_TIMESTAMPNS_NEW:
- sock_set_timestamp(sk, valbool, optname);
+ sock_set_timestamp(sk, optname, valbool);
break;
case SO_TIMESTAMPING_NEW:
case SO_TIMESTAMPING_OLD:
- ret = sock_set_timestamping(sk, optname, val);
+ if (optlen == sizeof(timestamping)) {
+ if (copy_from_sockptr(×tamping, optval,
+ sizeof(timestamping))) {
+ ret = -EFAULT;
+ break;
+ }
+ } else {
+ memset(×tamping, 0, sizeof(timestamping));
+ timestamping.flags = val;
+ }
+ ret = sock_set_timestamping(sk, optname, timestamping);
break;
case SO_RCVLOWAT:
if (val < 0)
ret = -EINVAL;
else
- sk->sk_ll_usec = val;
+ WRITE_ONCE(sk->sk_ll_usec, val);
}
break;
case SO_PREFER_BUSY_POLL:
struct __kernel_old_timeval tm;
struct __kernel_sock_timeval stm;
struct sock_txtime txtime;
+ struct so_timestamping timestamping;
} v;
int lv = sizeof(int);
break;
case SO_TIMESTAMPING_OLD:
- v.val = sk->sk_tsflags;
+ lv = sizeof(v.timestamping);
+ v.timestamping.flags = sk->sk_tsflags;
+ v.timestamping.bind_phc = sk->sk_bind_phc;
break;
case SO_RCVTIMEO_OLD:
int err, port;
if (dst->index == info->tree_index && ds->index == info->sw_index &&
- ds->ops->port_bridge_join)
+ ds->ops->port_bridge_leave)
ds->ops->port_bridge_leave(ds, info->port, info->br);
if ((dst->index != info->tree_index || ds->index != info->sw_index) &&
- ds->ops->crosschip_bridge_join)
+ ds->ops->crosschip_bridge_leave)
ds->ops->crosschip_bridge_leave(ds, info->tree_index,
info->sw_index, info->port,
info->br);
info->port, info->lag,
info->info);
- return 0;
+ return -EOPNOTSUPP;
}
static int dsa_switch_lag_leave(struct dsa_switch *ds,
return ds->ops->crosschip_lag_leave(ds, info->sw_index,
info->port, info->lag);
- return 0;
+ return -EOPNOTSUPP;
}
static int dsa_switch_mdb_add(struct dsa_switch *ds,
ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o \
linkstate.o debug.o wol.o features.o privflags.o rings.o \
channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \
- tunnels.o fec.o eeprom.o stats.o
+ tunnels.o fec.o eeprom.o stats.o phc_vclocks.o
#include <linux/net_tstamp.h>
#include <linux/phy.h>
#include <linux/rtnetlink.h>
+#include <linux/ptp_clock_kernel.h>
#include "common.h"
[const_ilog2(SOF_TIMESTAMPING_OPT_STATS)] = "option-stats",
[const_ilog2(SOF_TIMESTAMPING_OPT_PKTINFO)] = "option-pktinfo",
[const_ilog2(SOF_TIMESTAMPING_OPT_TX_SWHW)] = "option-tx-swhw",
+ [const_ilog2(SOF_TIMESTAMPING_BIND_PHC)] = "bind-phc",
};
static_assert(ARRAY_SIZE(sof_timestamping_names) == __SOF_TIMESTAMPING_CNT);
return 0;
}
+int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index)
+{
+ struct ethtool_ts_info info = { };
+ int num = 0;
+
+ if (!__ethtool_get_ts_info(dev, &info))
+ num = ptp_get_vclocks_index(info.phc_index, vclock_index);
+
+ return num;
+}
+EXPORT_SYMBOL(ethtool_get_phc_vclocks);
+
const struct ethtool_phy_ops *ethtool_phy_ops;
void ethtool_set_ethtool_phy_ops(const struct ethtool_phy_ops *ops)
[ETHTOOL_MSG_TSINFO_GET] = ðnl_tsinfo_request_ops,
[ETHTOOL_MSG_MODULE_EEPROM_GET] = ðnl_module_eeprom_request_ops,
[ETHTOOL_MSG_STATS_GET] = ðnl_stats_request_ops,
+ [ETHTOOL_MSG_PHC_VCLOCKS_GET] = ðnl_phc_vclocks_request_ops,
};
static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb)
.policy = ethnl_stats_get_policy,
.maxattr = ARRAY_SIZE(ethnl_stats_get_policy) - 1,
},
+ {
+ .cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET,
+ .doit = ethnl_default_doit,
+ .start = ethnl_default_start,
+ .dumpit = ethnl_default_dumpit,
+ .done = ethnl_default_done,
+ .policy = ethnl_phc_vclocks_get_policy,
+ .maxattr = ARRAY_SIZE(ethnl_phc_vclocks_get_policy) - 1,
+ },
};
static const struct genl_multicast_group ethtool_nl_mcgrps[] = {
extern const struct ethnl_request_ops ethnl_fec_request_ops;
extern const struct ethnl_request_ops ethnl_module_eeprom_request_ops;
extern const struct ethnl_request_ops ethnl_stats_request_ops;
+extern const struct ethnl_request_ops ethnl_phc_vclocks_request_ops;
extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1];
extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1];
extern const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1];
extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS + 1];
extern const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_GROUPS + 1];
+extern const struct nla_policy ethnl_phc_vclocks_get_policy[ETHTOOL_A_PHC_VCLOCKS_HEADER + 1];
int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info);
int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info);
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2021 NXP
+ */
+#include "netlink.h"
+#include "common.h"
+
+struct phc_vclocks_req_info {
+ struct ethnl_req_info base;
+};
+
+struct phc_vclocks_reply_data {
+ struct ethnl_reply_data base;
+ int num;
+ int *index;
+};
+
+#define PHC_VCLOCKS_REPDATA(__reply_base) \
+ container_of(__reply_base, struct phc_vclocks_reply_data, base)
+
+const struct nla_policy ethnl_phc_vclocks_get_policy[] = {
+ [ETHTOOL_A_PHC_VCLOCKS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy),
+};
+
+static int phc_vclocks_prepare_data(const struct ethnl_req_info *req_base,
+ struct ethnl_reply_data *reply_base,
+ struct genl_info *info)
+{
+ struct phc_vclocks_reply_data *data = PHC_VCLOCKS_REPDATA(reply_base);
+ struct net_device *dev = reply_base->dev;
+ int ret;
+
+ ret = ethnl_ops_begin(dev);
+ if (ret < 0)
+ return ret;
+ data->num = ethtool_get_phc_vclocks(dev, &data->index);
+ ethnl_ops_complete(dev);
+
+ return ret;
+}
+
+static int phc_vclocks_reply_size(const struct ethnl_req_info *req_base,
+ const struct ethnl_reply_data *reply_base)
+{
+ const struct phc_vclocks_reply_data *data =
+ PHC_VCLOCKS_REPDATA(reply_base);
+ int len = 0;
+
+ if (data->num > 0) {
+ len += nla_total_size(sizeof(u32));
+ len += nla_total_size(sizeof(s32) * data->num);
+ }
+
+ return len;
+}
+
+static int phc_vclocks_fill_reply(struct sk_buff *skb,
+ const struct ethnl_req_info *req_base,
+ const struct ethnl_reply_data *reply_base)
+{
+ const struct phc_vclocks_reply_data *data =
+ PHC_VCLOCKS_REPDATA(reply_base);
+
+ if (data->num <= 0)
+ return 0;
+
+ if (nla_put_u32(skb, ETHTOOL_A_PHC_VCLOCKS_NUM, data->num) ||
+ nla_put(skb, ETHTOOL_A_PHC_VCLOCKS_INDEX,
+ sizeof(s32) * data->num, data->index))
+ return -EMSGSIZE;
+
+ return 0;
+}
+
+static void phc_vclocks_cleanup_data(struct ethnl_reply_data *reply_base)
+{
+ const struct phc_vclocks_reply_data *data =
+ PHC_VCLOCKS_REPDATA(reply_base);
+
+ kfree(data->index);
+}
+
+const struct ethnl_request_ops ethnl_phc_vclocks_request_ops = {
+ .request_cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET,
+ .reply_cmd = ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY,
+ .hdr_attr = ETHTOOL_A_PHC_VCLOCKS_HEADER,
+ .req_info_size = sizeof(struct phc_vclocks_req_info),
+ .reply_data_size = sizeof(struct phc_vclocks_reply_data),
+
+ .prepare_data = phc_vclocks_prepare_data,
+ .reply_size = phc_vclocks_reply_size,
+ .fill_reply = phc_vclocks_fill_reply,
+ .cleanup_data = phc_vclocks_cleanup_data,
+};
portid = NETLINK_CB(skb).portid; /* netlink portid */
NETLINK_CB(skb).portid = 0; /* from kernel */
NETLINK_CB(skb).dst_group = 0; /* unicast */
- netlink_unicast(net->ipv4.fibnl, skb, portid, MSG_DONTWAIT);
+ nlmsg_unicast(net->ipv4.fibnl, skb, portid);
}
static int __net_init nl_fib_lookup_init(struct net *net)
nlmsg_free(rep);
goto out;
}
- err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
out:
if (sk)
}
dev->needed_headroom = t_hlen + hlen;
- mtu -= t_hlen;
+ mtu -= t_hlen + (dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0);
if (mtu < IPV4_MIN_MTU)
mtu = IPV4_MIN_MTU;
t_hlen = nt->hlen + sizeof(struct iphdr);
dev->min_mtu = ETH_MIN_MTU;
dev->max_mtu = IP_MAX_MTU - t_hlen;
+ if (dev->type == ARPHRD_ETHER)
+ dev->max_mtu -= dev->hard_header_len;
+
ip_tunnel_add(itn, nt);
return nt;
tunnel_hlen = md ? tunnel_hlen : tunnel->hlen;
pkt_size = skb->len - tunnel_hlen;
+ pkt_size -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0;
- if (df)
+ if (df) {
mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel_hlen);
- else
+ mtu -= dev->type == ARPHRD_ETHER ? dev->hard_header_len : 0;
+ } else {
mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
+ }
if (skb_valid_dst(skb))
skb_dst_update_pmtu_no_confirm(skb, mtu);
int t_hlen = tunnel->hlen + sizeof(struct iphdr);
int max_mtu = IP_MAX_MTU - t_hlen;
+ if (dev->type == ARPHRD_ETHER)
+ max_mtu -= dev->hard_header_len;
+
if (new_mtu < ETH_MIN_MTU)
return -EINVAL;
if (tb[IFLA_MTU]) {
unsigned int max = IP_MAX_MTU - (nt->hlen + sizeof(struct iphdr));
+ if (dev->type == ARPHRD_ETHER)
+ max -= dev->hard_header_len;
+
mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, max);
}
raw_rcv(mroute_sk, skb);
return 0;
}
- }
+ }
}
/* already under rcu_read_lock() */
return err;
}
- err = netlink_unicast(net->diag_nlsk, rep,
- NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
+
return err;
}
}
pfrag->offset += copy;
} else {
+ if (!sk_wmem_schedule(sk, copy))
+ goto wait_for_space;
+
err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg);
if (err == -EMSGSIZE || err == -EEXIST) {
tcp_mark_push(tp, skb);
{
trace_tcp_receive_reset(sk);
+ /* mptcp can't tell us to ignore reset pkts,
+ * so just ignore the return value of mptcp_incoming_options().
+ */
if (sk_is_mptcp(sk))
mptcp_incoming_options(sk, skb);
bool fragstolen;
int eaten;
- if (sk_is_mptcp(sk))
- mptcp_incoming_options(sk, skb);
+ /* If a subflow has been reset, the packet should not continue
+ * to be processed, drop the packet.
+ */
+ if (sk_is_mptcp(sk) && !mptcp_incoming_options(sk, skb)) {
+ __kfree_skb(skb);
+ return;
+ }
if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
__kfree_skb(skb);
tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk));
tp->snd_cwnd_stamp = tcp_jiffies32;
- icsk->icsk_ca_initialized = 0;
bpf_skops_established(sk, bpf_op, skb);
+ /* Initialize congestion control unless BPF initialized it already: */
if (!icsk->icsk_ca_initialized)
tcp_init_congestion_control(sk);
tcp_init_buffer_space(sk);
case TCP_CLOSING:
case TCP_LAST_ACK:
if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
- if (sk_is_mptcp(sk))
- mptcp_incoming_options(sk, skb);
+ /* If a subflow has been reset, the packet should not
+ * continue to be processed, drop the packet.
+ */
+ if (sk_is_mptcp(sk) && !mptcp_incoming_options(sk, skb))
+ goto discard;
break;
}
fallthrough;
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
return;
- mtu = tcp_sk(sk)->mtu_info;
+ mtu = READ_ONCE(tcp_sk(sk)->mtu_info);
dst = inet_csk_update_pmtu(sk, mtu);
if (!dst)
return;
if (sk->sk_state == TCP_LISTEN)
goto out;
- tp->mtu_info = info;
+ WRITE_ONCE(tp->mtu_info, info);
if (!sock_owned_by_user(sk)) {
tcp_v4_mtu_reduced(sk);
} else {
return __tcp_mtu_to_mss(sk, pmtu) -
(tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr));
}
+EXPORT_SYMBOL(tcp_mtu_to_mss);
/* Inverse of above */
int tcp_mss_to_mtu(struct sock *sk, int mss)
}
ipcm_init_sk(&ipc, inet);
- ipc.gso_size = up->gso_size;
+ ipc.gso_size = READ_ONCE(up->gso_size);
if (msg->msg_controllen) {
err = udp_cmsg_send(sk, msg, &ipc.gso_size);
case UDP_SEGMENT:
if (val < 0 || val > USHRT_MAX)
return -EINVAL;
- up->gso_size = val;
+ WRITE_ONCE(up->gso_size, val);
break;
case UDP_GRO:
break;
case UDP_SEGMENT:
- val = up->gso_size;
+ val = READ_ONCE(up->gso_size);
break;
case UDP_GRO:
kfree_skb(rep);
goto out;
}
- err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
+
out:
if (sk)
sock_put(sk);
if ((!sk && (skb->dev->features & NETIF_F_GRO_UDP_FWD)) ||
(sk && udp_sk(sk)->gro_enabled) || NAPI_GRO_CB(skb)->is_flist)
- pp = call_gro_receive(udp_gro_receive_segment, head, skb);
- return pp;
+ return call_gro_receive(udp_gro_receive_segment, head, skb);
+
+ /* no GRO, be sure flush the current packet */
+ goto out;
}
if (NAPI_GRO_CB(skb)->encap_mark ||
{
struct dst_entry *dst = skb_dst(skb);
struct net_device *dev = dst->dev;
+ unsigned int hh_len = LL_RESERVED_SPACE(dev);
+ int delta = hh_len - skb_headroom(skb);
const struct in6_addr *nexthop;
struct neighbour *neigh;
int ret;
+ /* Be paranoid, rather than too clever. */
+ if (unlikely(delta > 0) && dev->header_ops) {
+ /* pskb_expand_head() might crash, if skb is shared */
+ if (skb_shared(skb)) {
+ struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+
+ if (likely(nskb)) {
+ if (skb->sk)
+ skb_set_owner_w(skb, skb->sk);
+ consume_skb(skb);
+ } else {
+ kfree_skb(skb);
+ }
+ skb = nskb;
+ }
+ if (skb &&
+ pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) {
+ kfree_skb(skb);
+ skb = NULL;
+ }
+ if (!skb) {
+ IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS);
+ return -ENOMEM;
+ }
+ }
+
if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) {
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
if (skb_warn_if_lro(skb))
goto drop;
- if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
+ if (!net->ipv6.devconf_all->disable_policy &&
+ !idev->cnf.disable_policy &&
+ !xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
__IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS);
goto drop;
}
static void tcp_v6_mtu_reduced(struct sock *sk)
{
struct dst_entry *dst;
+ u32 mtu;
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
return;
- dst = inet6_csk_update_pmtu(sk, tcp_sk(sk)->mtu_info);
+ mtu = READ_ONCE(tcp_sk(sk)->mtu_info);
+
+ /* Drop requests trying to increase our current mss.
+ * Check done in __ip6_rt_update_pmtu() is too late.
+ */
+ if (tcp_mtu_to_mss(sk, mtu) >= tcp_sk(sk)->mss_cache)
+ return;
+
+ dst = inet6_csk_update_pmtu(sk, mtu);
if (!dst)
return;
}
if (type == ICMPV6_PKT_TOOBIG) {
+ u32 mtu = ntohl(info);
+
/* We are not interested in TCP_LISTEN and open_requests
* (SYN-ACKs send out by Linux are always <576bytes so
* they should go through unfragmented).
if (!ip6_sk_accept_pmtu(sk))
goto out;
- tp->mtu_info = ntohl(info);
+ if (mtu < IPV6_MIN_MTU)
+ goto out;
+
+ WRITE_ONCE(tp->mtu_info, mtu);
+
if (!sock_owned_by_user(sk))
tcp_v6_mtu_reduced(sk);
else if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED,
opt = ireq->ipv6_opt;
if (!opt)
opt = rcu_dereference(np->opt);
- err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt,
+ err = ip6_xmit(sk, skb, fl6, skb->mark ? : sk->sk_mark, opt,
tclass, sk->sk_priority);
rcu_read_unlock();
err = net_xmit_eval(err);
int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
ipcm6_init(&ipc6);
- ipc6.gso_size = up->gso_size;
+ ipc6.gso_size = READ_ONCE(up->gso_size);
ipc6.sockc.tsflags = sk->sk_tsflags;
ipc6.sockc.mark = sk->sk_mark;
{
struct dst_entry *dst = skb_dst(skb);
struct xfrm_state *x = dst->xfrm;
- int mtu;
+ unsigned int mtu;
bool toobig;
#ifdef CONFIG_NETFILTER
u8 iptype;
u32 ipmsgid;
u32 iptrgcls;
- union {
- u32 iprmmsg1_u32;
- u8 iprmmsg1[4];
- } ln1msg1;
- union {
- u32 ipbfln1f;
- u8 iprmmsg2[4];
- } ln1msg2;
+ struct {
+ union {
+ u32 iprmmsg1_u32;
+ u8 iprmmsg1[4];
+ } ln1msg1;
+ union {
+ u32 ipbfln1f;
+ u8 iprmmsg2[4];
+ } ln1msg2;
+ } rmmsg;
u32 res1[3];
u32 ipbfln2f;
u8 ippollfg;
msg.id = imp->ipmsgid;
msg.class = imp->iptrgcls;
if (imp->ipflags1 & IUCV_IPRMDATA) {
- memcpy(msg.rmmsg, imp->ln1msg1.iprmmsg1, 8);
+ memcpy(msg.rmmsg, &imp->rmmsg, 8);
msg.length = 8;
} else
- msg.length = imp->ln1msg2.ipbfln1f;
+ msg.length = imp->rmmsg.ln1msg2.ipbfln1f;
msg.reply_size = imp->ipbfln2f;
path->handler->message_pending(path, &msg);
}
SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW),
SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX),
SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX),
+ SNMP_MIB_ITEM("RcvPruned", MPTCP_MIB_RCVPRUNED),
SNMP_MIB_SENTINEL
};
MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */
MPTCP_MIB_MPPRIOTX, /* Transmit a MP_PRIO */
MPTCP_MIB_MPPRIORX, /* Received a MP_PRIO */
+ MPTCP_MIB_RCVPRUNED, /* Incoming packet dropped due to memory limit */
__MPTCP_MIB_MAX
};
kfree_skb(rep);
goto out;
}
- err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
+
out:
sock_put(sk);
return hmac == mp_opt->ahmac;
}
-void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
+/* Return false if a subflow has been reset, else return true */
+bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
{
struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
struct mptcp_sock *msk = mptcp_sk(subflow->conn);
__mptcp_check_push(subflow->conn, sk);
__mptcp_data_acked(subflow->conn);
mptcp_data_unlock(subflow->conn);
- return;
+ return true;
}
mptcp_get_options(sk, skb, &mp_opt);
+
+ /* The subflow can be in close state only if check_fully_established()
+ * just sent a reset. If so, tell the caller to ignore the current packet.
+ */
if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))
- return;
+ return sk->sk_state != TCP_CLOSE;
if (mp_opt.fastclose &&
msk->local_key == mp_opt.rcvr_key) {
}
if (!mp_opt.dss)
- return;
+ return true;
/* we can't wait for recvmsg() to update the ack_seq, otherwise
* monodirectional flows will stuck
schedule_work(&msk->work))
sock_hold(subflow->conn);
- return;
+ return true;
}
mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
if (!mpext)
- return;
+ return true;
memset(mpext, 0, sizeof(*mpext));
if (mpext->csum_reqd)
mpext->csum = mp_opt.csum;
}
+
+ return true;
}
static void mptcp_set_rwin(const struct tcp_sock *tp)
bool cleanup, rx_empty;
cleanup = (space > 0) && (space >= (old_space << 1));
- rx_empty = !atomic_read(&sk->sk_rmem_alloc);
+ rx_empty = !__mptcp_rmem(sk);
mptcp_for_each_subflow(msk, subflow) {
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
sk_rbuf = ssk_rbuf;
/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
- if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf)
+ if (__mptcp_rmem(sk) > sk_rbuf) {
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
return;
+ }
/* Wake-up the reader only for in-sequence data */
mptcp_data_lock(sk);
if (!(flags & MSG_PEEK)) {
/* we will bulk release the skb memory later */
skb->destructor = NULL;
- msk->rmem_released += skb->truesize;
+ WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize);
__skb_unlink(skb, &msk->receive_queue);
__kfree_skb(skb);
}
atomic_sub(msk->rmem_released, &sk->sk_rmem_alloc);
sk_mem_uncharge(sk, msk->rmem_released);
- msk->rmem_released = 0;
+ WRITE_ONCE(msk->rmem_released, 0);
}
static void __mptcp_splice_receive_queue(struct sock *sk)
msk->out_of_order_queue = RB_ROOT;
msk->first_pending = NULL;
msk->wmem_reserved = 0;
- msk->rmem_released = 0;
+ WRITE_ONCE(msk->rmem_released, 0);
msk->tx_pending_data = 0;
msk->first = NULL;
return (struct mptcp_sock *)sk;
}
+/* the msk socket don't use the backlog, also account for the bulk
+ * free memory
+ */
+static inline int __mptcp_rmem(const struct sock *sk)
+{
+ return atomic_read(&sk->sk_rmem_alloc) - READ_ONCE(mptcp_sk(sk)->rmem_released);
+}
+
static inline int __mptcp_space(const struct sock *sk)
{
- return tcp_space(sk) + READ_ONCE(mptcp_sk(sk)->rmem_released);
+ return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk));
}
static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)
struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
bool slow = lock_sock_fast(ssk);
- switch (optname) {
- case SO_TIMESTAMP_OLD:
- case SO_TIMESTAMP_NEW:
- case SO_TIMESTAMPNS_OLD:
- case SO_TIMESTAMPNS_NEW:
- sock_set_timestamp(sk, optname, !!val);
- break;
- case SO_TIMESTAMPING_NEW:
- case SO_TIMESTAMPING_OLD:
- sock_set_timestamping(sk, optname, val);
- break;
- }
-
+ sock_set_timestamp(sk, optname, !!val);
unlock_sock_fast(ssk, slow);
}
}
static int mptcp_setsockopt_sol_socket_int(struct mptcp_sock *msk, int optname,
- sockptr_t optval, unsigned int optlen)
+ sockptr_t optval,
+ unsigned int optlen)
{
int val, ret;
case SO_TIMESTAMP_NEW:
case SO_TIMESTAMPNS_OLD:
case SO_TIMESTAMPNS_NEW:
- case SO_TIMESTAMPING_OLD:
- case SO_TIMESTAMPING_NEW:
return mptcp_setsockopt_sol_socket_tstamp(msk, optname, val);
}
return -ENOPROTOOPT;
}
+static int mptcp_setsockopt_sol_socket_timestamping(struct mptcp_sock *msk,
+ int optname,
+ sockptr_t optval,
+ unsigned int optlen)
+{
+ struct mptcp_subflow_context *subflow;
+ struct sock *sk = (struct sock *)msk;
+ struct so_timestamping timestamping;
+ int ret;
+
+ if (optlen == sizeof(timestamping)) {
+ if (copy_from_sockptr(×tamping, optval,
+ sizeof(timestamping)))
+ return -EFAULT;
+ } else if (optlen == sizeof(int)) {
+ memset(×tamping, 0, sizeof(timestamping));
+
+ if (copy_from_sockptr(×tamping.flags, optval, sizeof(int)))
+ return -EFAULT;
+ } else {
+ return -EINVAL;
+ }
+
+ ret = sock_setsockopt(sk->sk_socket, SOL_SOCKET, optname,
+ KERNEL_SOCKPTR(×tamping),
+ sizeof(timestamping));
+ if (ret)
+ return ret;
+
+ lock_sock(sk);
+
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ bool slow = lock_sock_fast(ssk);
+
+ sock_set_timestamping(sk, optname, timestamping);
+ unlock_sock_fast(ssk, slow);
+ }
+
+ release_sock(sk);
+
+ return 0;
+}
+
static int mptcp_setsockopt_sol_socket_linger(struct mptcp_sock *msk, sockptr_t optval,
unsigned int optlen)
{
case SO_TIMESTAMP_NEW:
case SO_TIMESTAMPNS_OLD:
case SO_TIMESTAMPNS_NEW:
+ return mptcp_setsockopt_sol_socket_int(msk, optname, optval,
+ optlen);
case SO_TIMESTAMPING_OLD:
case SO_TIMESTAMPING_NEW:
- return mptcp_setsockopt_sol_socket_int(msk, optname, optval, optlen);
+ return mptcp_setsockopt_sol_socket_timestamping(msk, optname,
+ optval, optlen);
case SO_LINGER:
return mptcp_setsockopt_sol_socket_linger(msk, optval, optlen);
case SO_RCVLOWAT:
ntohs(inet_sk(sk_listener)->inet_sport),
ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport));
if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) {
- sock_put((struct sock *)subflow_req->msk);
- mptcp_token_destroy_request(req);
- tcp_request_sock_ops.destructor(req);
- subflow_req->msk = NULL;
- subflow_req->mp_join = 0;
SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTSYNRX);
return -EPERM;
}
if (unlikely(req->syncookie)) {
if (mptcp_can_accept_new_subflow(subflow_req->msk))
subflow_init_req_cookie_join_save(subflow_req, skb);
+ else
+ return -EPERM;
}
pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token,
if (!mptcp_token_join_cookie_init_state(subflow_req, skb))
return -EINVAL;
- if (mptcp_can_accept_new_subflow(subflow_req->msk))
- subflow_req->mp_join = 1;
-
+ subflow_req->mp_join = 1;
subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq - 1;
}
static u32 mptcp_join_entry_hash(struct sk_buff *skb, struct net *net)
{
- u32 i = skb_get_hash(skb) ^ net_hash_mix(net);
+ static u32 mptcp_join_hash_secret __read_mostly;
+ struct tcphdr *th = tcp_hdr(skb);
+ u32 seq, i;
+
+ net_get_random_once(&mptcp_join_hash_secret,
+ sizeof(mptcp_join_hash_secret));
+
+ if (th->syn)
+ seq = TCP_SKB_CB(skb)->seq;
+ else
+ seq = TCP_SKB_CB(skb)->seq - 1;
+
+ i = jhash_3words(seq, net_hash_mix(net),
+ (__force __u32)th->source << 16 | (__force __u32)th->dest,
+ mptcp_join_hash_secret);
return i % ARRAY_SIZE(join_entries);
}
help
This allows to get MAC address from NCSI firmware and set them back to
controller.
+config NCSI_OEM_CMD_KEEP_PHY
+ bool "Keep PHY Link up"
+ depends on NET_NCSI
+ help
+ This allows to keep PHY link up and prevents any channel resets during
+ the host load.
/* OEM Vendor Manufacture ID */
#define NCSI_OEM_MFR_MLX_ID 0x8119
#define NCSI_OEM_MFR_BCM_ID 0x113d
+#define NCSI_OEM_MFR_INTEL_ID 0x157
+/* Intel specific OEM command */
+#define NCSI_OEM_INTEL_CMD_KEEP_PHY 0x20 /* CMD ID for Keep PHY up */
/* Broadcom specific OEM Command */
#define NCSI_OEM_BCM_CMD_GMA 0x01 /* CMD ID for Get MAC */
/* Mellanox specific OEM Command */
#define NCSI_OEM_MLX_CMD_SMAF 0x01 /* CMD ID for Set MC Affinity */
#define NCSI_OEM_MLX_CMD_SMAF_PARAM 0x07 /* Parameter for SMAF */
/* OEM Command payload lengths*/
+#define NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN 7
#define NCSI_OEM_BCM_CMD_GMA_LEN 12
#define NCSI_OEM_MLX_CMD_GMA_LEN 8
#define NCSI_OEM_MLX_CMD_SMAF_LEN 60
ncsi_dev_state_probe_mlx_gma,
ncsi_dev_state_probe_mlx_smaf,
ncsi_dev_state_probe_cis,
+ ncsi_dev_state_probe_keep_phy,
ncsi_dev_state_probe_gvi,
ncsi_dev_state_probe_gc,
ncsi_dev_state_probe_gls,
return 0;
}
+#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY)
+
+static int ncsi_oem_keep_phy_intel(struct ncsi_cmd_arg *nca)
+{
+ unsigned char data[NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN];
+ int ret = 0;
+
+ nca->payload = NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN;
+
+ memset(data, 0, NCSI_OEM_INTEL_CMD_KEEP_PHY_LEN);
+ *(unsigned int *)data = ntohl((__force __be32)NCSI_OEM_MFR_INTEL_ID);
+
+ data[4] = NCSI_OEM_INTEL_CMD_KEEP_PHY;
+
+ /* PHY Link up attribute */
+ data[6] = 0x1;
+
+ nca->data = data;
+
+ ret = ncsi_xmit_cmd(nca);
+ if (ret)
+ netdev_err(nca->ndp->ndev.dev,
+ "NCSI: Failed to transmit cmd 0x%x during configure\n",
+ nca->type);
+ return ret;
+}
+
+#endif
+
#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC)
/* NCSI OEM Command APIs */
nca->payload = NCSI_OEM_BCM_CMD_GMA_LEN;
memset(data, 0, NCSI_OEM_BCM_CMD_GMA_LEN);
- *(unsigned int *)data = ntohl(NCSI_OEM_MFR_BCM_ID);
+ *(unsigned int *)data = ntohl((__force __be32)NCSI_OEM_MFR_BCM_ID);
data[5] = NCSI_OEM_BCM_CMD_GMA;
nca->data = data;
nca->payload = NCSI_OEM_MLX_CMD_GMA_LEN;
memset(&u, 0, sizeof(u));
- u.data_u32[0] = ntohl(NCSI_OEM_MFR_MLX_ID);
+ u.data_u32[0] = ntohl((__force __be32)NCSI_OEM_MFR_MLX_ID);
u.data_u8[5] = NCSI_OEM_MLX_CMD_GMA;
u.data_u8[6] = NCSI_OEM_MLX_CMD_GMA_PARAM;
int ret = 0;
memset(&u, 0, sizeof(u));
- u.data_u32[0] = ntohl(NCSI_OEM_MFR_MLX_ID);
+ u.data_u32[0] = ntohl((__force __be32)NCSI_OEM_MFR_MLX_ID);
u.data_u8[5] = NCSI_OEM_MLX_CMD_SMAF;
u.data_u8[6] = NCSI_OEM_MLX_CMD_SMAF_PARAM;
memcpy(&u.data_u8[MLX_SMAF_MAC_ADDR_OFFSET],
}
nd->state = ncsi_dev_state_probe_gvi;
+ if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY))
+ nd->state = ncsi_dev_state_probe_keep_phy;
+ break;
+#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_KEEP_PHY)
+ case ncsi_dev_state_probe_keep_phy:
+ ndp->pending_req_num = 1;
+
+ nca.type = NCSI_PKT_CMD_OEM;
+ nca.package = ndp->active_package->id;
+ nca.channel = 0;
+ ret = ncsi_oem_keep_phy_intel(&nca);
+ if (ret)
+ goto error;
+
+ nd->state = ncsi_dev_state_probe_gvi;
break;
+#endif /* CONFIG_NCSI_OEM_CMD_KEEP_PHY */
case ncsi_dev_state_probe_gvi:
case ncsi_dev_state_probe_gc:
case ncsi_dev_state_probe_gls:
/* Update to VLAN mode */
cmd = (struct ncsi_cmd_ev_pkt *)skb_network_header(nr->cmd);
ncm->enable = 1;
- ncm->data[0] = ntohl(cmd->mode);
+ ncm->data[0] = ntohl((__force __be32)cmd->mode);
return 0;
}
return 0;
}
+/* Response handler for Intel card */
+static int ncsi_rsp_handler_oem_intel(struct ncsi_request *nr)
+{
+ return 0;
+}
+
static struct ncsi_rsp_oem_handler {
unsigned int mfr_id;
int (*handler)(struct ncsi_request *nr);
} ncsi_rsp_oem_handlers[] = {
{ NCSI_OEM_MFR_MLX_ID, ncsi_rsp_handler_oem_mlx },
- { NCSI_OEM_MFR_BCM_ID, ncsi_rsp_handler_oem_bcm }
+ { NCSI_OEM_MFR_BCM_ID, ncsi_rsp_handler_oem_bcm },
+ { NCSI_OEM_MFR_INTEL_ID, ncsi_rsp_handler_oem_intel }
};
/* Response handler for OEM command */
spin_lock(&nf_conntrack_locks_all_lock);
- nf_conntrack_locks_all = true;
+ /* For nf_contrack_locks_all, only the latest time when another
+ * CPU will see an update is controlled, by the "release" of the
+ * spin_lock below.
+ * The earliest time is not controlled, an thus KCSAN could detect
+ * a race when nf_conntract_lock() reads the variable.
+ * WRITE_ONCE() is used to ensure the compiler will not
+ * optimize the write.
+ */
+ WRITE_ONCE(nf_conntrack_locks_all, true);
for (i = 0; i < CONNTRACK_LOCKS; i++) {
spin_lock(&nf_conntrack_locks[i]);
}
list_for_each_entry(net, net_exit_list, exit_list) {
- nf_conntrack_proto_pernet_fini(net);
nf_conntrack_ecache_pernet_fini(net);
nf_conntrack_expect_pernet_fini(net);
free_percpu(net->ct.stat);
if (!help)
return 0;
+ rcu_read_lock();
helper = rcu_dereference(help->helper);
if (!helper)
goto out;
nla_nest_end(skb, nest_helper);
out:
+ rcu_read_unlock();
return 0;
nla_put_failure:
+ rcu_read_unlock();
return -1;
}
#endif
}
-void nf_conntrack_proto_pernet_fini(struct net *net)
-{
-#ifdef CONFIG_NF_CT_PROTO_GRE
- nf_ct_gre_keymap_flush(net);
-#endif
-}
-
module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint,
&nf_conntrack_htable_size, 0600);
return &net->ct.nf_ct_proto.gre;
}
-void nf_ct_gre_keymap_flush(struct net *net)
-{
- struct nf_gre_net *net_gre = gre_pernet(net);
- struct nf_ct_gre_keymap *km, *tmp;
-
- spin_lock_bh(&keymap_lock);
- list_for_each_entry_safe(km, tmp, &net_gre->keymap_list, list) {
- list_del_rcu(&km->list);
- kfree_rcu(km, rcu);
- }
- spin_unlock_bh(&keymap_lock);
-}
-
static inline int gre_key_cmpfn(const struct nf_ct_gre_keymap *km,
const struct nf_conntrack_tuple *t)
{
return true;
}
+static bool tcp_can_early_drop(const struct nf_conn *ct)
+{
+ switch (ct->proto.tcp.state) {
+ case TCP_CONNTRACK_FIN_WAIT:
+ case TCP_CONNTRACK_LAST_ACK:
+ case TCP_CONNTRACK_TIME_WAIT:
+ case TCP_CONNTRACK_CLOSE:
+ case TCP_CONNTRACK_CLOSE_WAIT:
+ return true;
+ default:
+ break;
+ }
+
+ return false;
+}
+
/* Returns verdict for packet, or -1 for invalid. */
int nf_conntrack_tcp_packet(struct nf_conn *ct,
struct sk_buff *skb,
if (index != TCP_RST_SET)
break;
- if (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) {
+ /* If we are closing, tuple might have been re-used already.
+ * last_index, last_ack, and all other ct fields used for
+ * sequence/window validation are outdated in that case.
+ *
+ * As the conntrack can already be expired by GC under pressure,
+ * just skip validation checks.
+ */
+ if (tcp_can_early_drop(ct))
+ goto in_window;
+
+ /* td_maxack might be outdated if we let a SYN through earlier */
+ if ((ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) &&
+ ct->proto.tcp.last_index != TCP_SYN_SET) {
u32 seq = ntohl(th->seq);
- if (before(seq, ct->proto.tcp.seen[!dir].td_maxack)) {
+ /* If we are not in established state and SEQ=0 this is most
+ * likely an answer to a SYN we let go through above (last_index
+ * can be updated due to out-of-order ACKs).
+ */
+ if (seq == 0 && !nf_conntrack_tcp_established(ct))
+ break;
+
+ if (before(seq, ct->proto.tcp.seen[!dir].td_maxack) &&
+ !tn->tcp_ignore_invalid_rst) {
/* Invalid RST */
spin_unlock_bh(&ct->lock);
nf_ct_l4proto_log_invalid(skb, ct, state, "invalid rst");
nf_ct_kill_acct(ct, ctinfo, skb);
return NF_ACCEPT;
}
+
+ if (index == TCP_SYN_SET && old_state == TCP_CONNTRACK_SYN_SENT) {
+ /* do not renew timeout on SYN retransmit.
+ *
+ * Else port reuse by client or NAT middlebox can keep
+ * entry alive indefinitely (including nat info).
+ */
+ return NF_ACCEPT;
+ }
+
/* ESTABLISHED without SEEN_REPLY, i.e. mid-connection
* pickup with loose=1. Avoid large ESTABLISHED timeout.
*/
return NF_ACCEPT;
}
-static bool tcp_can_early_drop(const struct nf_conn *ct)
-{
- switch (ct->proto.tcp.state) {
- case TCP_CONNTRACK_FIN_WAIT:
- case TCP_CONNTRACK_LAST_ACK:
- case TCP_CONNTRACK_TIME_WAIT:
- case TCP_CONNTRACK_CLOSE:
- case TCP_CONNTRACK_CLOSE_WAIT:
- return true;
- default:
- break;
- }
-
- return false;
-}
-
#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
#include <linux/netfilter/nfnetlink.h>
*/
tn->tcp_be_liberal = 0;
+ /* If it's non-zero, we turn off RST sequence number check */
+ tn->tcp_ignore_invalid_rst = 0;
+
/* Max number of the retransmitted packets without receiving an (acceptable)
* ACK from the destination. If this number is reached, a shorter timer
* will be started.
#endif
NF_SYSCTL_CT_PROTO_TCP_LOOSE,
NF_SYSCTL_CT_PROTO_TCP_LIBERAL,
+ NF_SYSCTL_CT_PROTO_TCP_IGNORE_INVALID_RST,
NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS,
NF_SYSCTL_CT_PROTO_TIMEOUT_UDP,
NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM,
.extra1 = SYSCTL_ZERO,
.extra2 = SYSCTL_ONE,
},
+ [NF_SYSCTL_CT_PROTO_TCP_IGNORE_INVALID_RST] = {
+ .procname = "nf_conntrack_tcp_ignore_invalid_rst",
+ .maxlen = sizeof(u8),
+ .mode = 0644,
+ .proc_handler = proc_dou8vec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
[NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS] = {
.procname = "nf_conntrack_tcp_max_retrans",
.maxlen = sizeof(u8),
XASSIGN(LOOSE, &tn->tcp_loose);
XASSIGN(LIBERAL, &tn->tcp_be_liberal);
XASSIGN(MAX_RETRANS, &tn->tcp_max_retrans);
+ XASSIGN(IGNORE_INVALID_RST, &tn->tcp_ignore_invalid_rst);
#undef XASSIGN
#if IS_ENABLED(CONFIG_NF_FLOW_TABLE)
return 0;
err_destroy_flow_rule:
- nft_flow_rule_destroy(flow);
+ if (flow)
+ nft_flow_rule_destroy(flow);
err_release_rule:
nf_tables_rule_release(&ctx, rule);
err_release_expr:
{
struct nft_last_priv *priv = nft_expr_priv(expr);
u64 last_jiffies;
+ u32 last_set = 0;
int err;
- if (tb[NFTA_LAST_MSECS]) {
+ if (tb[NFTA_LAST_SET]) {
+ last_set = ntohl(nla_get_be32(tb[NFTA_LAST_SET]));
+ if (last_set == 1)
+ priv->last_set = 1;
+ }
+
+ if (last_set && tb[NFTA_LAST_MSECS]) {
err = nf_msecs_to_jiffies64(tb[NFTA_LAST_MSECS], &last_jiffies);
if (err < 0)
return err;
- priv->last_jiffies = jiffies + (unsigned long)last_jiffies;
- priv->last_set = 1;
+ priv->last_jiffies = jiffies - (unsigned long)last_jiffies;
}
return 0;
nlmsg_end(skb, rep);
- netlink_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid, MSG_DONTWAIT);
+ nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid);
}
EXPORT_SYMBOL(netlink_ack);
{
const long *cp1 = (const long *)((const u8 *)key1 + key_start);
const long *cp2 = (const long *)((const u8 *)key2 + key_start);
- long diffs = 0;
int i;
for (i = key_start; i < key_end; i += sizeof(long))
- diffs |= *cp1++ ^ *cp2++;
+ if (*cp1++ ^ *cp2++)
+ return false;
- return diffs == 0;
+ return true;
}
static bool flow_cmp_masked_key(const struct sw_flow *flow,
static void tcf_ct_flow_table_cleanup_work(struct work_struct *work)
{
+ struct flow_block_cb *block_cb, *tmp_cb;
struct tcf_ct_flow_table *ct_ft;
+ struct flow_block *block;
ct_ft = container_of(to_rcu_work(work), struct tcf_ct_flow_table,
rwork);
nf_flow_table_free(&ct_ft->nf_ft);
+
+ /* Remove any remaining callbacks before cleanup */
+ block = &ct_ft->nf_ft.flow_block;
+ down_write(&ct_ft->nf_ft.flow_block_lock);
+ list_for_each_entry_safe(block_cb, tmp_cb, &block->cb_list, list) {
+ list_del(&block_cb->list);
+ flow_block_cb_free(block_cb);
+ }
+ up_write(&ct_ft->nf_ft.flow_block_lock);
kfree(ct_ft);
module_put(THIS_MODULE);
/* This will take care of sending queued events
* even if the connection is already confirmed.
*/
- nf_conntrack_confirm(skb);
+ if (nf_conntrack_confirm(skb) != NF_ACCEPT)
+ goto drop;
}
if (!skip_add)
/* if there's no entry, it means that the schedule didn't
* start yet, so force all gates to be open, this is in
* accordance to IEEE 802.1Qbv-2015 Section 8.6.9.4.5
- * "AdminGateSates"
+ * "AdminGateStates"
*/
gate_mask = entry ? entry->gate_mask : TAPRIO_ALL_GATES_OPEN;
goto out;
}
- err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
+
out:
return err;
}
retval = SCTP_SCOPE_LINK;
} else if (ipv4_is_private_10(addr->v4.sin_addr.s_addr) ||
ipv4_is_private_172(addr->v4.sin_addr.s_addr) ||
- ipv4_is_private_192(addr->v4.sin_addr.s_addr)) {
+ ipv4_is_private_192(addr->v4.sin_addr.s_addr) ||
+ ipv4_is_test_198(addr->v4.sin_addr.s_addr)) {
retval = SCTP_SCOPE_PRIVATE;
} else {
retval = SCTP_SCOPE_GLOBAL;
const struct sctp_transport *transport,
__u32 probe_size)
{
- struct sctp_sender_hb_info hbinfo;
+ struct sctp_sender_hb_info hbinfo = {};
struct sctp_chunk *retval;
retval = sctp_make_control(asoc, SCTP_CID_HEARTBEAT, 0,
t->pathmtu = t->pl.pmtu + sctp_transport_pl_hlen(t);
sctp_assoc_sync_pmtu(t->asoc);
}
- } else if (t->pl.state == SCTP_PL_COMPLETE && ++t->pl.raise_count == 30) {
- /* Raise probe_size again after 30 * interval in Search Complete */
- t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */
- t->pl.probe_size += SCTP_PL_MIN_STEP;
+ } else if (t->pl.state == SCTP_PL_COMPLETE) {
+ t->pl.raise_count++;
+ if (t->pl.raise_count == 30) {
+ /* Raise probe_size again after 30 * interval in Search Complete */
+ t->pl.state = SCTP_PL_SEARCH; /* Search Complete -> Search */
+ t->pl.probe_size += SCTP_PL_MIN_STEP;
+ }
}
}
#include <linux/sockios.h>
#include <net/busy_poll.h>
#include <linux/errqueue.h>
+#include <linux/ptp_clock_kernel.h>
#ifdef CONFIG_NET_RX_BUSY_POLL
unsigned int sysctl_net_busy_read __read_mostly;
empty = 0;
if (shhwtstamps &&
(sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) &&
- !skb_is_swtx_tstamp(skb, false_tstamp) &&
- ktime_to_timespec64_cond(shhwtstamps->hwtstamp, tss.ts + 2)) {
- empty = 0;
- if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) &&
- !skb_is_err_queue(skb))
- put_ts_pktinfo(msg, skb);
+ !skb_is_swtx_tstamp(skb, false_tstamp)) {
+ if (sk->sk_tsflags & SOF_TIMESTAMPING_BIND_PHC)
+ ptp_convert_timestamp(shhwtstamps, sk->sk_bind_phc);
+
+ if (ktime_to_timespec64_cond(shhwtstamps->hwtstamp,
+ tss.ts + 2)) {
+ empty = 0;
+
+ if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) &&
+ !skb_is_err_queue(skb))
+ put_ts_pktinfo(msg, skb);
+ }
}
if (!empty) {
if (sock_flag(sk, SOCK_TSTAMP_NEW))
goto again;
}
- err = netlink_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid,
- MSG_DONTWAIT);
- if (err > 0)
- err = 0;
+ err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);
+
out:
if (sk)
sock_put(sk);
-Wno-gnu-variable-sized-type-not-at-end \
-Wno-address-of-packed-member -Wno-tautological-compare \
-Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \
+ -fno-asynchronous-unwind-tables \
-I$(srctree)/samples/bpf/ -include asm_goto_workaround.h \
-O2 -emit-llvm -Xclang -disable-llvm-passes -c $< -o - | \
$(OPT) -O2 -mtriple=bpf-pc-linux | $(LLVM_DIS) | \
static int opt_timeout = 1000;
static bool opt_need_wakeup = true;
static u32 opt_num_xsks = 1;
+static u32 prog_id;
static bool opt_busy_poll;
static bool opt_reduced_cap;
return NULL;
}
+static void remove_xdp_program(void)
+{
+ u32 curr_prog_id = 0;
+
+ if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) {
+ printf("bpf_get_link_xdp_id failed\n");
+ exit(EXIT_FAILURE);
+ }
+
+ if (prog_id == curr_prog_id)
+ bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags);
+ else if (!curr_prog_id)
+ printf("couldn't find a prog id on a given interface\n");
+ else
+ printf("program on interface changed, not removing\n");
+}
+
static void int_exit(int sig)
{
benchmark_done = true;
{
fprintf(stderr, "%s:%s:%i: errno: %d/\"%s\"\n", file, func,
line, error, strerror(error));
+
+ if (opt_num_xsks > 1)
+ remove_xdp_program();
exit(EXIT_FAILURE);
}
if (write(sock, &cmd, sizeof(int)) < 0)
exit_with_error(errno);
}
+
+ if (opt_num_xsks > 1)
+ remove_xdp_program();
}
static void swap_mac_addresses(void *data)
if (ret)
exit_with_error(-ret);
+ ret = bpf_get_link_xdp_id(opt_ifindex, &prog_id, opt_xdp_flags);
+ if (ret)
+ exit_with_error(-ret);
+
xsk->app_stats.rx_empty_polls = 0;
xsk->app_stats.fill_fail_polls = 0;
xsk->app_stats.copy_tx_sendtos = 0;
case MT8183_MTKAIF_PROTOCOL_1:
regmap_write(afe->regmap, AFE_AUD_PAD_TOP, 0x31);
regmap_write(afe->regmap, AFE_ADDA_MTKAIF_CFG0, 0x0);
+ break;
default:
break;
}
$(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpf
$(Q)$(RM) -r -- $(OUTPUT)feature
-install: $(PROGS) bpftool_install runqslower_install
+install: $(PROGS) bpftool_install
$(call QUIET_INSTALL, bpf_jit_disasm)
$(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(prefix)/bin
$(Q)$(INSTALL) $(OUTPUT)bpf_jit_disasm $(DESTDIR)$(prefix)/bin/bpf_jit_disasm
runqslower:
$(call descend,runqslower)
-runqslower_install:
- $(call descend,runqslower,install)
-
runqslower_clean:
$(call descend,runqslower,clean)
$(call descend,resolve_btfids,clean)
.PHONY: all install clean bpftool bpftool_install bpftool_clean \
- runqslower runqslower_install runqslower_clean \
+ runqslower runqslower_clean \
resolve_btfids resolve_btfids_clean
{
va_list ap;
char *s;
+ int err;
va_start(ap, fmt);
- if (vasprintf(&s, fmt, ap) < 0)
- return -1;
+ err = vasprintf(&s, fmt, ap);
va_end(ap);
+ if (err < 0)
+ return -1;
if (!oper_count) {
int i;
u32 pid;
/* ivcsw: treat like an enqueue event and store timestamp */
- if (prev->state == TASK_RUNNING)
+ if (prev->__state == TASK_RUNNING)
trace_enqueue(prev);
pid = next->pid;
err = unlink(link->pin_path);
if (err != 0)
- return libbpf_err_errno(err);
+ return -errno;
pr_debug("link fd=%d: unpinned from %s\n", link->fd, link->pin_path);
zfree(&link->pin_path);
cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, timeout_ms);
if (cnt < 0)
- return libbpf_err_errno(cnt);
+ return -errno;
for (i = 0; i < cnt; i++) {
struct perf_cpu_buf *cpu_buf = pb->events[i].data.ptr;
bpf_object__close(obj);
}
+#include "tailcall_bpf2bpf4.skel.h"
+
/* test_tailcall_bpf2bpf_4 checks that tailcall counter is correctly preserved
* across tailcalls combined with bpf2bpf calls. for making sure that tailcall
* counter behaves correctly, bpf program will go through following flow:
* the loop begins. At the end of the test make sure that the global counter is
* equal to 31, because tailcall counter includes the first two tailcalls
* whereas global counter is incremented only on loop presented on flow above.
+ *
+ * The noise parameter is used to insert bpf_map_update calls into the logic
+ * to force verifier to patch instructions. This allows us to ensure jump
+ * logic remains correct with instruction movement.
*/
-static void test_tailcall_bpf2bpf_4(void)
+static void test_tailcall_bpf2bpf_4(bool noise)
{
- int err, map_fd, prog_fd, main_fd, data_fd, i, val;
+ int err, map_fd, prog_fd, main_fd, data_fd, i;
+ struct tailcall_bpf2bpf4__bss val;
struct bpf_map *prog_array, *data_map;
struct bpf_program *prog;
struct bpf_object *obj;
goto out;
}
- err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0,
- &duration, &retval, NULL);
- CHECK(err || retval != sizeof(pkt_v4) * 3, "tailcall", "err %d errno %d retval %d\n",
- err, errno, retval);
-
data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
return;
return;
i = 0;
+ val.noise = noise;
+ val.count = 0;
+ err = bpf_map_update_elem(data_fd, &i, &val, BPF_ANY);
+ if (CHECK_FAIL(err))
+ goto out;
+
+ err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0,
+ &duration, &retval, NULL);
+ CHECK(err || retval != sizeof(pkt_v4) * 3, "tailcall", "err %d errno %d retval %d\n",
+ err, errno, retval);
+
+ i = 0;
err = bpf_map_lookup_elem(data_fd, &i, &val);
- CHECK(err || val != 31, "tailcall count", "err %d errno %d count %d\n",
- err, errno, val);
+ CHECK(err || val.count != 31, "tailcall count", "err %d errno %d count %d\n",
+ err, errno, val.count);
out:
bpf_object__close(obj);
if (test__start_subtest("tailcall_bpf2bpf_3"))
test_tailcall_bpf2bpf_3();
if (test__start_subtest("tailcall_bpf2bpf_4"))
- test_tailcall_bpf2bpf_4();
+ test_tailcall_bpf2bpf_4(false);
+ if (test__start_subtest("tailcall_bpf2bpf_5"))
+ test_tailcall_bpf2bpf_4(true);
}
#include <bpf/bpf_helpers.h>
struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(__u32));
+} nop_table SEC(".maps");
+
+struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
__uint(max_entries, 3);
__uint(key_size, sizeof(__u32));
} jmp_table SEC(".maps");
int count = 0;
+int noise = 0;
+
+__always_inline int subprog_noise(void)
+{
+ __u32 key = 0;
+
+ bpf_map_lookup_elem(&nop_table, &key);
+ return 0;
+}
__noinline
int subprog_tail_2(struct __sk_buff *skb)
{
+ if (noise)
+ subprog_noise();
bpf_tail_call_static(skb, &jmp_table, 2);
return skb->len * 3;
}
VM_MODE_P40V48_64K,
VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */
VM_MODE_P47V64_4K,
+ VM_MODE_P44V64_4K,
NUM_VM_MODES,
};
#elif defined(__s390x__)
-#define VM_MODE_DEFAULT VM_MODE_P47V64_4K
+#define VM_MODE_DEFAULT VM_MODE_P44V64_4K
#define MIN_PAGE_SHIFT 12U
#define ptes_per_page(page_size) ((page_size) / 16)
void vm_init_descriptor_tables(struct kvm_vm *vm)
{
vm->handlers = vm_vaddr_alloc(vm, sizeof(struct handlers),
- vm->page_size, 0, 0);
+ vm->page_size);
*(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
}
}
}
#endif
+#ifdef __s390x__
+ {
+ int kvm_fd, vm_fd;
+ struct kvm_s390_vm_cpu_processor info;
+
+ kvm_fd = open_kvm_dev_path_or_exit();
+ vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, 0);
+ kvm_device_access(vm_fd, KVM_S390_VM_CPU_MODEL,
+ KVM_S390_VM_CPU_PROCESSOR, &info, false);
+ close(vm_fd);
+ close(kvm_fd);
+ /* Starting with z13 we have 47bits of physical address */
+ if (info.ibc >= 0x30)
+ guest_mode_append(VM_MODE_P47V64_4K, true, true);
+ }
+#endif
}
void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg)
[VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages",
[VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages",
[VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages",
+ [VM_MODE_P44V64_4K] = "PA-bits:44, VA-bits:64, 4K pages",
};
_Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES,
"Missing new mode strings?");
{ 40, 48, 0x10000, 16 },
{ 0, 0, 0x1000, 12 },
{ 47, 64, 0x1000, 12 },
+ { 44, 64, 0x1000, 12 },
};
_Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
"Missing new mode params?");
case VM_MODE_P47V64_4K:
vm->pgtable_levels = 5;
break;
+ case VM_MODE_P44V64_4K:
+ vm->pgtable_levels = 5;
+ break;
default:
TEST_FAIL("Unknown guest mode, mode: 0x%x", mode);
}
(max_mem_slots - 1), MEM_REGION_SIZE >> 10);
mem = mmap(NULL, (size_t)max_mem_slots * MEM_REGION_SIZE + alignment,
- PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE, -1, 0);
TEST_ASSERT(mem != MAP_FAILED, "Failed to mmap() host");
mem_aligned = (void *)(((size_t) mem + alignment - 1) & ~(alignment - 1));
vm_init_descriptor_tables(vm);
vcpu_init_descriptor_tables(vm, VCPU_ID);
- vm_handle_exception(vm, GP_VECTOR, guest_gp_handler);
+ vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler);
pr_info("Testing access to Hyper-V specific MSRs\n");
guest_test_msrs_access(vm, addr_gva2hva(vm, msr_gva),
/* Set up a #PF handler to eat the RSVD #PF and signal all done! */
vm_init_descriptor_tables(vm);
vcpu_init_descriptor_tables(vm, VCPU_ID);
- vm_handle_exception(vm, PF_VECTOR, guest_pf_handler);
+ vm_install_exception_handler(vm, PF_VECTOR, guest_pf_handler);
r = _vcpu_run(vm, VCPU_ID);
TEST_ASSERT(r == 0, "vcpu_run failed: %d\n", r);
: "+a" (phase));
}
-void self_smi(void)
+static void self_smi(void)
{
x2apic_write_reg(APIC_ICR,
APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI);
}
-void guest_code(void *arg)
+static void l2_guest_code(void)
{
+ sync_with_host(8);
+
+ sync_with_host(10);
+
+ vmcall();
+}
+
+static void guest_code(void *arg)
+{
+ #define L2_GUEST_STACK_SIZE 64
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
uint64_t apicbase = rdmsr(MSR_IA32_APICBASE);
+ struct svm_test_data *svm = arg;
+ struct vmx_pages *vmx_pages = arg;
sync_with_host(1);
sync_with_host(4);
if (arg) {
- if (cpu_has_svm())
- generic_svm_setup(arg, NULL, NULL);
- else
- GUEST_ASSERT(prepare_for_vmx_operation(arg));
+ if (cpu_has_svm()) {
+ generic_svm_setup(svm, l2_guest_code,
+ &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+ } else {
+ GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+ GUEST_ASSERT(load_vmcs(vmx_pages));
+ prepare_vmcs(vmx_pages, l2_guest_code,
+ &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+ }
sync_with_host(5);
self_smi();
sync_with_host(7);
+
+ if (cpu_has_svm()) {
+ run_guest(svm->vmcb, svm->vmcb_gpa);
+ svm->vmcb->save.rip += 3;
+ run_guest(svm->vmcb, svm->vmcb_gpa);
+ } else {
+ vmlaunch();
+ vmresume();
+ }
+
+ /* Stages 8-11 are eaten by SMM (SMRAM_STAGE reported instead) */
+ sync_with_host(12);
}
sync_with_host(DONE);
}
+void inject_smi(struct kvm_vm *vm)
+{
+ struct kvm_vcpu_events events;
+
+ vcpu_events_get(vm, VCPU_ID, &events);
+
+ events.smi.pending = 1;
+ events.flags |= KVM_VCPUEVENT_VALID_SMM;
+
+ vcpu_events_set(vm, VCPU_ID, &events);
+}
+
int main(int argc, char *argv[])
{
vm_vaddr_t nested_gva = 0;
"Unexpected stage: #%x, got %x",
stage, stage_reported);
+ /*
+ * Enter SMM during L2 execution and check that we correctly
+ * return from it. Do not perform save/restore while in SMM yet.
+ */
+ if (stage == 8) {
+ inject_smi(vm);
+ continue;
+ }
+
+ /*
+ * Perform save/restore while the guest is in SMM triggered
+ * during L2 execution.
+ */
+ if (stage == 10)
+ inject_smi(vm);
+
state = vcpu_save_state(vm, VCPU_ID);
kvm_vm_release(vm);
kvm_vm_restart(vm, O_RDWR);
fi
log_test $? 0 "IPv4: ${desc}"
- if [ "$with_redirect" = "yes" ]; then
+ # No PMTU info for test "redirect" and "mtu exception plus redirect"
+ if [ "$with_redirect" = "yes" ] && [ "$desc" != "redirect exception plus mtu" ]; then
ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \
- grep -q "${H2_N2_IP6} from :: via ${R2_LLADDR} dev br0.*${mtu}"
+ grep -v "mtu" | grep -q "${H2_N2_IP6} .*via ${R2_LLADDR} dev br0"
elif [ -n "${mtu}" ]; then
ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \
grep -q "${mtu}"
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
run_tests $ns1 $ns2 10.0.1.1
- chk_join_nr "subflows limited by server w cookies" 2 2 1
+ chk_join_nr "subflows limited by server w cookies" 2 1 1
# test signal address with cookies
reset_with_cookies
{
if (error)
printf("invalid option: %s\n", error);
- printf("timestamping interface option*\n\n"
+ printf("timestamping <interface> [bind_phc_index] [option]*\n\n"
"Options:\n"
" IP_MULTICAST_LOOP - looping outgoing multicasts\n"
" SO_TIMESTAMP - normal software time stamping, ms resolution\n"
" SOF_TIMESTAMPING_RX_SOFTWARE - software fallback for incoming packets\n"
" SOF_TIMESTAMPING_SOFTWARE - request reporting of software time stamps\n"
" SOF_TIMESTAMPING_RAW_HARDWARE - request reporting of raw HW time stamps\n"
+ " SOF_TIMESTAMPING_BIND_PHC - request to bind a PHC of PTP vclock\n"
" SIOCGSTAMP - check last socket time stamp\n"
" SIOCGSTAMPNS - more accurate socket time stamp\n"
" PTPV2 - use PTPv2 messages\n");
int main(int argc, char **argv)
{
- int so_timestamping_flags = 0;
int so_timestamp = 0;
int so_timestampns = 0;
int siocgstamp = 0;
struct ifreq device;
struct ifreq hwtstamp;
struct hwtstamp_config hwconfig, hwconfig_requested;
+ struct so_timestamping so_timestamping_get = { 0, -1 };
+ struct so_timestamping so_timestamping = { 0, -1 };
struct sockaddr_in addr;
struct ip_mreq imr;
struct in_addr iaddr;
exit(1);
}
- for (i = 2; i < argc; i++) {
+ if (argc >= 3 && sscanf(argv[2], "%d", &so_timestamping.bind_phc) == 1)
+ val = 3;
+ else
+ val = 2;
+
+ for (i = val; i < argc; i++) {
if (!strcasecmp(argv[i], "SO_TIMESTAMP"))
so_timestamp = 1;
else if (!strcasecmp(argv[i], "SO_TIMESTAMPNS"))
else if (!strcasecmp(argv[i], "PTPV2"))
ptpv2 = 1;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_HARDWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_TX_HARDWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_TX_HARDWARE;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_SOFTWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_TX_SOFTWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_TX_SOFTWARE;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_HARDWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_RX_HARDWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_RX_HARDWARE;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_SOFTWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_RX_SOFTWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_RX_SOFTWARE;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_SOFTWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_SOFTWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_SOFTWARE;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RAW_HARDWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_RAW_HARDWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_RAW_HARDWARE;
+ else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_BIND_PHC"))
+ so_timestamping.flags |= SOF_TIMESTAMPING_BIND_PHC;
else
usage(argv[i]);
}
hwtstamp.ifr_data = (void *)&hwconfig;
memset(&hwconfig, 0, sizeof(hwconfig));
hwconfig.tx_type =
- (so_timestamping_flags & SOF_TIMESTAMPING_TX_HARDWARE) ?
+ (so_timestamping.flags & SOF_TIMESTAMPING_TX_HARDWARE) ?
HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
hwconfig.rx_filter =
- (so_timestamping_flags & SOF_TIMESTAMPING_RX_HARDWARE) ?
+ (so_timestamping.flags & SOF_TIMESTAMPING_RX_HARDWARE) ?
ptpv2 ? HWTSTAMP_FILTER_PTP_V2_L4_SYNC :
HWTSTAMP_FILTER_PTP_V1_L4_SYNC : HWTSTAMP_FILTER_NONE;
hwconfig_requested = hwconfig;
sizeof(struct sockaddr_in)) < 0)
bail("bind");
+ if (setsockopt(sock, SOL_SOCKET, SO_BINDTODEVICE, interface, if_len))
+ bail("bind device");
+
/* set multicast group for outgoing packets */
inet_aton("224.0.1.130", &iaddr); /* alternate PTP domain 1 */
addr.sin_addr = iaddr;
&enabled, sizeof(enabled)) < 0)
bail("setsockopt SO_TIMESTAMPNS");
- if (so_timestamping_flags &&
- setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING,
- &so_timestamping_flags,
- sizeof(so_timestamping_flags)) < 0)
+ if (so_timestamping.flags &&
+ setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &so_timestamping,
+ sizeof(so_timestamping)) < 0)
bail("setsockopt SO_TIMESTAMPING");
/* request IP_PKTINFO for debugging purposes */
else
printf("SO_TIMESTAMPNS %d\n", val);
- if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &val, &len) < 0) {
+ len = sizeof(so_timestamping_get);
+ if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &so_timestamping_get,
+ &len) < 0) {
printf("%s: %s\n", "getsockopt SO_TIMESTAMPING",
strerror(errno));
} else {
- printf("SO_TIMESTAMPING %d\n", val);
- if (val != so_timestamping_flags)
- printf(" not the expected value %d\n",
- so_timestamping_flags);
+ printf("SO_TIMESTAMPING flags %d, bind phc %d\n",
+ so_timestamping_get.flags, so_timestamping_get.bind_phc);
+ if (so_timestamping_get.flags != so_timestamping.flags ||
+ so_timestamping_get.bind_phc != so_timestamping.bind_phc)
+ printf(" not expected, flags %d, bind phc %d\n",
+ so_timestamping.flags, so_timestamping.bind_phc);
}
/* send packets forever every five seconds */
conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \
nft_concat_range.sh nft_conntrack_helper.sh \
nft_queue.sh nft_meta.sh nf_nat_edemux.sh \
- ipip-conntrack-mtu.sh
+ ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh
LDLIBS = -lmnl
TEST_GEN_FILES = nf-queue
--- /dev/null
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Check that UNREPLIED tcp conntrack will eventually timeout.
+#
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+waittime=20
+sfx=$(mktemp -u "XXXXXXXX")
+ns1="ns1-$sfx"
+ns2="ns2-$sfx"
+
+nft --version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without nft tool"
+ exit $ksft_skip
+fi
+
+ip -Version > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run test without ip tool"
+ exit $ksft_skip
+fi
+
+cleanup() {
+ ip netns pids $ns1 | xargs kill 2>/dev/null
+ ip netns pids $ns2 | xargs kill 2>/dev/null
+
+ ip netns del $ns1
+ ip netns del $ns2
+}
+
+ipv4() {
+ echo -n 192.168.$1.2
+}
+
+check_counter()
+{
+ ns=$1
+ name=$2
+ expect=$3
+ local lret=0
+
+ cnt=$(ip netns exec $ns2 nft list counter inet filter "$name" | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ echo "ERROR: counter $name in $ns2 has unexpected value (expected $expect)" 1>&2
+ ip netns exec $ns2 nft list counter inet filter "$name" 1>&2
+ lret=1
+ fi
+
+ return $lret
+}
+
+# Create test namespaces
+ip netns add $ns1 || exit 1
+
+trap cleanup EXIT
+
+ip netns add $ns2 || exit 1
+
+# Connect the namespace to the host using a veth pair
+ip -net $ns1 link add name veth1 type veth peer name veth2
+ip -net $ns1 link set netns $ns2 dev veth2
+
+ip -net $ns1 link set up dev lo
+ip -net $ns2 link set up dev lo
+ip -net $ns1 link set up dev veth1
+ip -net $ns2 link set up dev veth2
+
+ip -net $ns2 addr add 10.11.11.2/24 dev veth2
+ip -net $ns2 route add default via 10.11.11.1
+
+ip netns exec $ns2 sysctl -q net.ipv4.conf.veth2.forwarding=1
+
+# add a rule inside NS so we enable conntrack
+ip netns exec $ns1 iptables -A INPUT -m state --state established,related -j ACCEPT
+
+ip -net $ns1 addr add 10.11.11.1/24 dev veth1
+ip -net $ns1 route add 10.99.99.99 via 10.11.11.2
+
+# Check connectivity works
+ip netns exec $ns1 ping -q -c 2 10.11.11.2 >/dev/null || exit 1
+
+ip netns exec $ns2 nc -l -p 8080 < /dev/null &
+
+# however, conntrack entries are there
+
+ip netns exec $ns2 nft -f - <<EOF
+table inet filter {
+ counter connreq { }
+ counter redir { }
+ chain input {
+ type filter hook input priority 0; policy accept;
+ ct state new tcp flags syn ip daddr 10.99.99.99 tcp dport 80 counter name "connreq" accept
+ ct state new ct status dnat tcp dport 8080 counter name "redir" accept
+ }
+}
+EOF
+if [ $? -ne 0 ]; then
+ echo "ERROR: Could not load nft rules"
+ exit 1
+fi
+
+ip netns exec $ns2 sysctl -q net.netfilter.nf_conntrack_tcp_timeout_syn_sent=10
+
+echo "INFO: connect $ns1 -> $ns2 to the virtual ip"
+ip netns exec $ns1 bash -c 'while true ; do
+ nc -p 60000 10.99.99.99 80
+ sleep 1
+ done' &
+
+sleep 1
+
+ip netns exec $ns2 nft -f - <<EOF
+table inet nat {
+ chain prerouting {
+ type nat hook prerouting priority 0; policy accept;
+ ip daddr 10.99.99.99 tcp dport 80 redirect to :8080
+ }
+}
+EOF
+if [ $? -ne 0 ]; then
+ echo "ERROR: Could not load nat redirect"
+ exit 1
+fi
+
+count=$(ip netns exec $ns2 conntrack -L -p tcp --dport 80 2>/dev/null | wc -l)
+if [ $count -eq 0 ]; then
+ echo "ERROR: $ns2 did not pick up tcp connection from peer"
+ exit 1
+fi
+
+echo "INFO: NAT redirect added in ns $ns2, waiting for $waittime seconds for nat to take effect"
+for i in $(seq 1 $waittime); do
+ echo -n "."
+
+ sleep 1
+
+ count=$(ip netns exec $ns2 conntrack -L -p tcp --reply-port-src 8080 2>/dev/null | wc -l)
+ if [ $count -gt 0 ]; then
+ echo
+ echo "PASS: redirection took effect after $i seconds"
+ break
+ fi
+
+ m=$((i%20))
+ if [ $m -eq 0 ]; then
+ echo " waited for $i seconds"
+ fi
+done
+
+expect="packets 1 bytes 60"
+check_counter "$ns2" "redir" "$expect"
+if [ $? -ne 0 ]; then
+ ret=1
+fi
+
+if [ $ret -eq 0 ];then
+ echo "PASS: redirection counter has expected values"
+else
+ echo "ERROR: no tcp connection was redirected"
+fi
+
+exit $ret
coalesced_mmio_in_range(dev, zone->addr, zone->size)) {
r = kvm_io_bus_unregister_dev(kvm,
zone->pio ? KVM_PIO_BUS : KVM_MMIO_BUS, &dev->dev);
- kvm_iodevice_destructor(&dev->dev);
/*
* On failure, unregister destroys all devices on the
*/
if (r)
break;
+ kvm_iodevice_destructor(&dev->dev);
}
}
stat_data->kvm = kvm;
stat_data->desc = pdesc;
stat_data->kind = KVM_STAT_VCPU;
- kvm->debugfs_stat_data[i] = stat_data;
+ kvm->debugfs_stat_data[i + kvm_vm_stats_header.num_desc] = stat_data;
debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc),
kvm->debugfs_dentry, stat_data,
&stat_fops_per_vm);
projects / platform / kernel / linux-rpi.git / commitdiff