Files
kernel_xiaomi_sm8250/net/sched/sch_mqprio.c
Greg Kroah-Hartman 813e482b1b Merge 4.19.291 into android-4.19-stable
Changes in 4.19.291
	gfs2: Don't deref jdesc in evict
	x86/smp: Use dedicated cache-line for mwait_play_dead()
	video: imsttfb: check for ioremap() failures
	fbdev: imsttfb: Fix use after free bug in imsttfb_probe
	drm/edid: Fix uninitialized variable in drm_cvt_modes()
	scripts/tags.sh: Resolve gtags empty index generation
	drm/amdgpu: Validate VM ioctl flags.
	treewide: Remove uninitialized_var() usage
	md/raid10: check slab-out-of-bounds in md_bitmap_get_counter
	md/raid10: fix overflow of md/safe_mode_delay
	md/raid10: fix wrong setting of max_corr_read_errors
	md/raid10: fix io loss while replacement replace rdev
	irqchip/jcore-aic: Kill use of irq_create_strict_mappings()
	irqchip/jcore-aic: Fix missing allocation of IRQ descriptors
	clocksource/drivers: Unify the names to timer-* format
	clocksource/drivers/cadence-ttc: Use ttc driver as platform driver
	clocksource/drivers/cadence-ttc: Fix memory leak in ttc_timer_probe
	PM: domains: fix integer overflow issues in genpd_parse_state()
	ARM: 9303/1: kprobes: avoid missing-declaration warnings
	evm: Complete description of evm_inode_setattr()
	wifi: ath9k: fix AR9003 mac hardware hang check register offset calculation
	wifi: ath9k: avoid referencing uninit memory in ath9k_wmi_ctrl_rx
	samples/bpf: Fix buffer overflow in tcp_basertt
	wifi: mwifiex: Fix the size of a memory allocation in mwifiex_ret_802_11_scan()
	nfc: constify several pointers to u8, char and sk_buff
	nfc: llcp: fix possible use of uninitialized variable in nfc_llcp_send_connect()
	wifi: orinoco: Fix an error handling path in spectrum_cs_probe()
	wifi: orinoco: Fix an error handling path in orinoco_cs_probe()
	wifi: atmel: Fix an error handling path in atmel_probe()
	wl3501_cs: Fix a bunch of formatting issues related to function docs
	wl3501_cs: Remove unnecessary NULL check
	wl3501_cs: Fix misspelling and provide missing documentation
	net: create netdev->dev_addr assignment helpers
	wl3501_cs: use eth_hw_addr_set()
	wifi: wl3501_cs: Fix an error handling path in wl3501_probe()
	wifi: ray_cs: Utilize strnlen() in parse_addr()
	wifi: ray_cs: Drop useless status variable in parse_addr()
	wifi: ray_cs: Fix an error handling path in ray_probe()
	wifi: ath9k: don't allow to overwrite ENDPOINT0 attributes
	wifi: rsi: Do not set MMC_PM_KEEP_POWER in shutdown
	watchdog/perf: define dummy watchdog_update_hrtimer_threshold() on correct config
	watchdog/perf: more properly prevent false positives with turbo modes
	kexec: fix a memory leak in crash_shrink_memory()
	memstick r592: make memstick_debug_get_tpc_name() static
	wifi: ath9k: Fix possible stall on ath9k_txq_list_has_key()
	wifi: ath9k: convert msecs to jiffies where needed
	netlink: fix potential deadlock in netlink_set_err()
	netlink: do not hard code device address lenth in fdb dumps
	gtp: Fix use-after-free in __gtp_encap_destroy().
	lib/ts_bm: reset initial match offset for every block of text
	netfilter: nf_conntrack_sip: fix the ct_sip_parse_numerical_param() return value.
	ipvlan: Fix return value of ipvlan_queue_xmit()
	netlink: Add __sock_i_ino() for __netlink_diag_dump().
	radeon: avoid double free in ci_dpm_init()
	Input: drv260x - sleep between polling GO bit
	ARM: dts: BCM5301X: Drop "clock-names" from the SPI node
	Input: adxl34x - do not hardcode interrupt trigger type
	drm/panel: simple: fix active size for Ampire AM-480272H3TMQW-T01H
	ARM: ep93xx: fix missing-prototype warnings
	ASoC: es8316: Increment max value for ALC Capture Target Volume control
	soc/fsl/qe: fix usb.c build errors
	IB/hfi1: Fix sdma.h tx->num_descs off-by-one errors
	arm64: dts: renesas: ulcb-kf: Remove flow control for SCIF1
	fbdev: omapfb: lcd_mipid: Fix an error handling path in mipid_spi_probe()
	drm/radeon: fix possible division-by-zero errors
	ALSA: ac97: Fix possible NULL dereference in snd_ac97_mixer
	scsi: 3w-xxxx: Add error handling for initialization failure in tw_probe()
	PCI: Add pci_clear_master() stub for non-CONFIG_PCI
	pinctrl: cherryview: Return correct value if pin in push-pull mode
	perf dwarf-aux: Fix off-by-one in die_get_varname()
	pinctrl: at91-pio4: check return value of devm_kasprintf()
	hwrng: virtio - add an internal buffer
	hwrng: virtio - don't wait on cleanup
	hwrng: virtio - don't waste entropy
	hwrng: virtio - always add a pending request
	hwrng: virtio - Fix race on data_avail and actual data
	crypto: nx - fix build warnings when DEBUG_FS is not enabled
	modpost: fix section mismatch message for R_ARM_ABS32
	modpost: fix section mismatch message for R_ARM_{PC24,CALL,JUMP24}
	ARCv2: entry: comments about hardware auto-save on taken interrupts
	ARCv2: entry: push out the Z flag unclobber from common EXCEPTION_PROLOGUE
	ARCv2: entry: avoid a branch
	ARCv2: entry: rewrite to enable use of double load/stores LDD/STD
	ARC: define ASM_NL and __ALIGN(_STR) outside #ifdef __ASSEMBLY__ guard
	USB: serial: option: add LARA-R6 01B PIDs
	block: change all __u32 annotations to __be32 in affs_hardblocks.h
	w1: fix loop in w1_fini()
	sh: j2: Use ioremap() to translate device tree address into kernel memory
	media: usb: Check az6007_read() return value
	media: videodev2.h: Fix struct v4l2_input tuner index comment
	media: usb: siano: Fix warning due to null work_func_t function pointer
	extcon: Fix kernel doc of property fields to avoid warnings
	extcon: Fix kernel doc of property capability fields to avoid warnings
	usb: phy: phy-tahvo: fix memory leak in tahvo_usb_probe()
	mfd: rt5033: Drop rt5033-battery sub-device
	KVM: s390: fix KVM_S390_GET_CMMA_BITS for GFNs in memslot holes
	mfd: intel-lpss: Add missing check for platform_get_resource
	mfd: stmpe: Only disable the regulators if they are enabled
	rtc: st-lpc: Release some resources in st_rtc_probe() in case of error
	sctp: fix potential deadlock on &net->sctp.addr_wq_lock
	Add MODULE_FIRMWARE() for FIRMWARE_TG357766.
	spi: bcm-qspi: return error if neither hif_mspi nor mspi is available
	mailbox: ti-msgmgr: Fill non-message tx data fields with 0x0
	f2fs: fix error path handling in truncate_dnode()
	powerpc: allow PPC_EARLY_DEBUG_CPM only when SERIAL_CPM=y
	net: bridge: keep ports without IFF_UNICAST_FLT in BR_PROMISC mode
	tcp: annotate data races in __tcp_oow_rate_limited()
	net/sched: act_pedit: Add size check for TCA_PEDIT_PARMS_EX
	sh: dma: Fix DMA channel offset calculation
	i2c: xiic: Defer xiic_wakeup() and __xiic_start_xfer() in xiic_process()
	i2c: xiic: Don't try to handle more interrupt events after error
	ALSA: jack: Fix mutex call in snd_jack_report()
	NFSD: add encoding of op_recall flag for write delegation
	mmc: core: disable TRIM on Kingston EMMC04G-M627
	mmc: core: disable TRIM on Micron MTFC4GACAJCN-1M
	bcache: Remove unnecessary NULL point check in node allocations
	integrity: Fix possible multiple allocation in integrity_inode_get()
	jffs2: reduce stack usage in jffs2_build_xattr_subsystem()
	btrfs: fix race when deleting quota root from the dirty cow roots list
	ARM: orion5x: fix d2net gpio initialization
	spi: spi-fsl-spi: remove always-true conditional in fsl_spi_do_one_msg
	spi: spi-fsl-spi: relax message sanity checking a little
	spi: spi-fsl-spi: allow changing bits_per_word while CS is still active
	netfilter: nf_tables: fix nat hook table deletion
	netfilter: nf_tables: add rescheduling points during loop detection walks
	netfilter: nftables: add helper function to set the base sequence number
	netfilter: add helper function to set up the nfnetlink header and use it
	netfilter: nf_tables: use net_generic infra for transaction data
	netfilter: nf_tables: incorrect error path handling with NFT_MSG_NEWRULE
	netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain
	netfilter: nf_tables: reject unbound anonymous set before commit phase
	netfilter: nf_tables: unbind non-anonymous set if rule construction fails
	netfilter: nf_tables: fix scheduling-while-atomic splat
	netfilter: conntrack: Avoid nf_ct_helper_hash uses after free
	netfilter: nf_tables: prevent OOB access in nft_byteorder_eval
	net: lan743x: Don't sleep in atomic context
	workqueue: clean up WORK_* constant types, clarify masking
	net: mvneta: fix txq_map in case of txq_number==1
	vrf: Increment Icmp6InMsgs on the original netdev
	icmp6: Fix null-ptr-deref of ip6_null_entry->rt6i_idev in icmp6_dev().
	udp6: fix udp6_ehashfn() typo
	ntb: idt: Fix error handling in idt_pci_driver_init()
	NTB: amd: Fix error handling in amd_ntb_pci_driver_init()
	ntb: intel: Fix error handling in intel_ntb_pci_driver_init()
	NTB: ntb_transport: fix possible memory leak while device_register() fails
	NTB: ntb_tool: Add check for devm_kcalloc
	ipv6/addrconf: fix a potential refcount underflow for idev
	wifi: airo: avoid uninitialized warning in airo_get_rate()
	net/sched: make psched_mtu() RTNL-less safe
	pinctrl: amd: Fix mistake in handling clearing pins at startup
	pinctrl: amd: Detect internal GPIO0 debounce handling
	pinctrl: amd: Only use special debounce behavior for GPIO 0
	tpm: tpm_vtpm_proxy: fix a race condition in /dev/vtpmx creation
	net: bcmgenet: Ensure MDIO unregistration has clocks enabled
	SUNRPC: Fix UAF in svc_tcp_listen_data_ready()
	perf intel-pt: Fix CYC timestamps after standalone CBR
	ext4: fix wrong unit use in ext4_mb_clear_bb
	ext4: only update i_reserved_data_blocks on successful block allocation
	jfs: jfs_dmap: Validate db_l2nbperpage while mounting
	PCI/PM: Avoid putting EloPOS E2/S2/H2 PCIe Ports in D3cold
	PCI: Add function 1 DMA alias quirk for Marvell 88SE9235
	PCI: qcom: Disable write access to read only registers for IP v2.3.3
	PCI: rockchip: Assert PCI Configuration Enable bit after probe
	PCI: rockchip: Write PCI Device ID to correct register
	PCI: rockchip: Add poll and timeout to wait for PHY PLLs to be locked
	PCI: rockchip: Fix legacy IRQ generation for RK3399 PCIe endpoint core
	PCI: rockchip: Use u32 variable to access 32-bit registers
	misc: pci_endpoint_test: Free IRQs before removing the device
	misc: pci_endpoint_test: Re-init completion for every test
	md/raid0: add discard support for the 'original' layout
	fs: dlm: return positive pid value for F_GETLK
	serial: atmel: don't enable IRQs prematurely
	hwrng: imx-rngc - fix the timeout for init and self check
	ceph: don't let check_caps skip sending responses for revoke msgs
	meson saradc: fix clock divider mask length
	Revert "8250: add support for ASIX devices with a FIFO bug"
	tty: serial: samsung_tty: Fix a memory leak in s3c24xx_serial_getclk() in case of error
	tty: serial: samsung_tty: Fix a memory leak in s3c24xx_serial_getclk() when iterating clk
	ring-buffer: Fix deadloop issue on reading trace_pipe
	xtensa: ISS: fix call to split_if_spec
	scsi: qla2xxx: Wait for io return on terminate rport
	scsi: qla2xxx: Fix potential NULL pointer dereference
	scsi: qla2xxx: Check valid rport returned by fc_bsg_to_rport()
	scsi: qla2xxx: Pointer may be dereferenced
	drm/atomic: Fix potential use-after-free in nonblocking commits
	tracing/histograms: Add histograms to hist_vars if they have referenced variables
	perf probe: Add test for regression introduced by switch to die_get_decl_file()
	fuse: revalidate: don't invalidate if interrupted
	can: bcm: Fix UAF in bcm_proc_show()
	ext4: correct inline offset when handling xattrs in inode body
	debugobjects: Recheck debug_objects_enabled before reporting
	nbd: Add the maximum limit of allocated index in nbd_dev_add
	md: fix data corruption for raid456 when reshape restart while grow up
	md/raid10: prevent soft lockup while flush writes
	posix-timers: Ensure timer ID search-loop limit is valid
	sched/fair: Don't balance task to its current running CPU
	bpf: Address KCSAN report on bpf_lru_list
	wifi: wext-core: Fix -Wstringop-overflow warning in ioctl_standard_iw_point()
	wifi: iwlwifi: mvm: avoid baid size integer overflow
	igb: Fix igb_down hung on surprise removal
	spi: bcm63xx: fix max prepend length
	fbdev: imxfb: warn about invalid left/right margin
	pinctrl: amd: Use amd_pinconf_set() for all config options
	net: ethernet: ti: cpsw_ale: Fix cpsw_ale_get_field()/cpsw_ale_set_field()
	net:ipv6: check return value of pskb_trim()
	Revert "tcp: avoid the lookup process failing to get sk in ehash table"
	fbdev: au1200fb: Fix missing IRQ check in au1200fb_drv_probe
	llc: Don't drop packet from non-root netns.
	netfilter: nf_tables: fix spurious set element insertion failure
	netfilter: nf_tables: can't schedule in nft_chain_validate
	net: Replace the limit of TCP_LINGER2 with TCP_FIN_TIMEOUT_MAX
	tcp: annotate data-races around tp->linger2
	tcp: annotate data-races around rskq_defer_accept
	tcp: annotate data-races around tp->notsent_lowat
	tcp: annotate data-races around fastopenq.max_qlen
	tracing/histograms: Return an error if we fail to add histogram to hist_vars list
	gpio: tps68470: Make tps68470_gpio_output() always set the initial value
	bcache: use MAX_CACHES_PER_SET instead of magic number 8 in __bch_bucket_alloc_set
	bcache: remove 'int n' from parameter list of bch_bucket_alloc_set()
	bcache: Fix __bch_btree_node_alloc to make the failure behavior consistent
	btrfs: fix extent buffer leak after tree mod log failure at split_node()
	ext4: rename journal_dev to s_journal_dev inside ext4_sb_info
	ext4: Fix reusing stale buffer heads from last failed mounting
	PCI: Rework pcie_retrain_link() wait loop
	PCI/ASPM: Return 0 or -ETIMEDOUT from pcie_retrain_link()
	PCI/ASPM: Factor out pcie_wait_for_retrain()
	PCI/ASPM: Avoid link retraining race
	dlm: cleanup plock_op vs plock_xop
	dlm: rearrange async condition return
	fs: dlm: interrupt posix locks only when process is killed
	ftrace: Add information on number of page groups allocated
	ftrace: Check if pages were allocated before calling free_pages()
	ftrace: Store the order of pages allocated in ftrace_page
	ftrace: Fix possible warning on checking all pages used in ftrace_process_locs()
	scsi: qla2xxx: Fix inconsistent format argument type in qla_os.c
	scsi: qla2xxx: Array index may go out of bound
	ext4: fix to check return value of freeze_bdev() in ext4_shutdown()
	i40e: Fix an NULL vs IS_ERR() bug for debugfs_create_dir()
	phy: hisilicon: Fix an out of bounds check in hisi_inno_phy_probe()
	ethernet: atheros: fix return value check in atl1e_tso_csum()
	ipv6 addrconf: fix bug where deleting a mngtmpaddr can create a new temporary address
	tcp: Reduce chance of collisions in inet6_hashfn().
	bonding: reset bond's flags when down link is P2P device
	team: reset team's flags when down link is P2P device
	platform/x86: msi-laptop: Fix rfkill out-of-sync on MSI Wind U100
	net/sched: mqprio: refactor nlattr parsing to a separate function
	net/sched: mqprio: add extack to mqprio_parse_nlattr()
	net/sched: mqprio: Add length check for TCA_MQPRIO_{MAX/MIN}_RATE64
	benet: fix return value check in be_lancer_xmit_workarounds()
	RDMA/mlx4: Make check for invalid flags stricter
	drm/msm: Fix IS_ERR_OR_NULL() vs NULL check in a5xx_submit_in_rb()
	ASoC: fsl_spdif: Silence output on stop
	block: Fix a source code comment in include/uapi/linux/blkzoned.h
	dm raid: fix missing reconfig_mutex unlock in raid_ctr() error paths
	ata: pata_ns87415: mark ns87560_tf_read static
	ring-buffer: Fix wrong stat of cpu_buffer->read
	tracing: Fix warning in trace_buffered_event_disable()
	USB: serial: option: support Quectel EM060K_128
	USB: serial: option: add Quectel EC200A module support
	USB: serial: simple: add Kaufmann RKS+CAN VCP
	USB: serial: simple: sort driver entries
	can: gs_usb: gs_can_close(): add missing set of CAN state to CAN_STATE_STOPPED
	Revert "usb: dwc3: core: Enable AutoRetry feature in the controller"
	usb: dwc3: pci: skip BYT GPIO lookup table for hardwired phy
	usb: dwc3: don't reset device side if dwc3 was configured as host-only
	usb: ohci-at91: Fix the unhandle interrupt when resume
	USB: quirks: add quirk for Focusrite Scarlett
	usb: xhci-mtk: set the dma max_seg_size
	Documentation: security-bugs.rst: update preferences when dealing with the linux-distros group
	Documentation: security-bugs.rst: clarify CVE handling
	staging: ks7010: potential buffer overflow in ks_wlan_set_encode_ext()
	hwmon: (nct7802) Fix for temp6 (PECI1) processed even if PECI1 disabled
	btrfs: check for commit error at btrfs_attach_transaction_barrier()
	tpm_tis: Explicitly check for error code
	irq-bcm6345-l1: Do not assume a fixed block to cpu mapping
	serial: 8250_dw: split Synopsys DesignWare 8250 common functions
	serial: 8250_dw: Preserve original value of DLF register
	virtio-net: fix race between set queues and probe
	s390/dasd: fix hanging device after quiesce/resume
	ASoC: wm8904: Fill the cache for WM8904_ADC_TEST_0 register
	dm cache policy smq: ensure IO doesn't prevent cleaner policy progress
	drm/client: Fix memory leak in drm_client_target_cloned
	net/sched: cls_fw: Fix improper refcount update leads to use-after-free
	net/sched: sch_qfq: account for stab overhead in qfq_enqueue
	ASoC: cs42l51: fix driver to properly autoload with automatic module loading
	net/sched: cls_u32: Fix reference counter leak leading to overflow
	perf: Fix function pointer case
	loop: Select I/O scheduler 'none' from inside add_disk()
	word-at-a-time: use the same return type for has_zero regardless of endianness
	KVM: s390: fix sthyi error handling
	net/mlx5e: fix return value check in mlx5e_ipsec_remove_trailer()
	perf test uprobe_from_different_cu: Skip if there is no gcc
	net: sched: cls_u32: Fix match key mis-addressing
	net: add missing data-race annotations around sk->sk_peek_off
	net: add missing data-race annotation for sk_ll_usec
	net/sched: cls_u32: No longer copy tcf_result on update to avoid use-after-free
	net/sched: cls_route: No longer copy tcf_result on update to avoid use-after-free
	ip6mr: Fix skb_under_panic in ip6mr_cache_report()
	tcp_metrics: fix addr_same() helper
	tcp_metrics: annotate data-races around tm->tcpm_stamp
	tcp_metrics: annotate data-races around tm->tcpm_lock
	tcp_metrics: annotate data-races around tm->tcpm_vals[]
	tcp_metrics: annotate data-races around tm->tcpm_net
	tcp_metrics: fix data-race in tcpm_suck_dst() vs fastopen
	scsi: zfcp: Defer fc_rport blocking until after ADISC response
	libceph: fix potential hang in ceph_osdc_notify()
	USB: zaurus: Add ID for A-300/B-500/C-700
	fs/sysv: Null check to prevent null-ptr-deref bug
	Bluetooth: L2CAP: Fix use-after-free in l2cap_sock_ready_cb
	net: usbnet: Fix WARNING in usbnet_start_xmit/usb_submit_urb
	ext2: Drop fragment support
	test_firmware: fix a memory leak with reqs buffer
	test_firmware: return ENOMEM instead of ENOSPC on failed memory allocation
	mtd: rawnand: omap_elm: Fix incorrect type in assignment
	powerpc/mm/altmap: Fix altmap boundary check
	PM / wakeirq: support enabling wake-up irq after runtime_suspend called
	PM: sleep: wakeirq: fix wake irq arming
	ARM: dts: imx6sll: Make ssi node name same as other platforms
	ARM: dts: imx: add usb alias
	ARM: dts: imx6sll: fixup of operating points
	ARM: dts: nxp/imx6sll: fix wrong property name in usbphy node
	drivers core: Use sysfs_emit and sysfs_emit_at for show(device *...) functions
	arm64: dts: stratix10: fix incorrect I2C property for SCL signal
	drm/edid: fix objtool warning in drm_cvt_modes()
	Linux 4.19.291

Change-Id: I4f78e25efd18415989ecf5e227a17e05b0d6386c
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
2023-08-25 11:24:56 +00:00

695 lines
18 KiB
C

/*
* net/sched/sch_mqprio.c
*
* Copyright (c) 2010 John Fastabend <john.r.fastabend@intel.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* version 2 as published by the Free Software Foundation.
*/
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <linux/module.h>
#include <net/netlink.h>
#include <net/pkt_sched.h>
#include <net/sch_generic.h>
#include <net/pkt_cls.h>
struct mqprio_sched {
struct Qdisc **qdiscs;
u16 mode;
u16 shaper;
int hw_offload;
u32 flags;
u64 min_rate[TC_QOPT_MAX_QUEUE];
u64 max_rate[TC_QOPT_MAX_QUEUE];
};
static void mqprio_destroy(struct Qdisc *sch)
{
struct net_device *dev = qdisc_dev(sch);
struct mqprio_sched *priv = qdisc_priv(sch);
unsigned int ntx;
if (priv->qdiscs) {
for (ntx = 0;
ntx < dev->num_tx_queues && priv->qdiscs[ntx];
ntx++)
qdisc_put(priv->qdiscs[ntx]);
kfree(priv->qdiscs);
}
if (priv->hw_offload && dev->netdev_ops->ndo_setup_tc) {
struct tc_mqprio_qopt_offload mqprio = { { 0 } };
switch (priv->mode) {
case TC_MQPRIO_MODE_DCB:
case TC_MQPRIO_MODE_CHANNEL:
dev->netdev_ops->ndo_setup_tc(dev,
TC_SETUP_QDISC_MQPRIO,
&mqprio);
break;
default:
return;
}
} else {
netdev_set_num_tc(dev, 0);
}
}
static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt)
{
int i, j;
/* Verify num_tc is not out of max range */
if (qopt->num_tc > TC_MAX_QUEUE)
return -EINVAL;
/* Verify priority mapping uses valid tcs */
for (i = 0; i < TC_BITMASK + 1; i++) {
if (qopt->prio_tc_map[i] >= qopt->num_tc)
return -EINVAL;
}
/* Limit qopt->hw to maximum supported offload value. Drivers have
* the option of overriding this later if they don't support the a
* given offload type.
*/
if (qopt->hw > TC_MQPRIO_HW_OFFLOAD_MAX)
qopt->hw = TC_MQPRIO_HW_OFFLOAD_MAX;
/* If hardware offload is requested we will leave it to the device
* to either populate the queue counts itself or to validate the
* provided queue counts. If ndo_setup_tc is not present then
* hardware doesn't support offload and we should return an error.
*/
if (qopt->hw)
return dev->netdev_ops->ndo_setup_tc ? 0 : -EINVAL;
for (i = 0; i < qopt->num_tc; i++) {
unsigned int last = qopt->offset[i] + qopt->count[i];
/* Verify the queue count is in tx range being equal to the
* real_num_tx_queues indicates the last queue is in use.
*/
if (qopt->offset[i] >= dev->real_num_tx_queues ||
!qopt->count[i] ||
last > dev->real_num_tx_queues)
return -EINVAL;
/* Verify that the offset and counts do not overlap */
for (j = i + 1; j < qopt->num_tc; j++) {
if (last > qopt->offset[j])
return -EINVAL;
}
}
return 0;
}
static const struct nla_policy mqprio_policy[TCA_MQPRIO_MAX + 1] = {
[TCA_MQPRIO_MODE] = { .len = sizeof(u16) },
[TCA_MQPRIO_SHAPER] = { .len = sizeof(u16) },
[TCA_MQPRIO_MIN_RATE64] = { .type = NLA_NESTED },
[TCA_MQPRIO_MAX_RATE64] = { .type = NLA_NESTED },
};
static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
const struct nla_policy *policy, int len)
{
int nested_len = nla_len(nla) - NLA_ALIGN(len);
if (nested_len >= nla_attr_size(0))
return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len),
nested_len, policy, NULL);
memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
return 0;
}
static int mqprio_parse_nlattr(struct Qdisc *sch, struct tc_mqprio_qopt *qopt,
struct nlattr *opt,
struct netlink_ext_ack *extack)
{
struct mqprio_sched *priv = qdisc_priv(sch);
struct nlattr *tb[TCA_MQPRIO_MAX + 1];
struct nlattr *attr;
int i, rem, err;
err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy,
sizeof(*qopt));
if (err < 0)
return err;
if (!qopt->hw) {
NL_SET_ERR_MSG(extack,
"mqprio TCA_OPTIONS can only contain netlink attributes in hardware mode");
return -EINVAL;
}
if (tb[TCA_MQPRIO_MODE]) {
priv->flags |= TC_MQPRIO_F_MODE;
priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]);
}
if (tb[TCA_MQPRIO_SHAPER]) {
priv->flags |= TC_MQPRIO_F_SHAPER;
priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]);
}
if (tb[TCA_MQPRIO_MIN_RATE64]) {
if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) {
NL_SET_ERR_MSG_ATTR(extack, tb[TCA_MQPRIO_MIN_RATE64],
"min_rate accepted only when shaper is in bw_rlimit mode");
return -EINVAL;
}
i = 0;
nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64],
rem) {
if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) {
NL_SET_ERR_MSG_ATTR(extack, attr,
"Attribute type expected to be TCA_MQPRIO_MIN_RATE64");
return -EINVAL;
}
if (nla_len(attr) != sizeof(u64)) {
NL_SET_ERR_MSG_ATTR(extack, attr,
"Attribute TCA_MQPRIO_MIN_RATE64 expected to have 8 bytes length");
return -EINVAL;
}
if (i >= qopt->num_tc)
break;
priv->min_rate[i] = *(u64 *)nla_data(attr);
i++;
}
priv->flags |= TC_MQPRIO_F_MIN_RATE;
}
if (tb[TCA_MQPRIO_MAX_RATE64]) {
if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) {
NL_SET_ERR_MSG_ATTR(extack, tb[TCA_MQPRIO_MAX_RATE64],
"max_rate accepted only when shaper is in bw_rlimit mode");
return -EINVAL;
}
i = 0;
nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64],
rem) {
if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) {
NL_SET_ERR_MSG_ATTR(extack, attr,
"Attribute type expected to be TCA_MQPRIO_MAX_RATE64");
return -EINVAL;
}
if (nla_len(attr) != sizeof(u64)) {
NL_SET_ERR_MSG_ATTR(extack, attr,
"Attribute TCA_MQPRIO_MAX_RATE64 expected to have 8 bytes length");
return -EINVAL;
}
if (i >= qopt->num_tc)
break;
priv->max_rate[i] = *(u64 *)nla_data(attr);
i++;
}
priv->flags |= TC_MQPRIO_F_MAX_RATE;
}
return 0;
}
static int mqprio_init(struct Qdisc *sch, struct nlattr *opt,
struct netlink_ext_ack *extack)
{
struct net_device *dev = qdisc_dev(sch);
struct mqprio_sched *priv = qdisc_priv(sch);
struct netdev_queue *dev_queue;
struct Qdisc *qdisc;
int i, err = -EOPNOTSUPP;
struct tc_mqprio_qopt *qopt = NULL;
int len;
BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE);
BUILD_BUG_ON(TC_BITMASK != TC_QOPT_BITMASK);
if (sch->parent != TC_H_ROOT)
return -EOPNOTSUPP;
if (!netif_is_multiqueue(dev))
return -EOPNOTSUPP;
/* make certain can allocate enough classids to handle queues */
if (dev->num_tx_queues >= TC_H_MIN_PRIORITY)
return -ENOMEM;
if (!opt || nla_len(opt) < sizeof(*qopt))
return -EINVAL;
qopt = nla_data(opt);
if (mqprio_parse_opt(dev, qopt))
return -EINVAL;
len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt));
if (len > 0) {
err = mqprio_parse_nlattr(sch, qopt, opt, extack);
if (err)
return err;
}
/* pre-allocate qdisc, attachment can't fail */
priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]),
GFP_KERNEL);
if (!priv->qdiscs)
return -ENOMEM;
for (i = 0; i < dev->num_tx_queues; i++) {
dev_queue = netdev_get_tx_queue(dev, i);
qdisc = qdisc_create_dflt(dev_queue,
get_default_qdisc_ops(dev, i),
TC_H_MAKE(TC_H_MAJ(sch->handle),
TC_H_MIN(i + 1)), extack);
if (!qdisc)
return -ENOMEM;
priv->qdiscs[i] = qdisc;
qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
}
/* If the mqprio options indicate that hardware should own
* the queue mapping then run ndo_setup_tc otherwise use the
* supplied and verified mapping
*/
if (qopt->hw) {
struct tc_mqprio_qopt_offload mqprio = {.qopt = *qopt};
switch (priv->mode) {
case TC_MQPRIO_MODE_DCB:
if (priv->shaper != TC_MQPRIO_SHAPER_DCB)
return -EINVAL;
break;
case TC_MQPRIO_MODE_CHANNEL:
mqprio.flags = priv->flags;
if (priv->flags & TC_MQPRIO_F_MODE)
mqprio.mode = priv->mode;
if (priv->flags & TC_MQPRIO_F_SHAPER)
mqprio.shaper = priv->shaper;
if (priv->flags & TC_MQPRIO_F_MIN_RATE)
for (i = 0; i < mqprio.qopt.num_tc; i++)
mqprio.min_rate[i] = priv->min_rate[i];
if (priv->flags & TC_MQPRIO_F_MAX_RATE)
for (i = 0; i < mqprio.qopt.num_tc; i++)
mqprio.max_rate[i] = priv->max_rate[i];
break;
default:
return -EINVAL;
}
err = dev->netdev_ops->ndo_setup_tc(dev,
TC_SETUP_QDISC_MQPRIO,
&mqprio);
if (err)
return err;
priv->hw_offload = mqprio.qopt.hw;
} else {
netdev_set_num_tc(dev, qopt->num_tc);
for (i = 0; i < qopt->num_tc; i++)
netdev_set_tc_queue(dev, i,
qopt->count[i], qopt->offset[i]);
}
/* Always use supplied priority mappings */
for (i = 0; i < TC_BITMASK + 1; i++)
netdev_set_prio_tc_map(dev, i, qopt->prio_tc_map[i]);
sch->flags |= TCQ_F_MQROOT;
return 0;
}
static void mqprio_attach(struct Qdisc *sch)
{
struct net_device *dev = qdisc_dev(sch);
struct mqprio_sched *priv = qdisc_priv(sch);
struct Qdisc *qdisc, *old;
unsigned int ntx;
/* Attach underlying qdisc */
for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
qdisc = priv->qdiscs[ntx];
old = dev_graft_qdisc(qdisc->dev_queue, qdisc);
if (old)
qdisc_put(old);
if (ntx < dev->real_num_tx_queues)
qdisc_hash_add(qdisc, false);
}
kfree(priv->qdiscs);
priv->qdiscs = NULL;
}
static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch,
unsigned long cl)
{
struct net_device *dev = qdisc_dev(sch);
unsigned long ntx = cl - 1;
if (ntx >= dev->num_tx_queues)
return NULL;
return netdev_get_tx_queue(dev, ntx);
}
static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
struct Qdisc **old, struct netlink_ext_ack *extack)
{
struct net_device *dev = qdisc_dev(sch);
struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
if (!dev_queue)
return -EINVAL;
if (dev->flags & IFF_UP)
dev_deactivate(dev);
*old = dev_graft_qdisc(dev_queue, new);
if (new)
new->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT;
if (dev->flags & IFF_UP)
dev_activate(dev);
return 0;
}
static int dump_rates(struct mqprio_sched *priv,
struct tc_mqprio_qopt *opt, struct sk_buff *skb)
{
struct nlattr *nest;
int i;
if (priv->flags & TC_MQPRIO_F_MIN_RATE) {
nest = nla_nest_start(skb, TCA_MQPRIO_MIN_RATE64);
if (!nest)
goto nla_put_failure;
for (i = 0; i < opt->num_tc; i++) {
if (nla_put(skb, TCA_MQPRIO_MIN_RATE64,
sizeof(priv->min_rate[i]),
&priv->min_rate[i]))
goto nla_put_failure;
}
nla_nest_end(skb, nest);
}
if (priv->flags & TC_MQPRIO_F_MAX_RATE) {
nest = nla_nest_start(skb, TCA_MQPRIO_MAX_RATE64);
if (!nest)
goto nla_put_failure;
for (i = 0; i < opt->num_tc; i++) {
if (nla_put(skb, TCA_MQPRIO_MAX_RATE64,
sizeof(priv->max_rate[i]),
&priv->max_rate[i]))
goto nla_put_failure;
}
nla_nest_end(skb, nest);
}
return 0;
nla_put_failure:
nla_nest_cancel(skb, nest);
return -1;
}
static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
{
struct net_device *dev = qdisc_dev(sch);
struct mqprio_sched *priv = qdisc_priv(sch);
struct nlattr *nla = (struct nlattr *)skb_tail_pointer(skb);
struct tc_mqprio_qopt opt = { 0 };
struct Qdisc *qdisc;
unsigned int ntx, tc;
sch->q.qlen = 0;
memset(&sch->bstats, 0, sizeof(sch->bstats));
memset(&sch->qstats, 0, sizeof(sch->qstats));
/* MQ supports lockless qdiscs. However, statistics accounting needs
* to account for all, none, or a mix of locked and unlocked child
* qdiscs. Percpu stats are added to counters in-band and locking
* qdisc totals are added at end.
*/
for (ntx = 0; ntx < dev->num_tx_queues; ntx++) {
qdisc = netdev_get_tx_queue(dev, ntx)->qdisc_sleeping;
spin_lock_bh(qdisc_lock(qdisc));
if (qdisc_is_percpu_stats(qdisc)) {
__u32 qlen = qdisc_qlen_sum(qdisc);
__gnet_stats_copy_basic(NULL, &sch->bstats,
qdisc->cpu_bstats,
&qdisc->bstats);
__gnet_stats_copy_queue(&sch->qstats,
qdisc->cpu_qstats,
&qdisc->qstats, qlen);
sch->q.qlen += qlen;
} else {
sch->q.qlen += qdisc->q.qlen;
sch->bstats.bytes += qdisc->bstats.bytes;
sch->bstats.packets += qdisc->bstats.packets;
sch->qstats.backlog += qdisc->qstats.backlog;
sch->qstats.drops += qdisc->qstats.drops;
sch->qstats.requeues += qdisc->qstats.requeues;
sch->qstats.overlimits += qdisc->qstats.overlimits;
}
spin_unlock_bh(qdisc_lock(qdisc));
}
opt.num_tc = netdev_get_num_tc(dev);
memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map));
opt.hw = priv->hw_offload;
for (tc = 0; tc < netdev_get_num_tc(dev); tc++) {
opt.count[tc] = dev->tc_to_txq[tc].count;
opt.offset[tc] = dev->tc_to_txq[tc].offset;
}
if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
goto nla_put_failure;
if ((priv->flags & TC_MQPRIO_F_MODE) &&
nla_put_u16(skb, TCA_MQPRIO_MODE, priv->mode))
goto nla_put_failure;
if ((priv->flags & TC_MQPRIO_F_SHAPER) &&
nla_put_u16(skb, TCA_MQPRIO_SHAPER, priv->shaper))
goto nla_put_failure;
if ((priv->flags & TC_MQPRIO_F_MIN_RATE ||
priv->flags & TC_MQPRIO_F_MAX_RATE) &&
(dump_rates(priv, &opt, skb) != 0))
goto nla_put_failure;
return nla_nest_end(skb, nla);
nla_put_failure:
nlmsg_trim(skb, nla);
return -1;
}
static struct Qdisc *mqprio_leaf(struct Qdisc *sch, unsigned long cl)
{
struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
if (!dev_queue)
return NULL;
return dev_queue->qdisc_sleeping;
}
static unsigned long mqprio_find(struct Qdisc *sch, u32 classid)
{
struct net_device *dev = qdisc_dev(sch);
unsigned int ntx = TC_H_MIN(classid);
/* There are essentially two regions here that have valid classid
* values. The first region will have a classid value of 1 through
* num_tx_queues. All of these are backed by actual Qdiscs.
*/
if (ntx < TC_H_MIN_PRIORITY)
return (ntx <= dev->num_tx_queues) ? ntx : 0;
/* The second region represents the hardware traffic classes. These
* are represented by classid values of TC_H_MIN_PRIORITY through
* TC_H_MIN_PRIORITY + netdev_get_num_tc - 1
*/
return ((ntx - TC_H_MIN_PRIORITY) < netdev_get_num_tc(dev)) ? ntx : 0;
}
static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl,
struct sk_buff *skb, struct tcmsg *tcm)
{
if (cl < TC_H_MIN_PRIORITY) {
struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
struct net_device *dev = qdisc_dev(sch);
int tc = netdev_txq_to_tc(dev, cl - 1);
tcm->tcm_parent = (tc < 0) ? 0 :
TC_H_MAKE(TC_H_MAJ(sch->handle),
TC_H_MIN(tc + TC_H_MIN_PRIORITY));
tcm->tcm_info = dev_queue->qdisc_sleeping->handle;
} else {
tcm->tcm_parent = TC_H_ROOT;
tcm->tcm_info = 0;
}
tcm->tcm_handle |= TC_H_MIN(cl);
return 0;
}
static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
struct gnet_dump *d)
__releases(d->lock)
__acquires(d->lock)
{
if (cl >= TC_H_MIN_PRIORITY) {
int i;
__u32 qlen = 0;
struct gnet_stats_queue qstats = {0};
struct gnet_stats_basic_packed bstats = {0};
struct net_device *dev = qdisc_dev(sch);
struct netdev_tc_txq tc = dev->tc_to_txq[cl & TC_BITMASK];
/* Drop lock here it will be reclaimed before touching
* statistics this is required because the d->lock we
* hold here is the look on dev_queue->qdisc_sleeping
* also acquired below.
*/
if (d->lock)
spin_unlock_bh(d->lock);
for (i = tc.offset; i < tc.offset + tc.count; i++) {
struct netdev_queue *q = netdev_get_tx_queue(dev, i);
struct Qdisc *qdisc = rtnl_dereference(q->qdisc);
spin_lock_bh(qdisc_lock(qdisc));
if (qdisc_is_percpu_stats(qdisc)) {
qlen = qdisc_qlen_sum(qdisc);
__gnet_stats_copy_basic(NULL, &bstats,
qdisc->cpu_bstats,
&qdisc->bstats);
__gnet_stats_copy_queue(&qstats,
qdisc->cpu_qstats,
&qdisc->qstats,
qlen);
} else {
qlen += qdisc->q.qlen;
bstats.bytes += qdisc->bstats.bytes;
bstats.packets += qdisc->bstats.packets;
qstats.backlog += qdisc->qstats.backlog;
qstats.drops += qdisc->qstats.drops;
qstats.requeues += qdisc->qstats.requeues;
qstats.overlimits += qdisc->qstats.overlimits;
}
spin_unlock_bh(qdisc_lock(qdisc));
}
/* Reclaim root sleeping lock before completing stats */
if (d->lock)
spin_lock_bh(d->lock);
if (gnet_stats_copy_basic(NULL, d, NULL, &bstats) < 0 ||
gnet_stats_copy_queue(d, NULL, &qstats, qlen) < 0)
return -1;
} else {
struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl);
sch = dev_queue->qdisc_sleeping;
if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d,
sch->cpu_bstats, &sch->bstats) < 0 ||
gnet_stats_copy_queue(d, NULL,
&sch->qstats, sch->q.qlen) < 0)
return -1;
}
return 0;
}
static void mqprio_walk(struct Qdisc *sch, struct qdisc_walker *arg)
{
struct net_device *dev = qdisc_dev(sch);
unsigned long ntx;
if (arg->stop)
return;
/* Walk hierarchy with a virtual class per tc */
arg->count = arg->skip;
for (ntx = arg->skip; ntx < netdev_get_num_tc(dev); ntx++) {
if (arg->fn(sch, ntx + TC_H_MIN_PRIORITY, arg) < 0) {
arg->stop = 1;
return;
}
arg->count++;
}
/* Pad the values and skip over unused traffic classes */
if (ntx < TC_MAX_QUEUE) {
arg->count = TC_MAX_QUEUE;
ntx = TC_MAX_QUEUE;
}
/* Reset offset, sort out remaining per-queue qdiscs */
for (ntx -= TC_MAX_QUEUE; ntx < dev->num_tx_queues; ntx++) {
if (arg->fn(sch, ntx + 1, arg) < 0) {
arg->stop = 1;
return;
}
arg->count++;
}
}
static struct netdev_queue *mqprio_select_queue(struct Qdisc *sch,
struct tcmsg *tcm)
{
return mqprio_queue_get(sch, TC_H_MIN(tcm->tcm_parent));
}
static const struct Qdisc_class_ops mqprio_class_ops = {
.graft = mqprio_graft,
.leaf = mqprio_leaf,
.find = mqprio_find,
.walk = mqprio_walk,
.dump = mqprio_dump_class,
.dump_stats = mqprio_dump_class_stats,
.select_queue = mqprio_select_queue,
};
static struct Qdisc_ops mqprio_qdisc_ops __read_mostly = {
.cl_ops = &mqprio_class_ops,
.id = "mqprio",
.priv_size = sizeof(struct mqprio_sched),
.init = mqprio_init,
.destroy = mqprio_destroy,
.attach = mqprio_attach,
.dump = mqprio_dump,
.owner = THIS_MODULE,
};
static int __init mqprio_module_init(void)
{
return register_qdisc(&mqprio_qdisc_ops);
}
static void __exit mqprio_module_exit(void)
{
unregister_qdisc(&mqprio_qdisc_ops);
}
module_init(mqprio_module_init);
module_exit(mqprio_module_exit);
MODULE_LICENSE("GPL");