From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ... --- arch/powerpc/include/asm/atomic.h | 489 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 489 insertions(+) create mode 100644 arch/powerpc/include/asm/atomic.h (limited to 'arch/powerpc/include/asm/atomic.h') diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h new file mode 100644 index 000000000..486ab7889 --- /dev/null +++ b/arch/powerpc/include/asm/atomic.h @@ -0,0 +1,489 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_POWERPC_ATOMIC_H_ +#define _ASM_POWERPC_ATOMIC_H_ + +/* + * PowerPC atomic operations + */ + +#ifdef __KERNEL__ +#include +#include +#include +#include + +/* + * Since *_return_relaxed and {cmp}xchg_relaxed are implemented with + * a "bne-" instruction at the end, so an isync is enough as a acquire barrier + * on the platform without lwsync. + */ +#define __atomic_acquire_fence() \ + __asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory") + +#define __atomic_release_fence() \ + __asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory") + +static __inline__ int arch_atomic_read(const atomic_t *v) +{ + int t; + + __asm__ __volatile__("lwz%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter)); + + return t; +} + +static __inline__ void arch_atomic_set(atomic_t *v, int i) +{ + __asm__ __volatile__("stw%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i)); +} + +#define ATOMIC_OP(op, asm_op, suffix, sign, ...) \ +static __inline__ void arch_atomic_##op(int a, atomic_t *v) \ +{ \ + int t; \ + \ + __asm__ __volatile__( \ +"1: lwarx %0,0,%3 # atomic_" #op "\n" \ + #asm_op "%I2" suffix " %0,%0,%2\n" \ +" stwcx. %0,0,%3 \n" \ +" bne- 1b\n" \ + : "=&r" (t), "+m" (v->counter) \ + : "r"#sign (a), "r" (&v->counter) \ + : "cc", ##__VA_ARGS__); \ +} \ + +#define ATOMIC_OP_RETURN_RELAXED(op, asm_op, suffix, sign, ...) \ +static inline int arch_atomic_##op##_return_relaxed(int a, atomic_t *v) \ +{ \ + int t; \ + \ + __asm__ __volatile__( \ +"1: lwarx %0,0,%3 # atomic_" #op "_return_relaxed\n" \ + #asm_op "%I2" suffix " %0,%0,%2\n" \ +" stwcx. %0,0,%3\n" \ +" bne- 1b\n" \ + : "=&r" (t), "+m" (v->counter) \ + : "r"#sign (a), "r" (&v->counter) \ + : "cc", ##__VA_ARGS__); \ + \ + return t; \ +} + +#define ATOMIC_FETCH_OP_RELAXED(op, asm_op, suffix, sign, ...) \ +static inline int arch_atomic_fetch_##op##_relaxed(int a, atomic_t *v) \ +{ \ + int res, t; \ + \ + __asm__ __volatile__( \ +"1: lwarx %0,0,%4 # atomic_fetch_" #op "_relaxed\n" \ + #asm_op "%I3" suffix " %1,%0,%3\n" \ +" stwcx. %1,0,%4\n" \ +" bne- 1b\n" \ + : "=&r" (res), "=&r" (t), "+m" (v->counter) \ + : "r"#sign (a), "r" (&v->counter) \ + : "cc", ##__VA_ARGS__); \ + \ + return res; \ +} + +#define ATOMIC_OPS(op, asm_op, suffix, sign, ...) \ + ATOMIC_OP(op, asm_op, suffix, sign, ##__VA_ARGS__) \ + ATOMIC_OP_RETURN_RELAXED(op, asm_op, suffix, sign, ##__VA_ARGS__)\ + ATOMIC_FETCH_OP_RELAXED(op, asm_op, suffix, sign, ##__VA_ARGS__) + +ATOMIC_OPS(add, add, "c", I, "xer") +ATOMIC_OPS(sub, sub, "c", I, "xer") + +#define arch_atomic_add_return_relaxed arch_atomic_add_return_relaxed +#define arch_atomic_sub_return_relaxed arch_atomic_sub_return_relaxed + +#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add_relaxed +#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub_relaxed + +#undef ATOMIC_OPS +#define ATOMIC_OPS(op, asm_op, suffix, sign) \ + ATOMIC_OP(op, asm_op, suffix, sign) \ + ATOMIC_FETCH_OP_RELAXED(op, asm_op, suffix, sign) + +ATOMIC_OPS(and, and, ".", K) +ATOMIC_OPS(or, or, "", K) +ATOMIC_OPS(xor, xor, "", K) + +#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and_relaxed +#define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or_relaxed +#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor_relaxed + +#undef ATOMIC_OPS +#undef ATOMIC_FETCH_OP_RELAXED +#undef ATOMIC_OP_RETURN_RELAXED +#undef ATOMIC_OP + +#define arch_atomic_cmpxchg(v, o, n) \ + (arch_cmpxchg(&((v)->counter), (o), (n))) +#define arch_atomic_cmpxchg_relaxed(v, o, n) \ + arch_cmpxchg_relaxed(&((v)->counter), (o), (n)) +#define arch_atomic_cmpxchg_acquire(v, o, n) \ + arch_cmpxchg_acquire(&((v)->counter), (o), (n)) + +#define arch_atomic_xchg(v, new) \ + (arch_xchg(&((v)->counter), new)) +#define arch_atomic_xchg_relaxed(v, new) \ + arch_xchg_relaxed(&((v)->counter), (new)) + +/* + * Don't want to override the generic atomic_try_cmpxchg_acquire, because + * we add a lock hint to the lwarx, which may not be wanted for the + * _acquire case (and is not used by the other _acquire variants so it + * would be a surprise). + */ +static __always_inline bool +arch_atomic_try_cmpxchg_lock(atomic_t *v, int *old, int new) +{ + int r, o = *old; + unsigned int eh = IS_ENABLED(CONFIG_PPC64); + + __asm__ __volatile__ ( +"1: lwarx %0,0,%2,%[eh] # atomic_try_cmpxchg_acquire \n" +" cmpw 0,%0,%3 \n" +" bne- 2f \n" +" stwcx. %4,0,%2 \n" +" bne- 1b \n" +"\t" PPC_ACQUIRE_BARRIER " \n" +"2: \n" + : "=&r" (r), "+m" (v->counter) + : "r" (&v->counter), "r" (o), "r" (new), [eh] "n" (eh) + : "cr0", "memory"); + + if (unlikely(r != o)) + *old = r; + return likely(r == o); +} + +/** + * atomic_fetch_add_unless - add unless the number is a given value + * @v: pointer of type atomic_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, so long as it was not @u. + * Returns the old value of @v. + */ +static __inline__ int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u) +{ + int t; + + __asm__ __volatile__ ( + PPC_ATOMIC_ENTRY_BARRIER +"1: lwarx %0,0,%1 # atomic_fetch_add_unless\n\ + cmpw 0,%0,%3 \n\ + beq 2f \n\ + add%I2c %0,%0,%2 \n" +" stwcx. %0,0,%1 \n\ + bne- 1b \n" + PPC_ATOMIC_EXIT_BARRIER +" sub%I2c %0,%0,%2 \n\ +2:" + : "=&r" (t) + : "r" (&v->counter), "rI" (a), "r" (u) + : "cc", "memory", "xer"); + + return t; +} +#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless + +/* + * Atomically test *v and decrement if it is greater than 0. + * The function returns the old value of *v minus 1, even if + * the atomic variable, v, was not decremented. + */ +static __inline__ int arch_atomic_dec_if_positive(atomic_t *v) +{ + int t; + + __asm__ __volatile__( + PPC_ATOMIC_ENTRY_BARRIER +"1: lwarx %0,0,%1 # atomic_dec_if_positive\n\ + cmpwi %0,1\n\ + addi %0,%0,-1\n\ + blt- 2f\n" +" stwcx. %0,0,%1\n\ + bne- 1b" + PPC_ATOMIC_EXIT_BARRIER + "\n\ +2:" : "=&b" (t) + : "r" (&v->counter) + : "cc", "memory"); + + return t; +} +#define arch_atomic_dec_if_positive arch_atomic_dec_if_positive + +#ifdef __powerpc64__ + +#define ATOMIC64_INIT(i) { (i) } + +static __inline__ s64 arch_atomic64_read(const atomic64_t *v) +{ + s64 t; + + __asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter)); + + return t; +} + +static __inline__ void arch_atomic64_set(atomic64_t *v, s64 i) +{ + __asm__ __volatile__("std%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i)); +} + +#define ATOMIC64_OP(op, asm_op) \ +static __inline__ void arch_atomic64_##op(s64 a, atomic64_t *v) \ +{ \ + s64 t; \ + \ + __asm__ __volatile__( \ +"1: ldarx %0,0,%3 # atomic64_" #op "\n" \ + #asm_op " %0,%2,%0\n" \ +" stdcx. %0,0,%3 \n" \ +" bne- 1b\n" \ + : "=&r" (t), "+m" (v->counter) \ + : "r" (a), "r" (&v->counter) \ + : "cc"); \ +} + +#define ATOMIC64_OP_RETURN_RELAXED(op, asm_op) \ +static inline s64 \ +arch_atomic64_##op##_return_relaxed(s64 a, atomic64_t *v) \ +{ \ + s64 t; \ + \ + __asm__ __volatile__( \ +"1: ldarx %0,0,%3 # atomic64_" #op "_return_relaxed\n" \ + #asm_op " %0,%2,%0\n" \ +" stdcx. %0,0,%3\n" \ +" bne- 1b\n" \ + : "=&r" (t), "+m" (v->counter) \ + : "r" (a), "r" (&v->counter) \ + : "cc"); \ + \ + return t; \ +} + +#define ATOMIC64_FETCH_OP_RELAXED(op, asm_op) \ +static inline s64 \ +arch_atomic64_fetch_##op##_relaxed(s64 a, atomic64_t *v) \ +{ \ + s64 res, t; \ + \ + __asm__ __volatile__( \ +"1: ldarx %0,0,%4 # atomic64_fetch_" #op "_relaxed\n" \ + #asm_op " %1,%3,%0\n" \ +" stdcx. %1,0,%4\n" \ +" bne- 1b\n" \ + : "=&r" (res), "=&r" (t), "+m" (v->counter) \ + : "r" (a), "r" (&v->counter) \ + : "cc"); \ + \ + return res; \ +} + +#define ATOMIC64_OPS(op, asm_op) \ + ATOMIC64_OP(op, asm_op) \ + ATOMIC64_OP_RETURN_RELAXED(op, asm_op) \ + ATOMIC64_FETCH_OP_RELAXED(op, asm_op) + +ATOMIC64_OPS(add, add) +ATOMIC64_OPS(sub, subf) + +#define arch_atomic64_add_return_relaxed arch_atomic64_add_return_relaxed +#define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return_relaxed + +#define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add_relaxed +#define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub_relaxed + +#undef ATOMIC64_OPS +#define ATOMIC64_OPS(op, asm_op) \ + ATOMIC64_OP(op, asm_op) \ + ATOMIC64_FETCH_OP_RELAXED(op, asm_op) + +ATOMIC64_OPS(and, and) +ATOMIC64_OPS(or, or) +ATOMIC64_OPS(xor, xor) + +#define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and_relaxed +#define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or_relaxed +#define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor_relaxed + +#undef ATOPIC64_OPS +#undef ATOMIC64_FETCH_OP_RELAXED +#undef ATOMIC64_OP_RETURN_RELAXED +#undef ATOMIC64_OP + +static __inline__ void arch_atomic64_inc(atomic64_t *v) +{ + s64 t; + + __asm__ __volatile__( +"1: ldarx %0,0,%2 # atomic64_inc\n\ + addic %0,%0,1\n\ + stdcx. %0,0,%2 \n\ + bne- 1b" + : "=&r" (t), "+m" (v->counter) + : "r" (&v->counter) + : "cc", "xer"); +} +#define arch_atomic64_inc arch_atomic64_inc + +static __inline__ s64 arch_atomic64_inc_return_relaxed(atomic64_t *v) +{ + s64 t; + + __asm__ __volatile__( +"1: ldarx %0,0,%2 # atomic64_inc_return_relaxed\n" +" addic %0,%0,1\n" +" stdcx. %0,0,%2\n" +" bne- 1b" + : "=&r" (t), "+m" (v->counter) + : "r" (&v->counter) + : "cc", "xer"); + + return t; +} + +static __inline__ void arch_atomic64_dec(atomic64_t *v) +{ + s64 t; + + __asm__ __volatile__( +"1: ldarx %0,0,%2 # atomic64_dec\n\ + addic %0,%0,-1\n\ + stdcx. %0,0,%2\n\ + bne- 1b" + : "=&r" (t), "+m" (v->counter) + : "r" (&v->counter) + : "cc", "xer"); +} +#define arch_atomic64_dec arch_atomic64_dec + +static __inline__ s64 arch_atomic64_dec_return_relaxed(atomic64_t *v) +{ + s64 t; + + __asm__ __volatile__( +"1: ldarx %0,0,%2 # atomic64_dec_return_relaxed\n" +" addic %0,%0,-1\n" +" stdcx. %0,0,%2\n" +" bne- 1b" + : "=&r" (t), "+m" (v->counter) + : "r" (&v->counter) + : "cc", "xer"); + + return t; +} + +#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return_relaxed +#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return_relaxed + +/* + * Atomically test *v and decrement if it is greater than 0. + * The function returns the old value of *v minus 1. + */ +static __inline__ s64 arch_atomic64_dec_if_positive(atomic64_t *v) +{ + s64 t; + + __asm__ __volatile__( + PPC_ATOMIC_ENTRY_BARRIER +"1: ldarx %0,0,%1 # atomic64_dec_if_positive\n\ + addic. %0,%0,-1\n\ + blt- 2f\n\ + stdcx. %0,0,%1\n\ + bne- 1b" + PPC_ATOMIC_EXIT_BARRIER + "\n\ +2:" : "=&r" (t) + : "r" (&v->counter) + : "cc", "xer", "memory"); + + return t; +} +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive + +#define arch_atomic64_cmpxchg(v, o, n) \ + (arch_cmpxchg(&((v)->counter), (o), (n))) +#define arch_atomic64_cmpxchg_relaxed(v, o, n) \ + arch_cmpxchg_relaxed(&((v)->counter), (o), (n)) +#define arch_atomic64_cmpxchg_acquire(v, o, n) \ + arch_cmpxchg_acquire(&((v)->counter), (o), (n)) + +#define arch_atomic64_xchg(v, new) \ + (arch_xchg(&((v)->counter), new)) +#define arch_atomic64_xchg_relaxed(v, new) \ + arch_xchg_relaxed(&((v)->counter), (new)) + +/** + * atomic64_fetch_add_unless - add unless the number is a given value + * @v: pointer of type atomic64_t + * @a: the amount to add to v... + * @u: ...unless v is equal to u. + * + * Atomically adds @a to @v, so long as it was not @u. + * Returns the old value of @v. + */ +static __inline__ s64 arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) +{ + s64 t; + + __asm__ __volatile__ ( + PPC_ATOMIC_ENTRY_BARRIER +"1: ldarx %0,0,%1 # atomic64_fetch_add_unless\n\ + cmpd 0,%0,%3 \n\ + beq 2f \n\ + add %0,%2,%0 \n" +" stdcx. %0,0,%1 \n\ + bne- 1b \n" + PPC_ATOMIC_EXIT_BARRIER +" subf %0,%2,%0 \n\ +2:" + : "=&r" (t) + : "r" (&v->counter), "r" (a), "r" (u) + : "cc", "memory"); + + return t; +} +#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless + +/** + * atomic_inc64_not_zero - increment unless the number is zero + * @v: pointer of type atomic64_t + * + * Atomically increments @v by 1, so long as @v is non-zero. + * Returns non-zero if @v was non-zero, and zero otherwise. + */ +static __inline__ int arch_atomic64_inc_not_zero(atomic64_t *v) +{ + s64 t1, t2; + + __asm__ __volatile__ ( + PPC_ATOMIC_ENTRY_BARRIER +"1: ldarx %0,0,%2 # atomic64_inc_not_zero\n\ + cmpdi 0,%0,0\n\ + beq- 2f\n\ + addic %1,%0,1\n\ + stdcx. %1,0,%2\n\ + bne- 1b\n" + PPC_ATOMIC_EXIT_BARRIER + "\n\ +2:" + : "=&r" (t1), "=&r" (t2) + : "r" (&v->counter) + : "cc", "xer", "memory"); + + return t1 != 0; +} +#define arch_atomic64_inc_not_zero(v) arch_atomic64_inc_not_zero((v)) + +#endif /* __powerpc64__ */ + +#endif /* __KERNEL__ */ +#endif /* _ASM_POWERPC_ATOMIC_H_ */ -- cgit v1.2.3