July 2024 - Linux-stable-mirror

[PATCH fs/bfs 0/2] bfs: fix null-ptr-deref and possible warning in bfs_move_block() func

by kovalev＠altlinux.org

https://syzkaller.appspot.com/bug?extid=d98fd19acd08b36ff422 [PATCH fs/bfs 1/2] bfs: fix null-ptr-deref in bfs_move_block [PATCH fs/bfs 2/2] bfs: add buffer_uptodate check before mark_buffer_dirty

2 months, 3 weeks

4
6
0 0

[PATCH] perf/x86/intel: Fix ARCH_PERFMON_NUM_COUNTER_LEAF

by kan.liang＠linux.intel.com

From: Kan Liang <kan.liang(a)linux.intel.com> The EAX of the CPUID Leaf 023H enumerates the mask of valid sub-leaves. To tell the availability of the sub-leaf 1 (enumerate the counter mask), perf should check the bit 1 (0x2) of EAS, rather than bit 0 (0x1). The error is not user-visible on bare metal. Because the sub-leaf 0 and the sub-leaf 1 are always available. However, it may bring issues in a virtualization environment when a VMM only enumerates the sub-leaf 0. Fixes: eb467aaac21e ("perf/x86/intel: Support Architectural PerfMon Extension leaf") Signed-off-by: Kan Liang <kan.liang(a)linux.intel.com> Cc: stable(a)vger.kernel.org --- arch/x86/events/intel/core.c | 4 ++-- arch/x86/include/asm/perf_event.h | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index cd8f2db6cdf6..3fb81f7b618c 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4842,8 +4842,8 @@ static void update_pmu_cap(struct x86_hybrid_pmu *pmu) if (ebx & ARCH_PERFMON_EXT_EQ) pmu->config_mask |= ARCH_PERFMON_EVENTSEL_EQ; - if (sub_bitmaps & ARCH_PERFMON_NUM_COUNTER_LEAF_BIT) { - cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF, + if (sub_bitmaps & ARCH_PERFMON_NUM_COUNTER_LEAF) { + cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF_BIT, &eax, &ebx, &ecx, &edx); pmu->cntr_mask64 = eax; pmu->fixed_cntr_mask64 = ebx; diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 91b73571412f..41ace8431e01 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -190,7 +190,7 @@ union cpuid10_edx { #define ARCH_PERFMON_EXT_UMASK2 0x1 #define ARCH_PERFMON_EXT_EQ 0x2 #define ARCH_PERFMON_NUM_COUNTER_LEAF_BIT 0x1 -#define ARCH_PERFMON_NUM_COUNTER_LEAF 0x1 +#define ARCH_PERFMON_NUM_COUNTER_LEAF BIT(ARCH_PERFMON_NUM_COUNTER_LEAF_BIT) /* * Intel Architectural LBR CPUID detection/enumeration details: -- 2.38.1

2 months, 3 weeks

1
0
0 0

[tip: timers/core] tick/broadcast: Make takeover of broadcast hrtimer reliable

by tip-bot2 for Yu Liao

The following commit has been merged into the timers/core branch of tip: Commit-ID: f7d43dd206e7e18c182f200e67a8db8c209907fa Gitweb: https://git.kernel.org/tip/f7d43dd206e7e18c182f200e67a8db8c209907fa Author: Yu Liao <liaoyu15(a)huawei.com> AuthorDate: Thu, 11 Jul 2024 20:48:43 +08:00 Committer: Thomas Gleixner <tglx(a)linutronix.de> CommitterDate: Thu, 11 Jul 2024 18:00:24 +02:00 tick/broadcast: Make takeover of broadcast hrtimer reliable Running the LTP hotplug stress test on a aarch64 machine results in rcu_sched stall warnings when the broadcast hrtimer was owned by the un-plugged CPU. The issue is the following: CPU1 (owns the broadcast hrtimer) CPU2 tick_broadcast_enter() // shutdown local timer device broadcast_shutdown_local() ... tick_broadcast_exit() clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT) // timer device is not programmed cpumask_set_cpu(cpu, tick_broadcast_force_mask) initiates offlining of CPU1 take_cpu_down() /* * CPU1 shuts down and does not * send broadcast IPI anymore */ takedown_cpu() hotplug_cpu__broadcast_tick_pull() // move broadcast hrtimer to this CPU clockevents_program_event() bc_set_next() hrtimer_start() /* * timer device is not programmed * because only the first expiring * timer will trigger clockevent * device reprogramming */ What happens is that CPU2 exits broadcast mode with force bit set, then the local timer device is not reprogrammed and CPU2 expects to receive the expired event by the broadcast IPI. But this does not happen because CPU1 is offlined by CPU2. CPU switches the clockevent device to ONESHOT state, but does not reprogram the device. The subsequent reprogramming of the hrtimer broadcast device does not program the clockevent device of CPU2 either because the pending expiry time is already in the past and the CPU expects the event to be delivered. As a consequence all CPUs which wait for a broadcast event to be delivered are stuck forever. Fix this issue by reprogramming the local timer device if the broadcast force bit of the CPU is set so that the broadcast hrtimer is delivered. [ tglx: Massage comment and change log. Add Fixes tag ] Fixes: 989dcb645ca7 ("tick: Handle broadcast wakeup of multiple cpus") Signed-off-by: Yu Liao <liaoyu15(a)huawei.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/20240711124843.64167-1-liaoyu15@huawei.com --- kernel/time/tick-broadcast.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 771d1e0..b484309 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -1141,6 +1141,7 @@ void tick_broadcast_switch_to_oneshot(void) #ifdef CONFIG_HOTPLUG_CPU void hotplug_cpu__broadcast_tick_pull(int deadcpu) { + struct tick_device *td = this_cpu_ptr(&tick_cpu_device); struct clock_event_device *bc; unsigned long flags; @@ -1148,6 +1149,28 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu) bc = tick_broadcast_device.evtdev; if (bc && broadcast_needs_cpu(bc, deadcpu)) { + /* + * If the broadcast force bit of the current CPU is set, + * then the current CPU has not yet reprogrammed the local + * timer device to avoid a ping-pong race. See + * ___tick_broadcast_oneshot_control(). + * + * If the broadcast device is hrtimer based then + * programming the broadcast event below does not have any + * effect because the local clockevent device is not + * running and not programmed because the broadcast event + * is not earlier than the pending event of the local clock + * event device. As a consequence all CPUs waiting for a + * broadcast event are stuck forever. + * + * Detect this condition and reprogram the cpu local timer + * device to avoid the starvation. + */ + if (tick_check_broadcast_expired()) { + cpumask_clear_cpu(smp_processor_id(), tick_broadcast_force_mask); + tick_program_event(td->evtdev->next_event, 1); + } + /* This moves the broadcast assignment to this CPU: */ clockevents_program_event(bc, bc->next_event, 1); }

2 months, 3 weeks

1
0
0 0

[PATCH 1/2] mmc: davinci_mmc: Prevent transmitted data size from exceeding sgm's length

by Bastien Curutchet

No check is done on the size of the data to be transmiited. This causes a kernel panic when this size exceeds the sg_miter's length. Limit the number of transmitted bytes to sgm->length. Cc: stable(a)vger.kernel.org Fixes: ed01d210fd91 ("mmc: davinci_mmc: Use sg_miter for PIO") Signed-off-by: Bastien Curutchet <bastien.curutchet(a)bootlin.com> --- drivers/mmc/host/davinci_mmc.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/mmc/host/davinci_mmc.c b/drivers/mmc/host/davinci_mmc.c index d7427894e0bc..c302eb380e42 100644 --- a/drivers/mmc/host/davinci_mmc.c +++ b/drivers/mmc/host/davinci_mmc.c @@ -224,6 +224,9 @@ static void davinci_fifo_data_trans(struct mmc_davinci_host *host, } p = sgm->addr; + if (n > sgm->length) + n = sgm->length; + /* NOTE: we never transfer more than rw_threshold bytes * to/from the fifo here; there's no I/O overlap. * This also assumes that access width( i.e. ACCWD) is 4 bytes -- 2.45.0

2 months, 3 weeks

2
1
0 0

[tip: irq/core] irqchip/imx-irqsteer: Handle runtime power management correctly

by tip-bot2 for Shenwei Wang

The following commit has been merged into the irq/core branch of tip: Commit-ID: cd0406fab8d4a16ec4f617c0a4b405bf70543b5b Gitweb: https://git.kernel.org/tip/cd0406fab8d4a16ec4f617c0a4b405bf70543b5b Author: Shenwei Wang <shenwei.wang(a)nxp.com> AuthorDate: Wed, 03 Jul 2024 11:32:50 -05:00 Committer: Thomas Gleixner <tglx(a)linutronix.de> CommitterDate: Thu, 11 Jul 2024 17:06:02 +02:00 irqchip/imx-irqsteer: Handle runtime power management correctly The power domain is automatically activated from clk_prepare(). However, on certain platforms like i.MX8QM and i.MX8QXP, the power-on handling invokes sleeping functions, which triggers the 'scheduling while atomic' bug in the context switch path during device probing: BUG: scheduling while atomic: kworker/u13:1/48/0x00000002 Call trace: __schedule_bug+0x54/0x6c __schedule+0x7f0/0xa94 schedule+0x5c/0xc4 schedule_preempt_disabled+0x24/0x40 __mutex_lock.constprop.0+0x2c0/0x540 __mutex_lock_slowpath+0x14/0x20 mutex_lock+0x48/0x54 clk_prepare_lock+0x44/0xa0 clk_prepare+0x20/0x44 imx_irqsteer_resume+0x28/0xe0 pm_generic_runtime_resume+0x2c/0x44 __genpd_runtime_resume+0x30/0x80 genpd_runtime_resume+0xc8/0x2c0 __rpm_callback+0x48/0x1d8 rpm_callback+0x6c/0x78 rpm_resume+0x490/0x6b4 __pm_runtime_resume+0x50/0x94 irq_chip_pm_get+0x2c/0xa0 __irq_do_set_handler+0x178/0x24c irq_set_chained_handler_and_data+0x60/0xa4 mxc_gpio_probe+0x160/0x4b0 Cure this by implementing the irq_bus_lock/sync_unlock() interrupt chip callbacks and handle power management in them as they are invoked from non-atomic context. [ tglx: Rewrote change log, added Fixes tag ] Fixes: 0136afa08967 ("irqchip: Add driver for imx-irqsteer controller") Signed-off-by: Shenwei Wang <shenwei.wang(a)nxp.com> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/20240703163250.47887-1-shenwei.wang@nxp.com --- drivers/irqchip/irq-imx-irqsteer.c | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-) diff --git a/drivers/irqchip/irq-imx-irqsteer.c b/drivers/irqchip/irq-imx-irqsteer.c index 20cf7a9..75a0e98 100644 --- a/drivers/irqchip/irq-imx-irqsteer.c +++ b/drivers/irqchip/irq-imx-irqsteer.c @@ -36,6 +36,7 @@ struct irqsteer_data { int channel; struct irq_domain *domain; u32 *saved_reg; + struct device *dev; }; static int imx_irqsteer_get_reg_index(struct irqsteer_data *data, @@ -72,10 +73,26 @@ static void imx_irqsteer_irq_mask(struct irq_data *d) raw_spin_unlock_irqrestore(&data->lock, flags); } +static void imx_irqsteer_irq_bus_lock(struct irq_data *d) +{ + struct irqsteer_data *data = d->chip_data; + + pm_runtime_get_sync(data->dev); +} + +static void imx_irqsteer_irq_bus_sync_unlock(struct irq_data *d) +{ + struct irqsteer_data *data = d->chip_data; + + pm_runtime_put_autosuspend(data->dev); +} + static const struct irq_chip imx_irqsteer_irq_chip = { - .name = "irqsteer", - .irq_mask = imx_irqsteer_irq_mask, - .irq_unmask = imx_irqsteer_irq_unmask, + .name = "irqsteer", + .irq_mask = imx_irqsteer_irq_mask, + .irq_unmask = imx_irqsteer_irq_unmask, + .irq_bus_lock = imx_irqsteer_irq_bus_lock, + .irq_bus_sync_unlock = imx_irqsteer_irq_bus_sync_unlock, }; static int imx_irqsteer_irq_map(struct irq_domain *h, unsigned int irq, @@ -150,6 +167,7 @@ static int imx_irqsteer_probe(struct platform_device *pdev) if (!data) return -ENOMEM; + data->dev = &pdev->dev; data->regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(data->regs)) { dev_err(&pdev->dev, "failed to initialize reg\n");

2 months, 3 weeks

1
0
0 0

[PATCH v8] af_packet: Handle outgoing VLAN packets without hardware offloading

by Chengen Du

The issue initially stems from libpcap. The ethertype will be overwritten as the VLAN TPID if the network interface lacks hardware VLAN offloading. In the outbound packet path, if hardware VLAN offloading is unavailable, the VLAN tag is inserted into the payload but then cleared from the sk_buff struct. Consequently, this can lead to a false negative when checking for the presence of a VLAN tag, causing the packet sniffing outcome to lack VLAN tag information (i.e., TCI-TPID). As a result, the packet capturing tool may be unable to parse packets as expected. The TCI-TPID is missing because the prb_fill_vlan_info() function does not modify the tp_vlan_tci/tp_vlan_tpid values, as the information is in the payload and not in the sk_buff struct. The skb_vlan_tag_present() function only checks vlan_all in the sk_buff struct. In cooked mode, the L2 header is stripped, preventing the packet capturing tool from determining the correct TCI-TPID value. Additionally, the protocol in SLL is incorrect, which means the packet capturing tool cannot parse the L3 header correctly. Link: https://github.com/the-tcpdump-group/libpcap/issues/1105 Link: https://lore.kernel.org/netdev/20240520070348.26725-1-chengen.du@canonical.… Fixes: 393e52e33c6c ("packet: deliver VLAN TCI to userspace") Cc: stable(a)vger.kernel.org Signed-off-by: Chengen Du <chengen.du(a)canonical.com> --- net/packet/af_packet.c | 86 +++++++++++++++++++++++++++++++++++++++++- 1 file changed, 84 insertions(+), 2 deletions(-) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ea3ebc160e25..84e8884a77e3 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -538,6 +538,61 @@ static void *packet_current_frame(struct packet_sock *po, return packet_lookup_frame(po, rb, rb->head, status); } +static u16 vlan_get_tci(struct sk_buff *skb, struct net_device *dev) +{ + struct vlan_hdr vhdr, *vh; + u8 *skb_orig_data = skb->data; + int skb_orig_len = skb->len; + unsigned int header_len; + + if (!dev) + return 0; + + /* In the SOCK_DGRAM scenario, skb data starts at the network + * protocol, which is after the VLAN headers. The outer VLAN + * header is at the hard_header_len offset in non-variable + * length link layer headers. If it's a VLAN device, the + * min_header_len should be used to exclude the VLAN header + * size. + */ + if (dev->min_header_len == dev->hard_header_len) + header_len = dev->hard_header_len; + else if (is_vlan_dev(dev)) + header_len = dev->min_header_len; + else + return 0; + + skb_push(skb, skb->data - skb_mac_header(skb)); + vh = skb_header_pointer(skb, header_len, sizeof(vhdr), &vhdr); + if (skb_orig_data != skb->data) { + skb->data = skb_orig_data; + skb->len = skb_orig_len; + } + if (unlikely(!vh)) + return 0; + + return ntohs(vh->h_vlan_TCI); +} + +static __be16 vlan_get_protocol_dgram(struct sk_buff *skb) +{ + __be16 proto = skb->protocol; + + if (unlikely(eth_type_vlan(proto))) { + u8 *skb_orig_data = skb->data; + int skb_orig_len = skb->len; + + skb_push(skb, skb->data - skb_mac_header(skb)); + proto = __vlan_get_protocol(skb, proto, NULL); + if (skb_orig_data != skb->data) { + skb->data = skb_orig_data; + skb->len = skb_orig_len; + } + } + + return proto; +} + static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc) { del_timer_sync(&pkc->retire_blk_timer); @@ -1007,10 +1062,16 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc, static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc, struct tpacket3_hdr *ppd) { + struct packet_sock *po = container_of(pkc, struct packet_sock, rx_ring.prb_bdqc); + if (skb_vlan_tag_present(pkc->skb)) { ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb); ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto); ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else if (unlikely(po->sk.sk_type == SOCK_DGRAM && eth_type_vlan(pkc->skb->protocol))) { + ppd->hv1.tp_vlan_tci = vlan_get_tci(pkc->skb, pkc->skb->dev); + ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->protocol); + ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { ppd->hv1.tp_vlan_tci = 0; ppd->hv1.tp_vlan_tpid = 0; @@ -2428,6 +2489,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, h.h2->tp_vlan_tci = skb_vlan_tag_get(skb); h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto); status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else if (unlikely(sk->sk_type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { + h.h2->tp_vlan_tci = vlan_get_tci(skb, skb->dev); + h.h2->tp_vlan_tpid = ntohs(skb->protocol); + status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; } else { h.h2->tp_vlan_tci = 0; h.h2->tp_vlan_tpid = 0; @@ -2457,7 +2522,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, sll->sll_halen = dev_parse_header(skb, sll->sll_addr); sll->sll_family = AF_PACKET; sll->sll_hatype = dev->type; - sll->sll_protocol = skb->protocol; + sll->sll_protocol = (sk->sk_type == SOCK_DGRAM) ? + vlan_get_protocol_dgram(skb) : skb->protocol; sll->sll_pkttype = skb->pkt_type; if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV))) sll->sll_ifindex = orig_dev->ifindex; @@ -3482,7 +3548,8 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, /* Original length was stored in sockaddr_ll fields */ origlen = PACKET_SKB_CB(skb)->sa.origlen; sll->sll_family = AF_PACKET; - sll->sll_protocol = skb->protocol; + sll->sll_protocol = (sock->type == SOCK_DGRAM) ? + vlan_get_protocol_dgram(skb) : skb->protocol; } sock_recv_cmsgs(msg, sk, skb); @@ -3539,6 +3606,21 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, aux.tp_vlan_tci = skb_vlan_tag_get(skb); aux.tp_vlan_tpid = ntohs(skb->vlan_proto); aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else if (unlikely(sock->type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) { + struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll; + struct net_device *dev; + + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), sll->sll_ifindex); + if (dev) { + aux.tp_vlan_tci = vlan_get_tci(skb, dev); + aux.tp_vlan_tpid = ntohs(skb->protocol); + aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID; + } else { + aux.tp_vlan_tci = 0; + aux.tp_vlan_tpid = 0; + } + rcu_read_unlock(); } else { aux.tp_vlan_tci = 0; aux.tp_vlan_tpid = 0; -- 2.43.0

2 months, 3 weeks

3
10
0 0

[PATCH 05/11] drm/v3d: Validate passed in drm syncobj handles in the performance extension

by Tvrtko Ursulin

From: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com> If userspace provides an unknown or invalid handle anywhere in the handle array the rest of the driver will not handle that well. Fix it by checking handle was looked up successfully or otherwise fail the extension by jumping into the existing unwind. Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com> Fixes: bae7cb5d6800 ("drm/v3d: Create a CPU job extension for the reset performance query job") Cc: Maíra Canal <mcanal(a)igalia.com> Cc: Iago Toral Quiroga <itoral(a)igalia.com> Cc: <stable(a)vger.kernel.org> # v6.8+ Reviewed-by: Maíra Canal <mcanal(a)igalia.com> --- drivers/gpu/drm/v3d/v3d_submit.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c index 9a3e32075ebe..4cdfabbf4964 100644 --- a/drivers/gpu/drm/v3d/v3d_submit.c +++ b/drivers/gpu/drm/v3d/v3d_submit.c @@ -710,6 +710,10 @@ v3d_get_cpu_reset_performance_params(struct drm_file *file_priv, } job->performance_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); + if (!job->performance_query.queries[i].syncobj) { + err = -ENOENT; + goto error; + } } job->performance_query.count = reset.count; job->performance_query.nperfmons = reset.nperfmons; @@ -790,6 +794,10 @@ v3d_get_cpu_copy_performance_query_params(struct drm_file *file_priv, } job->performance_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); + if (!job->performance_query.queries[i].syncobj) { + err = -ENOENT; + goto error; + } } job->performance_query.count = copy.count; job->performance_query.nperfmons = copy.nperfmons; -- 2.44.0

2 months, 3 weeks

1
0
0 0

[PATCH 04/11] drm/v3d: Validate passed in drm syncobj handles in the timestamp extension

by Tvrtko Ursulin

From: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com> If userspace provides an unknown or invalid handle anywhere in the handle array the rest of the driver will not handle that well. Fix it by checking handle was looked up successfully or otherwise fail the extension by jumping into the existing unwind. Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com> Fixes: 9ba0ff3e083f ("drm/v3d: Create a CPU job extension for the timestamp query job") Cc: Maíra Canal <mcanal(a)igalia.com> Cc: Iago Toral Quiroga <itoral(a)igalia.com> Cc: <stable(a)vger.kernel.org> # v6.8+ Reviewed-by: Maíra Canal <mcanal(a)igalia.com> --- drivers/gpu/drm/v3d/v3d_submit.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c index 50be4e8a7512..9a3e32075ebe 100644 --- a/drivers/gpu/drm/v3d/v3d_submit.c +++ b/drivers/gpu/drm/v3d/v3d_submit.c @@ -498,6 +498,10 @@ v3d_get_cpu_timestamp_query_params(struct drm_file *file_priv, } job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); + if (!job->timestamp_query.queries[i].syncobj) { + err = -ENOENT; + goto error; + } } job->timestamp_query.count = timestamp.count; @@ -552,6 +556,10 @@ v3d_get_cpu_reset_timestamp_params(struct drm_file *file_priv, } job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); + if (!job->timestamp_query.queries[i].syncobj) { + err = -ENOENT; + goto error; + } } job->timestamp_query.count = reset.count; @@ -616,6 +624,10 @@ v3d_get_cpu_copy_query_results_params(struct drm_file *file_priv, } job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); + if (!job->timestamp_query.queries[i].syncobj) { + err = -ENOENT; + goto error; + } } job->timestamp_query.count = copy.count; -- 2.44.0

2 months, 3 weeks

1
0
0 0

[PATCH 03/11] drm/v3d: Fix potential memory leak in the performance extension

by Tvrtko Ursulin

From: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com> If fetching of userspace memory fails during the main loop, all drm sync objs looked up until that point will be leaked because of the missing drm_syncobj_put. Fix it by exporting and using a common cleanup helper. Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com> Fixes: bae7cb5d6800 ("drm/v3d: Create a CPU job extension for the reset performance query job") Cc: Maíra Canal <mcanal(a)igalia.com> Cc: Iago Toral Quiroga <itoral(a)igalia.com> Cc: <stable(a)vger.kernel.org> # v6.8+ --- drivers/gpu/drm/v3d/v3d_drv.h | 2 ++ drivers/gpu/drm/v3d/v3d_sched.c | 22 ++++++++++---- drivers/gpu/drm/v3d/v3d_submit.c | 52 ++++++++++++++++++++------------ 3 files changed, 50 insertions(+), 26 deletions(-) diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index e208ffdfba32..dd3ead4cb8bd 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -565,6 +565,8 @@ void v3d_mmu_remove_ptes(struct v3d_bo *bo); /* v3d_sched.c */ void v3d_timestamp_query_info_free(struct v3d_timestamp_query_info *query_info, unsigned int count); +void v3d_performance_query_info_free(struct v3d_performance_query_info *query_info, + unsigned int count); void v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue); int v3d_sched_init(struct v3d_dev *v3d); void v3d_sched_fini(struct v3d_dev *v3d); diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 59dc0287dab9..5fbbee47c6b7 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -87,20 +87,30 @@ v3d_timestamp_query_info_free(struct v3d_timestamp_query_info *query_info, } } +void +v3d_performance_query_info_free(struct v3d_performance_query_info *query_info, + unsigned int count) +{ + if (query_info->queries) { + unsigned int i; + + for (i = 0; i < count; i++) + drm_syncobj_put(query_info->queries[i].syncobj); + + kvfree(query_info->queries); + } +} + static void v3d_cpu_job_free(struct drm_sched_job *sched_job) { struct v3d_cpu_job *job = to_cpu_job(sched_job); - struct v3d_performance_query_info *performance_query = &job->performance_query; v3d_timestamp_query_info_free(&job->timestamp_query, job->timestamp_query.count); - if (performance_query->queries) { - for (int i = 0; i < performance_query->count; i++) - drm_syncobj_put(performance_query->queries[i].syncobj); - kvfree(performance_query->queries); - } + v3d_performance_query_info_free(&job->performance_query, + job->performance_query.count); v3d_job_cleanup(&job->base); } diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c index 121bf1314b80..50be4e8a7512 100644 --- a/drivers/gpu/drm/v3d/v3d_submit.c +++ b/drivers/gpu/drm/v3d/v3d_submit.c @@ -640,6 +640,8 @@ v3d_get_cpu_reset_performance_params(struct drm_file *file_priv, u32 __user *syncs; u64 __user *kperfmon_ids; struct drm_v3d_reset_performance_query reset; + unsigned int i, j; + int err; if (!job) { DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); @@ -668,39 +670,43 @@ v3d_get_cpu_reset_performance_params(struct drm_file *file_priv, syncs = u64_to_user_ptr(reset.syncs); kperfmon_ids = u64_to_user_ptr(reset.kperfmon_ids); - for (int i = 0; i < reset.count; i++) { + for (i = 0; i < reset.count; i++) { u32 sync; u64 ids; u32 __user *ids_pointer; u32 id; if (copy_from_user(&sync, syncs++, sizeof(sync))) { - kvfree(job->performance_query.queries); - return -EFAULT; + err = -EFAULT; + goto error; } - job->performance_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); - if (copy_from_user(&ids, kperfmon_ids++, sizeof(ids))) { - kvfree(job->performance_query.queries); - return -EFAULT; + err = -EFAULT; + goto error; } ids_pointer = u64_to_user_ptr(ids); - for (int j = 0; j < reset.nperfmons; j++) { + for (j = 0; j < reset.nperfmons; j++) { if (copy_from_user(&id, ids_pointer++, sizeof(id))) { - kvfree(job->performance_query.queries); - return -EFAULT; + err = -EFAULT; + goto error; } job->performance_query.queries[i].kperfmon_ids[j] = id; } + + job->performance_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); } job->performance_query.count = reset.count; job->performance_query.nperfmons = reset.nperfmons; return 0; + +error: + v3d_performance_query_info_free(&job->performance_query, i); + return err; } static int @@ -711,6 +717,8 @@ v3d_get_cpu_copy_performance_query_params(struct drm_file *file_priv, u32 __user *syncs; u64 __user *kperfmon_ids; struct drm_v3d_copy_performance_query copy; + unsigned int i, j; + int err; if (!job) { DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); @@ -742,34 +750,34 @@ v3d_get_cpu_copy_performance_query_params(struct drm_file *file_priv, syncs = u64_to_user_ptr(copy.syncs); kperfmon_ids = u64_to_user_ptr(copy.kperfmon_ids); - for (int i = 0; i < copy.count; i++) { + for (i = 0; i < copy.count; i++) { u32 sync; u64 ids; u32 __user *ids_pointer; u32 id; if (copy_from_user(&sync, syncs++, sizeof(sync))) { - kvfree(job->performance_query.queries); - return -EFAULT; + err = -EFAULT; + goto error; } - job->performance_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); - if (copy_from_user(&ids, kperfmon_ids++, sizeof(ids))) { - kvfree(job->performance_query.queries); - return -EFAULT; + err = -EFAULT; + goto error; } ids_pointer = u64_to_user_ptr(ids); - for (int j = 0; j < copy.nperfmons; j++) { + for (j = 0; j < copy.nperfmons; j++) { if (copy_from_user(&id, ids_pointer++, sizeof(id))) { - kvfree(job->performance_query.queries); - return -EFAULT; + err = -EFAULT; + goto error; } job->performance_query.queries[i].kperfmon_ids[j] = id; } + + job->performance_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); } job->performance_query.count = copy.count; job->performance_query.nperfmons = copy.nperfmons; @@ -782,6 +790,10 @@ v3d_get_cpu_copy_performance_query_params(struct drm_file *file_priv, job->copy.stride = copy.stride; return 0; + +error: + v3d_performance_query_info_free(&job->performance_query, i); + return err; } /* Whenever userspace sets ioctl extensions, v3d_get_extensions parses data -- 2.44.0

2 months, 3 weeks

1
0
0 0

[PATCH 02/11] drm/v3d: Fix potential memory leak in the timestamp extension

by Tvrtko Ursulin

From: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com> If fetching of userspace memory fails during the main loop, all drm sync objs looked up until that point will be leaked because of the missing drm_syncobj_put. Fix it by exporting and using a common cleanup helper. Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin(a)igalia.com> Fixes: 9ba0ff3e083f ("drm/v3d: Create a CPU job extension for the timestamp query job") Cc: Maíra Canal <mcanal(a)igalia.com> Cc: Iago Toral Quiroga <itoral(a)igalia.com> Cc: <stable(a)vger.kernel.org> # v6.8+ Reviewed-by: Maíra Canal <mcanal(a)igalia.com> --- drivers/gpu/drm/v3d/v3d_drv.h | 2 ++ drivers/gpu/drm/v3d/v3d_sched.c | 22 +++++++++++----- drivers/gpu/drm/v3d/v3d_submit.c | 43 ++++++++++++++++++++++---------- 3 files changed, 48 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h index 099b962bdfde..e208ffdfba32 100644 --- a/drivers/gpu/drm/v3d/v3d_drv.h +++ b/drivers/gpu/drm/v3d/v3d_drv.h @@ -563,6 +563,8 @@ void v3d_mmu_insert_ptes(struct v3d_bo *bo); void v3d_mmu_remove_ptes(struct v3d_bo *bo); /* v3d_sched.c */ +void v3d_timestamp_query_info_free(struct v3d_timestamp_query_info *query_info, + unsigned int count); void v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue); int v3d_sched_init(struct v3d_dev *v3d); void v3d_sched_fini(struct v3d_dev *v3d); diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c index 03df37a3acf5..59dc0287dab9 100644 --- a/drivers/gpu/drm/v3d/v3d_sched.c +++ b/drivers/gpu/drm/v3d/v3d_sched.c @@ -73,18 +73,28 @@ v3d_sched_job_free(struct drm_sched_job *sched_job) v3d_job_cleanup(job); } +void +v3d_timestamp_query_info_free(struct v3d_timestamp_query_info *query_info, + unsigned int count) +{ + if (query_info->queries) { + unsigned int i; + + for (i = 0; i < count; i++) + drm_syncobj_put(query_info->queries[i].syncobj); + + kvfree(query_info->queries); + } +} + static void v3d_cpu_job_free(struct drm_sched_job *sched_job) { struct v3d_cpu_job *job = to_cpu_job(sched_job); - struct v3d_timestamp_query_info *timestamp_query = &job->timestamp_query; struct v3d_performance_query_info *performance_query = &job->performance_query; - if (timestamp_query->queries) { - for (int i = 0; i < timestamp_query->count; i++) - drm_syncobj_put(timestamp_query->queries[i].syncobj); - kvfree(timestamp_query->queries); - } + v3d_timestamp_query_info_free(&job->timestamp_query, + job->timestamp_query.count); if (performance_query->queries) { for (int i = 0; i < performance_query->count; i++) diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c index 263fefc1d04f..121bf1314b80 100644 --- a/drivers/gpu/drm/v3d/v3d_submit.c +++ b/drivers/gpu/drm/v3d/v3d_submit.c @@ -452,6 +452,8 @@ v3d_get_cpu_timestamp_query_params(struct drm_file *file_priv, { u32 __user *offsets, *syncs; struct drm_v3d_timestamp_query timestamp; + unsigned int i; + int err; if (!job) { DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); @@ -480,19 +482,19 @@ v3d_get_cpu_timestamp_query_params(struct drm_file *file_priv, offsets = u64_to_user_ptr(timestamp.offsets); syncs = u64_to_user_ptr(timestamp.syncs); - for (int i = 0; i < timestamp.count; i++) { + for (i = 0; i < timestamp.count; i++) { u32 offset, sync; if (copy_from_user(&offset, offsets++, sizeof(offset))) { - kvfree(job->timestamp_query.queries); - return -EFAULT; + err = -EFAULT; + goto error; } job->timestamp_query.queries[i].offset = offset; if (copy_from_user(&sync, syncs++, sizeof(sync))) { - kvfree(job->timestamp_query.queries); - return -EFAULT; + err = -EFAULT; + goto error; } job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); @@ -500,6 +502,10 @@ v3d_get_cpu_timestamp_query_params(struct drm_file *file_priv, job->timestamp_query.count = timestamp.count; return 0; + +error: + v3d_timestamp_query_info_free(&job->timestamp_query, i); + return err; } static int @@ -509,6 +515,8 @@ v3d_get_cpu_reset_timestamp_params(struct drm_file *file_priv, { u32 __user *syncs; struct drm_v3d_reset_timestamp_query reset; + unsigned int i; + int err; if (!job) { DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); @@ -533,14 +541,14 @@ v3d_get_cpu_reset_timestamp_params(struct drm_file *file_priv, syncs = u64_to_user_ptr(reset.syncs); - for (int i = 0; i < reset.count; i++) { + for (i = 0; i < reset.count; i++) { u32 sync; job->timestamp_query.queries[i].offset = reset.offset + 8 * i; if (copy_from_user(&sync, syncs++, sizeof(sync))) { - kvfree(job->timestamp_query.queries); - return -EFAULT; + err = -EFAULT; + goto error; } job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); @@ -548,6 +556,10 @@ v3d_get_cpu_reset_timestamp_params(struct drm_file *file_priv, job->timestamp_query.count = reset.count; return 0; + +error: + v3d_timestamp_query_info_free(&job->timestamp_query, i); + return err; } /* Get data for the copy timestamp query results job submission. */ @@ -558,7 +570,8 @@ v3d_get_cpu_copy_query_results_params(struct drm_file *file_priv, { u32 __user *offsets, *syncs; struct drm_v3d_copy_timestamp_query copy; - int i; + unsigned int i; + int err; if (!job) { DRM_DEBUG("CPU job extension was attached to a GPU job.\n"); @@ -591,15 +604,15 @@ v3d_get_cpu_copy_query_results_params(struct drm_file *file_priv, u32 offset, sync; if (copy_from_user(&offset, offsets++, sizeof(offset))) { - kvfree(job->timestamp_query.queries); - return -EFAULT; + err = -EFAULT; + goto error; } job->timestamp_query.queries[i].offset = offset; if (copy_from_user(&sync, syncs++, sizeof(sync))) { - kvfree(job->timestamp_query.queries); - return -EFAULT; + err = -EFAULT; + goto error; } job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync); @@ -613,6 +626,10 @@ v3d_get_cpu_copy_query_results_params(struct drm_file *file_priv, job->copy.stride = copy.stride; return 0; + +error: + v3d_timestamp_query_info_free(&job->timestamp_query, i); + return err; } static int -- 2.44.0

2 months, 3 weeks

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror July 2024