4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Uwe Kleine-König u.kleine-koenig@pengutronix.de

[ Upstream commit e697271c4e2987b333148e16a2eb8b5b924fd40a ]

This is just preparatory work which allows to move some initialisation that currently is done in the per transfer hook .config to an earlier point in time in the next few patches. There is no change in behaviour introduced by this patch.

Signed-off-by: Uwe Kleine-König u.kleine-koenig@pengutronix.de Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-imx.c | 40 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 39 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 1ad4b69292ad8..eb27f47578eb9 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -59,6 +59,7 @@ struct spi_imx_data;

struct spi_imx_devtype_data { void (*intctrl)(struct spi_imx_data *, int); + int (*prepare_message)(struct spi_imx_data *, struct spi_message *); int (*config)(struct spi_device *); void (*trigger)(struct spi_imx_data *); int (*rx_available)(struct spi_imx_data *); @@ -502,6 +503,12 @@ static void mx51_ecspi_disable(struct spi_imx_data *spi_imx) writel(ctrl, spi_imx->base + MX51_ECSPI_CTRL); }

+static int mx51_ecspi_prepare_message(struct spi_imx_data *spi_imx, + struct spi_message *msg) +{ + return 0; +} + static int mx51_ecspi_config(struct spi_device *spi) { struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master); @@ -672,6 +679,12 @@ static void mx31_trigger(struct spi_imx_data *spi_imx) writel(reg, spi_imx->base + MXC_CSPICTRL); }

+static int mx31_prepare_message(struct spi_imx_data *spi_imx, + struct spi_message *msg) +{ + return 0; +} + static int mx31_config(struct spi_device *spi) { struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master); @@ -768,6 +781,12 @@ static void mx21_trigger(struct spi_imx_data *spi_imx) writel(reg, spi_imx->base + MXC_CSPICTRL); }

+static int mx21_prepare_message(struct spi_imx_data *spi_imx, + struct spi_message *msg) +{ + return 0; +} + static int mx21_config(struct spi_device *spi) { struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master); @@ -837,6 +856,12 @@ static void mx1_trigger(struct spi_imx_data *spi_imx) writel(reg, spi_imx->base + MXC_CSPICTRL); }

+static int mx1_prepare_message(struct spi_imx_data *spi_imx, + struct spi_message *msg) +{ + return 0; +} + static int mx1_config(struct spi_device *spi) { struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master); @@ -871,6 +896,7 @@ static void mx1_reset(struct spi_imx_data *spi_imx)

static struct spi_imx_devtype_data imx1_cspi_devtype_data = { .intctrl = mx1_intctrl, + .prepare_message = mx1_prepare_message, .config = mx1_config, .trigger = mx1_trigger, .rx_available = mx1_rx_available, @@ -884,6 +910,7 @@ static struct spi_imx_devtype_data imx1_cspi_devtype_data = {

static struct spi_imx_devtype_data imx21_cspi_devtype_data = { .intctrl = mx21_intctrl, + .prepare_message = mx21_prepare_message, .config = mx21_config, .trigger = mx21_trigger, .rx_available = mx21_rx_available, @@ -898,6 +925,7 @@ static struct spi_imx_devtype_data imx21_cspi_devtype_data = { static struct spi_imx_devtype_data imx27_cspi_devtype_data = { /* i.mx27 cspi shares the functions with i.mx21 one */ .intctrl = mx21_intctrl, + .prepare_message = mx21_prepare_message, .config = mx21_config, .trigger = mx21_trigger, .rx_available = mx21_rx_available, @@ -911,6 +939,7 @@ static struct spi_imx_devtype_data imx27_cspi_devtype_data = {

static struct spi_imx_devtype_data imx31_cspi_devtype_data = { .intctrl = mx31_intctrl, + .prepare_message = mx31_prepare_message, .config = mx31_config, .trigger = mx31_trigger, .rx_available = mx31_rx_available, @@ -925,6 +954,7 @@ static struct spi_imx_devtype_data imx31_cspi_devtype_data = { static struct spi_imx_devtype_data imx35_cspi_devtype_data = { /* i.mx35 and later cspi shares the functions with i.mx31 one */ .intctrl = mx31_intctrl, + .prepare_message = mx31_prepare_message, .config = mx31_config, .trigger = mx31_trigger, .rx_available = mx31_rx_available, @@ -938,6 +968,7 @@ static struct spi_imx_devtype_data imx35_cspi_devtype_data = {

static struct spi_imx_devtype_data imx51_ecspi_devtype_data = { .intctrl = mx51_ecspi_intctrl, + .prepare_message = mx51_ecspi_prepare_message, .config = mx51_ecspi_config, .trigger = mx51_ecspi_trigger, .rx_available = mx51_ecspi_rx_available, @@ -952,6 +983,7 @@ static struct spi_imx_devtype_data imx51_ecspi_devtype_data = {

static struct spi_imx_devtype_data imx53_ecspi_devtype_data = { .intctrl = mx51_ecspi_intctrl, + .prepare_message = mx51_ecspi_prepare_message, .config = mx51_ecspi_config, .trigger = mx51_ecspi_trigger, .rx_available = mx51_ecspi_rx_available, @@ -1486,7 +1518,13 @@ spi_imx_prepare_message(struct spi_master *master, struct spi_message *msg) return ret; }

- return 0; + ret = spi_imx->devtype_data->prepare_message(spi_imx, msg); + if (ret) { + clk_disable(spi_imx->clk_ipg); + clk_disable(spi_imx->clk_per); + } + + return ret; }

static int

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Robin Gong yibin.gong@nxp.com

[ Upstream commit 5ba5a3730639caddf42af11c60f3f3d99d9a5f00 ]

Correct wml as the last rx sg length instead of the whole transfer length. Otherwise, mtd_stresstest will be failed as below:

insmod mtd_stresstest.ko dev=0 ================================================= mtd_stresstest: MTD device: 0 mtd_stresstest: not NAND flash, assume page size is 512 bytes. mtd_stresstest: MTD device size 4194304, eraseblock size 65536, page size 512, count of eraseblocks 64, pa0 mtd_stresstest: doing operations mtd_stresstest: 0 operations done mtd_test: mtd_read from 1ff532, size 880 mtd_test: mtd_read from 20c267, size 64998 spi_master spi0: I/O Error in DMA RX m25p80 spi0.0: SPI transfer failed: -110 spi_master spi0: failed to transfer one message from queue mtd_test: error: read failed at 0x20c267 mtd_stresstest: error -110 occurred ================================================= insmod: ERROR: could not insert module mtd_stresstest.ko: Connection timed out

Signed-off-by: Robin Gong yibin.gong@nxp.com Signed-off-by: Mark Brown broonie@kernel.org Stable-dep-of: 00b80ac93553 ("spi: imx: mx51-ecspi: Move some initialisation to prepare_message hook.") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/spi/spi-imx.c | 29 +++++++++++++++++++---------- 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c index 686251e05edfe..139127e27a147 100644 --- a/drivers/spi/spi-imx.c +++ b/drivers/spi/spi-imx.c @@ -218,7 +218,6 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi, struct spi_transfer *transfer) { struct spi_imx_data *spi_imx = spi_master_get_devdata(master); - unsigned int bytes_per_word, i;

if (!master->dma_rx) return false; @@ -226,14 +225,6 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi, if (spi_imx->slave_mode) return false;

- bytes_per_word = spi_imx_bytes_per_word(transfer->bits_per_word); - - for (i = spi_imx->devtype_data->fifo_size / 2; i > 0; i--) { - if (!(transfer->len % (i * bytes_per_word))) - break; - } - - spi_imx->wml = i; spi_imx->dynamic_burst = 0;

return true; @@ -612,7 +603,7 @@ static void mx51_setup_wml(struct spi_imx_data *spi_imx) * and enable DMA request. */

- writel(MX51_ECSPI_DMA_RX_WML(spi_imx->wml) | + writel(MX51_ECSPI_DMA_RX_WML(spi_imx->wml - 1) | MX51_ECSPI_DMA_TX_WML(spi_imx->wml) | MX51_ECSPI_DMA_RXT_WML(spi_imx->wml) | MX51_ECSPI_DMA_TEDEN | MX51_ECSPI_DMA_RXDEN | @@ -1330,12 +1321,30 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx, unsigned long timeout; struct spi_master *master = spi_imx->bitbang.master; struct sg_table *tx = &transfer->tx_sg, *rx = &transfer->rx_sg; + struct scatterlist *last_sg = sg_last(rx->sgl, rx->nents); + unsigned int bytes_per_word, i; int ret;

+ /* Get the right burst length from the last sg to ensure no tail data */ + bytes_per_word = spi_imx_bytes_per_word(transfer->bits_per_word); + for (i = spi_imx->devtype_data->fifo_size / 2; i > 0; i--) { + if (!(sg_dma_len(last_sg) % (i * bytes_per_word))) + break; + } + /* Use 1 as wml in case no available burst length got */ + if (i == 0) + i = 1; + + spi_imx->wml = i; + ret = spi_imx_dma_configure(master); if (ret) return ret;

+ if (!spi_imx->devtype_data->setup_wml) { + dev_err(spi_imx->dev, "No setup_wml()?\n"); + return -EINVAL; + } spi_imx->devtype_data->setup_wml(spi_imx);

/*

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Evgeny Novikov novikov@ispras.ru

[ Upstream commit 602649eadaa0c977e362e641f51ec306bc1d365d ]

In case of errors vpif_probe_complete() releases memory for vpif_obj.sd and unregisters the V4L2 device. But then this is done again by vpif_probe() itself. The patch removes the cleaning from vpif_probe_complete().

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Evgeny Novikov novikov@ispras.ru Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab+huawei@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/platform/davinci/vpif_capture.c | 2 -- 1 file changed, 2 deletions(-)

diff --git a/drivers/media/platform/davinci/vpif_capture.c b/drivers/media/platform/davinci/vpif_capture.c index a96f53ce80886..cf1d11e6dd8c4 100644 --- a/drivers/media/platform/davinci/vpif_capture.c +++ b/drivers/media/platform/davinci/vpif_capture.c @@ -1489,8 +1489,6 @@ static int vpif_probe_complete(void) /* Unregister video device */ video_unregister_device(&ch->video_dev); } - kfree(vpif_obj.sd); - v4l2_device_unregister(&vpif_obj.v4l2_dev);

return err; }

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Gleixner tglx@linutronix.de

[ Upstream commit 5c0930ccaad5a74d74e8b18b648c5eb21ed2fe94 ]

2b8272ff4a70 ("cpu/hotplug: Prevent self deadlock on CPU hot-unplug") solved the straight forward CPU hotplug deadlock vs. the scheduler bandwidth timer. Yu discovered a more involved variant where a task which has a bandwidth timer started on the outgoing CPU holds a lock and then gets throttled. If the lock required by one of the CPU hotplug callbacks the hotplug operation deadlocks because the unthrottling timer event is not handled on the dying CPU and can only be recovered once the control CPU reaches the hotplug state which pulls the pending hrtimers from the dead CPU.

Solve this by pushing the hrtimers away from the dying CPU in the dying callbacks. Nothing can queue a hrtimer on the dying CPU at that point because all other CPUs spin in stop_machine() with interrupts disabled and once the operation is finished the CPU is marked offline.

Reported-by: Yu Liao liaoyu15@huawei.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Tested-by: Liu Tie liutie4@huawei.com Link: https://lore.kernel.org/r/87a5rphara.ffs@tglx Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/cpuhotplug.h | 1 + include/linux/hrtimer.h | 4 ++-- kernel/cpu.c | 8 +++++++- kernel/time/hrtimer.c | 33 ++++++++++++--------------------- 4 files changed, 22 insertions(+), 24 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index 71a0a5ffdbb1a..dd9f035be63f7 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -139,6 +139,7 @@ enum cpuhp_state { CPUHP_AP_ARM_CORESIGHT_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, CPUHP_AP_SMPCFD_DYING, + CPUHP_AP_HRTIMERS_DYING, CPUHP_AP_X86_TBOOT_DYING, CPUHP_AP_ARM_CACHE_B15_RAC_DYING, CPUHP_AP_ONLINE, diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 542b4fa2cda9b..3bdaa92a2cab3 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -508,9 +508,9 @@ extern void sysrq_timer_list_show(void);

int hrtimers_prepare_cpu(unsigned int cpu); #ifdef CONFIG_HOTPLUG_CPU -int hrtimers_dead_cpu(unsigned int cpu); +int hrtimers_cpu_dying(unsigned int cpu); #else -#define hrtimers_dead_cpu NULL +#define hrtimers_cpu_dying NULL #endif

#endif diff --git a/kernel/cpu.c b/kernel/cpu.c index c9ca190ec0347..34c09c3d37bc6 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -1418,7 +1418,7 @@ static struct cpuhp_step cpuhp_hp_states[] = { [CPUHP_HRTIMERS_PREPARE] = { .name = "hrtimers:prepare", .startup.single = hrtimers_prepare_cpu, - .teardown.single = hrtimers_dead_cpu, + .teardown.single = NULL, }, [CPUHP_SMPCFD_PREPARE] = { .name = "smpcfd:prepare", @@ -1485,6 +1485,12 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = NULL, .teardown.single = smpcfd_dying_cpu, }, + [CPUHP_AP_HRTIMERS_DYING] = { + .name = "hrtimers:dying", + .startup.single = NULL, + .teardown.single = hrtimers_cpu_dying, + }, + /* Entry state on starting. Interrupts enabled from here on. Transient * state for synchronsization */ [CPUHP_AP_ONLINE] = { diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 8512f06f0ebef..bf74f43e42af0 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1922,29 +1922,22 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, } }

-int hrtimers_dead_cpu(unsigned int scpu) +int hrtimers_cpu_dying(unsigned int dying_cpu) { struct hrtimer_cpu_base *old_base, *new_base; - int i; + int i, ncpu = cpumask_first(cpu_active_mask);

- BUG_ON(cpu_online(scpu)); - tick_cancel_sched_timer(scpu); + tick_cancel_sched_timer(dying_cpu); + + old_base = this_cpu_ptr(&hrtimer_bases); + new_base = &per_cpu(hrtimer_bases, ncpu);

- /* - * this BH disable ensures that raise_softirq_irqoff() does - * not wakeup ksoftirqd (and acquire the pi-lock) while - * holding the cpu_base lock - */ - local_bh_disable(); - local_irq_disable(); - old_base = &per_cpu(hrtimer_bases, scpu); - new_base = this_cpu_ptr(&hrtimer_bases); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ - raw_spin_lock(&new_base->lock); - raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); + raw_spin_lock(&old_base->lock); + raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING);

for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { migrate_hrtimer_list(&old_base->clock_base[i], @@ -1955,15 +1948,13 @@ int hrtimers_dead_cpu(unsigned int scpu) * The migration might have changed the first expiring softirq * timer on this CPU. Update it. */ - hrtimer_update_softirq_timer(new_base, false); + __hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT); + /* Tell the other CPU to retrigger the next event */ + smp_call_function_single(ncpu, retrigger_next_event, NULL, 0);

- raw_spin_unlock(&old_base->lock); raw_spin_unlock(&new_base->lock); + raw_spin_unlock(&old_base->lock);

- /* Check, if we got expired work to do */ - __hrtimer_peek_ahead_timers(); - local_irq_enable(); - local_bh_enable(); return 0; }

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Alex Pakhunov alexey.pakhunov@spacex.com

[ Upstream commit 907d1bdb8b2cc0357d03a1c34d2a08d9943760b1 ]

This change moves [rt]x_dropped counters to tg3_napi so that they can be updated by a single writer, race-free.

Signed-off-by: Alex Pakhunov alexey.pakhunov@spacex.com Signed-off-by: Vincent Wong vincent.wong2@spacex.com Reviewed-by: Michael Chan michael.chan@broadcom.com Link: https://lore.kernel.org/r/20231113182350.37472-1-alexey.pakhunov@spacex.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/tg3.c | 38 +++++++++++++++++++++++++---- drivers/net/ethernet/broadcom/tg3.h | 4 +-- 2 files changed, 35 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index f0b5c8a4d29f5..84a5bddf614c8 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -6859,7 +6859,7 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget) desc_idx, *post_ptr); drop_it_no_recycle: /* Other statistics kept track of by card. */ - tp->rx_dropped++; + tnapi->rx_dropped++; goto next_pkt; }

@@ -8163,7 +8163,7 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) drop: dev_kfree_skb_any(skb); drop_nofree: - tp->tx_dropped++; + tnapi->tx_dropped++; return NETDEV_TX_OK; }

@@ -9342,7 +9342,7 @@ static void __tg3_set_rx_mode(struct net_device *); /* tp->lock is held. */ static int tg3_halt(struct tg3 *tp, int kind, bool silent) { - int err; + int err, i;

tg3_stop_fw(tp);

@@ -9363,6 +9363,13 @@ static int tg3_halt(struct tg3 *tp, int kind, bool silent)

/* And make sure the next sample is new data */ memset(tp->hw_stats, 0, sizeof(struct tg3_hw_stats)); + + for (i = 0; i < TG3_IRQ_MAX_VECS; ++i) { + struct tg3_napi *tnapi = &tp->napi[i]; + + tnapi->rx_dropped = 0; + tnapi->tx_dropped = 0; + } }

return err; @@ -11919,6 +11926,9 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats) { struct rtnl_link_stats64 *old_stats = &tp->net_stats_prev; struct tg3_hw_stats *hw_stats = tp->hw_stats; + unsigned long rx_dropped; + unsigned long tx_dropped; + int i;

stats->rx_packets = old_stats->rx_packets + get_stat64(&hw_stats->rx_ucast_packets) + @@ -11965,8 +11975,26 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats) stats->rx_missed_errors = old_stats->rx_missed_errors + get_stat64(&hw_stats->rx_discards);

- stats->rx_dropped = tp->rx_dropped; - stats->tx_dropped = tp->tx_dropped; + /* Aggregate per-queue counters. The per-queue counters are updated + * by a single writer, race-free. The result computed by this loop + * might not be 100% accurate (counters can be updated in the middle of + * the loop) but the next tg3_get_nstats() will recompute the current + * value so it is acceptable. + * + * Note that these counters wrap around at 4G on 32bit machines. + */ + rx_dropped = (unsigned long)(old_stats->rx_dropped); + tx_dropped = (unsigned long)(old_stats->tx_dropped); + + for (i = 0; i < tp->irq_cnt; i++) { + struct tg3_napi *tnapi = &tp->napi[i]; + + rx_dropped += tnapi->rx_dropped; + tx_dropped += tnapi->tx_dropped; + } + + stats->rx_dropped = rx_dropped; + stats->tx_dropped = tx_dropped; }

static int tg3_get_regs_len(struct net_device *dev) diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index a772a33b685c5..b8cc8ff4e8782 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -3018,6 +3018,7 @@ struct tg3_napi { u16 *rx_rcb_prod_idx; struct tg3_rx_prodring_set prodring; struct tg3_rx_buffer_desc *rx_rcb; + unsigned long rx_dropped;

u32 tx_prod ____cacheline_aligned; u32 tx_cons; @@ -3026,6 +3027,7 @@ struct tg3_napi { u32 prodmbox; struct tg3_tx_buffer_desc *tx_ring; struct tg3_tx_ring_info *tx_buffers; + unsigned long tx_dropped;

dma_addr_t status_mapping; dma_addr_t rx_rcb_mapping; @@ -3219,8 +3221,6 @@ struct tg3 {

/* begin "everything else" cacheline(s) section */ - unsigned long rx_dropped; - unsigned long tx_dropped; struct rtnl_link_stats64 net_stats_prev; struct tg3_ethtool_stats estats_prev;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Masahiro Yamada masahiroy@kernel.org

[ Upstream commit ae1eff0349f2e908fc083630e8441ea6dc434dc0 ]

Currently, sym_validate_range() duplicates the range string using xstrdup(), which is overwritten by a subsequent sym_calc_value() call. It results in a memory leak.

Instead, only the pointer should be copied.

Below is a test case, with a summary from Valgrind.

[Test Kconfig]

config FOO int "foo" range 10 20

[Test .config]

CONFIG_FOO=0

[Before]

LEAK SUMMARY: definitely lost: 3 bytes in 1 blocks indirectly lost: 0 bytes in 0 blocks possibly lost: 0 bytes in 0 blocks still reachable: 17,465 bytes in 21 blocks suppressed: 0 bytes in 0 blocks

[After]

LEAK SUMMARY: definitely lost: 0 bytes in 0 blocks indirectly lost: 0 bytes in 0 blocks possibly lost: 0 bytes in 0 blocks still reachable: 17,462 bytes in 20 blocks suppressed: 0 bytes in 0 blocks

Signed-off-by: Masahiro Yamada masahiroy@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- scripts/kconfig/symbol.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c index 703b9b899ee9c..5adb60b7e12f3 100644 --- a/scripts/kconfig/symbol.c +++ b/scripts/kconfig/symbol.c @@ -119,9 +119,9 @@ static long long sym_get_range_val(struct symbol *sym, int base) static void sym_validate_range(struct symbol *sym) { struct property *prop; + struct symbol *range_sym; int base; long long val, val2; - char str[64];

switch (sym->type) { case S_INT: @@ -137,17 +137,15 @@ static void sym_validate_range(struct symbol *sym) if (!prop) return; val = strtoll(sym->curr.val, NULL, base); - val2 = sym_get_range_val(prop->expr->left.sym, base); + range_sym = prop->expr->left.sym; + val2 = sym_get_range_val(range_sym, base); if (val >= val2) { - val2 = sym_get_range_val(prop->expr->right.sym, base); + range_sym = prop->expr->right.sym; + val2 = sym_get_range_val(range_sym, base); if (val <= val2) return; } - if (sym->type == S_INT) - sprintf(str, "%lld", val2); - else - sprintf(str, "0x%llx", val2); - sym->curr.val = xstrdup(str); + sym->curr.val = range_sym->curr.val; }

static void sym_set_changed(struct symbol *sym)

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

[ Upstream commit 75475bb51e78a3f54ad2f69380f2a1c985e85f2d ]

If fib6_find_prefix() returns NULL, we should silently fallback using fib6_null_entry regardless of RT6_DEBUG value.

syzbot reported:

WARNING: CPU: 0 PID: 5477 at net/ipv6/ip6_fib.c:1516 fib6_add+0x310d/0x3fa0 net/ipv6/ip6_fib.c:1516 Modules linked in: CPU: 0 PID: 5477 Comm: syz-executor.0 Not tainted 6.7.0-rc2-syzkaller-00029-g9b6de136b5f0 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/10/2023 RIP: 0010:fib6_add+0x310d/0x3fa0 net/ipv6/ip6_fib.c:1516 Code: 00 48 8b 54 24 68 e8 42 22 00 00 48 85 c0 74 14 49 89 c6 e8 d5 d3 c2 f7 eb 5d e8 ce d3 c2 f7 e9 ca 00 00 00 e8 c4 d3 c2 f7 90 <0f> 0b 90 48 b8 00 00 00 00 00 fc ff df 48 8b 4c 24 38 80 3c 01 00 RSP: 0018:ffffc90005067740 EFLAGS: 00010293 RAX: ffffffff89cba5bc RBX: ffffc90005067ab0 RCX: ffff88801a2e9dc0 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000 RBP: ffffc90005067980 R08: ffffffff89cbca85 R09: 1ffff110040d4b85 R10: dffffc0000000000 R11: ffffed10040d4b86 R12: 00000000ffffffff R13: 1ffff110051c3904 R14: ffff8880206a5c00 R15: ffff888028e1c820 FS: 00007f763783c6c0(0000) GS:ffff8880b9800000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f763783bff8 CR3: 000000007f74d000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> __ip6_ins_rt net/ipv6/route.c:1303 [inline] ip6_route_add+0x88/0x120 net/ipv6/route.c:3847 ipv6_route_ioctl+0x525/0x7b0 net/ipv6/route.c:4467 inet6_ioctl+0x21a/0x270 net/ipv6/af_inet6.c:575 sock_do_ioctl+0x152/0x460 net/socket.c:1220 sock_ioctl+0x615/0x8c0 net/socket.c:1339 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:871 [inline] __se_sys_ioctl+0xf8/0x170 fs/ioctl.c:857 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x45/0x110 arch/x86/entry/common.c:82

Fixes: 7bbfe00e0252 ("ipv6: fix general protection fault in fib6_add()") Reported-by: syzbot syzkaller@googlegroups.com Signed-off-by: Eric Dumazet edumazet@google.com Cc: Wei Wang weiwan@google.com Reviewed-by: David Ahern dsahern@kernel.org Link: https://lore.kernel.org/r/20231129160630.3509216-1-edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/ip6_fib.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 5ff67cb8b6ace..92bc56028b8b6 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1351,13 +1351,9 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { pn_leaf = fib6_find_prefix(info->nl_net, table, pn); -#if RT6_DEBUG >= 2 - if (!pn_leaf) { - WARN_ON(!pn_leaf); + if (!pn_leaf) pn_leaf = info->nl_net->ipv6.fib6_null_entry; - } -#endif fib6_info_hold(pn_leaf); rcu_assign_pointer(pn->leaf, pn_leaf); }

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ahmed S. Darwish a.darwish@linutronix.de

[ Upstream commit 01365633bd1c836240f9bbf86bbeee749795480a ]

The main arcnet interrupt handler calls arcnet_close() then arcnet_open(), if the RESET status flag is encountered.

This is invalid:

1) In general, interrupt handlers should never call ->ndo_stop() and ->ndo_open() functions. They are usually full of blocking calls and other methods that are expected to be called only from drivers init and exit code paths.

2) arcnet_close() contains a del_timer_sync(). If the irq handler interrupts the to-be-deleted timer, del_timer_sync() will just loop forever.

3) arcnet_close() also calls tasklet_kill(), which has a warning if called from irq context.

4) For device reset, the sequence "arcnet_close(); arcnet_open();" is not complete. Some children arcnet drivers have special init/exit code sequences, which then embed a call to arcnet_open() and arcnet_close() accordingly. Check drivers/net/arcnet/com20020.c.

Run the device RESET sequence from a scheduled workqueue instead.

Signed-off-by: Ahmed S. Darwish a.darwish@linutronix.de Signed-off-by: Sebastian Andrzej Siewior bigeasy@linutronix.de Link: https://lore.kernel.org/r/20210128194802.727770-1-a.darwish@linutronix.de Signed-off-by: Jakub Kicinski kuba@kernel.org Stable-dep-of: 6b17a597fc2f ("arcnet: restoring support for multiple Sohard Arcnet cards") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/arcnet/arc-rimi.c | 4 +- drivers/net/arcnet/arcdevice.h | 6 +++ drivers/net/arcnet/arcnet.c | 66 +++++++++++++++++++++++++++++++++++--- drivers/net/arcnet/com20020-isa.c | 4 +- drivers/net/arcnet/com20020-pci.c | 2 - drivers/net/arcnet/com20020_cs.c | 2 - drivers/net/arcnet/com90io.c | 4 +- drivers/net/arcnet/com90xx.c | 4 +- 8 files changed, 78 insertions(+), 14 deletions(-)

--- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -332,7 +332,7 @@ static int __init arc_rimi_init(void) dev->irq = 9;

if (arcrimi_probe(dev)) { - free_netdev(dev); + free_arcdev(dev); return -EIO; }

@@ -349,7 +349,7 @@ static void __exit arc_rimi_exit(void) iounmap(lp->mem_start); release_mem_region(dev->mem_start, dev->mem_end - dev->mem_start + 1); free_irq(dev->irq, dev); - free_netdev(dev); + free_arcdev(dev); }

#ifndef MODULE --- a/drivers/net/arcnet/arcdevice.h +++ b/drivers/net/arcnet/arcdevice.h @@ -303,6 +303,10 @@ struct arcnet_local {

int excnak_pending; /* We just got an excesive nak interrupt */

+ /* RESET flag handling */ + int reset_in_progress; + struct work_struct reset_work; + struct { uint16_t sequence; /* sequence number (incs with each packet) */ __be16 aborted_seq; @@ -355,7 +359,9 @@ void arcnet_dump_skb(struct net_device *

void arcnet_unregister_proto(struct ArcProto *proto); irqreturn_t arcnet_interrupt(int irq, void *dev_id); + struct net_device *alloc_arcdev(const char *name); +void free_arcdev(struct net_device *dev);

int arcnet_open(struct net_device *dev); int arcnet_close(struct net_device *dev); --- a/drivers/net/arcnet/arcnet.c +++ b/drivers/net/arcnet/arcnet.c @@ -387,10 +387,44 @@ static void arcnet_timer(struct timer_li struct arcnet_local *lp = from_timer(lp, t, timer); struct net_device *dev = lp->dev;

- if (!netif_carrier_ok(dev)) { + spin_lock_irq(&lp->lock); + + if (!lp->reset_in_progress && !netif_carrier_ok(dev)) { netif_carrier_on(dev); netdev_info(dev, "link up\n"); } + + spin_unlock_irq(&lp->lock); +} + +static void reset_device_work(struct work_struct *work) +{ + struct arcnet_local *lp; + struct net_device *dev; + + lp = container_of(work, struct arcnet_local, reset_work); + dev = lp->dev; + + /* Do not bring the network interface back up if an ifdown + * was already done. + */ + if (!netif_running(dev) || !lp->reset_in_progress) + return; + + rtnl_lock(); + + /* Do another check, in case of an ifdown that was triggered in + * the small race window between the exit condition above and + * acquiring RTNL. + */ + if (!netif_running(dev) || !lp->reset_in_progress) + goto out; + + dev_close(dev); + dev_open(dev); + +out: + rtnl_unlock(); }

static void arcnet_reply_tasklet(unsigned long data) @@ -452,12 +486,25 @@ struct net_device *alloc_arcdev(const ch lp->dev = dev; spin_lock_init(&lp->lock); timer_setup(&lp->timer, arcnet_timer, 0); + INIT_WORK(&lp->reset_work, reset_device_work); }

return dev; } EXPORT_SYMBOL(alloc_arcdev);

+void free_arcdev(struct net_device *dev) +{ + struct arcnet_local *lp = netdev_priv(dev); + + /* Do not cancel this at ->ndo_close(), as the workqueue itself + * indirectly calls the ifdown path through dev_close(). + */ + cancel_work_sync(&lp->reset_work); + free_netdev(dev); +} +EXPORT_SYMBOL(free_arcdev); + /* Open/initialize the board. This is called sometime after booting when * the 'ifconfig' program is run. * @@ -587,6 +634,10 @@ int arcnet_close(struct net_device *dev)

/* shut down the card */ lp->hw.close(dev); + + /* reset counters */ + lp->reset_in_progress = 0; + module_put(lp->hw.owner); return 0; } @@ -820,6 +871,9 @@ irqreturn_t arcnet_interrupt(int irq, vo

spin_lock_irqsave(&lp->lock, flags);

+ if (lp->reset_in_progress) + goto out; + /* RESET flag was enabled - if device is not running, we must * clear it right away (but nothing else). */ @@ -852,11 +906,14 @@ irqreturn_t arcnet_interrupt(int irq, vo if (status & RESETflag) { arc_printk(D_NORMAL, dev, "spurious reset (status=%Xh)\n", status); - arcnet_close(dev); - arcnet_open(dev); + + lp->reset_in_progress = 1; + netif_stop_queue(dev); + netif_carrier_off(dev); + schedule_work(&lp->reset_work);

/* get out of the interrupt handler! */ - break; + goto out; } /* RX is inhibited - we must have received something. * Prepare to receive into the next buffer. @@ -1052,6 +1109,7 @@ irqreturn_t arcnet_interrupt(int irq, vo udelay(1); lp->hw.intmask(dev, lp->intmask);

+out: spin_unlock_irqrestore(&lp->lock, flags); return retval; } --- a/drivers/net/arcnet/com20020-isa.c +++ b/drivers/net/arcnet/com20020-isa.c @@ -169,7 +169,7 @@ static int __init com20020_init(void) dev->irq = 9;

if (com20020isa_probe(dev)) { - free_netdev(dev); + free_arcdev(dev); return -EIO; }

@@ -182,7 +182,7 @@ static void __exit com20020_exit(void) unregister_netdev(my_dev); free_irq(my_dev->irq, my_dev); release_region(my_dev->base_addr, ARCNET_TOTAL_SIZE); - free_netdev(my_dev); + free_arcdev(my_dev); }

#ifndef MODULE --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -294,7 +294,7 @@ static void com20020pci_remove(struct pc

unregister_netdev(dev); free_irq(dev->irq, dev); - free_netdev(dev); + free_arcdev(dev); } }

--- a/drivers/net/arcnet/com20020_cs.c +++ b/drivers/net/arcnet/com20020_cs.c @@ -177,7 +177,7 @@ static void com20020_detach(struct pcmci dev = info->dev; if (dev) { dev_dbg(&link->dev, "kfree...\n"); - free_netdev(dev); + free_arcdev(dev); } dev_dbg(&link->dev, "kfree2...\n"); kfree(info); --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -394,7 +394,7 @@ static int __init com90io_init(void) err = com90io_probe(dev);

if (err) { - free_netdev(dev); + free_arcdev(dev); return err; }

@@ -417,7 +417,7 @@ static void __exit com90io_exit(void)

free_irq(dev->irq, dev); release_region(dev->base_addr, ARCNET_TOTAL_SIZE); - free_netdev(dev); + free_arcdev(dev); }

module_init(com90io_init) --- a/drivers/net/arcnet/com90xx.c +++ b/drivers/net/arcnet/com90xx.c @@ -554,7 +554,7 @@ err_free_irq: err_release_mem: release_mem_region(dev->mem_start, dev->mem_end - dev->mem_start + 1); err_free_dev: - free_netdev(dev); + free_arcdev(dev); return -EIO; }

@@ -672,7 +672,7 @@ static void __exit com90xx_exit(void) release_region(dev->base_addr, ARCNET_TOTAL_SIZE); release_mem_region(dev->mem_start, dev->mem_end - dev->mem_start + 1); - free_netdev(dev); + free_arcdev(dev); } }

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Thomas Reichinger thomas.reichinger@sohard.de

[ Upstream commit 6b17a597fc2f13aaaa0a2780eb7edb9ae7ac9aea ]

Probe of Sohard Arcnet cards fails, if 2 or more cards are installed in a system. See kernel log: [ 2.759203] arcnet: arcnet loaded [ 2.763648] arcnet:com20020: COM20020 chipset support (by David Woodhouse et al.) [ 2.770585] arcnet:com20020_pci: COM20020 PCI support [ 2.772295] com20020 0000:02:00.0: enabling device (0000 -> 0003) [ 2.772354] (unnamed net_device) (uninitialized): PLX-PCI Controls ... [ 3.071301] com20020 0000:02:00.0 arc0-0 (uninitialized): PCI COM20020: station FFh found at F080h, IRQ 101. [ 3.071305] com20020 0000:02:00.0 arc0-0 (uninitialized): Using CKP 64 - data rate 2.5 Mb/s [ 3.071534] com20020 0000:07:00.0: enabling device (0000 -> 0003) [ 3.071581] (unnamed net_device) (uninitialized): PLX-PCI Controls ... [ 3.369501] com20020 0000:07:00.0: Led pci:green:tx:0-0 renamed to pci:green:tx:0-0_1 due to name collision [ 3.369535] com20020 0000:07:00.0: Led pci:red:recon:0-0 renamed to pci:red:recon:0-0_1 due to name collision [ 3.370586] com20020 0000:07:00.0 arc0-0 (uninitialized): PCI COM20020: station E1h found at C000h, IRQ 35. [ 3.370589] com20020 0000:07:00.0 arc0-0 (uninitialized): Using CKP 64 - data rate 2.5 Mb/s [ 3.370608] com20020: probe of 0000:07:00.0 failed with error -5

commit 5ef216c1f848 ("arcnet: com20020-pci: add rotary index support") changes the device name of all COM20020 based PCI cards, even if only some cards support this: snprintf(dev->name, sizeof(dev->name), "arc%d-%d", dev->dev_id, i);

The error happens because all Sohard Arcnet cards would be called arc0-0, since the Sohard Arcnet cards don't have a PLX rotary coder. I.e. EAE Arcnet cards have a PLX rotary coder, which sets the first decimal, ensuring unique devices names.

This patch adds two new card feature flags to indicate which cards support LEDs and the PLX rotary coder. For EAE based cards the names still depend on the PLX rotary coder (untested, since missing EAE hardware). For Sohard based cards, this patch will result in devices being called arc0, arc1, ... (tested).

Signed-off-by: Thomas Reichinger thomas.reichinger@sohard.de Fixes: 5ef216c1f848 ("arcnet: com20020-pci: add rotary index support") Link: https://lore.kernel.org/r/20231130113503.6812-1-thomas.reichinger@sohard.de Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/arcnet/arcdevice.h | 2 + drivers/net/arcnet/com20020-pci.c | 89 ++++++++++++++++--------------- 2 files changed, 48 insertions(+), 43 deletions(-)

diff --git a/drivers/net/arcnet/arcdevice.h b/drivers/net/arcnet/arcdevice.h index 1ad5e4a03d23e..c72ad5e2ac5f0 100644 --- a/drivers/net/arcnet/arcdevice.h +++ b/drivers/net/arcnet/arcdevice.h @@ -191,6 +191,8 @@ do { \ #define ARC_IS_5MBIT 1 /* card default speed is 5MBit */ #define ARC_CAN_10MBIT 2 /* card uses COM20022, supporting 10MBit, but default is 2.5MBit. */ +#define ARC_HAS_LED 4 /* card has software controlled LEDs */ +#define ARC_HAS_ROTARY 8 /* card has rotary encoder */

/* information needed to define an encapsulation driver */ struct ArcProto { diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index 28dccbc0e8d8f..9d9e4200064f9 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -213,12 +213,13 @@ static int com20020pci_probe(struct pci_dev *pdev, if (!strncmp(ci->name, "EAE PLX-PCI FB2", 15)) lp->backplane = 1;

- /* Get the dev_id from the PLX rotary coder */ - if (!strncmp(ci->name, "EAE PLX-PCI MA1", 15)) - dev_id_mask = 0x3; - dev->dev_id = (inb(priv->misc + ci->rotary) >> 4) & dev_id_mask; - - snprintf(dev->name, sizeof(dev->name), "arc%d-%d", dev->dev_id, i); + if (ci->flags & ARC_HAS_ROTARY) { + /* Get the dev_id from the PLX rotary coder */ + if (!strncmp(ci->name, "EAE PLX-PCI MA1", 15)) + dev_id_mask = 0x3; + dev->dev_id = (inb(priv->misc + ci->rotary) >> 4) & dev_id_mask; + snprintf(dev->name, sizeof(dev->name), "arc%d-%d", dev->dev_id, i); + }

if (arcnet_inb(ioaddr, COM20020_REG_R_STATUS) == 0xFF) { pr_err("IO address %Xh is empty!\n", ioaddr); @@ -230,6 +231,10 @@ static int com20020pci_probe(struct pci_dev *pdev, goto err_free_arcdev; }

+ ret = com20020_found(dev, IRQF_SHARED); + if (ret) + goto err_free_arcdev; + card = devm_kzalloc(&pdev->dev, sizeof(struct com20020_dev), GFP_KERNEL); if (!card) { @@ -239,41 +244,39 @@ static int com20020pci_probe(struct pci_dev *pdev,

card->index = i; card->pci_priv = priv; - card->tx_led.brightness_set = led_tx_set; - card->tx_led.default_trigger = devm_kasprintf(&pdev->dev, - GFP_KERNEL, "arc%d-%d-tx", - dev->dev_id, i); - card->tx_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, - "pci:green:tx:%d-%d", - dev->dev_id, i); - - card->tx_led.dev = &dev->dev; - card->recon_led.brightness_set = led_recon_set; - card->recon_led.default_trigger = devm_kasprintf(&pdev->dev, - GFP_KERNEL, "arc%d-%d-recon", - dev->dev_id, i); - card->recon_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, - "pci:red:recon:%d-%d", - dev->dev_id, i); - card->recon_led.dev = &dev->dev; - card->dev = dev; - - ret = devm_led_classdev_register(&pdev->dev, &card->tx_led); - if (ret) - goto err_free_arcdev;

- ret = devm_led_classdev_register(&pdev->dev, &card->recon_led); - if (ret) - goto err_free_arcdev; - - dev_set_drvdata(&dev->dev, card); - - ret = com20020_found(dev, IRQF_SHARED); - if (ret) - goto err_free_arcdev; - - devm_arcnet_led_init(dev, dev->dev_id, i); + if (ci->flags & ARC_HAS_LED) { + card->tx_led.brightness_set = led_tx_set; + card->tx_led.default_trigger = devm_kasprintf(&pdev->dev, + GFP_KERNEL, "arc%d-%d-tx", + dev->dev_id, i); + card->tx_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, + "pci:green:tx:%d-%d", + dev->dev_id, i); + + card->tx_led.dev = &dev->dev; + card->recon_led.brightness_set = led_recon_set; + card->recon_led.default_trigger = devm_kasprintf(&pdev->dev, + GFP_KERNEL, "arc%d-%d-recon", + dev->dev_id, i); + card->recon_led.name = devm_kasprintf(&pdev->dev, GFP_KERNEL, + "pci:red:recon:%d-%d", + dev->dev_id, i); + card->recon_led.dev = &dev->dev; + + ret = devm_led_classdev_register(&pdev->dev, &card->tx_led); + if (ret) + goto err_free_arcdev; + + ret = devm_led_classdev_register(&pdev->dev, &card->recon_led); + if (ret) + goto err_free_arcdev; + + dev_set_drvdata(&dev->dev, card); + devm_arcnet_led_init(dev, dev->dev_id, i); + }

+ card->dev = dev; list_add(&card->list, &priv->list_dev); continue;

@@ -329,7 +332,7 @@ static struct com20020_pci_card_info card_info_5mbit = { };

static struct com20020_pci_card_info card_info_sohard = { - .name = "PLX-PCI", + .name = "SOHARD SH ARC-PCI", .devcount = 1, /* SOHARD needs PCI base addr 4 */ .chan_map_tbl = { @@ -364,7 +367,7 @@ static struct com20020_pci_card_info card_info_eae_arc1 = { }, }, .rotary = 0x0, - .flags = ARC_CAN_10MBIT, + .flags = ARC_HAS_ROTARY | ARC_HAS_LED | ARC_CAN_10MBIT, };

static struct com20020_pci_card_info card_info_eae_ma1 = { @@ -396,7 +399,7 @@ static struct com20020_pci_card_info card_info_eae_ma1 = { }, }, .rotary = 0x0, - .flags = ARC_CAN_10MBIT, + .flags = ARC_HAS_ROTARY | ARC_HAS_LED | ARC_CAN_10MBIT, };

static struct com20020_pci_card_info card_info_eae_fb2 = { @@ -421,7 +424,7 @@ static struct com20020_pci_card_info card_info_eae_fb2 = { }, }, .rotary = 0x0, - .flags = ARC_CAN_10MBIT, + .flags = ARC_HAS_ROTARY | ARC_HAS_LED | ARC_CAN_10MBIT, };

static const struct pci_device_id com20020pci_id_table[] = {

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Yonglong Liu liuyonglong@huawei.com

[ Upstream commit f708aba40f9c1eeb9c7e93ed4863b5f85b09b288 ]

If a xge port just connect with an optical module and no fiber, it may have a fake link up because there may be interference on the hardware. This patch adds an anti-shake to avoid the problem. And the time of anti-shake is base on tests.

Fixes: b917078c1c10 ("net: hns: Add ACPI support to check SFP present") Signed-off-by: Yonglong Liu liuyonglong@huawei.com Signed-off-by: Jijie Shao shaojijie@huawei.com Reviewed-by: Wojciech Drewek wojciech.drewek@intel.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/hisilicon/hns/hns_dsaf_mac.c | 29 +++++++++++++++++++ 1 file changed, 29 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index cfdc92de9dc0e..d2791bcff5d49 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -70,6 +70,27 @@ static enum mac_mode hns_get_enet_interface(const struct hns_mac_cb *mac_cb) } }

+static u32 hns_mac_link_anti_shake(struct mac_driver *mac_ctrl_drv) +{ +#define HNS_MAC_LINK_WAIT_TIME 5 +#define HNS_MAC_LINK_WAIT_CNT 40 + + u32 link_status = 0; + int i; + + if (!mac_ctrl_drv->get_link_status) + return link_status; + + for (i = 0; i < HNS_MAC_LINK_WAIT_CNT; i++) { + msleep(HNS_MAC_LINK_WAIT_TIME); + mac_ctrl_drv->get_link_status(mac_ctrl_drv, &link_status); + if (!link_status) + break; + } + + return link_status; +} + void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status) { struct mac_driver *mac_ctrl_drv; @@ -87,6 +108,14 @@ void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status) &sfp_prsnt); if (!ret) *link_status = *link_status && sfp_prsnt; + + /* for FIBER port, it may have a fake link up. + * when the link status changes from down to up, we need to do + * anti-shake. the anti-shake time is base on tests. + * only FIBER port need to do this. + */ + if (*link_status && !mac_cb->link) + *link_status = hns_mac_link_anti_shake(mac_ctrl_drv); }

mac_cb->link = *link_status;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Phil Sutter phil@nwl.cc

[ Upstream commit 7ae836a3d630e146b732fe8ef7d86b243748751f ]

A concurrently running sock_orphan() may NULL the sk_socket pointer in between check and deref. Follow other users (like nft_meta.c for instance) and acquire sk_callback_lock before dereferencing sk_socket.

Fixes: 0265ab44bacc ("[NETFILTER]: merge ipt_owner/ip6t_owner in xt_owner") Reported-by: Jann Horn jannh@google.com Signed-off-by: Phil Sutter phil@nwl.cc Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/xt_owner.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c index a8784502aca69..0c101b25cacf6 100644 --- a/net/netfilter/xt_owner.c +++ b/net/netfilter/xt_owner.c @@ -76,18 +76,23 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) */ return false;

- filp = sk->sk_socket->file; - if (filp == NULL) + read_lock_bh(&sk->sk_callback_lock); + filp = sk->sk_socket ? sk->sk_socket->file : NULL; + if (filp == NULL) { + read_unlock_bh(&sk->sk_callback_lock); return ((info->match ^ info->invert) & (XT_OWNER_UID | XT_OWNER_GID)) == 0; + }

if (info->match & XT_OWNER_UID) { kuid_t uid_min = make_kuid(net->user_ns, info->uid_min); kuid_t uid_max = make_kuid(net->user_ns, info->uid_max); if ((uid_gte(filp->f_cred->fsuid, uid_min) && uid_lte(filp->f_cred->fsuid, uid_max)) ^ - !(info->invert & XT_OWNER_UID)) + !(info->invert & XT_OWNER_UID)) { + read_unlock_bh(&sk->sk_callback_lock); return false; + } }

if (info->match & XT_OWNER_GID) { @@ -112,10 +117,13 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par) } }

- if (match ^ !(info->invert & XT_OWNER_GID)) + if (match ^ !(info->invert & XT_OWNER_GID)) { + read_unlock_bh(&sk->sk_callback_lock); return false; + } }

+ read_unlock_bh(&sk->sk_callback_lock); return true; }

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kalesh AP kalesh-anakkur.purayil@broadcom.com

[ Upstream commit 422b19f7f006e813ee0865aadce6a62b3c263c42 ]

The word "Driver" is repeated twice in the "modinfo bnxt_re" output description. Fix it.

Fixes: 1ac5a4047975 ("RDMA/bnxt_re: Add bnxt_re RoCE driver") Signed-off-by: Kalesh AP kalesh-anakkur.purayil@broadcom.com Signed-off-by: Selvin Xavier selvin.xavier@broadcom.com Link: https://lore.kernel.org/r/1700555387-6277-1-git-send-email-selvin.xavier@bro... Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/bnxt_re/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index f1b666c80f368..b34e221507f5c 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -70,7 +70,7 @@ static char version[] = BNXT_RE_DESC " v" ROCE_DRV_MODULE_VERSION "\n";

MODULE_AUTHOR("Eddie Wai eddie.wai@broadcom.com"); -MODULE_DESCRIPTION(BNXT_RE_DESC " Driver"); +MODULE_DESCRIPTION(BNXT_RE_DESC); MODULE_LICENSE("Dual BSD/GPL");

/* globals */

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Petr Pavlu petr.pavlu@suse.com

[ Upstream commit 34209fe83ef8404353f91ab4ea4035dbc9922d04 ]

Function trace_buffered_event_disable() produces an unexpected warning when the previous call to trace_buffered_event_enable() fails to allocate pages for buffered events.

The situation can occur as follows:

* The counter trace_buffered_event_ref is at 0.

* The soft mode gets enabled for some event and trace_buffered_event_enable() is called. The function increments trace_buffered_event_ref to 1 and starts allocating event pages.

* The allocation fails for some page and trace_buffered_event_disable() is called for cleanup.

* Function trace_buffered_event_disable() decrements trace_buffered_event_ref back to 0, recognizes that it was the last use of buffered events and frees all allocated pages.

* The control goes back to trace_buffered_event_enable() which returns. The caller of trace_buffered_event_enable() has no information that the function actually failed.

* Some time later, the soft mode is disabled for the same event. Function trace_buffered_event_disable() is called. It warns on "WARN_ON_ONCE(!trace_buffered_event_ref)" and returns.

Buffered events are just an optimization and can handle failures. Make trace_buffered_event_enable() exit on the first failure and left any cleanup later to when trace_buffered_event_disable() is called.

Link: https://lore.kernel.org/all/20231127151248.7232-2-petr.pavlu@suse.com/ Link: https://lkml.kernel.org/r/20231205161736.19663-3-petr.pavlu@suse.com

Fixes: 0fc1b09ff1ff ("tracing: Use temp buffer when filtering events") Signed-off-by: Petr Pavlu petr.pavlu@suse.com Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/trace/trace.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index f44c8f1fd3ec5..a6d84349bcc48 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2209,8 +2209,11 @@ void trace_buffered_event_enable(void) for_each_tracing_cpu(cpu) { page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY, 0); - if (!page) - goto failed; + /* This is just an optimization and can handle failures */ + if (!page) { + pr_err("Failed to allocate event buffer\n"); + break; + }

event = page_address(page); memset(event, 0, sizeof(*event)); @@ -2224,10 +2227,6 @@ void trace_buffered_event_enable(void) WARN_ON_ONCE(1); preempt_enable(); } - - return; - failed: - trace_buffered_event_disable(); }

static void enable_trace_buffered_event(void *data)

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Kunwu Chan chentao@kylinos.cn

[ Upstream commit 1c2b1049af3f86545fcc5fae0fc725fb64b3a09e ]

devm_kasprintf() returns a pointer to dynamically allocated memory which can be NULL upon failure. Ensure the allocation was successful by checking the pointer validity.

Release the id allocated in 'mmdc_pmu_init' when 'devm_kasprintf' return NULL

Suggested-by: Ahmad Fatoum a.fatoum@pengutronix.de Fixes: e76bdfd7403a ("ARM: imx: Added perf functionality to mmdc driver") Signed-off-by: Kunwu Chan chentao@kylinos.cn Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/mach-imx/mmdc.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/arm/mach-imx/mmdc.c b/arch/arm/mach-imx/mmdc.c index 965a41572283e..67cf02c2f2ec2 100644 --- a/arch/arm/mach-imx/mmdc.c +++ b/arch/arm/mach-imx/mmdc.c @@ -513,6 +513,10 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b

name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "mmdc%d", ret); + if (!name) { + ret = -ENOMEM; + goto pmu_release_id; + }

pmu_mmdc->mmdc_ipg_clk = mmdc_ipg_clk; pmu_mmdc->devtype_data = (struct fsl_mmdc_devtype_data *)of_id->data; @@ -535,9 +539,10 @@ static int imx_mmdc_perf_init(struct platform_device *pdev, void __iomem *mmdc_b

pmu_register_err: pr_warn("MMDC Perf PMU failed (%d), disabled\n", ret); - ida_simple_remove(&mmdc_ida, pmu_mmdc->id); cpuhp_state_remove_instance_nocalls(cpuhp_mmdc_state, &pmu_mmdc->node); hrtimer_cancel(&pmu_mmdc->hrtimer); +pmu_release_id: + ida_simple_remove(&mmdc_ida, pmu_mmdc->id); pmu_free: kfree(pmu_mmdc); return ret;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Philipp Zabel p.zabel@pengutronix.de

[ Upstream commit 397caf68e2d36532054cb14ae8995537f27f8b61 ]

The timer nodes declare compatibility with "fsl,imx6sx-gpt", which itself is compatible with "fsl,imx6dl-gpt". Switch the fallback compatible from "fsl,imx6sx-gpt" to "fsl,imx6dl-gpt".

Fixes: 949673450291 ("ARM: dts: add imx7d soc dtsi file") Signed-off-by: Philipp Zabel p.zabel@pengutronix.de Signed-off-by: Roland Hieber rhi@pengutronix.de Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/imx7s.dtsi | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 7cd05ab0b71ff..36c00fe29f4f8 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -440,7 +440,7 @@ };

gpt1: timer@302d0000 { - compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; + compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt"; reg = <0x302d0000 0x10000>; interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX7D_GPT1_ROOT_CLK>, @@ -449,7 +449,7 @@ };

gpt2: timer@302e0000 { - compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; + compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt"; reg = <0x302e0000 0x10000>; interrupts = <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX7D_GPT2_ROOT_CLK>, @@ -459,7 +459,7 @@ };

gpt3: timer@302f0000 { - compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; + compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt"; reg = <0x302f0000 0x10000>; interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX7D_GPT3_ROOT_CLK>, @@ -469,7 +469,7 @@ };

gpt4: timer@30300000 { - compatible = "fsl,imx7d-gpt", "fsl,imx6sx-gpt"; + compatible = "fsl,imx7d-gpt", "fsl,imx6dl-gpt"; reg = <0x30300000 0x10000>; interrupts = <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX7D_GPT4_ROOT_CLK>,

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Daniel Borkmann daniel@iogearbox.net

commit db3fadacaf0c817b222090290d06ca2a338422d0 upstream.

In some potential instances the reference count on struct packet_sock could be saturated and cause overflows which gets the kernel a bit confused. To prevent this, move to a 64-bit atomic reference count on 64-bit architectures to prevent the possibility of this type to overflow.

Because we can not handle saturation, using refcount_t is not possible in this place. Maybe someday in the future if it changes it could be used. Also, instead of using plain atomic64_t, use atomic_long_t instead. 32-bit machines tend to be memory-limited (i.e. anything that increases a reference uses so much memory that you can't actually get to 2**32 references). 32-bit architectures also tend to have serious problems with 64-bit atomics. Hence, atomic_long_t is the more natural solution.

Reported-by: "The UK's National Cyber Security Centre (NCSC)" security@ncsc.gov.uk Co-developed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Daniel Borkmann daniel@iogearbox.net Cc: Linus Torvalds torvalds@linux-foundation.org Cc: stable@kernel.org Reviewed-by: Willem de Bruijn willemb@google.com Reviewed-by: Eric Dumazet edumazet@google.com Link: https://lore.kernel.org/r/20231201131021.19999-1-daniel@iogearbox.net Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/packet/af_packet.c | 16 ++++++++-------- net/packet/internal.h | 2 +- 2 files changed, 9 insertions(+), 9 deletions(-)

--- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4214,7 +4214,7 @@ static void packet_mm_open(struct vm_are struct sock *sk = sock->sk;

if (sk) - atomic_inc(&pkt_sk(sk)->mapped); + atomic_long_inc(&pkt_sk(sk)->mapped); }

static void packet_mm_close(struct vm_area_struct *vma) @@ -4224,7 +4224,7 @@ static void packet_mm_close(struct vm_ar struct sock *sk = sock->sk;

if (sk) - atomic_dec(&pkt_sk(sk)->mapped); + atomic_long_dec(&pkt_sk(sk)->mapped); }

static const struct vm_operations_struct packet_mmap_ops = { @@ -4319,7 +4319,7 @@ static int packet_set_ring(struct sock *

err = -EBUSY; if (!closing) { - if (atomic_read(&po->mapped)) + if (atomic_long_read(&po->mapped)) goto out; if (packet_read_pending(rb)) goto out; @@ -4422,7 +4422,7 @@ static int packet_set_ring(struct sock *

err = -EBUSY; mutex_lock(&po->pg_vec_lock); - if (closing || atomic_read(&po->mapped) == 0) { + if (closing || atomic_long_read(&po->mapped) == 0) { err = 0; spin_lock_bh(&rb_queue->lock); swap(rb->pg_vec, pg_vec); @@ -4440,9 +4440,9 @@ static int packet_set_ring(struct sock * po->prot_hook.func = (po->rx_ring.pg_vec) ? tpacket_rcv : packet_rcv; skb_queue_purge(rb_queue); - if (atomic_read(&po->mapped)) - pr_err("packet_mmap: vma is busy: %d\n", - atomic_read(&po->mapped)); + if (atomic_long_read(&po->mapped)) + pr_err("packet_mmap: vma is busy: %ld\n", + atomic_long_read(&po->mapped)); } mutex_unlock(&po->pg_vec_lock);

@@ -4520,7 +4520,7 @@ static int packet_mmap(struct file *file } }

- atomic_inc(&po->mapped); + atomic_long_inc(&po->mapped); vma->vm_ops = &packet_mmap_ops; err = 0;

--- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -125,7 +125,7 @@ struct packet_sock { __be16 num; struct packet_rollover *rollover; struct packet_mclist *mclist; - atomic_t mapped; + atomic_long_t mapped; enum tpacket_versions tp_version; unsigned int tp_hdrlen; unsigned int tp_reserve;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Steven Rostedt (Google) rostedt@goodmis.org

commit 7be76461f302ec05cbd62b90b2a05c64299ca01f upstream.

It use to be that only the top level instance had a snapshot buffer (for latency tracers like wakeup and irqsoff). The update of the ring buffer size would check if the instance was the top level and if so, it would also update the snapshot buffer as it needs to be the same as the main buffer.

Now that lower level instances also has a snapshot buffer, they too need to update their snapshot buffer sizes when the main buffer is changed, otherwise the following can be triggered:

# cd /sys/kernel/tracing # echo 1500 > buffer_size_kb # mkdir instances/foo # echo irqsoff > instances/foo/current_tracer # echo 1000 > instances/foo/buffer_size_kb

Produces:

WARNING: CPU: 2 PID: 856 at kernel/trace/trace.c:1938 update_max_tr_single.part.0+0x27d/0x320

Which is:

ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->array_buffer.buffer, cpu);

if (ret == -EBUSY) { [..] }

WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY); <== here

That's because ring_buffer_swap_cpu() has:

int ret = -EINVAL;

[..]

/* At least make sure the two buffers are somewhat the same */ if (cpu_buffer_a->nr_pages != cpu_buffer_b->nr_pages) goto out;

[..] out: return ret; }

Instead, update all instances' snapshot buffer sizes when their main buffer size is updated.

Link: https://lkml.kernel.org/r/20231205220010.454662151@goodmis.org

Cc: stable@vger.kernel.org Cc: Masami Hiramatsu mhiramat@kernel.org Cc: Mark Rutland mark.rutland@arm.com Cc: Mathieu Desnoyers mathieu.desnoyers@efficios.com Cc: Andrew Morton akpm@linux-foundation.org Fixes: 6d9b3fa5e7f6 ("tracing: Move tracing_max_latency into trace_array") Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/trace.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -5258,8 +5258,7 @@ static int __tracing_resize_ring_buffer( return ret;

#ifdef CONFIG_TRACER_MAX_TRACE - if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL) || - !tr->current_trace->use_max_tr) + if (!tr->current_trace->use_max_tr) goto out;

ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu);

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Petr Pavlu petr.pavlu@suse.com

commit c0591b1cccf708a47bc465c62436d669a4213323 upstream.

Function trace_buffered_event_disable() is responsible for freeing pages backing buffered events and this process can run concurrently with trace_event_buffer_lock_reserve().

The following race is currently possible:

* Function trace_buffered_event_disable() is called on CPU 0. It increments trace_buffered_event_cnt on each CPU and waits via synchronize_rcu() for each user of trace_buffered_event to complete.

* After synchronize_rcu() is finished, function trace_buffered_event_disable() has the exclusive access to trace_buffered_event. All counters trace_buffered_event_cnt are at 1 and all pointers trace_buffered_event are still valid.

* At this point, on a different CPU 1, the execution reaches trace_event_buffer_lock_reserve(). The function calls preempt_disable_notrace() and only now enters an RCU read-side critical section. The function proceeds and reads a still valid pointer from trace_buffered_event[CPU1] into the local variable "entry". However, it doesn't yet read trace_buffered_event_cnt[CPU1] which happens later.

* Function trace_buffered_event_disable() continues. It frees trace_buffered_event[CPU1] and decrements trace_buffered_event_cnt[CPU1] back to 0.

* Function trace_event_buffer_lock_reserve() continues. It reads and increments trace_buffered_event_cnt[CPU1] from 0 to 1. This makes it believe that it can use the "entry" that it already obtained but the pointer is now invalid and any access results in a use-after-free.

Fix the problem by making a second synchronize_rcu() call after all trace_buffered_event values are set to NULL. This waits on all potential users in trace_event_buffer_lock_reserve() that still read a previous pointer from trace_buffered_event.

Link: https://lore.kernel.org/all/20231127151248.7232-2-petr.pavlu@suse.com/ Link: https://lkml.kernel.org/r/20231205161736.19663-4-petr.pavlu@suse.com

Cc: stable@vger.kernel.org Fixes: 0fc1b09ff1ff ("tracing: Use temp buffer when filtering events") Signed-off-by: Petr Pavlu petr.pavlu@suse.com Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/trace.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)

--- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -2272,13 +2272,17 @@ void trace_buffered_event_disable(void) free_page((unsigned long)per_cpu(trace_buffered_event, cpu)); per_cpu(trace_buffered_event, cpu) = NULL; } + /* - * Make sure trace_buffered_event is NULL before clearing - * trace_buffered_event_cnt. + * Wait for all CPUs that potentially started checking if they can use + * their event buffer only after the previous synchronize_rcu() call and + * they still read a valid pointer from trace_buffered_event. It must be + * ensured they don't see cleared trace_buffered_event_cnt else they + * could wrongly decide to use the pointed-to buffer which is now freed. */ - smp_wmb(); + synchronize_rcu();

- /* Do the work on each cpu */ + /* For each CPU, relinquish the buffer */ on_each_cpu_mask(tracing_buffer_mask, enable_trace_buffered_event, NULL, true); }

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Peter Zijlstra peterz@infradead.org

[ Upstream commit 382c27f4ed28f803b1f1473ac2d8db0afc795a1b ]

Budimir noted that perf_event_validate_size() only checks the size of the newly added event, even though the sizes of all existing events can also change due to not all events having the same read_format.

When we attach the new event, perf_group_attach(), we do re-compute the size for all events.

Fixes: a723968c0ed3 ("perf: Fix u16 overflows") Reported-by: Budimir Markovic markovicbudimir@gmail.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/events/core.c | 61 +++++++++++++++++++++++++++----------------- 1 file changed, 38 insertions(+), 23 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c index acc6403fc87be..4182e265176dc 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1710,31 +1710,34 @@ static inline void perf_event__state_init(struct perf_event *event) PERF_EVENT_STATE_INACTIVE; }

-static void __perf_event_read_size(struct perf_event *event, int nr_siblings) +static int __perf_event_read_size(u64 read_format, int nr_siblings) { int entry = sizeof(u64); /* value */ int size = 0; int nr = 1;

- if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) + if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) size += sizeof(u64);

- if (event->attr.read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) + if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) size += sizeof(u64);

- if (event->attr.read_format & PERF_FORMAT_ID) + if (read_format & PERF_FORMAT_ID) entry += sizeof(u64);

- if (event->attr.read_format & PERF_FORMAT_LOST) + if (read_format & PERF_FORMAT_LOST) entry += sizeof(u64);

- if (event->attr.read_format & PERF_FORMAT_GROUP) { + if (read_format & PERF_FORMAT_GROUP) { nr += nr_siblings; size += sizeof(u64); }

- size += entry * nr; - event->read_size = size; + /* + * Since perf_event_validate_size() limits this to 16k and inhibits + * adding more siblings, this will never overflow. + */ + return size + nr * entry; }

static void __perf_event_header_size(struct perf_event *event, u64 sample_type) @@ -1775,8 +1778,9 @@ static void __perf_event_header_size(struct perf_event *event, u64 sample_type) */ static void perf_event__header_size(struct perf_event *event) { - __perf_event_read_size(event, - event->group_leader->nr_siblings); + event->read_size = + __perf_event_read_size(event->attr.read_format, + event->group_leader->nr_siblings); __perf_event_header_size(event, event->attr.sample_type); }

@@ -1807,24 +1811,35 @@ static void perf_event__id_header_size(struct perf_event *event) event->id_header_size = size; }

+/* + * Check that adding an event to the group does not result in anybody + * overflowing the 64k event limit imposed by the output buffer. + * + * Specifically, check that the read_size for the event does not exceed 16k, + * read_size being the one term that grows with groups size. Since read_size + * depends on per-event read_format, also (re)check the existing events. + * + * This leaves 48k for the constant size fields and things like callchains, + * branch stacks and register sets. + */ static bool perf_event_validate_size(struct perf_event *event) { - /* - * The values computed here will be over-written when we actually - * attach the event. - */ - __perf_event_read_size(event, event->group_leader->nr_siblings + 1); - __perf_event_header_size(event, event->attr.sample_type & ~PERF_SAMPLE_READ); - perf_event__id_header_size(event); + struct perf_event *sibling, *group_leader = event->group_leader;

- /* - * Sum the lot; should not exceed the 64k limit we have on records. - * Conservative limit to allow for callchains and other variable fields. - */ - if (event->read_size + event->header_size + - event->id_header_size + sizeof(struct perf_event_header) >= 16*1024) + if (__perf_event_read_size(event->attr.read_format, + group_leader->nr_siblings + 1) > 16*1024) return false;

+ if (__perf_event_read_size(group_leader->attr.read_format, + group_leader->nr_siblings + 1) > 16*1024) + return false; + + for_each_sibling_event(sibling, group_leader) { + if (__perf_event_read_size(sibling->attr.read_format, + group_leader->nr_siblings + 1) > 16*1024) + return false; + } + return true; }

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Konstantin Aladyshev aladyshev22@gmail.com

commit 61890dc28f7d9e9aac8a9471302613824c22fae4 upstream.

The commit 89ff3dfac604 ("usb: gadget: f_hid: fix f_hidg lifetime vs cdev") has introduced a bug that leads to hid device corruption after the replug operation. Reverse device managed memory allocation for the report descriptor to fix the issue.

Tested: This change was tested on the AMD EthanolX CRB server with the BMC based on the OpenBMC distribution. The BMC provides KVM functionality via the USB gadget device: - before: KVM page refresh results in a broken USB device, - after: KVM page refresh works without any issues.

Fixes: 89ff3dfac604 ("usb: gadget: f_hid: fix f_hidg lifetime vs cdev") Cc: stable@vger.kernel.org Signed-off-by: Konstantin Aladyshev aladyshev22@gmail.com Link: https://lore.kernel.org/r/20231206080744.253-2-aladyshev22@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/gadget/function/f_hid.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

--- a/drivers/usb/gadget/function/f_hid.c +++ b/drivers/usb/gadget/function/f_hid.c @@ -88,6 +88,7 @@ static void hidg_release(struct device * { struct f_hidg *hidg = container_of(dev, struct f_hidg, dev);

+ kfree(hidg->report_desc); kfree(hidg->set_report_buf); kfree(hidg); } @@ -1293,9 +1294,9 @@ static struct usb_function *hidg_alloc(s hidg->report_length = opts->report_length; hidg->report_desc_length = opts->report_desc_length; if (opts->report_desc) { - hidg->report_desc = devm_kmemdup(&hidg->dev, opts->report_desc, - opts->report_desc_length, - GFP_KERNEL); + hidg->report_desc = kmemdup(opts->report_desc, + opts->report_desc_length, + GFP_KERNEL); if (!hidg->report_desc) { put_device(&hidg->dev); --opts->refcnt;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: RD Babiera rdbabiera@google.com

commit b17b7fe6dd5c6ff74b38b0758ca799cdbb79e26e upstream.

When typec_altmode_put_partner is called by a plug altmode upon release, the port altmode the plug belongs to will not remove its reference to the plug. The check to see if the altmode being released evaluates against the released altmode's partner instead of the calling altmode itself, so change adev in typec_altmode_put_partner to properly refer to the altmode being released.

typec_altmode_set_partner is not run for port altmodes, so also add a check in typec_altmode_release to prevent typec_altmode_put_partner() calls on port altmode release.

Fixes: 8a37d87d72f0 ("usb: typec: Bus type for alternate modes") Cc: stable@vger.kernel.org Signed-off-by: RD Babiera rdbabiera@google.com Reviewed-by: Heikki Krogerus heikki.krogerus@linux.intel.com Link: https://lore.kernel.org/r/20231129192349.1773623-2-rdbabiera@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/typec/class.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

--- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -192,7 +192,7 @@ static void typec_altmode_put_partner(st if (!partner) return;

- adev = &partner->adev; + adev = &altmode->adev;

if (is_typec_plug(adev->dev.parent)) { struct typec_plug *plug = to_typec_plug(adev->dev.parent); @@ -459,7 +459,8 @@ static void typec_altmode_release(struct { struct altmode *alt = to_altmode(to_typec_altmode(dev));

- typec_altmode_put_partner(alt); + if (!is_typec_port(dev->parent)) + typec_altmode_put_partner(alt);

altmode_id_remove(alt->adev.dev.parent, alt->id); kfree(alt);

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Daniel Mack daniel@zonque.org

commit 08ce9a1b72e38cf44c300a44ac5858533eb3c860 upstream.

This device has a silicon bug that makes it report a timeout interrupt but no data in the FIFO.

The datasheet states the following in the errata section 18.1.4:

"If the host reads the receive FIFO at the same time as a time-out interrupt condition happens, the host might read 0xCC (time-out) in the Interrupt Indication Register (IIR), but bit 0 of the Line Status Register (LSR) is not set (means there is no data in the receive FIFO)."

The errata description seems to indicate it concerns only polled mode of operation when reading bit 0 of the LSR register. However, tests have shown and NXP has confirmed that the RXLVL register also yields 0 when the bug is triggered, and hence the IRQ driven implementation in this driver is equally affected.

This bug has hit us on production units and when it does, sc16is7xx_irq() would spin forever because sc16is7xx_port_irq() keeps seeing an interrupt in the IIR register that is not cleared because the driver does not call into sc16is7xx_handle_rx() unless the RXLVL register reports at least one byte in the FIFO.

Fix this by always reading one byte from the FIFO when this condition is detected in order to clear the interrupt. This approach was confirmed to be correct by NXP through their support channels.

Tested by: Hugo Villeneuve hvilleneuve@dimonoff.com

Signed-off-by: Daniel Mack daniel@zonque.org Co-Developed-by: Maxim Popov maxim.snafu@gmail.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20231123072818.1394539-1-daniel@zonque.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/tty/serial/sc16is7xx.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)

--- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -694,6 +694,18 @@ static bool sc16is7xx_port_irq(struct sc case SC16IS7XX_IIR_RTOI_SRC: case SC16IS7XX_IIR_XOFFI_SRC: rxlen = sc16is7xx_port_read(port, SC16IS7XX_RXLVL_REG); + + /* + * There is a silicon bug that makes the chip report a + * time-out interrupt but no data in the FIFO. This is + * described in errata section 18.1.4. + * + * When this happens, read one byte from the FIFO to + * clear the interrupt. + */ + if (iir == SC16IS7XX_IIR_RTOI_SRC && !rxlen) + rxlen = 1; + if (rxlen) sc16is7xx_handle_rx(port, rxlen, iir); break;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Borislav Petkov (AMD) bp@alien8.de

commit 9b8493dc43044376716d789d07699f17d538a7c4 upstream.

Commit in Fixes added an AMD-specific microcode callback. However, it didn't check the CPU vendor the kernel runs on explicitly.

The only reason the Zenbleed check in it didn't run on other x86 vendors hardware was pure coincidental luck:

if (!cpu_has_amd_erratum(c, amd_zenbleed)) return;

gives true on other vendors because they don't have those families and models.

However, with the removal of the cpu_has_amd_erratum() in

05f5f73936fa ("x86/CPU/AMD: Drop now unused CPU erratum checking function")

that coincidental condition is gone, leading to the zenbleed check getting executed on other vendors too.

Add the explicit vendor check for the whole callback as it should've been done in the first place.

Fixes: 522b1d69219d ("x86/cpu/amd: Add a Zenbleed fix") Cc: stable@kernel.org Signed-off-by: Borislav Petkov (AMD) bp@alien8.de Link: https://lore.kernel.org/r/20231201184226.16749-1-bp@alien8.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/cpu/amd.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1253,5 +1253,8 @@ static void zenbleed_check_cpu(void *unu

void amd_check_microcode(void) { + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + return; + on_each_cpu(zenbleed_check_cpu, NULL, 1); }

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ryusuke Konishi konishi.ryusuke@gmail.com

commit d61d0ab573649789bf9eb909c89a1a193b2e3d10 upstream.

When mounting a filesystem image with a block size larger than the page size, nilfs2 repeatedly outputs long error messages with stack traces to the kernel log, such as the following:

getblk(): invalid block size 8192 requested logical block size: 512 ... Call Trace: dump_stack_lvl+0x92/0xd4 dump_stack+0xd/0x10 bdev_getblk+0x33a/0x354 __breadahead+0x11/0x80 nilfs_search_super_root+0xe2/0x704 [nilfs2] load_nilfs+0x72/0x504 [nilfs2] nilfs_mount+0x30f/0x518 [nilfs2] legacy_get_tree+0x1b/0x40 vfs_get_tree+0x18/0xc4 path_mount+0x786/0xa88 __ia32_sys_mount+0x147/0x1a8 __do_fast_syscall_32+0x56/0xc8 do_fast_syscall_32+0x29/0x58 do_SYSENTER_32+0x15/0x18 entry_SYSENTER_32+0x98/0xf1 ...

This overloads the system logger. And to make matters worse, it sometimes crashes the kernel with a memory access violation.

This is because the return value of the sb_set_blocksize() call, which should be checked for errors, is not checked.

The latter issue is due to out-of-buffer memory being accessed based on a large block size that caused sb_set_blocksize() to fail for buffers read with the initial minimum block size that remained unupdated in the super_block structure.

Since nilfs2 mkfs tool does not accept block sizes larger than the system page size, this has been overlooked. However, it is possible to create this situation by intentionally modifying the tool or by passing a filesystem image created on a system with a large page size to a system with a smaller page size and mounting it.

Fix this issue by inserting the expected error handling for the call to sb_set_blocksize().

Link: https://lkml.kernel.org/r/20231129141547.4726-1-konishi.ryusuke@gmail.com Signed-off-by: Ryusuke Konishi konishi.ryusuke@gmail.com Tested-by: Ryusuke Konishi konishi.ryusuke@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/nilfs2/the_nilfs.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -688,7 +688,11 @@ int init_nilfs(struct the_nilfs *nilfs, goto failed_sbh; } nilfs_release_super_block(nilfs); - sb_set_blocksize(sb, blocksize); + if (!sb_set_blocksize(sb, blocksize)) { + nilfs_msg(sb, KERN_ERR, "bad blocksize %d", blocksize); + err = -EINVAL; + goto out; + }

err = nilfs_load_super_block(nilfs, sb, blocksize, &sbp); if (err)

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ido Schimmel idosch@nvidia.com

This is a partial backport of upstream commit 4d54cc32112d ("mptcp: avoid lock_fast usage in accept path"). It is only a partial backport because the patch in the link below was erroneously squash-merged into upstream commit 4d54cc32112d ("mptcp: avoid lock_fast usage in accept path"). Below is the original patch description from Florian Westphal:

" genetlink sets NL_CFG_F_NONROOT_RECV for its netlink socket so anyone can subscribe to multicast messages.

rtnetlink doesn't allow this unconditionally, rtnetlink_bind() restricts bind requests to CAP_NET_ADMIN for a few groups.

This allows to set GENL_UNS_ADMIN_PERM flag on genl mcast groups to mandate CAP_NET_ADMIN.

This will be used by the upcoming mptcp netlink event facility which exposes the token (mptcp connection identifier) to userspace. "

Link: https://lore.kernel.org/mptcp/20210213000001.379332-8-mathew.j.martineau@lin... Signed-off-by: Ido Schimmel idosch@nvidia.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/genetlink.h | 1 + net/netlink/genetlink.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 33 insertions(+)

--- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -14,6 +14,7 @@ */ struct genl_multicast_group { char name[GENL_NAMSIZ]; + u8 flags; };

struct genl_ops; --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -961,11 +961,43 @@ static struct genl_family genl_ctrl __ro .netnsok = true, };

+static int genl_bind(struct net *net, int group) +{ + const struct genl_family *family; + unsigned int id; + int ret = 0; + + genl_lock_all(); + + idr_for_each_entry(&genl_fam_idr, family, id) { + const struct genl_multicast_group *grp; + int i; + + if (family->n_mcgrps == 0) + continue; + + i = group - family->mcgrp_offset; + if (i < 0 || i >= family->n_mcgrps) + continue; + + grp = &family->mcgrps[i]; + if ((grp->flags & GENL_UNS_ADMIN_PERM) && + !ns_capable(net->user_ns, CAP_NET_ADMIN)) + ret = -EPERM; + + break; + } + + genl_unlock_all(); + return ret; +} + static int __net_init genl_pernet_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = genl_rcv, .flags = NL_CFG_F_NONROOT_RECV, + .bind = genl_bind, };

/* we'll bump the group number right afterwards */

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ido Schimmel idosch@nvidia.com

commit e03781879a0d524ce3126678d50a80484a513c4b upstream.

The "NET_DM" generic netlink family notifies drop locations over the "events" multicast group. This is problematic since by default generic netlink allows non-root users to listen to these notifications.

Fix by adding a new field to the generic netlink multicast group structure that when set prevents non-root users or root without the 'CAP_SYS_ADMIN' capability (in the user namespace owning the network namespace) from joining the group. Set this field for the "events" group. Use 'CAP_SYS_ADMIN' rather than 'CAP_NET_ADMIN' because of the nature of the information that is shared over this group.

Note that the capability check in this case will always be performed against the initial user namespace since the family is not netns aware and only operates in the initial network namespace.

A new field is added to the structure rather than using the "flags" field because the existing field uses uAPI flags and it is inappropriate to add a new uAPI flag for an internal kernel check. In net-next we can rework the "flags" field to use internal flags and fold the new field into it. But for now, in order to reduce the amount of changes, add a new field.

Since the information can only be consumed by root, mark the control plane operations that start and stop the tracing as root-only using the 'GENL_ADMIN_PERM' flag.

Tested using [1].

Before:

# capsh -- -c ./dm_repo # capsh --drop=cap_sys_admin -- -c ./dm_repo

After:

# capsh -- -c ./dm_repo # capsh --drop=cap_sys_admin -- -c ./dm_repo Failed to join "events" multicast group

[1] $ cat dm.c #include <stdio.h> #include <netlink/genl/ctrl.h> #include <netlink/genl/genl.h> #include <netlink/socket.h>

int main(int argc, char **argv) { struct nl_sock *sk; int grp, err;

sk = nl_socket_alloc(); if (!sk) { fprintf(stderr, "Failed to allocate socket\n"); return -1; }

err = genl_connect(sk); if (err) { fprintf(stderr, "Failed to connect socket\n"); return err; }

grp = genl_ctrl_resolve_grp(sk, "NET_DM", "events"); if (grp < 0) { fprintf(stderr, "Failed to resolve "events" multicast group\n"); return grp; }

err = nl_socket_add_memberships(sk, grp, NFNLGRP_NONE); if (err) { fprintf(stderr, "Failed to join "events" multicast group\n"); return err; }

return 0; } $ gcc -I/usr/include/libnl3 -lnl-3 -lnl-genl-3 -o dm_repo dm.c

Fixes: 9a8afc8d3962 ("Network Drop Monitor: Adding drop monitor implementation & Netlink protocol") Reported-by: "The UK's National Cyber Security Centre (NCSC)" security@ncsc.gov.uk Signed-off-by: Ido Schimmel idosch@nvidia.com Reviewed-by: Jacob Keller jacob.e.keller@intel.com Reviewed-by: Jiri Pirko jiri@nvidia.com Link: https://lore.kernel.org/r/20231206213102.1824398-3-idosch@nvidia.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/genetlink.h | 2 ++ net/core/drop_monitor.c | 4 +++- net/netlink/genetlink.c | 3 +++ 3 files changed, 8 insertions(+), 1 deletion(-)

--- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -11,10 +11,12 @@ /** * struct genl_multicast_group - generic netlink multicast group * @name: name of the multicast group, names are per-family + * @cap_sys_admin: whether %CAP_SYS_ADMIN is required for binding */ struct genl_multicast_group { char name[GENL_NAMSIZ]; u8 flags; + u8 cap_sys_admin:1; };

struct genl_ops; --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -122,7 +122,7 @@ out: }

static const struct genl_multicast_group dropmon_mcgrps[] = { - { .name = "events", }, + { .name = "events", .cap_sys_admin = 1 }, };

static void send_dm_alert(struct work_struct *work) @@ -370,10 +370,12 @@ static const struct genl_ops dropmon_ops { .cmd = NET_DM_CMD_START, .doit = net_dm_cmd_trace, + .flags = GENL_ADMIN_PERM, }, { .cmd = NET_DM_CMD_STOP, .doit = net_dm_cmd_trace, + .flags = GENL_ADMIN_PERM, }, };

--- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -984,6 +984,9 @@ static int genl_bind(struct net *net, in if ((grp->flags & GENL_UNS_ADMIN_PERM) && !ns_capable(net->user_ns, CAP_NET_ADMIN)) ret = -EPERM; + if (grp->cap_sys_admin && + !ns_capable(net->user_ns, CAP_SYS_ADMIN)) + ret = -EPERM;

break; }

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Sagi Grimberg sagi@grimberg.me

commit 0b089c1ef7047652b13b4cdfdb1e0e7dbdb8c9ab upstream.

Currently we allocate rx buffers in a single contiguous buffers for headers (iser and iscsi) and data trailer. This means that most likely the data starting offset is aligned to 76 bytes (size of both headers).

This worked fine for years, but at some point this broke, resulting in data corruptions in isert when a command comes with immediate data and the underlying backend device assumes 512 bytes buffer alignment.

We assume a hard-requirement for all direct I/O buffers to be 512 bytes aligned. To fix this, we should avoid passing unaligned buffers for I/O.

Instead, we allocate our recv buffers with some extra space such that we can have the data portion align to 512 byte boundary. This also means that we cannot reference headers or data using structure but rather accessors (as they may move based on alignment). Also, get rid of the wrong __packed annotation from iser_rx_desc as this has only harmful effects (not aligned to anything).

This affects the rx descriptors for iscsi login and data plane.

Fixes: 3d75ca0adef4 ("block: introduce multi-page bvec helpers") Link: https://lore.kernel.org/r/20200904195039.31687-1-sagi@grimberg.me Reported-by: Stephen Rust srust@blockbridge.com Tested-by: Doug Dumitru doug@dumitru.com Signed-off-by: Sagi Grimberg sagi@grimberg.me Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/infiniband/ulp/isert/ib_isert.c | 93 ++++++++++++++++---------------- drivers/infiniband/ulp/isert/ib_isert.h | 41 ++++++++++---- 2 files changed, 78 insertions(+), 56 deletions(-)

--- a/drivers/infiniband/ulp/isert/ib_isert.c +++ b/drivers/infiniband/ulp/isert/ib_isert.c @@ -190,15 +190,15 @@ isert_alloc_rx_descriptors(struct isert_ rx_desc = isert_conn->rx_descs;

for (i = 0; i < ISERT_QP_MAX_RECV_DTOS; i++, rx_desc++) { - dma_addr = ib_dma_map_single(ib_dev, (void *)rx_desc, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + dma_addr = ib_dma_map_single(ib_dev, rx_desc->buf, + ISER_RX_SIZE, DMA_FROM_DEVICE); if (ib_dma_mapping_error(ib_dev, dma_addr)) goto dma_map_fail;

rx_desc->dma_addr = dma_addr;

rx_sg = &rx_desc->rx_sg; - rx_sg->addr = rx_desc->dma_addr; + rx_sg->addr = rx_desc->dma_addr + isert_get_hdr_offset(rx_desc); rx_sg->length = ISER_RX_PAYLOAD_SIZE; rx_sg->lkey = device->pd->local_dma_lkey; rx_desc->rx_cqe.done = isert_recv_done; @@ -210,7 +210,7 @@ dma_map_fail: rx_desc = isert_conn->rx_descs; for (j = 0; j < i; j++, rx_desc++) { ib_dma_unmap_single(ib_dev, rx_desc->dma_addr, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ISER_RX_SIZE, DMA_FROM_DEVICE); } kfree(isert_conn->rx_descs); isert_conn->rx_descs = NULL; @@ -231,7 +231,7 @@ isert_free_rx_descriptors(struct isert_c rx_desc = isert_conn->rx_descs; for (i = 0; i < ISERT_QP_MAX_RECV_DTOS; i++, rx_desc++) { ib_dma_unmap_single(ib_dev, rx_desc->dma_addr, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ISER_RX_SIZE, DMA_FROM_DEVICE); }

kfree(isert_conn->rx_descs); @@ -416,10 +416,9 @@ isert_free_login_buf(struct isert_conn * ISER_RX_PAYLOAD_SIZE, DMA_TO_DEVICE); kfree(isert_conn->login_rsp_buf);

- ib_dma_unmap_single(ib_dev, isert_conn->login_req_dma, - ISER_RX_PAYLOAD_SIZE, - DMA_FROM_DEVICE); - kfree(isert_conn->login_req_buf); + ib_dma_unmap_single(ib_dev, isert_conn->login_desc->dma_addr, + ISER_RX_SIZE, DMA_FROM_DEVICE); + kfree(isert_conn->login_desc); }

static int @@ -428,25 +427,25 @@ isert_alloc_login_buf(struct isert_conn { int ret;

- isert_conn->login_req_buf = kzalloc(sizeof(*isert_conn->login_req_buf), + isert_conn->login_desc = kzalloc(sizeof(*isert_conn->login_desc), GFP_KERNEL); - if (!isert_conn->login_req_buf) + if (!isert_conn->login_desc) return -ENOMEM;

- isert_conn->login_req_dma = ib_dma_map_single(ib_dev, - isert_conn->login_req_buf, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); - ret = ib_dma_mapping_error(ib_dev, isert_conn->login_req_dma); + isert_conn->login_desc->dma_addr = ib_dma_map_single(ib_dev, + isert_conn->login_desc->buf, + ISER_RX_SIZE, DMA_FROM_DEVICE); + ret = ib_dma_mapping_error(ib_dev, isert_conn->login_desc->dma_addr); if (ret) { - isert_err("login_req_dma mapping error: %d\n", ret); - isert_conn->login_req_dma = 0; - goto out_free_login_req_buf; + isert_err("login_desc dma mapping error: %d\n", ret); + isert_conn->login_desc->dma_addr = 0; + goto out_free_login_desc; }

isert_conn->login_rsp_buf = kzalloc(ISER_RX_PAYLOAD_SIZE, GFP_KERNEL); if (!isert_conn->login_rsp_buf) { ret = -ENOMEM; - goto out_unmap_login_req_buf; + goto out_unmap_login_desc; }

isert_conn->login_rsp_dma = ib_dma_map_single(ib_dev, @@ -463,11 +462,11 @@ isert_alloc_login_buf(struct isert_conn

out_free_login_rsp_buf: kfree(isert_conn->login_rsp_buf); -out_unmap_login_req_buf: - ib_dma_unmap_single(ib_dev, isert_conn->login_req_dma, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); -out_free_login_req_buf: - kfree(isert_conn->login_req_buf); +out_unmap_login_desc: + ib_dma_unmap_single(ib_dev, isert_conn->login_desc->dma_addr, + ISER_RX_SIZE, DMA_FROM_DEVICE); +out_free_login_desc: + kfree(isert_conn->login_desc); return ret; }

@@ -586,7 +585,7 @@ isert_connect_release(struct isert_conn ib_destroy_qp(isert_conn->qp); }

- if (isert_conn->login_req_buf) + if (isert_conn->login_desc) isert_free_login_buf(isert_conn);

isert_device_put(device); @@ -976,17 +975,18 @@ isert_login_post_recv(struct isert_conn int ret;

memset(&sge, 0, sizeof(struct ib_sge)); - sge.addr = isert_conn->login_req_dma; + sge.addr = isert_conn->login_desc->dma_addr + + isert_get_hdr_offset(isert_conn->login_desc); sge.length = ISER_RX_PAYLOAD_SIZE; sge.lkey = isert_conn->device->pd->local_dma_lkey;

isert_dbg("Setup sge: addr: %llx length: %d 0x%08x\n", sge.addr, sge.length, sge.lkey);

- isert_conn->login_req_buf->rx_cqe.done = isert_login_recv_done; + isert_conn->login_desc->rx_cqe.done = isert_login_recv_done;

memset(&rx_wr, 0, sizeof(struct ib_recv_wr)); - rx_wr.wr_cqe = &isert_conn->login_req_buf->rx_cqe; + rx_wr.wr_cqe = &isert_conn->login_desc->rx_cqe; rx_wr.sg_list = &sge; rx_wr.num_sge = 1;

@@ -1063,7 +1063,7 @@ post_send: static void isert_rx_login_req(struct isert_conn *isert_conn) { - struct iser_rx_desc *rx_desc = isert_conn->login_req_buf; + struct iser_rx_desc *rx_desc = isert_conn->login_desc; int rx_buflen = isert_conn->login_req_len; struct iscsi_conn *conn = isert_conn->conn; struct iscsi_login *login = conn->conn_login; @@ -1075,7 +1075,7 @@ isert_rx_login_req(struct isert_conn *is

if (login->first_request) { struct iscsi_login_req *login_req = - (struct iscsi_login_req *)&rx_desc->iscsi_header; + (struct iscsi_login_req *)isert_get_iscsi_hdr(rx_desc); /* * Setup the initial iscsi_login values from the leading * login request PDU. @@ -1094,13 +1094,13 @@ isert_rx_login_req(struct isert_conn *is login->tsih = be16_to_cpu(login_req->tsih); }

- memcpy(&login->req[0], (void *)&rx_desc->iscsi_header, ISCSI_HDR_LEN); + memcpy(&login->req[0], isert_get_iscsi_hdr(rx_desc), ISCSI_HDR_LEN);

size = min(rx_buflen, MAX_KEY_VALUE_PAIRS); isert_dbg("Using login payload size: %d, rx_buflen: %d " "MAX_KEY_VALUE_PAIRS: %d\n", size, rx_buflen, MAX_KEY_VALUE_PAIRS); - memcpy(login->req_buf, &rx_desc->data[0], size); + memcpy(login->req_buf, isert_get_data(rx_desc), size);

if (login->first_request) { complete(&isert_conn->login_comp); @@ -1165,14 +1165,15 @@ isert_handle_scsi_cmd(struct isert_conn if (imm_data_len != data_len) { sg_nents = max(1UL, DIV_ROUND_UP(imm_data_len, PAGE_SIZE)); sg_copy_from_buffer(cmd->se_cmd.t_data_sg, sg_nents, - &rx_desc->data[0], imm_data_len); + isert_get_data(rx_desc), imm_data_len); isert_dbg("Copy Immediate sg_nents: %u imm_data_len: %d\n", sg_nents, imm_data_len); } else { sg_init_table(&isert_cmd->sg, 1); cmd->se_cmd.t_data_sg = &isert_cmd->sg; cmd->se_cmd.t_data_nents = 1; - sg_set_buf(&isert_cmd->sg, &rx_desc->data[0], imm_data_len); + sg_set_buf(&isert_cmd->sg, isert_get_data(rx_desc), + imm_data_len); isert_dbg("Transfer Immediate imm_data_len: %d\n", imm_data_len); } @@ -1241,9 +1242,9 @@ isert_handle_iscsi_dataout(struct isert_ } isert_dbg("Copying DataOut: sg_start: %p, sg_off: %u " "sg_nents: %u from %p %u\n", sg_start, sg_off, - sg_nents, &rx_desc->data[0], unsol_data_len); + sg_nents, isert_get_data(rx_desc), unsol_data_len);

- sg_copy_from_buffer(sg_start, sg_nents, &rx_desc->data[0], + sg_copy_from_buffer(sg_start, sg_nents, isert_get_data(rx_desc), unsol_data_len);

rc = iscsit_check_dataout_payload(cmd, hdr, false); @@ -1302,7 +1303,7 @@ isert_handle_text_cmd(struct isert_conn } cmd->text_in_ptr = text_in;

- memcpy(cmd->text_in_ptr, &rx_desc->data[0], payload_length); + memcpy(cmd->text_in_ptr, isert_get_data(rx_desc), payload_length);

return iscsit_process_text_cmd(conn, cmd, hdr); } @@ -1312,7 +1313,7 @@ isert_rx_opcode(struct isert_conn *isert uint32_t read_stag, uint64_t read_va, uint32_t write_stag, uint64_t write_va) { - struct iscsi_hdr *hdr = &rx_desc->iscsi_header; + struct iscsi_hdr *hdr = isert_get_iscsi_hdr(rx_desc); struct iscsi_conn *conn = isert_conn->conn; struct iscsi_cmd *cmd; struct isert_cmd *isert_cmd; @@ -1410,8 +1411,8 @@ isert_recv_done(struct ib_cq *cq, struct struct isert_conn *isert_conn = wc->qp->qp_context; struct ib_device *ib_dev = isert_conn->cm_id->device; struct iser_rx_desc *rx_desc = cqe_to_rx_desc(wc->wr_cqe); - struct iscsi_hdr *hdr = &rx_desc->iscsi_header; - struct iser_ctrl *iser_ctrl = &rx_desc->iser_header; + struct iscsi_hdr *hdr = isert_get_iscsi_hdr(rx_desc); + struct iser_ctrl *iser_ctrl = isert_get_iser_hdr(rx_desc); uint64_t read_va = 0, write_va = 0; uint32_t read_stag = 0, write_stag = 0;

@@ -1425,7 +1426,7 @@ isert_recv_done(struct ib_cq *cq, struct rx_desc->in_use = true;

ib_dma_sync_single_for_cpu(ib_dev, rx_desc->dma_addr, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ISER_RX_SIZE, DMA_FROM_DEVICE);

isert_dbg("DMA: 0x%llx, iSCSI opcode: 0x%02x, ITT: 0x%08x, flags: 0x%02x dlen: %d\n", rx_desc->dma_addr, hdr->opcode, hdr->itt, hdr->flags, @@ -1460,7 +1461,7 @@ isert_recv_done(struct ib_cq *cq, struct read_stag, read_va, write_stag, write_va);

ib_dma_sync_single_for_device(ib_dev, rx_desc->dma_addr, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ISER_RX_SIZE, DMA_FROM_DEVICE); }

static void @@ -1474,8 +1475,8 @@ isert_login_recv_done(struct ib_cq *cq, return; }

- ib_dma_sync_single_for_cpu(ib_dev, isert_conn->login_req_dma, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ib_dma_sync_single_for_cpu(ib_dev, isert_conn->login_desc->dma_addr, + ISER_RX_SIZE, DMA_FROM_DEVICE);

isert_conn->login_req_len = wc->byte_len - ISER_HEADERS_LEN;

@@ -1490,8 +1491,8 @@ isert_login_recv_done(struct ib_cq *cq, complete(&isert_conn->login_req_comp); mutex_unlock(&isert_conn->mutex);

- ib_dma_sync_single_for_device(ib_dev, isert_conn->login_req_dma, - ISER_RX_PAYLOAD_SIZE, DMA_FROM_DEVICE); + ib_dma_sync_single_for_device(ib_dev, isert_conn->login_desc->dma_addr, + ISER_RX_SIZE, DMA_FROM_DEVICE); }

static void --- a/drivers/infiniband/ulp/isert/ib_isert.h +++ b/drivers/infiniband/ulp/isert/ib_isert.h @@ -59,9 +59,11 @@ ISERT_MAX_TX_MISC_PDUS + \ ISERT_MAX_RX_MISC_PDUS)

-#define ISER_RX_PAD_SIZE (ISCSI_DEF_MAX_RECV_SEG_LEN + 4096 - \ - (ISER_RX_PAYLOAD_SIZE + sizeof(u64) + sizeof(struct ib_sge) + \ - sizeof(struct ib_cqe) + sizeof(bool))) +/* + * RX size is default of 8k plus headers, but data needs to align to + * 512 boundary, so use 1024 to have the extra space for alignment. + */ +#define ISER_RX_SIZE (ISCSI_DEF_MAX_RECV_SEG_LEN + 1024)

#define ISCSI_ISER_SG_TABLESIZE 256

@@ -80,21 +82,41 @@ enum iser_conn_state { };

struct iser_rx_desc { - struct iser_ctrl iser_header; - struct iscsi_hdr iscsi_header; - char data[ISCSI_DEF_MAX_RECV_SEG_LEN]; + char buf[ISER_RX_SIZE]; u64 dma_addr; struct ib_sge rx_sg; struct ib_cqe rx_cqe; bool in_use; - char pad[ISER_RX_PAD_SIZE]; -} __packed; +};

static inline struct iser_rx_desc *cqe_to_rx_desc(struct ib_cqe *cqe) { return container_of(cqe, struct iser_rx_desc, rx_cqe); }

+static void *isert_get_iser_hdr(struct iser_rx_desc *desc) +{ + return PTR_ALIGN(desc->buf + ISER_HEADERS_LEN, 512) - ISER_HEADERS_LEN; +} + +static size_t isert_get_hdr_offset(struct iser_rx_desc *desc) +{ + return isert_get_iser_hdr(desc) - (void *)desc->buf; +} + +static void *isert_get_iscsi_hdr(struct iser_rx_desc *desc) +{ + return isert_get_iser_hdr(desc) + sizeof(struct iser_ctrl); +} + +static void *isert_get_data(struct iser_rx_desc *desc) +{ + void *data = isert_get_iser_hdr(desc) + ISER_HEADERS_LEN; + + WARN_ON((uintptr_t)data & 511); + return data; +} + struct iser_tx_desc { struct iser_ctrl iser_header; struct iscsi_hdr iscsi_header; @@ -141,9 +163,8 @@ struct isert_conn { u32 responder_resources; u32 initiator_depth; bool pi_support; - struct iser_rx_desc *login_req_buf; + struct iser_rx_desc *login_desc; char *login_rsp_buf; - u64 login_req_dma; int login_req_len; u64 login_rsp_dma; struct iser_rx_desc *rx_descs;

4.19-stable review patch. If anyone has any objections, please let me know.

------------------

From: Mukesh Ojha quic_mojha@quicinc.com

[ Upstream commit af54d778a03853801d681c98c0c2a6c316ef9ca7 ]

dev_coredumpm() creates a devcoredump device and adds it to the core kernel framework which eventually end up sending uevent to the user space and later creates a symbolic link to the failed device. An application running in userspace may be interested in this symbolic link to get the name of the failed device.

In a issue scenario, once uevent sent to the user space it start reading '/sys/class/devcoredump/devcdX/failing_device' to get the actual name of the device which might not been created and it is in its path of creation.

To fix this, suppress sending uevent till the failing device symbolic link gets created and send uevent once symbolic link is created successfully.

Fixes: 833c95456a70 ("device coredump: add new device coredump class") Signed-off-by: Mukesh Ojha quic_mojha@quicinc.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/1700232572-25823-1-git-send-email-quic_mojha@quici... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/base/devcoredump.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/base/devcoredump.c b/drivers/base/devcoredump.c index 1ba4af7f2f21f..b13574cdef69b 100644 --- a/drivers/base/devcoredump.c +++ b/drivers/base/devcoredump.c @@ -376,6 +376,7 @@ void dev_coredumpm(struct device *dev, struct module *owner, devcd->devcd_dev.class = &devcd_class;

mutex_lock(&devcd->mutex); + dev_set_uevent_suppress(&devcd->devcd_dev, true); if (device_add(&devcd->devcd_dev)) goto put_device;

@@ -387,6 +388,8 @@ void dev_coredumpm(struct device *dev, struct module *owner, "devcoredump")) /* nothing - symlink will be missing */;

+ dev_set_uevent_suppress(&devcd->devcd_dev, false); + kobject_uevent(&devcd->devcd_dev.kobj, KOBJ_ADD); INIT_DELAYED_WORK(&devcd->del_wk, devcd_del); schedule_delayed_work(&devcd->del_wk, DEVCD_TIMEOUT); mutex_unlock(&devcd->mutex);