ASoC: max98088: fix ni clock divider calculation
Subsystems (14)
Sasha Levin
maintainerPATCH 20/39 cgroup: disable controllers at parse time
In reply to Sasha LevinFrom: Shakeel Butt <[email protected]>
[ Upstream commit 45e1ba40837ac2f6f4d4716bddb8d44bd7e4a251 ]
This patch effectively reverts the commit a3e72739b7a7 ("cgroup: fix too early usage of static_branch_disable()"). The commit 6041186a3258 ("init: initialize jump labels before command line option parsing") has moved the jump_label_init() before parse_args() which has made the commit a3e72739b7a7 unnecessary. On the other hand there are consequences of disabling the controllers later as there are subsystems doing the controller checks for different decisions. One such incident is reported [1] regarding the memory controller and its impact on memory reclaim code.
[1] https://lore.kernel.org/linux-mm/921e53f3-4b13-aab8-4a9e-e83ff15371e4-YMj9X0ASwKA@public.gmane.org
--- kernel/cgroup/cgroup.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-)
kernel/cgroup/cgroup.c +5 -8
@@ -5665,8 +5665,6 @@ int __init cgroup_init_early(void)return 0 ; } -static u16 cgroup_disable_mask__initdata ; -/** * cgroup_init - cgroup initialization *
@@ -5725,12 +5723,8 @@ int __init cgroup_init(void)* disabled flag and cftype registration needs kmalloc, * both of which aren't available during early_init. */ -if (cgroup_disable_mask & (1 << ssid)) { -static_branch_disable (cgroup_subsys_enabled_key[ssid]); -printk (KERN_INFO "Disabling %s control group subsystem\n" , - ss->name); +if (!cgroup_ssid_enabled (ssid))continue ; - }if (cgroup1_ssid_disabled (ssid)) printk(KERN_INFO "Disabling %s control group subsystem in v1 mounts\n",
@@ -6245,7 +6239,10 @@ static int __init cgroup_disable(char *str)if (strcmp (token, ss->name) &&strcmp (token, ss->legacy_name))continue ; - cgroup_disable_mask |=1 << i; + +static_branch_disable (cgroup_subsys_enabled_key[i]); +pr_info ("Disabling %s control group subsystem\n" , + ss->name); } }return 1 ;
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 3/39 spi: Fix spi device unregister flow
In reply to Sasha LevinFrom: Saravana Kannan <[email protected]>
[ Upstream commit c7299fea67696db5bd09d924d1f1080d894f92ef ]
When an SPI device is unregistered, the spi->controller->cleanup() is called in the device's release callback. That's wrong for a couple of reasons:
1. spi_dev_put() can be called before spi_add_device() is called. And it's spi_add_device() that calls spi_setup(). This will cause clean() to get called without the spi device ever being setup.
2. There's no guarantee that the controller's driver would be present by the time the spi device's release function gets called.
3. It also causes "sleeping in atomic context" stack dump[1] when device link deletion code does a put_device() on the spi device.
Fix these issues by simply moving the cleanup from the device release callback to the actual spi_unregister_device() function.
[1] - https://lore.kernel.org/lkml/CAHp75Vc=FCGcUyS0v6fnxme2YJ+qD+Y-hQDQLa2JhWNON9VmsQ@mail.gmail.com/
--- drivers/spi/spi.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-)
drivers/spi/spi.c +12 -6
@@ -47,10 +47,6 @@ static void spidev_release(struct device *dev) {struct spi_device *spi =to_spi_device (dev); -/* spi controllers may cleanup for released devices */ -if (spi->controller->cleanup) - spi->controller->cleanup (spi); -spi_controller_put (spi->controller);kfree (spi->driver_override);kfree (spi);
@@ -550,6 +546,12 @@ static int spi_dev_check(struct device *dev, void *data)return 0 ; } +static void spi_cleanup (struct spi_device *spi) +{ +if (spi->controller->cleanup) + spi->controller->cleanup (spi); +} +/** * spi_add_device - Add spi_device allocated with spi_alloc_device * @spi: spi_device to register
@@ -614,11 +616,13 @@ int spi_add_device(struct spi_device *spi)/* Device may be bound to an active driver when this returns */ status =device_add (&spi->dev); -if (status <0 ) +if (status <0 ) {dev_err (dev,"can't add %s, status %d\n" ,dev_name (&spi->dev), status); -else +spi_cleanup (spi); + }else {dev_dbg (dev,"registered child %s\n" ,dev_name (&spi->dev)); + } done:mutex_unlock (&spi_add_lock);
@@ -705,6 +709,8 @@ void spi_unregister_device(struct spi_device *spi)if (!spi)return ; +spi_cleanup (spi); +if (spi->dev.of_node) {of_node_clear_flag (spi->dev.of_node,OF_POPULATED );of_node_put (spi->dev.of_node);
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 4/39 spi: spi-zynq-qspi: Fix stack violation bug
In reply to Sasha LevinFrom: Karen Dombroski <[email protected]>
[ Upstream commit 6d5ff8e632a4f2389c331e5554cd1c2a9a28c7aa ]
When the number of bytes for the op is greater than one, the read could run off the end of the function stack and cause a crash.
This patch restores the behaviour of safely reading out of the original opcode location.
--- drivers/spi/spi-zynq-qspi.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-)
drivers/spi/spi-zynq-qspi.c +3 -4
@@ -528,18 +528,17 @@ static int zynq_qspi_exec_mem_op(struct spi_mem *mem,struct zynq_qspi *xqspi =spi_controller_get_devdata (mem->spi->master);int err =0 , i;u8 *tmpbuf; -u8 opcode = op->cmd.opcode;dev_dbg (xqspi->dev,"cmd:%#x mode:%d.%d.%d.%d\n" , - opcode, op->cmd.buswidth, op->addr.buswidth, + op->cmd.opcode, op->cmd.buswidth, op->addr.buswidth, op->dummy.buswidth, op->data.buswidth);zynq_qspi_chipselect (mem->spi, true);zynq_qspi_config_op (xqspi, mem->spi); -if (op->cmd.nbytes) { +if (op->cmd.opcode) {reinit_completion (&xqspi->data_completion); - xqspi->txbuf = &opcode; + xqspi->txbuf = (u8 *)&op->cmd.opcode; xqspi->rxbuf =NULL ; xqspi->tx_bytes = op->cmd.nbytes; xqspi->rx_bytes = op->cmd.nbytes;
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 2/39 ASoC: amd: fix for pcm_read() error
In reply to Sasha LevinFrom: Vijendar Mukunda <[email protected]>
[ Upstream commit 6879e8e759bf9e05eaee85e32ca1a936e6b46da1 ]
Below phython script throwing pcm_read() error.
import subprocess
p = subprocess.Popen(["aplay -t raw -D plughw:1,0 /dev/zero"], shell=True) subprocess.call(["arecord -Dhw:1,0 --dump-hw-params"], shell=True) subprocess.call(["arecord -Dhw:1,0 -fdat -d1 /dev/null"], shell=True) p.kill()
Handling ACP global external interrupt enable register causing this issue.
This register got updated wrongly when there is active stream causing interrupts disabled for active stream. Refactored code to handle enabling and disabling external interrupts.
--- sound/soc/amd/raven/acp3x-pcm-dma.c | 10 ---------- sound/soc/amd/raven/acp3x.h | 1 + sound/soc/amd/raven/pci-acp3x.c | 15 +++++++++++++++ 3 files changed, 16 insertions(+), 10 deletions(-)
sound/soc/amd/raven/acp3x-pcm-dma.c +0 -10
@@ -237,10 +237,6 @@ static int acp3x_dma_open(struct snd_soc_component *component,return ret; } -if (!adata->play_stream && !adata->capture_stream && - !adata->i2ssp_play_stream && !adata->i2ssp_capture_stream) -rv_writel (1 , adata->acp3x_base + mmACP_EXTERNAL_INTR_ENB); - i2s_data->acp3x_base = adata->acp3x_base; runtime->private_data = i2s_data;return ret;
@@ -367,12 +363,6 @@ static int acp3x_dma_close(struct snd_soc_component *component, } } -/* Disable ACP irq, when the current stream is being closed and -* another stream is also not active. -*/ -if (!adata->play_stream && !adata->capture_stream && - !adata->i2ssp_play_stream && !adata->i2ssp_capture_stream) -rv_writel (0 , adata->acp3x_base + mmACP_EXTERNAL_INTR_ENB);return 0 ; }
sound/soc/amd/raven/acp3x.h +1 -0
@@ -77,6 +77,7 @@#define ACP_POWER_OFF_IN_PROGRESS 0x03#define ACP3x_ITER_IRER_SAMP_LEN_MASK 0x38 +#define ACP_EXT_INTR_STAT_CLEAR_MASK 0xFFFFFFFFstruct acp3x_platform_info {u16 play_i2s_instance;
sound/soc/amd/raven/pci-acp3x.c +15 -0
@@ -76,6 +76,19 @@ static int acp3x_reset(void __iomem *acp3x_base)return -ETIMEDOUT ; } +static void acp3x_enable_interrupts (void __iomem *acp_base) +{ +rv_writel (0x01 , acp_base + mmACP_EXTERNAL_INTR_ENB); +} + +static void acp3x_disable_interrupts (void __iomem *acp_base) +{ +rv_writel (ACP_EXT_INTR_STAT_CLEAR_MASK , acp_base + + mmACP_EXTERNAL_INTR_STAT); +rv_writel (0x00 , acp_base + mmACP_EXTERNAL_INTR_CNTL); +rv_writel (0x00 , acp_base + mmACP_EXTERNAL_INTR_ENB); +} +static int acp3x_init (struct acp3x_dev_data *adata) {void __iomem *acp3x_base = adata->acp3x_base;
@@ -93,6 +106,7 @@ static int acp3x_init(struct acp3x_dev_data *adata)pr_err ("ACP3x reset failed\n" );return ret; } +acp3x_enable_interrupts (acp3x_base);return 0 ; }
@@ -100,6 +114,7 @@ static int acp3x_deinit(void __iomem *acp3x_base) {int ret; +acp3x_disable_interrupts (acp3x_base);/* Reset */ ret =acp3x_reset (acp3x_base);if (ret) {
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 5/39 bpf: Forbid trampoline attach for functions with variable arguments
In reply to Sasha LevinFrom: Jiri Olsa <[email protected]>
[ Upstream commit 31379397dcc364a59ce764fabb131b645c43e340 ]
We can't currently allow to attach functions with variable arguments. The problem is that we should save all the registers for arguments, which is probably doable, but if caller uses more than 6 arguments, we need stack data, which will be wrong, because of the extra stack frame we do in bpf trampoline, so we could crash.
Also currently there's malformed trampoline code generated for such functions at the moment as described in:
https://lore.kernel.org/bpf/[email protected]/
--- kernel/bpf/btf.c | 12 ++++++++++++ 1 file changed, 12 insertions(+)
kernel/bpf/btf.c +12 -0
@@ -4960,6 +4960,12 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, m->ret_size = ret;for (i =0 ; i < nargs; i++) { +if (i == nargs -1 && args[i].type ==0 ) { +bpf_log (log, +"The function %s with variable args is unsupported.\n" , + tname); +return -EINVAL ; + } ret =__get_type_size (btf, args[i].type, &t);if (ret <0 ) { bpf_log(log,
@@ -4967,6 +4973,12 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, tname, i, btf_kind_str[BTF_INFO_KIND(t->info)]);return -EINVAL ; } +if (ret ==0 ) { +bpf_log (log, +"The function %s has malformed void argument.\n" , + tname); +return -EINVAL ; + } m->arg_size[i] = ret; } m->nr_args = nargs;
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 1/39 ASoC: max98088: fix ni clock divider calculation
From: Marco Felsch <[email protected]>
[ Upstream commit 6c9762a78c325107dc37d20ee21002b841679209 ]
The ni1/ni2 ratio formula [1] uses the pclk which is the prescaled mclk. The max98088 datasheet [2] has no such formula but table-12 equals so we can assume that it is the same for both devices.
While on it make use of DIV_ROUND_CLOSEST_ULL().
[1] https://datasheets.maximintegrated.com/en/ds/MAX98089.pdf; page 86
[2] https://datasheets.maximintegrated.com/en/ds/MAX98088.pdf; page 82
--- sound/soc/codecs/max98088.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-)
sound/soc/codecs/max98088.c +11 -2
@@ -41,6 +41,7 @@ struct max98088_priv {enum max98088_type devtype;struct max98088_pdata *pdata;struct clk *mclk; +unsigned char mclk_prescaler;unsigned int sysclk;struct max98088_cdata dai[2 ];int eq_textcnt;
@@ -998,13 +999,16 @@ static int max98088_dai1_hw_params(struct snd_pcm_substream *substream,/* Configure NI when operating as master */ if (snd_soc_component_read (component,M98088_REG_14_DAI1_FORMAT ) &M98088_DAI_MAS ) { +unsigned long pclk; +if (max98088->sysclk ==0 ) {dev_err (component->dev,"Invalid system clock frequency\n" );return -EINVAL ; } ni =65536ULL * (rate <50000 ?96ULL :48ULL ) * (unsigned long long int )rate; -do_div (ni, (unsigned long long int )max98088->sysclk); + pclk =DIV_ROUND_CLOSEST (max98088->sysclk, max98088->mclk_prescaler); + ni =DIV_ROUND_CLOSEST_ULL (ni, pclk);snd_soc_component_write (component,M98088_REG_12_DAI1_CLKCFG_HI , (ni >>8 ) &0x7F ); snd_soc_component_write(component, M98088_REG_13_DAI1_CLKCFG_LO,
@@ -1065,13 +1069,16 @@ static int max98088_dai2_hw_params(struct snd_pcm_substream *substream,/* Configure NI when operating as master */ if (snd_soc_component_read (component,M98088_REG_1C_DAI2_FORMAT ) &M98088_DAI_MAS ) { +unsigned long pclk; +if (max98088->sysclk ==0 ) {dev_err (component->dev,"Invalid system clock frequency\n" );return -EINVAL ; } ni =65536ULL * (rate <50000 ?96ULL :48ULL ) * (unsigned long long int )rate; -do_div (ni, (unsigned long long int )max98088->sysclk); + pclk =DIV_ROUND_CLOSEST (max98088->sysclk, max98088->mclk_prescaler); + ni =DIV_ROUND_CLOSEST_ULL (ni, pclk);snd_soc_component_write (component,M98088_REG_1A_DAI2_CLKCFG_HI , (ni >>8 ) &0x7F ); snd_soc_component_write(component, M98088_REG_1B_DAI2_CLKCFG_LO,
@@ -1113,8 +1120,10 @@ static int max98088_dai_set_sysclk(struct snd_soc_dai *dai,*/ if ((freq >=10000000 ) && (freq <20000000 )) {snd_soc_component_write (component,M98088_REG_10_SYS_CLK ,0x10 ); + max98088->mclk_prescaler =1 ; }else if ((freq >=20000000 ) && (freq <30000000 )) {snd_soc_component_write (component,M98088_REG_10_SYS_CLK ,0x20 ); + max98088->mclk_prescaler =2 ; }else {dev_err (component->dev,"Invalid master clock frequency\n" );return -EINVAL ;
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 7/39 usb: cdns3: Fix runtime PM imbalance on error
From: Dinghao Liu <[email protected]>
[ Upstream commit 07adc0225484fc199e3dc15ec889f75f498c4fca ]
When cdns3_gadget_start() fails, a pairing PM usage counter decrement is needed to keep the counter balanced.
--- drivers/usb/cdns3/gadget.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/usb/cdns3/gadget.c +3 -1
@@ -3255,8 +3255,10 @@ static int __cdns3_gadget_init(struct cdns3 *cdns)pm_runtime_get_sync (cdns->dev); ret =cdns3_gadget_start (cdns); -if (ret) +if (ret) { +pm_runtime_put_sync (cdns->dev);return ret; + }/* * Because interrupt line can be shared with other components in
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 6/39 net/nfc/rawsock.c: fix a permission check bug
In reply to Sasha LevinFrom: Jeimon <[email protected]>
[ Upstream commit 8ab78863e9eff11910e1ac8bcf478060c29b379e ]
The function rawsock_create() calls a privileged function sk_alloc(), which requires a ns-aware check to check net->user_ns, i.e., ns_capable(). However, the original code checks the init_user_ns using capable(). So we replace the capable() with ns_capable().
--- net/nfc/rawsock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/nfc/rawsock.c +1 -1
@@ -329,7 +329,7 @@ static int rawsock_create(struct net *net, struct socket *sock,return -ESOCKTNOSUPPORT ;if (sock->type ==SOCK_RAW ) { -if (!capable (CAP_NET_RAW )) +if (!ns_capable (net->user_ns,CAP_NET_RAW ))return -EPERM ; sock->ops = &rawsock_raw_ops; }else {
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 8/39 ASoC: Intel: bytcr_rt5640: Add quirk for the Glavey TM800A550L tablet
In reply to Sasha LevinFrom: Hans de Goede <[email protected]>
[ Upstream commit 28c268d3acdd4cbcd2ac320b85609e77f84e74a7 ]
Add a quirk for the Glavey TM800A550L tablet, this BYTCR tablet has no CHAN package in its ACPI tables and uses SSP0-AIF1 rather then SSP0-AIF2 which is the default for BYTCR devices.
--- sound/soc/intel/boards/bytcr_rt5640.c | 11 +++++++++++ 1 file changed, 11 insertions(+)
sound/soc/intel/boards/bytcr_rt5640.c +11 -0
@@ -570,6 +570,17 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {BYT_RT5640_SSP0_AIF1 | BYT_RT5640_MCLK_EN), }, + { /* Glavey TM800A550L */ + .matches = { +DMI_MATCH (DMI_BOARD_VENDOR ,"AMI Corporation" ), +DMI_MATCH (DMI_BOARD_NAME ,"Aptio CRB" ), +/* Above strings are too generic, also match on BIOS version */ + DMI_MATCH(DMI_BIOS_VERSION, "ZY-8-BI-PX4S70VTR400-X423B-005-D"), + }, + .driver_data = (void *)(BYTCR_INPUT_DEFAULTS | +BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, { .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 10/39 bpf: Add deny list of btf ids check for tracing programs
In reply to Sasha LevinFrom: Jiri Olsa <[email protected]>
[ Upstream commit 35e3815fa8102fab4dee75f3547472c66581125d ]
The recursion check in __bpf_prog_enter and __bpf_prog_exit leaves some (not inlined) functions unprotected:
In __bpf_prog_enter:
- migrate_disable is called before prog->active is checked
In __bpf_prog_exit:
- migrate_enable,rcu_read_unlock_strict are called after
prog->active is decreased
When attaching trampoline to them we get panic like:
traps: PANIC: double fault, error_code: 0x0 double fault: 0000 [#1] SMP PTI
RIP: 0010:__bpf_prog_enter+0x4/0x50 ... Call Trace: <IRQ> bpf_trampoline_6442466513_0+0x18/0x1000 migrate_disable+0x5/0x50 __bpf_prog_enter+0x9/0x50 bpf_trampoline_6442466513_0+0x18/0x1000 migrate_disable+0x5/0x50 __bpf_prog_enter+0x9/0x50 bpf_trampoline_6442466513_0+0x18/0x1000 migrate_disable+0x5/0x50 __bpf_prog_enter+0x9/0x50 bpf_trampoline_6442466513_0+0x18/0x1000 migrate_disable+0x5/0x50 ...
Fixing this by adding deny list of btf ids for tracing programs and checking btf id during program verification. Adding above functions to this list.
--- kernel/bpf/verifier.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)
kernel/bpf/verifier.c +14 -0
@@ -12206,6 +12206,17 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,return 0 ; } +BTF_SET_START (btf_id_deny) +BTF_ID_UNUSED +#ifdef CONFIG_SMP +BTF_ID(func, migrate_disable) +BTF_ID(func, migrate_enable) +#endif +#if !definedCONFIG_PREEMPT_RCU && !definedCONFIG_TINY_RCU +BTF_ID(func, rcu_read_unlock_strict) +#endif +BTF_SET_END (btf_id_deny) + static int check_attach_btf_id(struct bpf_verifier_env *env) {struct bpf_prog *prog = env->prog;
@@ -12265,6 +12276,9 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) ret =bpf_lsm_verify_prog (&env->log, prog);if (ret <0 )return ret; + }else if (prog->type ==BPF_PROG_TYPE_TRACING && +btf_id_set_contains (&btf_id_deny, btf_id)) { +return -EINVAL ; } key =bpf_trampoline_compute_key (tgt_prog, btf_id);
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 9/39 ASoC: Intel: bytcr_rt5640: Add quirk for the Lenovo Miix 3-830 tablet
In reply to Sasha LevinFrom: Hans de Goede <[email protected]>
[ Upstream commit f0353e1f53f92f7b3da91e6669f5d58ee222ebe8 ]
The Lenovo Miix 3-830 tablet has only 1 speaker, has an internal analog mic on IN1 and uses JD2 for jack-detect, add a quirk to automatically apply these settings on Lenovo Miix 3-830 tablets.
--- sound/soc/intel/boards/bytcr_rt5640.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)
sound/soc/intel/boards/bytcr_rt5640.c +14 -0
@@ -659,6 +659,20 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {BYT_RT5640_MONO_SPEAKER | BYT_RT5640_MCLK_EN), }, + { /* Lenovo Miix 3-830 */ + .matches = { +DMI_EXACT_MATCH (DMI_SYS_VENDOR ,"LENOVO" ), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Lenovo MIIX 3-830"), + }, + .driver_data = (void *)(BYT_RT5640_IN1_MAP | +BYT_RT5640_JD_SRC_JD2_IN4N | +BYT_RT5640_OVCD_TH_2000UA | +BYT_RT5640_OVCD_SF_0P75 | +BYT_RT5640_MONO_SPEAKER | +BYT_RT5640_DIFF_MIC | +BYT_RT5640_SSP0_AIF1 | + BYT_RT5640_MCLK_EN), + }, { /* Linx Linx7 tablet */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LINX"),
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 11/39 vfio-ccw: Reset FSM state to IDLE inside FSM
In reply to Sasha LevinFrom: Eric Farman <[email protected]>
[ Upstream commit 6c02ac4c9211edabe17bda437ac97e578756f31b ]
When an I/O request is made, the fsm_io_request() routine moves the FSM state from IDLE to CP_PROCESSING, and then fsm_io_helper() moves it to CP_PENDING if the START SUBCHANNEL received a cc0. Yet, the error case to go from CP_PROCESSING back to IDLE is done after the FSM call returns.
Let's move this up into the FSM proper, to provide some better symmetry when unwinding in this case.
Message-Id: <[email protected]>
--- drivers/s390/cio/vfio_ccw_fsm.c | 1 + drivers/s390/cio/vfio_ccw_ops.c | 2 -- 2 files changed, 1 insertion(+), 2 deletions(-)
drivers/s390/cio/vfio_ccw_fsm.c +1 -0
@@ -318,6 +318,7 @@ static void fsm_io_request(struct vfio_ccw_private *private, } err_out: + private->state =VFIO_CCW_STATE_IDLE ;trace_vfio_ccw_fsm_io_request (scsw->cmd.fctl, schid, io_region->ret_code, errstr); }
drivers/s390/cio/vfio_ccw_ops.c +0 -2
@@ -276,8 +276,6 @@ static ssize_t vfio_ccw_mdev_write_io_region(struct vfio_ccw_private *private, }vfio_ccw_fsm_event (private,VFIO_CCW_EVENT_IO_REQ ); -if (region->ret_code !=0 ) - private->state =VFIO_CCW_STATE_IDLE ; ret = (region->ret_code !=0 ) ? region->ret_code : count; out_unlock:
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 14/39 spi: sprd: Add missing MODULE_DEVICE_TABLE
In reply to Sasha LevinFrom: Chunyan Zhang <[email protected]>
[ Upstream commit 7907cad7d07e0055789ec0c534452f19dfe1fc80 ]
MODULE_DEVICE_TABLE is used to extract the device information out of the driver and builds a table when being compiled. If using this macro, kernel can find the driver if available when the device is plugged in, and then loads that driver and initializes the device.
--- drivers/spi/spi-sprd.c | 1 + 1 file changed, 1 insertion(+)
drivers/spi/spi-sprd.c +1 -0
@@ -1068,6 +1068,7 @@ static const struct of_device_id sprd_spi_of_match[] = { { .compatible = "sprd,sc9860-spi", }, {/* sentinel */ } }; +MODULE_DEVICE_TABLE (of, sprd_spi_of_match);static struct platform_driver sprd_spi_driver = { .driver = {
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 22/39 net/qla3xxx: fix schedule while atomic in ql_sem_spinlock
In reply to Sasha LevinFrom: Zheyu Ma <[email protected]>
[ Upstream commit 13a6f3153922391e90036ba2267d34eed63196fc ]
When calling the 'ql_sem_spinlock', the driver has already acquired the spin lock, so the driver should not call 'ssleep' in atomic context.
This bug can be fixed by using 'mdelay' instead of 'ssleep'.
The KASAN's log reveals it:
[ 3.238124 ] BUG: scheduling while atomic: swapper/0/1/0x00000002
[ 3.238748 ] 2 locks held by swapper/0/1:
[ 3.239151 ] #0: ffff88810177b240 (&dev->mutex){....}-{3:3}, at:
__device_driver_lock+0x41/0x60
[ 3.240026 ] #1: ffff888107c60e28 (&qdev->hw_lock){....}-{2:2}, at:
ql3xxx_probe+0x2aa/0xea0
[ 3.240873 ] Modules linked in:
[ 3.241187 ] irq event stamp: 460854
[ 3.241541 ] hardirqs last enabled at (460853): [<ffffffff843051bf>]_raw_spin_unlock_irqrestore+0x4f/0x70
[ 3.242245 ] hardirqs last disabled at (460854): [<ffffffff843058ca>]_raw_spin_lock_irqsave+0x2a/0x70
[ 3.242245 ] softirqs last enabled at (446076): [<ffffffff846002e4>]__do_softirq+0x2e4/0x4b1
[ 3.242245 ] softirqs last disabled at (446069): [<ffffffff811ba5e0>]irq_exit_rcu+0x100/0x110
[ 3.242245 ] Preemption disabled at: [ 3.242245 ] [<ffffffff828ca5ba>] ql3xxx_probe+0x2aa/0xea0 [ 3.242245 ] Kernel panic - not syncing: scheduling while atomic [ 3.242245 ] CPU: 2 PID: 1 Comm: swapper/0 Not tainted 5.13.0-rc1-00145 -gee7dc339169-dirty #16 [ 3.242245 ] Call Trace: [ 3.242245 ] dump_stack+0xba/0xf5 [ 3.242245 ] ? ql3xxx_probe+0x1f0/0xea0 [ 3.242245 ] panic+0x15a/0x3f2 [ 3.242245 ] ? vprintk+0x76/0x150 [ 3.242245 ] ? ql3xxx_probe+0x2aa/0xea0 [ 3.242245 ] __schedule_bug+0xae/0xe0 [ 3.242245 ] __schedule+0x72e/0xa00 [ 3.242245 ] schedule+0x43/0xf0 [ 3.242245 ] schedule_timeout+0x28b/0x500 [ 3.242245 ] ? del_timer_sync+0xf0/0xf0 [ 3.242245 ] ? msleep+0x2f/0x70 [ 3.242245 ] msleep+0x59/0x70 [ 3.242245 ] ql3xxx_probe+0x307/0xea0 [ 3.242245 ] ? _raw_spin_unlock_irqrestore+0x3a/0x70 [ 3.242245 ] ? pci_device_remove+0x110/0x110 [ 3.242245 ] local_pci_probe+0x45/0xa0 [ 3.242245 ] pci_device_probe+0x12b/0x1d0 [ 3.242245 ] really_probe+0x2a9/0x610 [ 3.242245 ] driver_probe_device+0x90/0x1d0 [ 3.242245 ] ? mutex_lock_nested+0x1b/0x20 [ 3.242245 ] device_driver_attach+0x68/0x70 [ 3.242245 ] __driver_attach+0x124/0x1b0 [ 3.242245 ] ? device_driver_attach+0x70/0x70 [ 3.242245 ] bus_for_each_dev+0xbb/0x110 [ 3.242245 ] ? rdinit_setup+0x45/0x45 [ 3.242245 ] driver_attach+0x27/0x30 [ 3.242245 ] bus_add_driver+0x1eb/0x2a0 [ 3.242245 ] driver_register+0xa9/0x180 [ 3.242245 ] __pci_register_driver+0x82/0x90 [ 3.242245 ] ? yellowfin_init+0x25/0x25 [ 3.242245 ] ql3xxx_driver_init+0x23/0x25 [ 3.242245 ] do_one_initcall+0x7f/0x3d0 [ 3.242245 ] ? rdinit_setup+0x45/0x45 [ 3.242245 ] ? rcu_read_lock_sched_held+0x4f/0x80 [ 3.242245 ] kernel_init_freeable+0x2aa/0x301 [ 3.242245 ] ? rest_init+0x2c0/0x2c0 [ 3.242245 ] kernel_init+0x18/0x190 [ 3.242245 ] ? rest_init+0x2c0/0x2c0 [ 3.242245 ] ? rest_init+0x2c0/0x2c0 [ 3.242245 ] ret_from_fork+0x1f/0x30 [ 3.242245 ] Dumping ftrace buffer: [ 3.242245 ] (ftrace buffer empty) [ 3.242245 ] Kernel Offset: disabled [ 3.242245 ] Rebooting in 1 seconds.
--- drivers/net/ethernet/qlogic/qla3xxx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/qlogic/qla3xxx.c +1 -1
@@ -114,7 +114,7 @@ static int ql_sem_spinlock(struct ql3_adapter *qdev, value =readl (&port_regs->CommonRegs.semaphoreReg);if ((value & (sem_mask >>16 )) == sem_bits)return 0 ; -ssleep (1 ); +mdelay (1000 ); }while (--seconds);return -1 ; }
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 21/39 wq: handle VM suspension in stall detection
In reply to Sasha LevinFrom: Sergey Senozhatsky <[email protected]>
[ Upstream commit 940d71c6462e8151c78f28e4919aa8882ff2054e ]
If VCPU is suspended (VM suspend) in wq_watchdog_timer_fn() then once this VCPU resumes it will see the new jiffies value, while it may take a while before IRQ detects PVCLOCK_GUEST_STOPPED on this VCPU and updates all the watchdogs via pvclock_touch_watchdogs(). There is a small chance of misreported WQ stalls in the meantime, because new jiffies is time_after() old 'ts + thresh'.
wq_watchdog_timer_fn()
{
for_each_pool(pool, pi) {
if (time_after(jiffies, ts + thresh)) {
pr_emerg("BUG: workqueue lockup - pool");
}
}
}Save jiffies at the beginning of this function and use that value for stall detection. If VM gets suspended then we continue using "old" jiffies value and old WQ touch timestamps. If IRQ at some point restarts the stall detection cycle (pvclock_touch_watchdogs()) then old jiffies will always be before new 'ts + thresh'.
--- kernel/workqueue.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-)
kernel/workqueue.c +10 -2
@@ -50,6 +50,7 @@#include <linux/uaccess.h> #include <linux/sched/isolation.h> #include <linux/nmi.h> +#include <linux/kvm_para.h> #include "workqueue_internal.h"
@@ -5758,6 +5759,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) {unsigned long thresh =READ_ONCE (wq_watchdog_thresh) *HZ ;bool lockup_detected = false; +unsigned long now = jiffies;struct worker_pool *pool;int pi;
@@ -5772,6 +5774,12 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)if (list_empty (&pool->worklist))continue ; +/* +* If a virtual machine is stopped by the host it can look to +* the watchdog like a stall. +*/ +kvm_check_and_clear_guest_paused (); +/* get the latest of pool and touched timestamps */ pool_ts =READ_ONCE (pool->watchdog_ts); touched =READ_ONCE (wq_watchdog_touched);
@@ -5790,12 +5798,12 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) }/* did we stall? */ -if (time_after (jiffies, ts + thresh)) { +if (time_after (now, ts + thresh)) { lockup_detected = true;pr_emerg ("BUG: workqueue lockup - pool" );pr_cont_pool_info (pool);pr_cont (" stuck for %us!\n" , -jiffies_to_msecs (jiffies - pool_ts) /1000 ); +jiffies_to_msecs (now - pool_ts) /1000 ); } }
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 23/39 RDS tcp loopback connection can hang
In reply to Sasha LevinFrom: Rao Shoaib <[email protected]>
[ Upstream commit aced3ce57cd37b5ca332bcacd370d01f5a8c5371 ]
When TCP is used as transport and a program on the system connects to RDS port 16385, connection is accepted but denied per the rules of RDS. However, RDS connections object is left in the list. Next loopback connection will select that connection object as it is at the head of list. The connection attempt will hang as the connection object is set to connect over TCP which is not allowed
The issue can be reproduced easily, use rds-ping to ping a local IP address. After that use any program like ncat to connect to the same IP address and port 16385. This will hang so ctrl-c out. Now try rds-ping, it will hang.
To fix the issue this patch adds checks to disallow the connection object creation and destroys the connection object.
--- net/rds/connection.c | 23 +++++++++++++++++------ net/rds/tcp.c | 4 ++-- net/rds/tcp.h | 3 ++- net/rds/tcp_listen.c | 6 ++++++ 4 files changed, 27 insertions(+), 9 deletions(-)
net/rds/connection.c +17 -6
@@ -240,12 +240,23 @@ static struct rds_connection *__rds_conn_create(struct net *net,if (loop_trans) {rds_trans_put (loop_trans); conn->c_loopback =1 ; -if (is_outgoing && trans->t_prefer_loopback) { -/* "outgoing" connection - and the transport -* says it wants the connection handled by the -* loopback transport. This is what TCP does. -*/ - trans = &rds_loop_transport; +if (trans->t_prefer_loopback) { +if (likely (is_outgoing)) { +/* "outgoing" connection to local address. +* Protocol says it wants the connection +* handled by the loopback transport. +* This is what TCP does. +*/ + trans = &rds_loop_transport; + }else { +/* No transport currently in use +* should end up here, but if it +* does, reset/destroy the connection. +*/ +kmem_cache_free (rds_conn_slab, conn); + conn =ERR_PTR (-EOPNOTSUPP ); + goto out; + } } }
net/rds/tcp.c +2 -2
@@ -313,8 +313,8 @@ static void rds6_tcp_tc_info(struct socket *sock, unsigned int len, }#endif -static int rds_tcp_laddr_check (struct net *net,const struct in6_addr *addr, -__u32 scope_id) +int rds_tcp_laddr_check (struct net *net,const struct in6_addr *addr, +__u32 scope_id) {struct net_device *dev =NULL ;#if IS_ENABLED (CONFIG_IPV6 )
net/rds/tcp.h +2 -1
@@ -59,7 +59,8 @@ u32 rds_tcp_snd_una(struct rds_tcp_connection *tc);u64 rds_tcp_map_seq (struct rds_tcp_connection *tc,u32 seq);extern struct rds_transport rds_tcp_transport;void rds_tcp_accept_work (struct sock *sk); - +int rds_tcp_laddr_check (struct net *net,const struct in6_addr *addr, +__u32 scope_id);/* tcp_connect.c */ int rds_tcp_conn_path_connect (struct rds_conn_path *cp);void rds_tcp_conn_path_shutdown (struct rds_conn_path *conn);
net/rds/tcp_listen.c +6 -0
@@ -167,6 +167,12 @@ int rds_tcp_accept_one(struct socket *sock) }#endif +if (!rds_tcp_laddr_check (sock_net (sock->sk), peer_addr, dev_if)) { +/* local address connection is only allowed via loopback */ + ret = -EOPNOTSUPP ; + goto out; + } + conn =rds_conn_create (sock_net (sock->sk), my_addr, peer_addr, &rds_tcp_transport,0 ,GFP_KERNEL , dev_if);
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 19/39 net: mdiobus: get rid of a BUG_ON()
In reply to Sasha LevinFrom: Dan Carpenter <[email protected]>
[ Upstream commit 1dde47a66d4fb181830d6fa000e5ea86907b639e ]
We spotted a bug recently during a review where a driver was unregistering a bus that wasn't registered, which would trigger this BUG_ON(). Let's handle that situation more gracefully, and just print a warning and return.
--- drivers/net/phy/mdio_bus.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/phy/mdio_bus.c +2 -1
@@ -608,7 +608,8 @@ void mdiobus_unregister(struct mii_bus *bus)struct mdio_device *mdiodev;int i; -BUG_ON (bus->state !=MDIOBUS_REGISTERED ); +if (WARN_ON_ONCE (bus->state !=MDIOBUS_REGISTERED )) +return ; bus->state =MDIOBUS_UNREGISTERED ;for (i =0 ; i <PHY_MAX_ADDR ; i++) {
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 25/39 scsi: bnx2fc: Return failure if io_req is already in ABTS processing
In reply to Sasha LevinFrom: Javed Hasan <[email protected]>
[ Upstream commit 122c81c563b0c1c6b15ff76a9159af5ee1f21563 ]
Return failure from bnx2fc_eh_abort() if io_req is already in ABTS processing.
--- drivers/scsi/bnx2fc/bnx2fc_io.c | 1 + 1 file changed, 1 insertion(+)
drivers/scsi/bnx2fc/bnx2fc_io.c +1 -0
@@ -1220,6 +1220,7 @@ int bnx2fc_eh_abort(struct scsi_cmnd *sc_cmd)was a result from the ABTS request rather than the CLEANUP request */ set_bit (BNX2FC_FLAG_IO_CLEANUP , &io_req->req_flags); + rc =FAILED ; goto done; }
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 18/39 netlink: disable IRQs for netlink_lock_table()
In reply to Sasha LevinFrom: Johannes Berg <[email protected]>
[ Upstream commit 1d482e666b8e74c7555dbdfbfb77205eeed3ff2d ]
Syzbot reports that in mac80211 we have a potential deadlock between our "local->stop_queue_reasons_lock" (spinlock) and netlink's nl_table_lock (rwlock). This is because there's at least one situation in which we might try to send a netlink message with this spinlock held while it is also possible to take the spinlock from a hardirq context, resulting in the following deadlock scenario reported by lockdep:
CPU0 CPU1
---- ----
lock(nl_table_lock);
local_irq_disable();
lock(&local->queue_stop_reason_lock);
lock(nl_table_lock);
<Interrupt>
lock(&local->queue_stop_reason_lock);This seems valid, we can take the queue_stop_reason_lock in any kind of context ("CPU0"), and call ieee80211_report_ack_skb() with the spinlock held and IRQs disabled ("CPU1") in some code path (ieee80211_do_stop() via ieee80211_free_txskb()).
Short of disallowing netlink use in scenarios like these (which would be rather complex in mac80211's case due to the deep callchain), it seems the only fix for this is to disable IRQs while nl_table_lock is held to avoid hitting this scenario, this disallows the "CPU0" portion of the reported deadlock.
Note that the writer side (netlink_table_grab()) already disables IRQs for this lock.
Unfortunately though, this seems like a huge hammer, and maybe the whole netlink table locking should be reworked.
--- net/netlink/af_netlink.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
net/netlink/af_netlink.c +4 -2
@@ -453,11 +453,13 @@ void netlink_table_ungrab(void)static inline void netlink_lock_table (void ) { +unsigned long flags; +/* read_lock() synchronizes us to netlink_table_grab */ -read_lock (&nl_table_lock); +read_lock_irqsave (&nl_table_lock, flags);atomic_inc (&nl_table_users); -read_unlock (&nl_table_lock); +read_unlock_irqrestore (&nl_table_lock, flags); } static inline void
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 24/39 net:sfc: fix non-freed irq in legacy irq mode
In reply to Sasha LevinFrom: Íñigo Huguet <[email protected]>
[ Upstream commit 8f03eeb6e0a0a0b8d617ee0a4bce729e47130036 ]
SFC driver can be configured via modparam to work using MSI-X, MSI or legacy IRQ interrupts. In the last one, the interrupt was not properly released on module remove.
It was not freed because the flag irqs_hooked was not set during initialization in the case of using legacy IRQ.
Example of (trimmed) trace during module remove without this fix:
remove_proc_entry: removing non-empty directory 'irq/125', leaking at least '0000:3b:00.1'
WARNING: CPU: 39 PID: 3658 at fs/proc/generic.c:715 remove_proc_entry+0x15c/0x170 ...trimmed... Call Trace: unregister_irq_proc+0xe3/0x100 free_desc+0x29/0x70 irq_free_descs+0x47/0x70 mp_unmap_irq+0x58/0x60 acpi_unregister_gsi_ioapic+0x2a/0x40 acpi_pci_irq_disable+0x78/0xb0 pci_disable_device+0xd1/0x100 efx_pci_remove+0xa1/0x1e0 [sfc] pci_device_remove+0x38/0xa0 __device_release_driver+0x177/0x230 driver_detach+0xcb/0x110 bus_remove_driver+0x58/0xd0 pci_unregister_driver+0x2a/0xb0 efx_exit_module+0x24/0xf40 [sfc] __do_sys_delete_module.constprop.0+0x171/0x280 ? exit_to_user_mode_prepare+0x83/0x1d0 do_syscall_64+0x3d/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f9f9385800b
...trimmed...
--- drivers/net/ethernet/sfc/nic.c | 1 + 1 file changed, 1 insertion(+)
drivers/net/ethernet/sfc/nic.c +1 -0
@@ -90,6 +90,7 @@ int efx_nic_init_interrupt(struct efx_nic *efx) efx->pci_dev->irq); goto fail1; } + efx->irqs_hooked = true;return 0 ; }
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 31/39 net: dsa: microchip: enable phy errata workaround on 9567
In reply to Sasha LevinFrom: George McCollister <[email protected]>
[ Upstream commit 8c42a49738f16af0061f9ae5c2f5a955f268d9e3 ]
Also enable phy errata workaround on 9567 since has the same errata as the 9477 according to the manufacture's documentation.
--- drivers/net/dsa/microchip/ksz9477.c | 1 + 1 file changed, 1 insertion(+)
drivers/net/dsa/microchip/ksz9477.c +1 -0
@@ -1532,6 +1532,7 @@ static const struct ksz_chip_data ksz9477_switch_chips[] = { .num_statics = 16, .cpu_ports = 0x7F, /* can be configured as cpu port */ .port_cnt = 7, /* total physical port count */ + .phy_errata_9477 = true, }, };
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 30/39 net: appletalk: cops: Fix data race in cops_probe1
In reply to Sasha LevinFrom: Saubhik Mukherjee <[email protected]>
[ Upstream commit a4dd4fc6105e54393d637450a11d4cddb5fabc4f ]
In cops_probe1(), there is a write to dev->base_addr after requesting an interrupt line and registering the interrupt handler cops_interrupt(). The handler might be called in parallel to handle an interrupt. cops_interrupt() tries to read dev->base_addr leading to a potential data race. So write to dev->base_addr before calling request_irq().
Found by Linux Driver Verification project (linuxtesting.org).
--- drivers/net/appletalk/cops.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/net/appletalk/cops.c +2 -2
@@ -327,6 +327,8 @@ static int __init cops_probe1(struct net_device *dev, int ioaddr)break ; } + dev->base_addr = ioaddr; +/* Reserve any actual interrupt. */ if (dev->irq) { retval =request_irq (dev->irq, cops_interrupt,0 , dev->name, dev);
@@ -334,8 +336,6 @@ static int __init cops_probe1(struct net_device *dev, int ioaddr) goto err_out; } - dev->base_addr = ioaddr; - lp =netdev_priv (dev);spin_lock_init (&lp->lock);
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 32/39 nvme-fabrics: decode host pathing error for connect
In reply to Sasha LevinFrom: Hannes Reinecke <[email protected]>
[ Upstream commit 4d9442bf263ac45d495bb7ecf75009e59c0622b2 ]
Add an additional decoding for 'host pathing error' during connect.
--- drivers/nvme/host/fabrics.c | 5 +++++ 1 file changed, 5 insertions(+)
drivers/nvme/host/fabrics.c +5 -0
@@ -336,6 +336,11 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl, cmd->connect.recfmt);break ; +case NVME_SC_HOST_PATH_ERROR : +dev_err (ctrl->device, +"Connect command failed: host path error\n" ); +break ; +default : dev_err(ctrl->device, "Connect command failed, error wo/DNR bit: %d\n",
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 28/39 scsi: target: qla2xxx: Wait for stop_phase1 at WWN removal
In reply to Sasha LevinFrom: Dmitry Bogdanov <[email protected]>
[ Upstream commit 2ef7665dfd88830f15415ba007c7c9a46be7acd8 ]
Target de-configuration panics at high CPU load because TPGT and WWPN can be removed on separate threads.
TPGT removal requests a reset HBA on a separate thread and waits for reset complete (phase1). Due to high CPU load that HBA reset can be delayed for some time.
WWPN removal does qlt_stop_phase2(). There it is believed that phase1 has already completed and thus tgt.tgt_ops is subsequently cleared. However, tgt.tgt_ops is needed to process incoming traffic and therefore this will cause one of the following panics:
NIP qlt_reset+0x7c/0x220 [qla2xxx]
LR qlt_reset+0x68/0x220 [qla2xxx]
Call Trace: 0xc000003ffff63a78 (unreliable) qlt_handle_imm_notify+0x800/0x10c0 [qla2xxx] qlt_24xx_atio_pkt+0x208/0x590 [qla2xxx] qlt_24xx_process_atio_queue+0x33c/0x7a0 [qla2xxx] qla83xx_msix_atio_q+0x54/0x90 [qla2xxx]
or
NIP qlt_24xx_handle_abts+0xd0/0x2a0 [qla2xxx]
LR qlt_24xx_handle_abts+0xb4/0x2a0 [qla2xxx]
Call Trace: qlt_24xx_handle_abts+0x90/0x2a0 [qla2xxx] (unreliable) qlt_24xx_process_atio_queue+0x500/0x7a0 [qla2xxx] qla83xx_msix_atio_q+0x54/0x90 [qla2xxx]
or
NIP qlt_create_sess+0x90/0x4e0 [qla2xxx]
LR qla24xx_do_nack_work+0xa8/0x180 [qla2xxx]
Call Trace: 0xc0000000348fba30 (unreliable) qla24xx_do_nack_work+0xa8/0x180 [qla2xxx] qla2x00_do_work+0x674/0xbf0 [qla2xxx]
qla2x00_iocb_work_fn
The patch fixes the issue by serializing qlt_stop_phase1() and qlt_stop_phase2() functions to make WWPN removal wait for phase1 completion.
--- drivers/scsi/qla2xxx/qla_target.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/scsi/qla2xxx/qla_target.c +2 -0
@@ -1559,10 +1559,12 @@ void qlt_stop_phase2(struct qla_tgt *tgt)return ; } +mutex_lock (&tgt->ha->optrom_mutex);mutex_lock (&vha->vha_tgt.tgt_mutex); tgt->tgt_stop =0 ; tgt->tgt_stopped =1 ;mutex_unlock (&vha->vha_tgt.tgt_mutex); +mutex_unlock (&tgt->ha->optrom_mutex);ql_dbg (ql_dbg_tgt_mgt, vha,0xf00c ,"Stop of tgt %p finished\n" , tgt);
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 29/39 net: macb: ensure the device is available before accessing GEMGXL control registers
In reply to Sasha LevinFrom: Zong Li <[email protected]>
[ Upstream commit 5eff1461a6dec84f04fafa9128548bad51d96147 ]
If runtime power menagement is enabled, the gigabit ethernet PLL would be disabled after macb_probe(). During this period of time, the system would hang up if we try to access GEMGXL control registers.
We can't put runtime_pm_get/runtime_pm_put/ there due to the issue of sleep inside atomic section (7fa2955ff70ce453 ("sh_eth: Fix sleeping function called from invalid context"). Add netif_running checking to ensure the device is available before accessing GEMGXL device.
Changed in v2:
- Use netif_running instead of its own flag
--- drivers/net/ethernet/cadence/macb_main.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/net/ethernet/cadence/macb_main.c +3 -0
@@ -2709,6 +2709,9 @@ static struct net_device_stats *gem_get_stats(struct macb *bp)struct gem_stats *hwstat = &bp->hw_stats.gem;struct net_device_stats *nstat = &bp->dev->stats; +if (!netif_running (bp->dev)) +return nstat; +gem_update_stats (bp); nstat->rx_errors = (hwstat->rx_frame_check_sequence_errors +
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 37/39 nvmet: fix false keep-alive timeout when a controller is torn down
In reply to Sasha LevinFrom: Sagi Grimberg <[email protected]>
[ Upstream commit aaeadd7075dc9e184bc7876e9dd7b3bada771df2 ]
Controller teardown flow may take some time in case it has many I/O queues, and the host may not send us keep-alive during this period. Hence reset the traffic based keep-alive timer so we don't trigger a controller teardown as a result of a keep-alive expiration.
--- drivers/nvme/target/core.c | 15 +++++++++++---- drivers/nvme/target/nvmet.h | 2 +- 2 files changed, 12 insertions(+), 5 deletions(-)
drivers/nvme/target/core.c +11 -4
@@ -379,10 +379,10 @@ static void nvmet_keep_alive_timer(struct work_struct *work) {struct nvmet_ctrl *ctrl =container_of (to_delayed_work (work), struct nvmet_ctrl, ka_work); -bool cmd_seen = ctrl->cmd_seen; +bool reset_tbkas = ctrl->reset_tbkas; - ctrl->cmd_seen = false; -if (cmd_seen) { + ctrl->reset_tbkas = false; +if (reset_tbkas) {pr_debug ("ctrl %d reschedule traffic based keep-alive timer\n" , ctrl->cntlid);schedule_delayed_work (&ctrl->ka_work, ctrl->kato *HZ );
@@ -792,6 +792,13 @@ void nvmet_sq_destroy(struct nvmet_sq *sq)percpu_ref_exit (&sq->ref);if (ctrl) { +/* +* The teardown flow may take some time, and the host may not +* send us keep-alive during this period, hence reset the +* traffic based keep-alive timer so we don't trigger a +* controller teardown as a result of a keep-alive expiration. +*/ + ctrl->reset_tbkas = true;nvmet_ctrl_put (ctrl); sq->ctrl =NULL ;/* allows reusing the queue later */ }
@@ -942,7 +949,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, }if (sq->ctrl) - sq->ctrl->cmd_seen = true; + sq->ctrl->reset_tbkas = true;return true;
drivers/nvme/target/nvmet.h +1 -1
@@ -166,7 +166,7 @@ struct nvmet_ctrl {struct nvmet_subsys *subsys;struct nvmet_sq **sqs; -bool cmd_seen; +bool reset_tbkas;struct mutex lock;u64 cap;
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 38/39 powerpc/fsl: set fsl,i2c-erratum-a004447 flag for P2041 i2c controllers
In reply to Sasha LevinFrom: Chris Packham <[email protected]>
[ Upstream commit 7adc7b225cddcfd0f346d10144fd7a3d3d9f9ea7 ]
The i2c controllers on the P2040/P2041 have an erratum where the documented scheme for i2c bus recovery will not work (A-004447). A different mechanism is needed which is documented in the P2040 Chip Errata Rev Q (latest available at the time of writing).
--- arch/powerpc/boot/dts/fsl/p2041si-post.dtsi | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)
arch/powerpc/boot/dts/fsl/p2041si-post.dtsi +16 -0
@@ -371,7 +371,23 @@ sdhc@114000 { }; /include/ "qoriq-i2c-0.dtsi" + i2c@118000 { + fsl,i2c-erratum-a004447; + }; + + i2c@118100 { + fsl,i2c-erratum-a004447; + }; + /include/ "qoriq-i2c-1.dtsi" + i2c@119000 { + fsl,i2c-erratum-a004447; + }; + + i2c@119100 { + fsl,i2c-erratum-a004447; + }; + /include/ "qoriq-duart-0.dtsi" /include/ "qoriq-duart-1.dtsi" /include/ "qoriq-gpio-0.dtsi"
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 39/39 powerpc/fsl: set fsl,i2c-erratum-a004447 flag for P1010 i2c controllers
In reply to Sasha LevinFrom: Chris Packham <[email protected]>
[ Upstream commit 19ae697a1e4edf1d755b413e3aa38da65e2db23b ]
The i2c controllers on the P1010 have an erratum where the documented scheme for i2c bus recovery will not work (A-004447). A different mechanism is needed which is documented in the P1010 Chip Errata Rev L.
--- arch/powerpc/boot/dts/fsl/p1010si-post.dtsi | 8 ++++++++ 1 file changed, 8 insertions(+)
arch/powerpc/boot/dts/fsl/p1010si-post.dtsi +8 -0
@@ -122,7 +122,15 @@ memory-controller@2000 { }; /include/ "pq3-i2c-0.dtsi" + i2c@3000 { + fsl,i2c-erratum-a004447; + }; + /include/ "pq3-i2c-1.dtsi" + i2c@3100 { + fsl,i2c-erratum-a004447; + }; + /include/ "pq3-duart-0.dtsi" /include/ "pq3-espi-0.dtsi" spi0: spi@7000 {
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 36/39 nvme-tcp: remove incorrect Kconfig dep in BLK_DEV_NVME
In reply to Sasha LevinFrom: Sagi Grimberg <[email protected]>
[ Upstream commit 042a3eaad6daeabcfaf163aa44da8ea3cf8b5496 ]
We need to select NVME_CORE.
--- drivers/nvme/host/Kconfig | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/nvme/host/Kconfig +2 -1
@@ -71,7 +71,8 @@ config NVME_FC config NVME_TCP tristate "NVM Express over Fabrics TCP host driver" depends on INET - depends on BLK_DEV_NVME + depends on BLOCK + select NVME_CORE select NVME_FABRICS select CRYPTO select CRYPTO_CRC32C
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 35/39 bnx2x: Fix missing error code in bnx2x_iov_init_one()
In reply to Sasha LevinFrom: Jiapeng Chong <[email protected]>
[ Upstream commit 65161c35554f7135e6656b3df1ce2c500ca0bdcf ]
Eliminate the follow smatch warning:
drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c:1227 bnx2x_iov_init_one() warn: missing error code 'err'.
--- drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +3 -1
@@ -1224,8 +1224,10 @@ int bnx2x_iov_init_one(struct bnx2x *bp, int int_mode_param, goto failed;/* SR-IOV capability was enabled but there are no VFs*/ -if (iov->total ==0 ) +if (iov->total ==0 ) { + err = -EINVAL ; goto failed; + } iov->nr_virtfn =min_t (u16, iov->total, num_vfs_param);
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 34/39 dm verity: fix require_signatures module_param permissions
In reply to Sasha LevinFrom: John Keeping <[email protected]>
[ Upstream commit 0c1f3193b1cdd21e7182f97dc9bca7d284d18a15 ]
The third parameter of module_param() is permissions for the sysfs node but it looks like it is being used as the initial value of the parameter here. In fact, false here equates to omitting the file from sysfs and does not affect the value of require_signatures.
Making the parameter writable is not simple because going from false->true is fine but it should not be possible to remove the requirement to verify a signature. But it can be useful to inspect the value of this parameter from userspace, so change the permissions to make a read-only file in sysfs.
--- drivers/md/dm-verity-verify-sig.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/md/dm-verity-verify-sig.c +1 -1
@@ -15,7 +15,7 @@#define DM_VERITY_VERIFY_ERR (s) DM_VERITY_ROOT_HASH_VERIFICATION " " sstatic bool require_signatures; -module_param (require_signatures, bool, false); +module_param (require_signatures, bool,0444 );MODULE_PARM_DESC (require_signatures,"Verify the roothash of dm-verity hash tree" );
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 27/39 scsi: hisi_sas: Drop free_irq() of devm_request_irq() allocated irq
In reply to Sasha LevinFrom: Yang Yingliang <[email protected]>
[ Upstream commit 7907a021e4bbfa29cccacd2ba2dade894d9a7d4c ]
irqs allocated with devm_request_irq() should not be freed using free_irq(). Doing so causes a dangling pointer and a subsequent double free.
--- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +4 -4
@@ -3359,14 +3359,14 @@ hisi_sas_v3_destroy_irqs(struct pci_dev *pdev, struct hisi_hba *hisi_hba) {int i; -free_irq (pci_irq_vector (pdev,1 ), hisi_hba); -free_irq (pci_irq_vector (pdev,2 ), hisi_hba); -free_irq (pci_irq_vector (pdev,11 ), hisi_hba); +devm_free_irq (&pdev->dev,pci_irq_vector (pdev,1 ), hisi_hba); +devm_free_irq (&pdev->dev,pci_irq_vector (pdev,2 ), hisi_hba); +devm_free_irq (&pdev->dev,pci_irq_vector (pdev,11 ), hisi_hba);for (i =0 ; i < hisi_hba->cq_nvecs; i++) {struct hisi_sas_cq *cq = &hisi_hba->cq[i];int nr = hisi_sas_intr_conv ?16 :16 + i; -free_irq (pci_irq_vector (pdev, nr), cq); +devm_free_irq (&pdev->dev,pci_irq_vector (pdev, nr), cq); }pci_free_irq_vectors (pdev); }
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 33/39 MIPS: Fix kernel hang under FUNCTION_GRAPH_TRACER and PREEMPT_TRACER
In reply to Sasha LevinFrom: Tiezhu Yang <[email protected]>
[ Upstream commit 78cf0eb926cb1abeff2106bae67752e032fe5f3e ]
When update the latest mainline kernel with the following three configs, the kernel hangs during startup:
(1) CONFIG_FUNCTION_GRAPH_TRACER=y
(2) CONFIG_PREEMPT_TRACER=y
(3) CONFIG_FTRACE_STARTUP_TEST=y
When update the latest mainline kernel with the above two configs (1) and (2), the kernel starts normally, but it still hangs when execute the following command:
echo "function_graph" > /sys/kernel/debug/tracing/current_tracer
Without CONFIG_PREEMPT_TRACER=y, the above two kinds of kernel hangs disappeared, so it seems that CONFIG_PREEMPT_TRACER has some influences with function_graph tracer at the first glance.
I use ejtag to find out the epc address is related with preempt_enable() in the file arch/mips/lib/mips-atomic.c, because function tracing can trace the preempt_{enable,disable} calls that are traced, replace them with preempt_{enable,disable}_notrace to prevent function tracing from going into an infinite loop, and then it can fix the kernel hang issue.
By the way, it seems that this commit is a complement and improvement of commit f93a1a00f2bd ("MIPS: Fix crash that occurs when function tracing is enabled").
--- arch/mips/lib/mips-atomic.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)
arch/mips/lib/mips-atomic.c +6 -6
@@ -37,7 +37,7 @@*/ notrace void arch_local_irq_disable(void) { -preempt_disable (); +preempt_disable_notrace (); __asm__ __volatile__( " .set push \n"
@@ -53,7 +53,7 @@ notrace void arch_local_irq_disable(void) : /* no inputs */ : "memory"); -preempt_enable (); +preempt_enable_notrace (); }EXPORT_SYMBOL (arch_local_irq_disable);
@@ -61,7 +61,7 @@ notrace unsigned long arch_local_irq_save(void) {unsigned long flags; -preempt_disable (); +preempt_disable_notrace (); __asm__ __volatile__( " .set push \n"
@@ -78,7 +78,7 @@ notrace unsigned long arch_local_irq_save(void) : /* no inputs */ : "memory"); -preempt_enable (); +preempt_enable_notrace ();return flags; }
@@ -88,7 +88,7 @@ notrace void arch_local_irq_restore(unsigned long flags) {unsigned long __tmp1; -preempt_disable (); +preempt_disable_notrace (); __asm__ __volatile__( " .set push \n"
@@ -106,7 +106,7 @@ notrace void arch_local_irq_restore(unsigned long flags) : "0" (flags) : "memory"); -preempt_enable (); +preempt_enable_notrace (); }EXPORT_SYMBOL (arch_local_irq_restore);
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 26/39 scsi: vmw_pvscsi: Set correct residual data length
In reply to Sasha LevinFrom: Matt Wang <[email protected]>
[ Upstream commit e662502b3a782d479e67736a5a1c169a703d853a ]
Some commands (such as INQUIRY) may return less data than the initiator requested. To avoid conducting useless information, set the right residual count to make upper layer aware of this.
Before (INQUIRY PAGE 0xB0 with 128B buffer):
$ sg_raw -r 128 /dev/sda 12 01 B0 00 80 00 SCSI Status: Good
Received 128 bytes of data:
00 00 b0 00 3c 01 00 00 00 00 00 00 00 00 00 00 00 ...<............ 10 00 00 00 00 00 01 00 00 00 00 00 40 00 00 08 00 ...........@.... 20 80 00 00 00 00 00 00 00 00 00 20 00 00 00 00 00 .......... ..... 30 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 40 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 50 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 60 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 70 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
After:
$ sg_raw -r 128 /dev/sda 12 01 B0 00 80 00 SCSI Status: Good
Received 64 bytes of data:
00 00 b0 00 3c 01 00 00 00 00 00 00 00 00 00 00 00 ...<............ 10 00 00 00 00 00 01 00 00 00 00 00 40 00 00 08 00 ...........@.... 20 80 00 00 00 00 00 00 00 00 00 20 00 00 00 00 00 .......... ..... 30 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
[mkp: clarified description]
--- drivers/scsi/vmw_pvscsi.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
drivers/scsi/vmw_pvscsi.c +7 -1
@@ -587,7 +587,13 @@ static void pvscsi_complete_request(struct pvscsi_adapter *adapter,case BTSTAT_SUCCESS :case BTSTAT_LINKED_COMMAND_COMPLETED :case BTSTAT_LINKED_COMMAND_COMPLETED_WITH_FLAG : -/* If everything went fine, let's move on.. */ +/* +* Commands like INQUIRY may transfer less data than +* requested by the initiator via bufflen. Set residual +* count to make upper layer aware of the actual amount +* of data returned. +*/ +scsi_set_resid (cmd,scsi_bufflen (cmd) - e->dataLen); cmd->result = (DID_OK <<16 );break ;
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 15/39 usb: chipidea: udc: assign interrupt number to USB gadget structure
In reply to Sasha LevinFrom: Li Jun <[email protected]>
[ Upstream commit 9e3927f6373da54cb17e17f4bd700907e1123d2f ]
Chipidea also need sync interrupt before unbind the udc while gadget remove driver, otherwise setup irq handling may happen while unbind, see below dump generated from android function switch stress test:
[ 4703.503056] android_work: sent uevent USB_STATE=CONNECTED [ 4703.514642] android_work: sent uevent USB_STATE=DISCONNECTED [ 4703.651339] android_work: sent uevent USB_STATE=CONNECTED [ 4703.661806] init: Control message: Processed ctl.stop for 'adbd' from pid: 561 (system_server) [ 4703.673469] init: processing action (init.svc.adbd=stopped) from (/system/etc/init/hw/init.usb.configfs.rc:14) [ 4703.676451] Unable to handle kernel read from unreadable memory at virtual address 0000000000000090 [ 4703.676454] Mem abort info: [ 4703.676458] ESR = 0x96000004 [ 4703.676461] EC = 0x25: DABT (current EL), IL = 32 bits [ 4703.676464] SET = 0, FnV = 0 [ 4703.676466] EA = 0, S1PTW = 0 [ 4703.676468] Data abort info: [ 4703.676471] ISV = 0, ISS = 0x00000004 [ 4703.676473] CM = 0, WnR = 0 [ 4703.676478] user pgtable: 4k pages, 48-bit VAs, pgdp=000000004a867000 [ 4703.676481] [0000000000000090] pgd=0000000000000000, p4d=0000000000000000 [ 4703.676503] Internal error: Oops: 96000004 [#1] PREEMPT SMP [ 4703.758297] Modules linked in: synaptics_dsx_i2c moal(O) mlan(O) [ 4703.764327] CPU: 0 PID: 235 Comm: lmkd Tainted: G W O 5.10.9-00001-g3f5fd8487c38-dirty #63 [ 4703.773720] Hardware name: NXP i.MX8MNano EVK board (DT) [ 4703.779033] pstate: 60400085 (nZCv daIf +PAN -UAO -TCO BTYPE=--) [ 4703.785046] pc : _raw_write_unlock_bh+0xc0/0x2c8 [ 4703.789667] lr : android_setup+0x4c/0x168 [ 4703.793676] sp : ffff80001256bd80 [ 4703.796989] x29: ffff80001256bd80 x28: 00000000000000a8 [ 4703.802304] x27: ffff800012470000 x26: ffff80006d923000 [ 4703.807616] x25: ffff800012471000 x24: ffff00000b091140 [ 4703.812929] x23: ffff0000077dbd38 x22: ffff0000077da490 [ 4703.818242] x21: ffff80001256be30 x20: 0000000000000000 [ 4703.823554] x19: 0000000000000080 x18: ffff800012561048 [ 4703.828867] x17: 0000000000000000 x16: 0000000000000039 [ 4703.834180] x15: ffff8000106ad258 x14: ffff80001194c277 [ 4703.839493] x13: 0000000000003934 x12: 0000000000000000 [ 4703.844805] x11: 0000000000000000 x10: 0000000000000001 [ 4703.850117] x9 : 0000000000000000 x8 : 0000000000000090 [ 4703.855429] x7 : 6f72646e61203a70 x6 : ffff8000124f2450 [ 4703.860742] x5 : ffffffffffffffff x4 : 0000000000000009 [ 4703.866054] x3 : ffff8000108a290c x2 : ffff00007fb3a9c8 [ 4703.871367] x1 : 0000000000000000 x0 : 0000000000000090 [ 4703.876681] Call trace: [ 4703.879129] _raw_write_unlock_bh+0xc0/0x2c8 [ 4703.883397] android_setup+0x4c/0x168 [ 4703.887059] udc_irq+0x824/0xa9c [ 4703.890287] ci_irq+0x124/0x148 [ 4703.893429] __handle_irq_event_percpu+0x84/0x268 [ 4703.898131] handle_irq_event+0x64/0x14c [ 4703.902054] handle_fasteoi_irq+0x110/0x210 [ 4703.906236] __handle_domain_irq+0x8c/0xd4 [ 4703.910332] gic_handle_irq+0x6c/0x124 [ 4703.914081] el1_irq+0xdc/0x1c0 [ 4703.917221] _raw_spin_unlock_irq+0x20/0x54 [ 4703.921405] finish_task_switch+0x84/0x224 [ 4703.925502] __schedule+0x4a4/0x734 [ 4703.928990] schedule+0xa0/0xe8 [ 4703.932132] do_notify_resume+0x150/0x184 [ 4703.936140] work_pending+0xc/0x40c [ 4703.939633] Code: d5384613 521b0a69 d5184609 f9800111 (885ffd01) [ 4703.945732] ---[ end trace ba5c1875ae49d53c ]--- [ 4703.950350] Kernel panic - not syncing: Oops: Fatal exception in interrupt [ 4703.957223] SMP: stopping secondary CPUs [ 4703.961151] Kernel Offset: disabled [ 4703.964638] CPU features: 0x0240002,2000200c [ 4703.968905] Memory Limit: none [ 4703.971963] Rebooting in 5 seconds..
--- drivers/usb/chipidea/udc.c | 1 + 1 file changed, 1 insertion(+)
drivers/usb/chipidea/udc.c +1 -0
@@ -2055,6 +2055,7 @@ static int udc_start(struct ci_hdrc *ci) ci->gadget.name = ci->platdata->name; ci->gadget.otg_caps = otg_caps; ci->gadget.sg_supported =1 ; + ci->gadget.irq = ci->irq;if (ci->platdata->flags &CI_HDRC_REQUIRES_ALIGNED_DMA ) ci->gadget.quirk_avoids_skb_reserve =1 ;
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 16/39 isdn: mISDN: netjet: Fix crash in nj_probe:
In reply to Sasha LevinFrom: Zheyu Ma <[email protected]>
[ Upstream commit 9f6f852550d0e1b7735651228116ae9d300f69b3 ]
'nj_setup' in netjet.c might fail with -EIO and in this case 'card->irq' is initialized and is bigger than zero. A subsequent call to 'nj_release' will free the irq that has not been requested.
Fix this bug by deleting the previous assignment to 'card->irq' and just keep the assignment before 'request_irq'.
The KASAN's log reveals it:
[ 3.354615 ] WARNING: CPU: 0 PID: 1 at kernel/irq/manage.c:1826free_irq+0x100/0x480
[ 3.355112 ] Modules linked in:
[ 3.355310 ] CPU: 0 PID: 1 Comm: swapper/0 Not tainted
5.13.0-rc1-00144-g25a1298726e #13
[ 3.355816 ] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS
rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014
[ 3.356552 ] RIP: 0010:free_irq+0x100/0x480
[ 3.356820 ] Code: 6e 08 74 6f 4d 89 f4 e8 5e ac 09 00 4d 8b 74 24 18
4d 85 f6 75 e3 e8 4f ac 09 00 8b 75 c8 48 c7 c7 78 c1 2e 85 e8 e0 cf f5 ff <0f> 0b 48 8b 75 c0 4c 89 ff e8 72 33 0b 03 48 8b 43 40 4c 8b a0 80
[ 3.358012 ] RSP: 0000:ffffc90000017b48 EFLAGS: 00010082
[ 3.358357 ] RAX: 0000000000000000 RBX: ffff888104dc8000 RCX:
0000000000000000
[ 3.358814 ] RDX: ffff8881003c8000 RSI: ffffffff8124a9e6 RDI:00000000ffffffff
[ 3.359272 ] RBP: ffffc90000017b88 R08: 0000000000000000 R09:
0000000000000000
[ 3.359732 ] R10: ffffc900000179f0 R11: 0000000000001d04 R12:
0000000000000000
[ 3.360195 ] R13: ffff888107dc6000 R14: ffff888107dc6928 R15:ffff888104dc80a8
[ 3.360652 ] FS: 0000000000000000(0000) GS:ffff88817bc00000(0000)
knlGS:0000000000000000
[ 3.361170 ] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 3.361538 ] CR2: 0000000000000000 CR3: 000000000582e000 CR4:00000000000006f0
[ 3.362003 ] DR0: 0000000000000000 DR1: 0000000000000000 DR2:
0000000000000000
[ 3.362175 ] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7:
0000000000000400
[ 3.362175 ] Call Trace: [ 3.362175 ] nj_release+0x51/0x1e0 [ 3.362175 ] nj_probe+0x450/0x950 [ 3.362175 ] ? pci_device_remove+0x110/0x110 [ 3.362175 ] local_pci_probe+0x45/0xa0 [ 3.362175 ] pci_device_probe+0x12b/0x1d0 [ 3.362175 ] really_probe+0x2a9/0x610 [ 3.362175 ] driver_probe_device+0x90/0x1d0 [ 3.362175 ] ? mutex_lock_nested+0x1b/0x20 [ 3.362175 ] device_driver_attach+0x68/0x70 [ 3.362175 ] __driver_attach+0x124/0x1b0 [ 3.362175 ] ? device_driver_attach+0x70/0x70 [ 3.362175 ] bus_for_each_dev+0xbb/0x110 [ 3.362175 ] ? rdinit_setup+0x45/0x45 [ 3.362175 ] driver_attach+0x27/0x30 [ 3.362175 ] bus_add_driver+0x1eb/0x2a0 [ 3.362175 ] driver_register+0xa9/0x180 [ 3.362175 ] __pci_register_driver+0x82/0x90 [ 3.362175 ] ? w6692_init+0x38/0x38 [ 3.362175 ] nj_init+0x36/0x38 [ 3.362175 ] do_one_initcall+0x7f/0x3d0 [ 3.362175 ] ? rdinit_setup+0x45/0x45 [ 3.362175 ] ? rcu_read_lock_sched_held+0x4f/0x80 [ 3.362175 ] kernel_init_freeable+0x2aa/0x301 [ 3.362175 ] ? rest_init+0x2c0/0x2c0 [ 3.362175 ] kernel_init+0x18/0x190 [ 3.362175 ] ? rest_init+0x2c0/0x2c0 [ 3.362175 ] ? rest_init+0x2c0/0x2c0 [ 3.362175 ] ret_from_fork+0x1f/0x30 [ 3.362175 ] Kernel panic - not syncing: panic_on_warn set ... [ 3.362175 ] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.13.0-rc1-00144-g25a1298726e #13 [ 3.362175 ] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 [ 3.362175 ] Call Trace: [ 3.362175 ] dump_stack+0xba/0xf5 [ 3.362175 ] ? free_irq+0x100/0x480 [ 3.362175 ] panic+0x15a/0x3f2 [ 3.362175 ] ? __warn+0xf2/0x150 [ 3.362175 ] ? free_irq+0x100/0x480 [ 3.362175 ] __warn+0x108/0x150 [ 3.362175 ] ? free_irq+0x100/0x480 [ 3.362175 ] report_bug+0x119/0x1c0 [ 3.362175 ] handle_bug+0x3b/0x80 [ 3.362175 ] exc_invalid_op+0x18/0x70 [ 3.362175 ] asm_exc_invalid_op+0x12/0x20 [ 3.362175 ] RIP: 0010:free_irq+0x100/0x480 [ 3.362175 ] Code: 6e 08 74 6f 4d 89 f4 e8 5e ac 09 00 4d 8b 74 24 18
4d 85 f6 75 e3 e8 4f ac 09 00 8b 75 c8 48 c7 c7 78 c1 2e 85 e8 e0 cf f5 ff <0f> 0b 48 8b 75 c0 4c 89 ff e8 72 33 0b 03 48 8b 43 40 4c 8b a0 80
[ 3.362175 ] RSP: 0000:ffffc90000017b48 EFLAGS: 00010082
[ 3.362175 ] RAX: 0000000000000000 RBX: ffff888104dc8000 RCX:
0000000000000000
[ 3.362175 ] RDX: ffff8881003c8000 RSI: ffffffff8124a9e6 RDI:00000000ffffffff
[ 3.362175 ] RBP: ffffc90000017b88 R08: 0000000000000000 R09:
0000000000000000
[ 3.362175 ] R10: ffffc900000179f0 R11: 0000000000001d04 R12:
0000000000000000
[ 3.362175 ] R13: ffff888107dc6000 R14: ffff888107dc6928 R15:ffff888104dc80a8
[ 3.362175 ] ? vprintk+0x76/0x150 [ 3.362175 ] ? free_irq+0x100/0x480 [ 3.362175 ] nj_release+0x51/0x1e0 [ 3.362175 ] nj_probe+0x450/0x950 [ 3.362175 ] ? pci_device_remove+0x110/0x110 [ 3.362175 ] local_pci_probe+0x45/0xa0 [ 3.362175 ] pci_device_probe+0x12b/0x1d0 [ 3.362175 ] really_probe+0x2a9/0x610 [ 3.362175 ] driver_probe_device+0x90/0x1d0 [ 3.362175 ] ? mutex_lock_nested+0x1b/0x20 [ 3.362175 ] device_driver_attach+0x68/0x70 [ 3.362175 ] __driver_attach+0x124/0x1b0 [ 3.362175 ] ? device_driver_attach+0x70/0x70 [ 3.362175 ] bus_for_each_dev+0xbb/0x110 [ 3.362175 ] ? rdinit_setup+0x45/0x45 [ 3.362175 ] driver_attach+0x27/0x30 [ 3.362175 ] bus_add_driver+0x1eb/0x2a0 [ 3.362175 ] driver_register+0xa9/0x180 [ 3.362175 ] __pci_register_driver+0x82/0x90 [ 3.362175 ] ? w6692_init+0x38/0x38 [ 3.362175 ] nj_init+0x36/0x38 [ 3.362175 ] do_one_initcall+0x7f/0x3d0 [ 3.362175 ] ? rdinit_setup+0x45/0x45 [ 3.362175 ] ? rcu_read_lock_sched_held+0x4f/0x80 [ 3.362175 ] kernel_init_freeable+0x2aa/0x301 [ 3.362175 ] ? rest_init+0x2c0/0x2c0 [ 3.362175 ] kernel_init+0x18/0x190 [ 3.362175 ] ? rest_init+0x2c0/0x2c0 [ 3.362175 ] ? rest_init+0x2c0/0x2c0 [ 3.362175 ] ret_from_fork+0x1f/0x30 [ 3.362175 ] Dumping ftrace buffer: [ 3.362175 ] (ftrace buffer empty) [ 3.362175 ] Kernel Offset: disabled [ 3.362175 ] Rebooting in 1 seconds..
--- drivers/isdn/hardware/mISDN/netjet.c | 1 - 1 file changed, 1 deletion(-)
drivers/isdn/hardware/mISDN/netjet.c +0 -1
@@ -1100,7 +1100,6 @@ nj_probe(struct pci_dev *pdev, const struct pci_device_id *ent) card->typ =NETJET_S_TJ300 ; card->base =pci_resource_start (pdev,0 ); - card->irq = pdev->irq;pci_set_drvdata (pdev, card); err =setup_instance (card);if (err)
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 12/39 vfio-ccw: Serialize FSM IDLE state with I/O completion
In reply to Sasha LevinFrom: Eric Farman <[email protected]>
[ Upstream commit 2af7a834a435460d546f0cf0a8b8e4d259f1d910 ]
Today, the stacked call to vfio_ccw_sch_io_todo() does three things:
1) Update a solicited IRB with CP information, and release the CP if the interrupt was the end of a START operation.
2) Copy the IRB data into the io_region, under the protection of the io_mutex
3) Reset the vfio-ccw FSM state to IDLE to acknowledge that vfio-ccw can accept more work.
The trouble is that step 3 is (A) invoked for both solicited and unsolicited interrupts, and (B) sitting after the mutex for step 2. This second piece becomes a problem if it processes an interrupt for a CLEAR SUBCHANNEL while another thread initiates a START, thus allowing the CP and FSM states to get out of sync. That is:
CPU 1 CPU 2
fsm_do_clear()
fsm_irq()
fsm_io_request()
vfio_ccw_sch_io_todo()
fsm_io_helper()Since the FSM state and CP should be kept in sync, let's make a note when the CP is released, and rely on that as an indication that the FSM should also be reset at the end of this routine and open up the device for more work.
Message-Id: <[email protected]>
--- drivers/s390/cio/vfio_ccw_drv.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-)
drivers/s390/cio/vfio_ccw_drv.c +10 -2
@@ -86,6 +86,7 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work)struct vfio_ccw_private *private;struct irb *irb;bool is_final; +bool cp_is_finished = false; private = container_of(work, struct vfio_ccw_private, io_work); irb = &private->irb;
@@ -94,14 +95,21 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work) (SCSW_ACTL_DEVACT | SCSW_ACTL_SCHACT));if (scsw_is_solicited (&irb->scsw)) {cp_update_scsw (&private->cp, &irb->scsw); -if (is_final && private->state ==VFIO_CCW_STATE_CP_PENDING ) +if (is_final && private->state ==VFIO_CCW_STATE_CP_PENDING ) {cp_free (&private->cp); + cp_is_finished = true; + } }mutex_lock (&private->io_mutex);memcpy (private->io_region->irb_area, irb,sizeof (*irb));mutex_unlock (&private->io_mutex); -if (private->mdev && is_final) +/* +* Reset to IDLE only if processing of a channel program +* has finished. Do not overwrite a possible processing +* state if the final interrupt was for HSCH or CSCH. +*/ +if (private->mdev && cp_is_finished) private->state =VFIO_CCW_STATE_IDLE ;if (private->io_trigger)
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 17/39 bonding: init notify_work earlier to avoid uninitialized use
In reply to Sasha LevinFrom: Johannes Berg <[email protected]>
[ Upstream commit 35d96e631860226d5dc4de0fad0a415362ec2457 ]
If bond_kobj_init() or later kzalloc() in bond_alloc_slave() fail, then we call kobject_put() on the slave->kobj. This in turn calls the release function slave_kobj_release() which will always try to cancel_delayed_work_sync(&slave->notify_work), which shouldn't be done on an uninitialized work struct.
Always initialize the work struct earlier to avoid problems here.
Syzbot bisected this down to a completely pointless commit, some fault injection may have been at work here that caused the alloc failure in the first place, which may interact badly with bisect.
--- drivers/net/bonding/bond_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/bonding/bond_main.c +1 -1
@@ -1502,6 +1502,7 @@ static struct slave *bond_alloc_slave(struct bonding *bond, slave->bond = bond; slave->dev = slave_dev; +INIT_DELAYED_WORK (&slave->notify_work, bond_netdev_notify_work);if (bond_kobj_init (slave))return NULL ;
@@ -1514,7 +1515,6 @@ static struct slave *bond_alloc_slave(struct bonding *bond,return NULL ; } } -INIT_DELAYED_WORK (&slave->notify_work, bond_netdev_notify_work);return slave; }
Signature · 1 line
2.30.2
Sasha Levin
maintainerPATCH 13/39 ASoC: sti-sas: add missing MODULE_DEVICE_TABLE
In reply to Sasha LevinFrom: Zou Wei <[email protected]>
[ Upstream commit e072b2671606c77538d6a4dd5dda80b508cb4816 ]
This patch adds missing MODULE_DEVICE_TABLE definition which generates correct modalias for automatic loading of this driver when it is built as an external module.
--- sound/soc/codecs/sti-sas.c | 1 + 1 file changed, 1 insertion(+)
sound/soc/codecs/sti-sas.c +1 -0
@@ -411,6 +411,7 @@ static const struct of_device_id sti_sas_dev_match[] = { }, {}, }; +MODULE_DEVICE_TABLE (of, sti_sas_dev_match);static int sti_sas_driver_probe (struct platform_device *pdev) {
Signature · 1 line
2.30.2