April 2025 - Linux-stable-mirror

[PATCH v2] iio: ad5933: Correct settling cycles encoding per datasheet

by Gabriel Shahrouzi

Implement the settling cycles encoding as specified in the AD5933 datasheet, Table 13 ("Number of Settling Times Cycles Register"). The previous logic did not correctly translate the user-requested effective cycle count into the required 9-bit base + 2-bit multiplier format (D10..D0) for values exceeding 511. Clamp the user input for out_altvoltage0_settling_cycles to the maximum effective value of 2044 cycles (511 * 4x multiplier). Fixes: f94aa354d676 ("iio: impedance-analyzer: New driver for AD5933/4 Impedance Converter, Network Analyzer") Cc: stable(a)vger.kernel.org Signed-off-by: Gabriel Shahrouzi <gshahrouzi(a)gmail.com> --- Changes in v2: - Fix spacing in comment around '+'. - Define mask and values for settling cycle multipliers. --- .../staging/iio/impedance-analyzer/ad5933.c | 23 +++++++++++++------ 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/drivers/staging/iio/impedance-analyzer/ad5933.c b/drivers/staging/iio/impedance-analyzer/ad5933.c index d5544fc2fe989..3c301a8ebd2ab 100644 --- a/drivers/staging/iio/impedance-analyzer/ad5933.c +++ b/drivers/staging/iio/impedance-analyzer/ad5933.c @@ -28,7 +28,7 @@ #define AD5933_REG_FREQ_START 0x82 /* R/W, 3 bytes */ #define AD5933_REG_FREQ_INC 0x85 /* R/W, 3 bytes */ #define AD5933_REG_INC_NUM 0x88 /* R/W, 2 bytes, 9 bit */ -#define AD5933_REG_SETTLING_CYCLES 0x8A /* R/W, 2 bytes */ +#define AD5933_REG_SETTLING_CYCLES 0x8A /* R/W, 2 bytes, 11 + 2 bit */ #define AD5933_REG_STATUS 0x8F /* R, 1 byte */ #define AD5933_REG_TEMP_DATA 0x92 /* R, 2 bytes*/ #define AD5933_REG_REAL_DATA 0x94 /* R, 2 bytes*/ @@ -71,6 +71,8 @@ #define AD5933_INT_OSC_FREQ_Hz 16776000 #define AD5933_MAX_OUTPUT_FREQ_Hz 100000 #define AD5933_MAX_RETRIES 100 +#define AD5933_MAX_FREQ_POINTS 511 +#define AD5933_MAX_SETTLING_CYCLES 2044 /* 511 * 4 */ #define AD5933_OUT_RANGE 1 #define AD5933_OUT_RANGE_AVAIL 2 @@ -82,6 +84,12 @@ #define AD5933_POLL_TIME_ms 10 #define AD5933_INIT_EXCITATION_TIME_ms 100 +/* Settling cycles multiplier bits D10, D9 */ +#define AD5933_SETTLE_MUL_MASK (BIT(10) | BIT(9)) +#define AD5933_SETTLE_MUL_1X 0 +#define AD5933_SETTLE_MUL_2X BIT(9) +#define AD5933_SETTLE_MUL_4X (BIT(10) | BIT(9)) + struct ad5933_state { struct i2c_client *client; struct clk *mclk; @@ -411,14 +419,15 @@ static ssize_t ad5933_store(struct device *dev, ret = ad5933_cmd(st, 0); break; case AD5933_OUT_SETTLING_CYCLES: - val = clamp(val, (u16)0, (u16)0x7FF); + val = clamp(val, (u16)0, (u16)AD5933_MAX_SETTLING_CYCLES); st->settling_cycles = val; - /* 2x, 4x handling, see datasheet */ + /* Encode value for register: D10..D0 */ + /* Datasheet Table 13: If cycles > 1022 -> val/4, set bits D10=1, D9=1 */ if (val > 1022) - val = (val >> 2) | (3 << 9); - else if (val > 511) - val = (val >> 1) | BIT(9); + val = (val >> 2) | AD5933_SETTLE_MUL_4X; + else if (val > 511) /* Datasheet: If cycles > 511 -> val/2, set bit D9=1 */ + val = (val >> 1) | AD5933_SETTLE_MUL_2X; dat = cpu_to_be16(val); ret = ad5933_i2c_write(st->client, @@ -426,7 +435,7 @@ static ssize_t ad5933_store(struct device *dev, 2, (u8 *)&dat); break; case AD5933_FREQ_POINTS: - val = clamp(val, (u16)0, (u16)511); + val = clamp(val, (u16)0, (u16)AD5933_MAX_FREQ_POINTS); st->freq_points = val; dat = cpu_to_be16(val); -- 2.43.0

3 months

1
0
0 0

[PATCH] x86/mm: fix _pgd_alloc() for Xen PV mode

by Juergen Gross

Recently _pgd_alloc() was switched from using __get_free_pages() to pagetable_alloc_noprof(), which might return a compound page in case the allocation order is larger than 0. On x86 this will be the case if CONFIG_MITIGATION_PAGE_TABLE_ISOLATION is set, even if PTI has been disabled at runtime. When running as a Xen PV guest (this will always disable PTI), using a compound page for a PGD will result in VM_BUG_ON_PGFLAGS being triggered when the Xen code tries to pin the PGD. Fix the Xen issue together with the not needed 8k allocation for a PGD with PTI disabled by using a variable holding the PGD allocation order in case CONFIG_MITIGATION_PAGE_TABLE_ISOLATION is set. Reported-by: Petr Vaněk <arkamar(a)atlas.cz> Fixes: a9b3c355c2e6 ("asm-generic: pgalloc: provide generic __pgd_{alloc,free}") Cc: stable(a)vger.kernel.org Signed-off-by: Juergen Gross <jgross(a)suse.com> --- arch/x86/include/asm/pgalloc.h | 7 ++++++- arch/x86/mm/pgtable.c | 4 ++++ arch/x86/mm/pti.c | 3 +++ 3 files changed, 13 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index a33147520044..754f95bddf98 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -34,8 +34,13 @@ static inline void paravirt_release_p4d(unsigned long pfn) {} * Instead of one PGD, we acquire two PGDs. Being order-1, it is * both 8k in size and 8k-aligned. That lets us just flip bit 12 * in a pointer to swap between the two 4k halves. + * + * As PTI can be runtime disabled (either via boot parameter or due to + * running as a Xen PV guest), store the actually needed allocation + * order in a global variable. */ -#define PGD_ALLOCATION_ORDER 1 +#define PGD_ALLOCATION_ORDER pgd_allocation_order +extern unsigned int pgd_allocation_order; #else #define PGD_ALLOCATION_ORDER 0 #endif diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index a05fcddfc811..f61b2d6be311 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -12,6 +12,10 @@ phys_addr_t physical_mask __ro_after_init = (1ULL << __PHYSICAL_MASK_SHIFT) - 1; EXPORT_SYMBOL(physical_mask); #endif +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION +unsigned int pgd_allocation_order = 0; +#endif + pgtable_t pte_alloc_one(struct mm_struct *mm) { return __pte_alloc_one(mm, GFP_PGTABLE_USER); diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 5f0d579932c6..44b7120c63e3 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -38,6 +38,7 @@ #include <asm/desc.h> #include <asm/sections.h> #include <asm/set_memory.h> +#include <asm/pgalloc.h> #undef pr_fmt #define pr_fmt(fmt) "Kernel/User page tables isolation: " fmt @@ -97,6 +98,8 @@ void __init pti_check_boottime_disable(void) if (pti_mode == PTI_AUTO && !boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) return; + pgd_allocation_order = 1; + setup_force_cpu_cap(X86_FEATURE_PTI); } -- 2.43.0

3 months

3
2
0 0

[PATCH AUTOSEL 5.10 8/8] fbdev: omapfb: Add 'plane' value check

by Sasha Levin

From: Leonid Arapov <arapovl839(a)gmail.com> [ Upstream commit 3e411827f31db7f938a30a3c7a7599839401ec30 ] Function dispc_ovl_setup is not intended to work with the value OMAP_DSS_WB of the enum parameter plane. The value of this parameter is initialized in dss_init_overlays and in the current state of the code it cannot take this value so it's not a real problem. For the purposes of defensive coding it wouldn't be superfluous to check the parameter value, because some functions down the call stack process this value correctly and some not. For example, in dispc_ovl_setup_global_alpha it may lead to buffer overflow. Add check for this value. Found by Linux Verification Center (linuxtesting.org) with SVACE static analysis tool. Signed-off-by: Leonid Arapov <arapovl839(a)gmail.com> Signed-off-by: Helge Deller <deller(a)gmx.de> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/video/fbdev/omap2/omapfb/dss/dispc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c index b2d6e6df21615..d852bef1d507f 100644 --- a/drivers/video/fbdev/omap2/omapfb/dss/dispc.c +++ b/drivers/video/fbdev/omap2/omapfb/dss/dispc.c @@ -2751,9 +2751,13 @@ int dispc_ovl_setup(enum omap_plane plane, const struct omap_overlay_info *oi, bool mem_to_mem) { int r; - enum omap_overlay_caps caps = dss_feat_get_overlay_caps(plane); + enum omap_overlay_caps caps; enum omap_channel channel; + if (plane == OMAP_DSS_WB) + return -EINVAL; + + caps = dss_feat_get_overlay_caps(plane); channel = dispc_ovl_get_channel_out(plane); DSSDBG("dispc_ovl_setup %d, pa %pad, pa_uv %pad, sw %d, %d,%d, %dx%d ->" -- 2.39.5

3 months

2
1
0 0

[PATCH AUTOSEL 6.6 01/26] wifi: ath12k: Fix invalid entry fetch in ath12k_dp_mon_srng_process

by Sasha Levin

From: P Praneesh <quic_ppranees(a)quicinc.com> [ Upstream commit 63fdc4509bcf483e79548de6bc08bf3c8e504bb3 ] Currently, ath12k_dp_mon_srng_process uses ath12k_hal_srng_src_get_next_entry to fetch the next entry from the destination ring. This is incorrect because ath12k_hal_srng_src_get_next_entry is intended for source rings, not destination rings. This leads to invalid entry fetches, causing potential data corruption or crashes due to accessing incorrect memory locations. This happens because the source ring and destination ring have different handling mechanisms and using the wrong function results in incorrect pointer arithmetic and ring management. To fix this issue, replace the call to ath12k_hal_srng_src_get_next_entry with ath12k_hal_srng_dst_get_next_entry in ath12k_dp_mon_srng_process. This ensures that the correct function is used for fetching entries from the destination ring, preventing invalid memory accesses. Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1 Tested-on: WCN7850 hw2.0 WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3 Signed-off-by: P Praneesh <quic_ppranees(a)quicinc.com> Link: https://patch.msgid.link/20241223060132.3506372-7-quic_ppranees@quicinc.com Signed-off-by: Jeff Johnson <jeff.johnson(a)oss.qualcomm.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/net/wireless/ath/ath12k/dp_mon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c index f1e57e98bdc60..35f22a4a16cf2 100644 --- a/drivers/net/wireless/ath/ath12k/dp_mon.c +++ b/drivers/net/wireless/ath/ath12k/dp_mon.c @@ -2571,7 +2571,7 @@ int ath12k_dp_mon_rx_process_stats(struct ath12k *ar, int mac_id, dest_idx = 0; move_next: ath12k_dp_mon_buf_replenish(ab, buf_ring, 1); - ath12k_hal_srng_src_get_next_entry(ab, srng); + ath12k_hal_srng_dst_get_next_entry(ab, srng); num_buffs_reaped++; } -- 2.39.5

3 months

2
26
0 0

[PATCH AUTOSEL 5.10 01/15] page_pool: avoid infinite loop to schedule delayed worker

by Sasha Levin

From: Jason Xing <kerneljasonxing(a)gmail.com> [ Upstream commit 43130d02baa137033c25297aaae95fd0edc41654 ] We noticed the kworker in page_pool_release_retry() was waken up repeatedly and infinitely in production because of the buggy driver causing the inflight less than 0 and warning us in page_pool_inflight()[1]. Since the inflight value goes negative, it means we should not expect the whole page_pool to get back to work normally. This patch mitigates the adverse effect by not rescheduling the kworker when detecting the inflight negative in page_pool_release_retry(). [1] [Mon Feb 10 20:36:11 2025] ------------[ cut here ]------------ [Mon Feb 10 20:36:11 2025] Negative(-51446) inflight packet-pages ... [Mon Feb 10 20:36:11 2025] Call Trace: [Mon Feb 10 20:36:11 2025] page_pool_release_retry+0x23/0x70 [Mon Feb 10 20:36:11 2025] process_one_work+0x1b1/0x370 [Mon Feb 10 20:36:11 2025] worker_thread+0x37/0x3a0 [Mon Feb 10 20:36:11 2025] kthread+0x11a/0x140 [Mon Feb 10 20:36:11 2025] ? process_one_work+0x370/0x370 [Mon Feb 10 20:36:11 2025] ? __kthread_cancel_work+0x40/0x40 [Mon Feb 10 20:36:11 2025] ret_from_fork+0x35/0x40 [Mon Feb 10 20:36:11 2025] ---[ end trace ebffe800f33e7e34 ]--- Note: before this patch, the above calltrace would flood the dmesg due to repeated reschedule of release_dw kworker. Signed-off-by: Jason Xing <kerneljasonxing(a)gmail.com> Reviewed-by: Mina Almasry <almasrymina(a)google.com> Link: https://patch.msgid.link/20250214064250.85987-1-kerneljasonxing@gmail.com Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- net/core/page_pool.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 08fbf4049c108..a11809b3149b4 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -485,7 +485,13 @@ static void page_pool_release_retry(struct work_struct *wq) int inflight; inflight = page_pool_release(pool); - if (!inflight) + /* In rare cases, a driver bug may cause inflight to go negative. + * Don't reschedule release if inflight is 0 or negative. + * - If 0, the page_pool has been destroyed + * - if negative, we will never recover + * in both cases no reschedule is necessary. + */ + if (inflight <= 0) return; /* Periodic warning */ -- 2.39.5

3 months

2
16
0 0

[PATCH AUTOSEL 6.1 1/9] HID: pidff: Convert infinite length from Linux API to PID standard

by Sasha Levin

From: Tomasz Pakuła <tomasz.pakula.oficjalny(a)gmail.com> [ Upstream commit 37e0591fe44dce39d1ebc7a82d5b6e4dba1582eb ] Software uses 0 as de-facto infinite lenght on Linux FF apis (SDL), Linux doesn't actually define anythi as of now, while USB PID defines NULL (0xffff). Most PID devices do not expect a 0-length effect and can't interpret it as infinite. This change fixes Force Feedback for most PID compliant devices. As most games depend on updating the values of already playing infinite effects, this is crucial to ensure they will actually work. Previously, users had to rely on third-party software to do this conversion and make their PID devices usable. Co-developed-by: Makarenko Oleg <oleg(a)makarenk.ooo> Signed-off-by: Makarenko Oleg <oleg(a)makarenk.ooo> Signed-off-by: Tomasz Pakuła <tomasz.pakula.oficjalny(a)gmail.com> Reviewed-by: Michał Kopeć <michal(a)nozomi.space> Reviewed-by: Paul Dino Jones <paul(a)spacefreak18.xyz> Tested-by: Paul Dino Jones <paul(a)spacefreak18.xyz> Tested-by: Cristóferson Bueno <cbueno81(a)gmail.com> Tested-by: Pablo Cisneros <patchkez(a)protonmail.com> Signed-off-by: Jiri Kosina <jkosina(a)suse.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/hid/usbhid/hid-pidff.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/hid/usbhid/hid-pidff.c b/drivers/hid/usbhid/hid-pidff.c index 3b4ee21cd8111..5fe4422bb5bad 100644 --- a/drivers/hid/usbhid/hid-pidff.c +++ b/drivers/hid/usbhid/hid-pidff.c @@ -21,6 +21,7 @@ #include "usbhid.h" #define PID_EFFECTS_MAX 64 +#define PID_INFINITE 0xffff /* Report usage table used to put reports into an array */ @@ -301,7 +302,12 @@ static void pidff_set_effect_report(struct pidff_device *pidff, pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0]; pidff->set_effect_type->value[0] = pidff->create_new_effect_type->value[0]; - pidff->set_effect[PID_DURATION].value[0] = effect->replay.length; + + /* Convert infinite length from Linux API (0) + to PID standard (NULL) if needed */ + pidff->set_effect[PID_DURATION].value[0] = + effect->replay.length == 0 ? PID_INFINITE : effect->replay.length; + pidff->set_effect[PID_TRIGGER_BUTTON].value[0] = effect->trigger.button; pidff->set_effect[PID_TRIGGER_REPEAT_INT].value[0] = effect->trigger.interval; -- 2.39.5

3 months

2
9
0 0

[PATCH AUTOSEL 5.10 1/5] HID: pidff: Convert infinite length from Linux API to PID standard

by Sasha Levin

From: Tomasz Pakuła <tomasz.pakula.oficjalny(a)gmail.com> [ Upstream commit 37e0591fe44dce39d1ebc7a82d5b6e4dba1582eb ] Software uses 0 as de-facto infinite lenght on Linux FF apis (SDL), Linux doesn't actually define anythi as of now, while USB PID defines NULL (0xffff). Most PID devices do not expect a 0-length effect and can't interpret it as infinite. This change fixes Force Feedback for most PID compliant devices. As most games depend on updating the values of already playing infinite effects, this is crucial to ensure they will actually work. Previously, users had to rely on third-party software to do this conversion and make their PID devices usable. Co-developed-by: Makarenko Oleg <oleg(a)makarenk.ooo> Signed-off-by: Makarenko Oleg <oleg(a)makarenk.ooo> Signed-off-by: Tomasz Pakuła <tomasz.pakula.oficjalny(a)gmail.com> Reviewed-by: Michał Kopeć <michal(a)nozomi.space> Reviewed-by: Paul Dino Jones <paul(a)spacefreak18.xyz> Tested-by: Paul Dino Jones <paul(a)spacefreak18.xyz> Tested-by: Cristóferson Bueno <cbueno81(a)gmail.com> Tested-by: Pablo Cisneros <patchkez(a)protonmail.com> Signed-off-by: Jiri Kosina <jkosina(a)suse.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/hid/usbhid/hid-pidff.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/drivers/hid/usbhid/hid-pidff.c b/drivers/hid/usbhid/hid-pidff.c index 07a9fe97d2e05..badcb5f28607e 100644 --- a/drivers/hid/usbhid/hid-pidff.c +++ b/drivers/hid/usbhid/hid-pidff.c @@ -21,6 +21,7 @@ #include "usbhid.h" #define PID_EFFECTS_MAX 64 +#define PID_INFINITE 0xffff /* Report usage table used to put reports into an array */ @@ -301,7 +302,12 @@ static void pidff_set_effect_report(struct pidff_device *pidff, pidff->block_load[PID_EFFECT_BLOCK_INDEX].value[0]; pidff->set_effect_type->value[0] = pidff->create_new_effect_type->value[0]; - pidff->set_effect[PID_DURATION].value[0] = effect->replay.length; + + /* Convert infinite length from Linux API (0) + to PID standard (NULL) if needed */ + pidff->set_effect[PID_DURATION].value[0] = + effect->replay.length == 0 ? PID_INFINITE : effect->replay.length; + pidff->set_effect[PID_TRIGGER_BUTTON].value[0] = effect->trigger.button; pidff->set_effect[PID_TRIGGER_REPEAT_INT].value[0] = effect->trigger.interval; -- 2.39.5

3 months

2
5
0 0

[PATCH v3] iio: adc: Correct conditional logic for store mode

by Gabriel Shahrouzi

The mode setting logic in ad7816_store_mode was reversed due to incorrect handling of the strcmp return value. strcmp returns 0 on match, so the `if (strcmp(buf, "full"))` block executed when the input was not "full". This resulted in "full" setting the mode to AD7816_PD (power-down) and other inputs setting it to AD7816_FULL. Fix this by checking it against 0 to correctly check for "full" and "power-down", mapping them to AD7816_FULL and AD7816_PD respectively. Fixes: 7924425db04a ("staging: iio: adc: new driver for AD7816 devices") Cc: stable(a)vger.kernel.org Signed-off-by: Gabriel Shahrouzi <gshahrouzi(a)gmail.com> --- Changes since v3: - Tag stable(a)vger.kernel.org instead of an email CC - Use the correct version for patch Changes since v2: - Add fixes tag that references commit that introduced the bug. - Replace sysfs_streq with strcmp. --- drivers/staging/iio/adc/ad7816.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/staging/iio/adc/ad7816.c b/drivers/staging/iio/adc/ad7816.c index 6c14d7bcdd675..081b17f498638 100644 --- a/drivers/staging/iio/adc/ad7816.c +++ b/drivers/staging/iio/adc/ad7816.c @@ -136,7 +136,7 @@ static ssize_t ad7816_store_mode(struct device *dev, struct iio_dev *indio_dev = dev_to_iio_dev(dev); struct ad7816_chip_info *chip = iio_priv(indio_dev); - if (strcmp(buf, "full")) { + if (strcmp(buf, "full") == 0) { gpiod_set_value(chip->rdwr_pin, 1); chip->mode = AD7816_FULL; } else { -- 2.43.0

3 months

3
4
0 0

[PATCH 5.15/5.10 1/2] blk-cgroup: support to track if policy is online

by bin.lan.cn＠windriver.com

From: Yu Kuai <yukuai3(a)huawei.com> [ Upstream commit dfd6200a095440b663099d8d42f1efb0175a1ce3 ] A new field 'online' is added to blkg_policy_data to fix following 2 problem: 1) In blkcg_activate_policy(), if pd_alloc_fn() with 'GFP_NOWAIT' failed, 'queue_lock' will be dropped and pd_alloc_fn() will try again without 'GFP_NOWAIT'. In the meantime, remove cgroup can race with it, and pd_offline_fn() will be called without pd_init_fn() and pd_online_fn(). This way null-ptr-deference can be triggered. 2) In order to synchronize pd_free_fn() from blkg_free_workfn() and blkcg_deactivate_policy(), 'list_del_init(&blkg->q_node)' will be delayed to blkg_free_workfn(), hence pd_offline_fn() can be called first in blkg_destroy(), and then blkcg_deactivate_policy() will call it again, we must prevent it. The new field 'online' will be set after pd_online_fn() and will be cleared after pd_offline_fn(), in the meantime pd_offline_fn() will only be called if 'online' is set. Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Acked-by: Tejun Heo <tj(a)kernel.org> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Link: https://lore.kernel.org/r/20230119110350.2287325-3-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Bin Lan <bin.lan.cn(a)windriver.com> Signed-off-by: He Zhe <zhe.he(a)windriver.com> --- Build test passed. --- block/blk-cgroup.c | 24 +++++++++++++++++------- include/linux/blk-cgroup.h | 1 + 2 files changed, 18 insertions(+), 7 deletions(-) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 6180c680136b..e372a3fc264e 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -192,6 +192,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, blkg->pd[i] = pd; pd->blkg = blkg; pd->plid = i; + pd->online = false; } return blkg; @@ -289,8 +290,11 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; - if (blkg->pd[i] && pol->pd_online_fn) - pol->pd_online_fn(blkg->pd[i]); + if (blkg->pd[i]) { + if (pol->pd_online_fn) + pol->pd_online_fn(blkg->pd[i]); + blkg->pd[i]->online = true; + } } } blkg->online = true; @@ -390,8 +394,11 @@ static void blkg_destroy(struct blkcg_gq *blkg) for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; - if (blkg->pd[i] && pol->pd_offline_fn) - pol->pd_offline_fn(blkg->pd[i]); + if (blkg->pd[i] && blkg->pd[i]->online) { + if (pol->pd_offline_fn) + pol->pd_offline_fn(blkg->pd[i]); + blkg->pd[i]->online = false; + } } blkg->online = false; @@ -1367,6 +1374,7 @@ int blkcg_activate_policy(struct request_queue *q, blkg->pd[pol->plid] = pd; pd->blkg = blkg; pd->plid = pol->plid; + pd->online = false; } /* all allocated, init in the same order */ @@ -1374,9 +1382,11 @@ int blkcg_activate_policy(struct request_queue *q, list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) pol->pd_init_fn(blkg->pd[pol->plid]); - if (pol->pd_online_fn) - list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) + list_for_each_entry_reverse(blkg, &q->blkg_list, q_node) { + if (pol->pd_online_fn) pol->pd_online_fn(blkg->pd[pol->plid]); + blkg->pd[pol->plid]->online = true; + } __set_bit(pol->plid, q->blkcg_pols); ret = 0; @@ -1438,7 +1448,7 @@ void blkcg_deactivate_policy(struct request_queue *q, spin_lock(&blkcg->lock); if (blkg->pd[pol->plid]) { - if (pol->pd_offline_fn) + if (blkg->pd[pol->plid]->online && pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[pol->plid]); pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 27c363f6b281..c5eda86e4118 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -92,6 +92,7 @@ struct blkg_policy_data { /* the blkg and policy id this per-policy data belongs to */ struct blkcg_gq *blkg; int plid; + bool online; }; /* -- 2.34.1

3 months

2
3
0 0

[PATCH 5.10.y] net: defer final 'struct net' free in netns dismantle

by jianqi.ren.cn＠windriver.com

From: Eric Dumazet <edumazet(a)google.com> [ Upstream commit 0f6ede9fbc747e2553612271bce108f7517e7a45 ] Ilya reported a slab-use-after-free in dst_destroy [1] Issue is in xfrm6_net_init() and xfrm4_net_init() : They copy xfrm[46]_dst_ops_template into net->xfrm.xfrm[46]_dst_ops. But net structure might be freed before all the dst callbacks are called. So when dst_destroy() calls later : if (dst->ops->destroy) dst->ops->destroy(dst); dst->ops points to the old net->xfrm.xfrm[46]_dst_ops, which has been freed. See a relevant issue fixed in : ac888d58869b ("net: do not delay dst_entries_add() in dst_release()") A fix is to queue the 'struct net' to be freed after one another cleanup_net() round (and existing rcu_barrier()) [1] BUG: KASAN: slab-use-after-free in dst_destroy (net/core/dst.c:112) Read of size 8 at addr ffff8882137ccab0 by task swapper/37/0 Dec 03 05:46:18 kernel: CPU: 37 UID: 0 PID: 0 Comm: swapper/37 Kdump: loaded Not tainted 6.12.0 #67 Hardware name: Red Hat KVM/RHEL, BIOS 1.16.1-1.el9 04/01/2014 Call Trace: <IRQ> dump_stack_lvl (lib/dump_stack.c:124) print_address_description.constprop.0 (mm/kasan/report.c:378) ? dst_destroy (net/core/dst.c:112) print_report (mm/kasan/report.c:489) ? dst_destroy (net/core/dst.c:112) ? kasan_addr_to_slab (mm/kasan/common.c:37) kasan_report (mm/kasan/report.c:603) ? dst_destroy (net/core/dst.c:112) ? rcu_do_batch (kernel/rcu/tree.c:2567) dst_destroy (net/core/dst.c:112) rcu_do_batch (kernel/rcu/tree.c:2567) ? __pfx_rcu_do_batch (kernel/rcu/tree.c:2491) ? lockdep_hardirqs_on_prepare (kernel/locking/lockdep.c:4339 kernel/locking/lockdep.c:4406) rcu_core (kernel/rcu/tree.c:2825) handle_softirqs (kernel/softirq.c:554) __irq_exit_rcu (kernel/softirq.c:589 kernel/softirq.c:428 kernel/softirq.c:637) irq_exit_rcu (kernel/softirq.c:651) sysvec_apic_timer_interrupt (arch/x86/kernel/apic/apic.c:1049 arch/x86/kernel/apic/apic.c:1049) </IRQ> <TASK> asm_sysvec_apic_timer_interrupt (./arch/x86/include/asm/idtentry.h:702) RIP: 0010:default_idle (./arch/x86/include/asm/irqflags.h:37 ./arch/x86/include/asm/irqflags.h:92 arch/x86/kernel/process.c:743) Code: 00 4d 29 c8 4c 01 c7 4c 29 c2 e9 6e ff ff ff 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 66 90 0f 00 2d c7 c9 27 00 fb f4 <fa> c3 cc cc cc cc 66 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 90 RSP: 0018:ffff888100d2fe00 EFLAGS: 00000246 RAX: 00000000001870ed RBX: 1ffff110201a5fc2 RCX: ffffffffb61a3e46 RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffffffffb3d4d123 RBP: 0000000000000000 R08: 0000000000000001 R09: ffffed11c7e1835d R10: ffff888e3f0c1aeb R11: 0000000000000000 R12: 0000000000000000 R13: ffff888100d20000 R14: dffffc0000000000 R15: 0000000000000000 ? ct_kernel_exit.constprop.0 (kernel/context_tracking.c:148) ? cpuidle_idle_call (kernel/sched/idle.c:186) default_idle_call (./include/linux/cpuidle.h:143 kernel/sched/idle.c:118) cpuidle_idle_call (kernel/sched/idle.c:186) ? __pfx_cpuidle_idle_call (kernel/sched/idle.c:168) ? lock_release (kernel/locking/lockdep.c:467 kernel/locking/lockdep.c:5848) ? lockdep_hardirqs_on_prepare (kernel/locking/lockdep.c:4347 kernel/locking/lockdep.c:4406) ? tsc_verify_tsc_adjust (arch/x86/kernel/tsc_sync.c:59) do_idle (kernel/sched/idle.c:326) cpu_startup_entry (kernel/sched/idle.c:423 (discriminator 1)) start_secondary (arch/x86/kernel/smpboot.c:202 arch/x86/kernel/smpboot.c:282) ? __pfx_start_secondary (arch/x86/kernel/smpboot.c:232) ? soft_restart_cpu (arch/x86/kernel/head_64.S:452) common_startup_64 (arch/x86/kernel/head_64.S:414) </TASK> Dec 03 05:46:18 kernel: Allocated by task 12184: kasan_save_stack (mm/kasan/common.c:48) kasan_save_track (./arch/x86/include/asm/current.h:49 mm/kasan/common.c:60 mm/kasan/common.c:69) __kasan_slab_alloc (mm/kasan/common.c:319 mm/kasan/common.c:345) kmem_cache_alloc_noprof (mm/slub.c:4085 mm/slub.c:4134 mm/slub.c:4141) copy_net_ns (net/core/net_namespace.c:421 net/core/net_namespace.c:480) create_new_namespaces (kernel/nsproxy.c:110) unshare_nsproxy_namespaces (kernel/nsproxy.c:228 (discriminator 4)) ksys_unshare (kernel/fork.c:3313) __x64_sys_unshare (kernel/fork.c:3382) do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Dec 03 05:46:18 kernel: Freed by task 11: kasan_save_stack (mm/kasan/common.c:48) kasan_save_track (./arch/x86/include/asm/current.h:49 mm/kasan/common.c:60 mm/kasan/common.c:69) kasan_save_free_info (mm/kasan/generic.c:582) __kasan_slab_free (mm/kasan/common.c:271) kmem_cache_free (mm/slub.c:4579 mm/slub.c:4681) cleanup_net (net/core/net_namespace.c:456 net/core/net_namespace.c:446 net/core/net_namespace.c:647) process_one_work (kernel/workqueue.c:3229) worker_thread (kernel/workqueue.c:3304 kernel/workqueue.c:3391) kthread (kernel/kthread.c:389) ret_from_fork (arch/x86/kernel/process.c:147) ret_from_fork_asm (arch/x86/entry/entry_64.S:257) Dec 03 05:46:18 kernel: Last potentially related work creation: kasan_save_stack (mm/kasan/common.c:48) __kasan_record_aux_stack (mm/kasan/generic.c:541) insert_work (./include/linux/instrumented.h:68 ./include/asm-generic/bitops/instrumented-non-atomic.h:141 kernel/workqueue.c:788 kernel/workqueue.c:795 kernel/workqueue.c:2186) __queue_work (kernel/workqueue.c:2340) queue_work_on (kernel/workqueue.c:2391) xfrm_policy_insert (net/xfrm/xfrm_policy.c:1610) xfrm_add_policy (net/xfrm/xfrm_user.c:2116) xfrm_user_rcv_msg (net/xfrm/xfrm_user.c:3321) netlink_rcv_skb (net/netlink/af_netlink.c:2536) xfrm_netlink_rcv (net/xfrm/xfrm_user.c:3344) netlink_unicast (net/netlink/af_netlink.c:1316 net/netlink/af_netlink.c:1342) netlink_sendmsg (net/netlink/af_netlink.c:1886) sock_write_iter (net/socket.c:729 net/socket.c:744 net/socket.c:1165) vfs_write (fs/read_write.c:590 fs/read_write.c:683) ksys_write (fs/read_write.c:736) do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Dec 03 05:46:18 kernel: Second to last potentially related work creation: kasan_save_stack (mm/kasan/common.c:48) __kasan_record_aux_stack (mm/kasan/generic.c:541) insert_work (./include/linux/instrumented.h:68 ./include/asm-generic/bitops/instrumented-non-atomic.h:141 kernel/workqueue.c:788 kernel/workqueue.c:795 kernel/workqueue.c:2186) __queue_work (kernel/workqueue.c:2340) queue_work_on (kernel/workqueue.c:2391) __xfrm_state_insert (./include/linux/workqueue.h:723 net/xfrm/xfrm_state.c:1150 net/xfrm/xfrm_state.c:1145 net/xfrm/xfrm_state.c:1513) xfrm_state_update (./include/linux/spinlock.h:396 net/xfrm/xfrm_state.c:1940) xfrm_add_sa (net/xfrm/xfrm_user.c:912) xfrm_user_rcv_msg (net/xfrm/xfrm_user.c:3321) netlink_rcv_skb (net/netlink/af_netlink.c:2536) xfrm_netlink_rcv (net/xfrm/xfrm_user.c:3344) netlink_unicast (net/netlink/af_netlink.c:1316 net/netlink/af_netlink.c:1342) netlink_sendmsg (net/netlink/af_netlink.c:1886) sock_write_iter (net/socket.c:729 net/socket.c:744 net/socket.c:1165) vfs_write (fs/read_write.c:590 fs/read_write.c:683) ksys_write (fs/read_write.c:736) do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83) entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130) Fixes: a8a572a6b5f2 ("xfrm: dst_entries_init() per-net dst_ops") Reported-by: Ilya Maximets <i.maximets(a)ovn.org> Closes: https://lore.kernel.org/netdev/CANn89iKKYDVpB=MtmfH7nyv2p=rJWSLedO5k7wSZgtY… Signed-off-by: Eric Dumazet <edumazet(a)google.com> Acked-by: Paolo Abeni <pabeni(a)redhat.com> Reviewed-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Link: https://patch.msgid.link/20241204125455.3871859-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> [Minor conflict resolved due to code context change.] Signed-off-by: Jianqi Ren <jianqi.ren.cn(a)windriver.com> Signed-off-by: He Zhe <zhe.he(a)windriver.com> --- Verified the build test --- include/net/net_namespace.h | 1 + net/core/net_namespace.c | 21 ++++++++++++++++++++- 2 files changed, 21 insertions(+), 1 deletion(-) diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 3cf6a5c17b84..1f985b64a666 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -80,6 +80,7 @@ struct net { * or to unregister pernet ops * (pernet_ops_rwsem write locked). */ + struct llist_node defer_free_list; struct llist_node cleanup_list; /* namespaces on death row */ #ifdef CONFIG_KEYS diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index bcf3533cb8ff..feee95cf2991 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -455,11 +455,28 @@ static struct net *net_alloc(void) goto out; } +static LLIST_HEAD(defer_free_list); + +static void net_complete_free(void) +{ + struct llist_node *kill_list; + struct net *net, *next; + + /* Get the list of namespaces to free from last round. */ + kill_list = llist_del_all(&defer_free_list); + + llist_for_each_entry_safe(net, next, kill_list, defer_free_list) + kmem_cache_free(net_cachep, net); + +} + static void net_free(struct net *net) { if (refcount_dec_and_test(&net->passive)) { kfree(rcu_access_pointer(net->gen)); - kmem_cache_free(net_cachep, net); + + /* Wait for an extra rcu_barrier() before final free. */ + llist_add(&net->defer_free_list, &defer_free_list); } } @@ -643,6 +660,8 @@ static void cleanup_net(struct work_struct *work) */ rcu_barrier(); + net_complete_free(); + /* Finally it is safe to free my network namespace structure */ list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { list_del_init(&net->exit_list); -- 2.34.1

3 months

3
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror April 2025