June 2025 - Linux-stable-mirror

[PATCH v4] iio: common: st_sensors: Fix use of uninitialize device structs

by Maud Spierings via B4 Relay

From: Maud Spierings <maudspierings(a)gocontroll.com> Throughout the various probe functions &indio_dev->dev is used before it is initialized. This caused a kernel panic in st_sensors_power_enable() when the call to devm_regulator_bulk_get_enable() fails and then calls dev_err_probe() with the uninitialized device. This seems to only cause a panic with dev_err_probe(), dev_err(), dev_warn() and dev_info() don't seem to cause a panic, but are fixed as well. The issue is reported and traced here: [1] Link: https://lore.kernel.org/all/AM7P189MB100986A83D2F28AF3FFAF976E39EA@AM7P189M… [1] Cc: stable(a)vger.kernel.org Signed-off-by: Maud Spierings <maudspierings(a)gocontroll.com> --- When I search for general &indio_dev->dev usage, I see quite a lot more hits, but I am not sure if there are issues with those too. This issue has existed for a long time it seems and therefore it is nearly impossible to find a proper fixes tag. I would love to see it at least backported to 6.12 as that is where I encountered it, and I believe the patch should apply without conflicts. --- Changes in v4: - Put the link to the original issue in a proper link tag - Remove stray newline - Link to v3: https://lore.kernel.org/r/20250526-st_iio_fix-v3-1-039fec38707c@gocontroll.… Changes in v3: - Added the stable cc to the commit message - Move the link to the original issue to the commit message - Fix function notation in the commit message - Move some more of the dev_*() calls to one line - Link to v2: https://lore.kernel.org/r/20250522-st_iio_fix-v2-1-07a32655a996@gocontroll.… Changes in v2: - Added SoB in commit message - Link to v1: https://lore.kernel.org/r/20250522-st_iio_fix-v1-1-d689b35f1612@gocontroll.… --- drivers/iio/accel/st_accel_core.c | 10 +++--- drivers/iio/common/st_sensors/st_sensors_core.c | 36 ++++++++++------------ drivers/iio/common/st_sensors/st_sensors_trigger.c | 20 ++++++------ 3 files changed, 31 insertions(+), 35 deletions(-) diff --git a/drivers/iio/accel/st_accel_core.c b/drivers/iio/accel/st_accel_core.c index 99cb661fabb2d9cc1943fa8d0a6f3becb71126e6..a7961c610ed203d039bbf298c8883031a578fb0b 100644 --- a/drivers/iio/accel/st_accel_core.c +++ b/drivers/iio/accel/st_accel_core.c @@ -1353,6 +1353,7 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev) union acpi_object *ont; union acpi_object *elements; acpi_status status; + struct device *parent = indio_dev->dev.parent; int ret = -EINVAL; unsigned int val; int i, j; @@ -1371,7 +1372,7 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev) }; - adev = ACPI_COMPANION(indio_dev->dev.parent); + adev = ACPI_COMPANION(parent); if (!adev) return -ENXIO; @@ -1380,8 +1381,7 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev) if (status == AE_NOT_FOUND) { return -ENXIO; } else if (ACPI_FAILURE(status)) { - dev_warn(&indio_dev->dev, "failed to execute _ONT: %d\n", - status); + dev_warn(parent, "failed to execute _ONT: %d\n", status); return status; } @@ -1457,12 +1457,12 @@ static int apply_acpi_orientation(struct iio_dev *indio_dev) } ret = 0; - dev_info(&indio_dev->dev, "computed mount matrix from ACPI\n"); + dev_info(parent, "computed mount matrix from ACPI\n"); out: kfree(buffer.pointer); if (ret) - dev_dbg(&indio_dev->dev, + dev_dbg(parent, "failed to apply ACPI orientation data: %d\n", ret); return ret; diff --git a/drivers/iio/common/st_sensors/st_sensors_core.c b/drivers/iio/common/st_sensors/st_sensors_core.c index 8ce1dccfea4f5aaff45d3d40f6542323dd1f0b09..dac593be56958fd0be92e13f628350fcfd0f040d 100644 --- a/drivers/iio/common/st_sensors/st_sensors_core.c +++ b/drivers/iio/common/st_sensors/st_sensors_core.c @@ -154,7 +154,7 @@ static int st_sensors_set_fullscale(struct iio_dev *indio_dev, unsigned int fs) return err; st_accel_set_fullscale_error: - dev_err(&indio_dev->dev, "failed to set new fullscale.\n"); + dev_err(indio_dev->dev.parent, "failed to set new fullscale.\n"); return err; } @@ -231,8 +231,7 @@ int st_sensors_power_enable(struct iio_dev *indio_dev) ARRAY_SIZE(regulator_names), regulator_names); if (err) - return dev_err_probe(&indio_dev->dev, err, - "unable to enable supplies\n"); + return dev_err_probe(parent, err, "unable to enable supplies\n"); return 0; } @@ -241,13 +240,14 @@ EXPORT_SYMBOL_NS(st_sensors_power_enable, "IIO_ST_SENSORS"); static int st_sensors_set_drdy_int_pin(struct iio_dev *indio_dev, struct st_sensors_platform_data *pdata) { + struct device *parent = indio_dev->dev.parent; struct st_sensor_data *sdata = iio_priv(indio_dev); /* Sensor does not support interrupts */ if (!sdata->sensor_settings->drdy_irq.int1.addr && !sdata->sensor_settings->drdy_irq.int2.addr) { if (pdata->drdy_int_pin) - dev_info(&indio_dev->dev, + dev_info(parent, "DRDY on pin INT%d specified, but sensor does not support interrupts\n", pdata->drdy_int_pin); return 0; @@ -256,29 +256,27 @@ static int st_sensors_set_drdy_int_pin(struct iio_dev *indio_dev, switch (pdata->drdy_int_pin) { case 1: if (!sdata->sensor_settings->drdy_irq.int1.mask) { - dev_err(&indio_dev->dev, - "DRDY on INT1 not available.\n"); + dev_err(parent, "DRDY on INT1 not available.\n"); return -EINVAL; } sdata->drdy_int_pin = 1; break; case 2: if (!sdata->sensor_settings->drdy_irq.int2.mask) { - dev_err(&indio_dev->dev, - "DRDY on INT2 not available.\n"); + dev_err(parent, "DRDY on INT2 not available.\n"); return -EINVAL; } sdata->drdy_int_pin = 2; break; default: - dev_err(&indio_dev->dev, "DRDY on pdata not valid.\n"); + dev_err(parent, "DRDY on pdata not valid.\n"); return -EINVAL; } if (pdata->open_drain) { if (!sdata->sensor_settings->drdy_irq.int1.addr_od && !sdata->sensor_settings->drdy_irq.int2.addr_od) - dev_err(&indio_dev->dev, + dev_err(parent, "open drain requested but unsupported.\n"); else sdata->int_pin_open_drain = true; @@ -336,6 +334,7 @@ EXPORT_SYMBOL_NS(st_sensors_dev_name_probe, "IIO_ST_SENSORS"); int st_sensors_init_sensor(struct iio_dev *indio_dev, struct st_sensors_platform_data *pdata) { + struct device *parent = indio_dev->dev.parent; struct st_sensor_data *sdata = iio_priv(indio_dev); struct st_sensors_platform_data *of_pdata; int err = 0; @@ -343,7 +342,7 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev, mutex_init(&sdata->odr_lock); /* If OF/DT pdata exists, it will take precedence of anything else */ - of_pdata = st_sensors_dev_probe(indio_dev->dev.parent, pdata); + of_pdata = st_sensors_dev_probe(parent, pdata); if (IS_ERR(of_pdata)) return PTR_ERR(of_pdata); if (of_pdata) @@ -370,7 +369,7 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev, if (err < 0) return err; } else - dev_info(&indio_dev->dev, "Full-scale not possible\n"); + dev_info(parent, "Full-scale not possible\n"); err = st_sensors_set_odr(indio_dev, sdata->odr); if (err < 0) @@ -405,7 +404,7 @@ int st_sensors_init_sensor(struct iio_dev *indio_dev, mask = sdata->sensor_settings->drdy_irq.int2.mask_od; } - dev_info(&indio_dev->dev, + dev_info(parent, "set interrupt line to open drain mode on pin %d\n", sdata->drdy_int_pin); err = st_sensors_write_data_with_mask(indio_dev, addr, @@ -593,21 +592,20 @@ EXPORT_SYMBOL_NS(st_sensors_get_settings_index, "IIO_ST_SENSORS"); int st_sensors_verify_id(struct iio_dev *indio_dev) { struct st_sensor_data *sdata = iio_priv(indio_dev); + struct device *parent = indio_dev->dev.parent; int wai, err; if (sdata->sensor_settings->wai_addr) { err = regmap_read(sdata->regmap, sdata->sensor_settings->wai_addr, &wai); if (err < 0) { - dev_err(&indio_dev->dev, - "failed to read Who-Am-I register.\n"); - return err; + return dev_err_probe(parent, err, + "failed to read Who-Am-I register.\n"); } if (sdata->sensor_settings->wai != wai) { - dev_warn(&indio_dev->dev, - "%s: WhoAmI mismatch (0x%x).\n", - indio_dev->name, wai); + dev_warn(parent, "%s: WhoAmI mismatch (0x%x).\n", + indio_dev->name, wai); } } diff --git a/drivers/iio/common/st_sensors/st_sensors_trigger.c b/drivers/iio/common/st_sensors/st_sensors_trigger.c index 9d4bf822a15dfcdd6c2835f6b9d7698cd3cb0b08..8a8ab688d7980f6dd43c660f90a0eba32c38388b 100644 --- a/drivers/iio/common/st_sensors/st_sensors_trigger.c +++ b/drivers/iio/common/st_sensors/st_sensors_trigger.c @@ -127,7 +127,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, sdata->trig = devm_iio_trigger_alloc(parent, "%s-trigger", indio_dev->name); if (sdata->trig == NULL) { - dev_err(&indio_dev->dev, "failed to allocate iio trigger.\n"); + dev_err(parent, "failed to allocate iio trigger.\n"); return -ENOMEM; } @@ -143,7 +143,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, case IRQF_TRIGGER_FALLING: case IRQF_TRIGGER_LOW: if (!sdata->sensor_settings->drdy_irq.addr_ihl) { - dev_err(&indio_dev->dev, + dev_err(parent, "falling/low specified for IRQ but hardware supports only rising/high: will request rising/high\n"); if (irq_trig == IRQF_TRIGGER_FALLING) irq_trig = IRQF_TRIGGER_RISING; @@ -156,21 +156,19 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, sdata->sensor_settings->drdy_irq.mask_ihl, 1); if (err < 0) return err; - dev_info(&indio_dev->dev, + dev_info(parent, "interrupts on the falling edge or active low level\n"); } break; case IRQF_TRIGGER_RISING: - dev_info(&indio_dev->dev, - "interrupts on the rising edge\n"); + dev_info(parent, "interrupts on the rising edge\n"); break; case IRQF_TRIGGER_HIGH: - dev_info(&indio_dev->dev, - "interrupts active high level\n"); + dev_info(parent, "interrupts active high level\n"); break; default: /* This is the most preferred mode, if possible */ - dev_err(&indio_dev->dev, + dev_err(parent, "unsupported IRQ trigger specified (%lx), enforce rising edge\n", irq_trig); irq_trig = IRQF_TRIGGER_RISING; } @@ -179,7 +177,7 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, if (irq_trig == IRQF_TRIGGER_FALLING || irq_trig == IRQF_TRIGGER_RISING) { if (!sdata->sensor_settings->drdy_irq.stat_drdy.addr) { - dev_err(&indio_dev->dev, + dev_err(parent, "edge IRQ not supported w/o stat register.\n"); return -EOPNOTSUPP; } @@ -214,13 +212,13 @@ int st_sensors_allocate_trigger(struct iio_dev *indio_dev, sdata->trig->name, sdata->trig); if (err) { - dev_err(&indio_dev->dev, "failed to request trigger IRQ.\n"); + dev_err(parent, "failed to request trigger IRQ.\n"); return err; } err = devm_iio_trigger_register(parent, sdata->trig); if (err < 0) { - dev_err(&indio_dev->dev, "failed to register iio trigger.\n"); + dev_err(parent, "failed to register iio trigger.\n"); return err; } indio_dev->trig = iio_trigger_get(sdata->trig); --- base-commit: 7bac2c97af4078d7a627500c9bcdd5b033f97718 change-id: 20250522-st_iio_fix-1c58fdd4d420 Best regards, -- Maud Spierings <maudspierings(a)gocontroll.com>

1 month, 2 weeks

4
4
0 0

[PATCH v 5] usb: dwc2: gadget: Fix enter to hibernation for UTMI+ PHY

by Minas Harutyunyan

For UTMI+ PHY, according to programming guide, first should be set PMUACTV bit then STOPPCLK bit. Otherwise, when the device issues Remote Wakeup, then host notices disconnect instead. For ULPI PHY, above mentioned bits must be set in reversed order: STOPPCLK then PMUACTV. Fixes: 4483ef3c1685 ("usb: dwc2: Add hibernation updates for ULPI PHY") Cc: stable(a)vger.kernel.org Signed-off-by: Minas Harutyunyan <Minas.Harutyunyan(a)synopsys.com> --- Changes in v5: - Rebased on top of Linux 6.16-rc2 Changes in v4: - Rebased on top of Linux 6.15-rc6 Changes in v3: - Rebased on top of Linux 6.15-rc4 Changes in v2: - Added Cc: stable(a)vger.kernel.org drivers/usb/dwc2/gadget.c | 38 ++++++++++++++++++++++++++------------ 1 file changed, 26 insertions(+), 12 deletions(-) diff --git a/drivers/usb/dwc2/gadget.c b/drivers/usb/dwc2/gadget.c index d5b622f78cf3..0637bfbc054e 100644 --- a/drivers/usb/dwc2/gadget.c +++ b/drivers/usb/dwc2/gadget.c @@ -5389,20 +5389,34 @@ int dwc2_gadget_enter_hibernation(struct dwc2_hsotg *hsotg) if (gusbcfg & GUSBCFG_ULPI_UTMI_SEL) { /* ULPI interface */ gpwrdn |= GPWRDN_ULPI_LATCH_EN_DURING_HIB_ENTRY; - } - dwc2_writel(hsotg, gpwrdn, GPWRDN); - udelay(10); + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); - /* Suspend the Phy Clock */ - pcgcctl = dwc2_readl(hsotg, PCGCTL); - pcgcctl |= PCGCTL_STOPPCLK; - dwc2_writel(hsotg, pcgcctl, PCGCTL); - udelay(10); + /* Suspend the Phy Clock */ + pcgcctl = dwc2_readl(hsotg, PCGCTL); + pcgcctl |= PCGCTL_STOPPCLK; + dwc2_writel(hsotg, pcgcctl, PCGCTL); + udelay(10); - gpwrdn = dwc2_readl(hsotg, GPWRDN); - gpwrdn |= GPWRDN_PMUACTV; - dwc2_writel(hsotg, gpwrdn, GPWRDN); - udelay(10); + gpwrdn = dwc2_readl(hsotg, GPWRDN); + gpwrdn |= GPWRDN_PMUACTV; + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); + } else { + /* UTMI+ Interface */ + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); + + gpwrdn = dwc2_readl(hsotg, GPWRDN); + gpwrdn |= GPWRDN_PMUACTV; + dwc2_writel(hsotg, gpwrdn, GPWRDN); + udelay(10); + + pcgcctl = dwc2_readl(hsotg, PCGCTL); + pcgcctl |= PCGCTL_STOPPCLK; + dwc2_writel(hsotg, pcgcctl, PCGCTL); + udelay(10); + } /* Set flag to indicate that we are in hibernation */ hsotg->hibernated = 1; base-commit: 7aed15379db9c6ec67999cdaf5c443b7be06ea73 -- 2.41.0

1 month, 2 weeks

2
1
0 0

[PATCH 6.12.y 0/2] crypto: rng - FIPS 140-3 compliance for random number generation

by Jay Wang

This patch series implements FIPS 140-3 compliance requirements for random number generation in the Linux kernel 6.12. The changes ensure that when the kernel is operating in FIPS mode, FIPS-compliant random number generators are used instead of the default /dev/random implementation. IMPORTANT: These two patches must be applied together as a series. Applying only the first patch without the second will cause a deadlock during boot in FIPS-enabled environments. The second patch fixes a critical timing issue introduced by the first patch where the crypto RNG attempts to override the drivers/char/random interface before the default RNG becomes available. The series consists of two patches: 1. Initial implementation to override drivers/char/random in FIPS mode 2. Refinement to ensure override only occurs after FIPS-mode RNGs are available These 2 patches are required for FIPS 140-3 certification and compliance in government and enterprise environments. Herbert Xu (1): crypto: rng - Override drivers/char/random in FIPS mode Jay Wang (1): Override drivers/char/random only after FIPS-mode RNGs become available crypto/rng.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 92 insertions(+) -- 2.47.1

1 month, 2 weeks

3
5
0 0

[tip: ras/urgent] x86/mce: Don't remove sysfs if thresholding sysfs init fails

by tip-bot2 for Yazen Ghannam

The following commit has been merged into the ras/urgent branch of tip: Commit-ID: 4c113a5b28bfd589e2010b5fc8867578b0135ed7 Gitweb: https://git.kernel.org/tip/4c113a5b28bfd589e2010b5fc8867578b0135ed7 Author: Yazen Ghannam <yazen.ghannam(a)amd.com> AuthorDate: Tue, 24 Jun 2025 14:15:56 Committer: Borislav Petkov (AMD) <bp(a)alien8.de> CommitterDate: Thu, 26 Jun 2025 17:28:13 +02:00 x86/mce: Don't remove sysfs if thresholding sysfs init fails Currently, the MCE subsystem sysfs interface will be removed if the thresholding sysfs interface fails to be created. A common failure is due to new MCA bank types that are not recognized and don't have a short name set. The MCA thresholding feature is optional and should not break the common MCE sysfs interface. Also, new MCA bank types are occasionally introduced, and updates will be needed to recognize them. But likewise, this should not break the common sysfs interface. Keep the MCE sysfs interface regardless of the status of the thresholding sysfs interface. Signed-off-by: Yazen Ghannam <yazen.ghannam(a)amd.com> Signed-off-by: Borislav Petkov (AMD) <bp(a)alien8.de> Reviewed-by: Qiuxu Zhuo <qiuxu.zhuo(a)intel.com> Reviewed-by: Tony Luck <tony.luck(a)intel.com> Tested-by: Tony Luck <tony.luck(a)intel.com> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/20250624-wip-mca-updates-v4-1-236dd74f645f@amd.com --- arch/x86/kernel/cpu/mce/core.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index e9b3c5d..07d6193 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -2801,15 +2801,9 @@ static int mce_cpu_dead(unsigned int cpu) static int mce_cpu_online(unsigned int cpu) { struct timer_list *t = this_cpu_ptr(&mce_timer); - int ret; mce_device_create(cpu); - - ret = mce_threshold_create_device(cpu); - if (ret) { - mce_device_remove(cpu); - return ret; - } + mce_threshold_create_device(cpu); mce_reenable_cpu(); mce_start_timer(t); return 0;

1 month, 2 weeks

1
0
0 0

[tip: ras/urgent] x86/mce: Ensure user polling settings are honored when restarting timer

by tip-bot2 for Yazen Ghannam

The following commit has been merged into the ras/urgent branch of tip: Commit-ID: 00c092de6f28ebd32208aef83b02d61af2229b60 Gitweb: https://git.kernel.org/tip/00c092de6f28ebd32208aef83b02d61af2229b60 Author: Yazen Ghannam <yazen.ghannam(a)amd.com> AuthorDate: Tue, 24 Jun 2025 14:15:57 Committer: Borislav Petkov (AMD) <bp(a)alien8.de> CommitterDate: Fri, 27 Jun 2025 12:41:44 +02:00 x86/mce: Ensure user polling settings are honored when restarting timer Users can disable MCA polling by setting the "ignore_ce" parameter or by setting "check_interval=0". This tells the kernel to *not* start the MCE timer on a CPU. If the user did not disable CMCI, then storms can occur. When these happen, the MCE timer will be started with a fixed interval. After the storm subsides, the timer's next interval is set to check_interval. This disregards the user's input through "ignore_ce" and "check_interval". Furthermore, if "check_interval=0", then the new timer will run faster than expected. Create a new helper to check these conditions and use it when a CMCI storm ends. [ bp: Massage. ] Fixes: 7eae17c4add5 ("x86/mce: Add per-bank CMCI storm mitigation") Signed-off-by: Yazen Ghannam <yazen.ghannam(a)amd.com> Signed-off-by: Borislav Petkov (AMD) <bp(a)alien8.de> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/20250624-wip-mca-updates-v4-2-236dd74f645f@amd.com --- arch/x86/kernel/cpu/mce/core.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 07d6193..4da4eab 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1740,6 +1740,11 @@ static void mc_poll_banks_default(void) void (*mc_poll_banks)(void) = mc_poll_banks_default; +static bool should_enable_timer(unsigned long iv) +{ + return !mca_cfg.ignore_ce && iv; +} + static void mce_timer_fn(struct timer_list *t) { struct timer_list *cpu_t = this_cpu_ptr(&mce_timer); @@ -1763,7 +1768,7 @@ static void mce_timer_fn(struct timer_list *t) if (mce_get_storm_mode()) { __start_timer(t, HZ); - } else { + } else if (should_enable_timer(iv)) { __this_cpu_write(mce_next_interval, iv); __start_timer(t, iv); } @@ -2156,11 +2161,10 @@ static void mce_start_timer(struct timer_list *t) { unsigned long iv = check_interval * HZ; - if (mca_cfg.ignore_ce || !iv) - return; - - this_cpu_write(mce_next_interval, iv); - __start_timer(t, iv); + if (should_enable_timer(iv)) { + this_cpu_write(mce_next_interval, iv); + __start_timer(t, iv); + } } static void __mcheck_cpu_setup_timer(void)

1 month, 2 weeks

1
0
0 0

[tip: ras/urgent] x86/mce/amd: Add default names for MCA banks and blocks

by tip-bot2 for Yazen Ghannam

The following commit has been merged into the ras/urgent branch of tip: Commit-ID: d66e1e90b16055d2f0ee76e5384e3f119c3c2773 Gitweb: https://git.kernel.org/tip/d66e1e90b16055d2f0ee76e5384e3f119c3c2773 Author: Yazen Ghannam <yazen.ghannam(a)amd.com> AuthorDate: Tue, 24 Jun 2025 14:15:58 Committer: Borislav Petkov (AMD) <bp(a)alien8.de> CommitterDate: Fri, 27 Jun 2025 13:13:36 +02:00 x86/mce/amd: Add default names for MCA banks and blocks Ensure that sysfs init doesn't fail for new/unrecognized bank types or if a bank has additional blocks available. Most MCA banks have a single thresholding block, so the block takes the same name as the bank. Unified Memory Controllers (UMCs) are a special case where there are two blocks and each has a unique name. However, the microarchitecture allows for five blocks. Any new MCA bank types with more than one block will be missing names for the extra blocks. The MCE sysfs will fail to initialize in this case. Fixes: 87a6d4091bd7 ("x86/mce/AMD: Update sysfs bank names for SMCA systems") Signed-off-by: Yazen Ghannam <yazen.ghannam(a)amd.com> Signed-off-by: Borislav Petkov (AMD) <bp(a)alien8.de> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/20250624-wip-mca-updates-v4-3-236dd74f645f@amd.com --- arch/x86/kernel/cpu/mce/amd.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 9d852c3..6820ebc 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -1113,13 +1113,20 @@ static const char *get_name(unsigned int cpu, unsigned int bank, struct threshol } bank_type = smca_get_bank_type(cpu, bank); - if (bank_type >= N_SMCA_BANK_TYPES) - return NULL; if (b && (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2)) { if (b->block < ARRAY_SIZE(smca_umc_block_names)) return smca_umc_block_names[b->block]; - return NULL; + } + + if (b && b->block) { + snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "th_block_%u", b->block); + return buf_mcatype; + } + + if (bank_type >= N_SMCA_BANK_TYPES) { + snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "th_bank_%u", bank); + return buf_mcatype; } if (per_cpu(smca_bank_counts, cpu)[bank_type] == 1)

1 month, 2 weeks

1
0
0 0

[tip: ras/urgent] x86/mce/amd: Fix threshold limit reset

by tip-bot2 for Yazen Ghannam

The following commit has been merged into the ras/urgent branch of tip: Commit-ID: 5f6e3b720694ad771911f637a51930f511427ce1 Gitweb: https://git.kernel.org/tip/5f6e3b720694ad771911f637a51930f511427ce1 Author: Yazen Ghannam <yazen.ghannam(a)amd.com> AuthorDate: Tue, 24 Jun 2025 14:15:59 Committer: Borislav Petkov (AMD) <bp(a)alien8.de> CommitterDate: Fri, 27 Jun 2025 13:16:23 +02:00 x86/mce/amd: Fix threshold limit reset The MCA threshold limit must be reset after servicing the interrupt. Currently, the restart function doesn't have an explicit check for this. It makes some assumptions based on the current limit and what's in the registers. These assumptions don't always hold, so the limit won't be reset in some cases. Make the reset condition explicit. Either an interrupt/overflow has occurred or the bank is being initialized. Signed-off-by: Yazen Ghannam <yazen.ghannam(a)amd.com> Signed-off-by: Borislav Petkov (AMD) <bp(a)alien8.de> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/20250624-wip-mca-updates-v4-4-236dd74f645f@amd.com --- arch/x86/kernel/cpu/mce/amd.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 6820ebc..5c4eb28 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -350,7 +350,6 @@ static void smca_configure(unsigned int bank, unsigned int cpu) struct thresh_restart { struct threshold_block *b; - int reset; int set_lvt_off; int lvt_off; u16 old_limit; @@ -432,13 +431,13 @@ static void threshold_restart_bank(void *_tr) rdmsr(tr->b->address, lo, hi); - if (tr->b->threshold_limit < (hi & THRESHOLD_MAX)) - tr->reset = 1; /* limit cannot be lower than err count */ - - if (tr->reset) { /* reset err count and overflow bit */ - hi = - (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) | - (THRESHOLD_MAX - tr->b->threshold_limit); + /* + * Reset error count and overflow bit. + * This is done during init or after handling an interrupt. + */ + if (hi & MASK_OVERFLOW_HI || tr->set_lvt_off) { + hi &= ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI); + hi |= THRESHOLD_MAX - tr->b->threshold_limit; } else if (tr->old_limit) { /* change limit w/o reset */ int new_count = (hi & THRESHOLD_MAX) + (tr->old_limit - tr->b->threshold_limit);

1 month, 2 weeks

1
0
0 0

[PATCH v2 1/1] mm/rmap: fix potential out-of-bounds page table access during batched unmap

by Lance Yang

From: Lance Yang <lance.yang(a)linux.dev> As pointed out by David[1], the batched unmap logic in try_to_unmap_one() can read past the end of a PTE table if a large folio is mapped starting at the last entry of that table. It would be quite rare in practice, as MADV_FREE typically splits the large folio ;) So let's fix the potential out-of-bounds read by refactoring the logic into a new helper, folio_unmap_pte_batch(). The new helper now correctly calculates the safe number of pages to scan by limiting the operation to the boundaries of the current VMA and the PTE table. In addition, the "all-or-nothing" batching restriction is removed to support partial batches. The reference counting is also cleaned up to use folio_put_refs(). [1] https://lore.kernel.org/linux-mm/a694398c-9f03-4737-81b9-7e49c857fcbe@redha… Fixes: 354dffd29575 ("mm: support batched unmap for lazyfree large folios during reclamation") Cc: <stable(a)vger.kernel.org> Suggested-by: David Hildenbrand <david(a)redhat.com> Suggested-by: Barry Song <baohua(a)kernel.org> Signed-off-by: Lance Yang <lance.yang(a)linux.dev> --- v1 -> v2: - Update subject and changelog (per Barry) - https://lore.kernel.org/linux-mm/20250627025214.30887-1-lance.yang@linux.dev mm/rmap.c | 46 ++++++++++++++++++++++++++++------------------ 1 file changed, 28 insertions(+), 18 deletions(-) diff --git a/mm/rmap.c b/mm/rmap.c index fb63d9256f09..1320b88fab74 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1845,23 +1845,32 @@ void folio_remove_rmap_pud(struct folio *folio, struct page *page, #endif } -/* We support batch unmapping of PTEs for lazyfree large folios */ -static inline bool can_batch_unmap_folio_ptes(unsigned long addr, - struct folio *folio, pte_t *ptep) +static inline unsigned int folio_unmap_pte_batch(struct folio *folio, + struct page_vma_mapped_walk *pvmw, + enum ttu_flags flags, pte_t pte) { const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY; - int max_nr = folio_nr_pages(folio); - pte_t pte = ptep_get(ptep); + unsigned long end_addr, addr = pvmw->address; + struct vm_area_struct *vma = pvmw->vma; + unsigned int max_nr; + + if (flags & TTU_HWPOISON) + return 1; + if (!folio_test_large(folio)) + return 1; + /* We may only batch within a single VMA and a single page table. */ + end_addr = pmd_addr_end(addr, vma->vm_end); + max_nr = (end_addr - addr) >> PAGE_SHIFT; + + /* We only support lazyfree batching for now ... */ if (!folio_test_anon(folio) || folio_test_swapbacked(folio)) - return false; + return 1; if (pte_unused(pte)) - return false; - if (pte_pfn(pte) != folio_pfn(folio)) - return false; + return 1; - return folio_pte_batch(folio, addr, ptep, pte, max_nr, fpb_flags, NULL, - NULL, NULL) == max_nr; + return folio_pte_batch(folio, addr, pvmw->pte, pte, max_nr, fpb_flags, + NULL, NULL, NULL); } /* @@ -2024,9 +2033,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, if (pte_dirty(pteval)) folio_mark_dirty(folio); } else if (likely(pte_present(pteval))) { - if (folio_test_large(folio) && !(flags & TTU_HWPOISON) && - can_batch_unmap_folio_ptes(address, folio, pvmw.pte)) - nr_pages = folio_nr_pages(folio); + nr_pages = folio_unmap_pte_batch(folio, &pvmw, flags, pteval); end_addr = address + nr_pages * PAGE_SIZE; flush_cache_range(vma, address, end_addr); @@ -2206,13 +2213,16 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, hugetlb_remove_rmap(folio); } else { folio_remove_rmap_ptes(folio, subpage, nr_pages, vma); - folio_ref_sub(folio, nr_pages - 1); } if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); - folio_put(folio); - /* We have already batched the entire folio */ - if (nr_pages > 1) + folio_put_refs(folio, nr_pages); + + /* + * If we are sure that we batched the entire folio and cleared + * all PTEs, we can just optimize and stop right here. + */ + if (nr_pages == folio_nr_pages(folio)) goto walk_done; continue; walk_abort: -- 2.49.0

1 month, 2 weeks

5
9
0 0

+ mm-shmem-swap-improve-cached-mthp-handling-and-fix-potential-hung.patch added to mm-new branch

by Andrew Morton

The patch titled Subject: mm/shmem, swap: improve cached mTHP handling and fix potential hung has been added to the -mm mm-new branch. Its filename is mm-shmem-swap-improve-cached-mthp-handling-and-fix-potential-hung.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-new branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Note, mm-new is a provisional staging ground for work-in-progress patches, and acceptance into mm-new is a notification for others take notice and to finish up reviews. Please do not hesitate to respond to review feedback and post updated versions to replace or incrementally fixup patches in mm-new. Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Kairui Song <kasong(a)tencent.com> Subject: mm/shmem, swap: improve cached mTHP handling and fix potential hung Date: Fri, 27 Jun 2025 14:20:14 +0800 Patch series "mm/shmem, swap: bugfix and improvement of mTHP swap in", v3. The current mTHP swapin path have some problems. It may potentially hang, may cause redundant faults due to false positive swap cache lookup, and it will involve at least 4 Xarray tree walks (get order, get order again, confirm swap, insert folio). And for !CONFIG_TRANSPARENT_HUGEPAGE builds, it will performs some mTHP related checks. This series fixes all of the mentioned issues, and the code should be more robust and prepared for the swap table series. Now tree walks is reduced to twice (get order & confirm, insert folio) and added more sanity checks and comments. !CONFIG_TRANSPARENT_HUGEPAGE build overhead is also minimized, and comes with a sanity check now. The performance is slightly better after this series, sequential swap in of 24G data from ZRAM, using transparent_hugepage_tmpfs=always (24 samples each): Before: 11.17, Standard Deviation: 0.02 After patch 1: 10.89, Standard Deviation: 0.05 After patch 2: 10.84, Standard Deviation: 0.03 After patch 3: 10.91, Standard Deviation: 0.03 After patch 4: 10.86, Standard Deviation: 0.03 After patch 5: 10.07, Standard Deviation: 0.04 After patch 7: 10.09, Standard Deviation: 0.03 Each patch improves the performance by a little, which is about ~10% faster in total. Build kernel test showed very slightly improvement, testing with make -j24 with defconfig in a 256M memcg also using ZRAM as swap, and transparent_hugepage_tmpfs=always (6 test runs): Before: system time avg: 3911.80s After: system time avg: 3863.76s This patch (of 7): The current swap-in code assumes that, when a swap entry in shmem mapping is order 0, its cached folios (if present) must be order 0 too, which turns out not always correct. The problem is shmem_split_large_entry is called before verifying the folio will eventually be swapped in, one possible race is: CPU1 CPU2 shmem_swapin_folio /* swap in of order > 0 swap entry S1 */ folio = swap_cache_get_folio /* folio = NULL */ order = xa_get_order /* order > 0 */ folio = shmem_swap_alloc_folio /* mTHP alloc failure, folio = NULL */ <... Interrupted ...> shmem_swapin_folio /* S1 is swapped in */ shmem_writeout /* S1 is swapped out, folio cached */ shmem_split_large_entry(..., S1) /* S1 is split, but the folio covering it has order > 0 now */ Now any following swapin of S1 will hang: `xa_get_order` returns 0, and folio lookup will return a folio with order > 0. The `xa_get_order(&mapping->i_pages, index) != folio_order(folio)` will always return false causing swap-in to return -EEXIST. And this looks fragile. So fix this up by allowing seeing a larger folio in swap cache, and check the whole shmem mapping range covered by the swapin have the right swap value upon inserting the folio. And drop the redundant tree walks before the insertion. This will actually improve performance, as it avoids two redundant Xarray tree walks in the hot path, and the only side effect is that in the failure path, shmem may redundantly reallocate a few folios causing temporary slight memory pressure. And worth noting, it may seems the order and value check before inserting might help reducing the lock contention, which is not true. The swap cache layer ensures raced swapin will either see a swap cache folio or failed to do a swapin (we have SWAP_HAS_CACHE bit even if swap cache is bypassed), so holding the folio lock and checking the folio flag is already good enough for avoiding the lock contention. The chance that a folio passes the swap entry value check but the shmem mapping slot has changed should be very low. Link: https://lkml.kernel.org/r/20250627062020.534-2-ryncsn@gmail.com Link: https://lkml.kernel.org/r/20250627062020.534-2-ryncsn@gmail.com Fixes: 809bc86517cc ("mm: shmem: support large folio swap out") Signed-off-by: Kairui Song <kasong(a)tencent.com> Reviewed-by: Kemeng Shi <shikemeng(a)huaweicloud.com> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: Baoquan He <bhe(a)redhat.com> Cc: Barry Song <baohua(a)kernel.org> Cc: Chris Li <chrisl(a)kernel.org> Cc: Hugh Dickins <hughd(a)google.com> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Nhat Pham <nphamcs(a)gmail.com> Cc: Dev Jain <dev.jain(a)arm.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/shmem.c | 30 +++++++++++++++++++++--------- 1 file changed, 21 insertions(+), 9 deletions(-) --- a/mm/shmem.c~mm-shmem-swap-improve-cached-mthp-handling-and-fix-potential-hung +++ a/mm/shmem.c @@ -884,7 +884,9 @@ static int shmem_add_to_page_cache(struc pgoff_t index, void *expected, gfp_t gfp) { XA_STATE_ORDER(xas, &mapping->i_pages, index, folio_order(folio)); - long nr = folio_nr_pages(folio); + unsigned long nr = folio_nr_pages(folio); + swp_entry_t iter, swap; + void *entry; VM_BUG_ON_FOLIO(index != round_down(index, nr), folio); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); @@ -896,14 +898,24 @@ static int shmem_add_to_page_cache(struc gfp &= GFP_RECLAIM_MASK; folio_throttle_swaprate(folio, gfp); + swap = iter = radix_to_swp_entry(expected); do { xas_lock_irq(&xas); - if (expected != xas_find_conflict(&xas)) { - xas_set_err(&xas, -EEXIST); - goto unlock; + xas_for_each_conflict(&xas, entry) { + /* + * The range must either be empty, or filled with + * expected swap entries. Shmem swap entries are never + * partially freed without split of both entry and + * folio, so there shouldn't be any holes. + */ + if (!expected || entry != swp_to_radix_entry(iter)) { + xas_set_err(&xas, -EEXIST); + goto unlock; + } + iter.val += 1 << xas_get_order(&xas); } - if (expected && xas_find_conflict(&xas)) { + if (expected && iter.val - nr != swap.val) { xas_set_err(&xas, -EEXIST); goto unlock; } @@ -2323,7 +2335,7 @@ static int shmem_swapin_folio(struct ino error = -ENOMEM; goto failed; } - } else if (order != folio_order(folio)) { + } else if (order > folio_order(folio)) { /* * Swap readahead may swap in order 0 folios into swapcache * asynchronously, while the shmem mapping can still stores @@ -2348,15 +2360,15 @@ static int shmem_swapin_folio(struct ino swap = swp_entry(swp_type(swap), swp_offset(swap) + offset); } + } else if (order < folio_order(folio)) { + swap.val = round_down(swap.val, 1 << folio_order(folio)); } alloced: /* We have to do this with folio locked to prevent races */ folio_lock(folio); if ((!skip_swapcache && !folio_test_swapcache(folio)) || - folio->swap.val != swap.val || - !shmem_confirm_swap(mapping, index, swap) || - xa_get_order(&mapping->i_pages, index) != folio_order(folio)) { + folio->swap.val != swap.val) { error = -EEXIST; goto unlock; } _ Patches currently in -mm which might be from kasong(a)tencent.com are mm-list_lru-refactor-the-locking-code.patch mm-shmem-swap-improve-cached-mthp-handling-and-fix-potential-hung.patch mm-shmem-swap-avoid-redundant-xarray-lookup-during-swapin.patch mm-shmem-swap-tidy-up-thp-swapin-checks.patch mm-shmem-swap-clean-up-swap-entry-splitting.patch mm-shmem-swap-never-use-swap-cache-and-readahead-for-swp_synchronous_io.patch mm-shmem-swap-fix-major-fault-counting.patch mm-shmem-swap-avoid-false-positive-swap-cache-lookup.patch

1 month, 2 weeks

1
0
0 0

+ mm-rmap-fix-potential-out-of-bounds-page-table-access-during-batched-unmap.patch added to mm-hotfixes-unstable branch

by Andrew Morton

The patch titled Subject: mm/rmap: fix potential out-of-bounds page table access during batched unmap has been added to the -mm mm-hotfixes-unstable branch. Its filename is mm-rmap-fix-potential-out-of-bounds-page-table-access-during-batched-unmap.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-hotfixes-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Lance Yang <lance.yang(a)linux.dev> Subject: mm/rmap: fix potential out-of-bounds page table access during batched unmap Date: Fri, 27 Jun 2025 14:23:19 +0800 As pointed out by David[1], the batched unmap logic in try_to_unmap_one() can read past the end of a PTE table if a large folio is mapped starting at the last entry of that table. It would be quite rare in practice, as MADV_FREE typically splits the large folio ;) So let's fix the potential out-of-bounds read by refactoring the logic into a new helper, folio_unmap_pte_batch(). The new helper now correctly calculates the safe number of pages to scan by limiting the operation to the boundaries of the current VMA and the PTE table. In addition, the "all-or-nothing" batching restriction is removed to support partial batches. The reference counting is also cleaned up to use folio_put_refs(). [1] https://lore.kernel.org/linux-mm/a694398c-9f03-4737-81b9-7e49c857fcbe@redha… Link: https://lkml.kernel.org/r/20250627062319.84936-1-lance.yang@linux.dev Fixes: 354dffd29575 ("mm: support batched unmap for lazyfree large folios during reclamation") Signed-off-by: Lance Yang <lance.yang(a)linux.dev> Suggested-by: David Hildenbrand <david(a)redhat.com> Suggested-by: Barry Song <baohua(a)kernel.org> Cc: Baolin Wang <baolin.wang(a)linux.alibaba.com> Cc: Barry Song <v-songbaohua(a)oppo.com> Cc: Chris Li <chrisl(a)kernel.org> Cc: "Huang, Ying" <huang.ying.caritas(a)gmail.com> Cc: Kairui Song <kasong(a)tencent.com> Cc: Lance Yang <lance.yang(a)linux.dev> Cc: Liam Howlett <liam.howlett(a)oracle.com> Cc: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Cc: Mingzhe Yang <mingzhe.yang(a)ly.com> Cc: Rik van Riel <riel(a)surriel.com> Cc: Ryan Roberts <ryan.roberts(a)arm.com> Cc: Tangquan Zheng <zhengtangquan(a)oppo.com> Cc: Vlastimil Babka <vbabka(a)suse.cz> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/rmap.c | 46 ++++++++++++++++++++++++++++------------------ 1 file changed, 28 insertions(+), 18 deletions(-) --- a/mm/rmap.c~mm-rmap-fix-potential-out-of-bounds-page-table-access-during-batched-unmap +++ a/mm/rmap.c @@ -1845,23 +1845,32 @@ void folio_remove_rmap_pud(struct folio #endif } -/* We support batch unmapping of PTEs for lazyfree large folios */ -static inline bool can_batch_unmap_folio_ptes(unsigned long addr, - struct folio *folio, pte_t *ptep) +static inline unsigned int folio_unmap_pte_batch(struct folio *folio, + struct page_vma_mapped_walk *pvmw, + enum ttu_flags flags, pte_t pte) { const fpb_t fpb_flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY; - int max_nr = folio_nr_pages(folio); - pte_t pte = ptep_get(ptep); + unsigned long end_addr, addr = pvmw->address; + struct vm_area_struct *vma = pvmw->vma; + unsigned int max_nr; + + if (flags & TTU_HWPOISON) + return 1; + if (!folio_test_large(folio)) + return 1; + + /* We may only batch within a single VMA and a single page table. */ + end_addr = pmd_addr_end(addr, vma->vm_end); + max_nr = (end_addr - addr) >> PAGE_SHIFT; + /* We only support lazyfree batching for now ... */ if (!folio_test_anon(folio) || folio_test_swapbacked(folio)) - return false; + return 1; if (pte_unused(pte)) - return false; - if (pte_pfn(pte) != folio_pfn(folio)) - return false; + return 1; - return folio_pte_batch(folio, addr, ptep, pte, max_nr, fpb_flags, NULL, - NULL, NULL) == max_nr; + return folio_pte_batch(folio, addr, pvmw->pte, pte, max_nr, fpb_flags, + NULL, NULL, NULL); } /* @@ -2024,9 +2033,7 @@ static bool try_to_unmap_one(struct foli if (pte_dirty(pteval)) folio_mark_dirty(folio); } else if (likely(pte_present(pteval))) { - if (folio_test_large(folio) && !(flags & TTU_HWPOISON) && - can_batch_unmap_folio_ptes(address, folio, pvmw.pte)) - nr_pages = folio_nr_pages(folio); + nr_pages = folio_unmap_pte_batch(folio, &pvmw, flags, pteval); end_addr = address + nr_pages * PAGE_SIZE; flush_cache_range(vma, address, end_addr); @@ -2206,13 +2213,16 @@ discard: hugetlb_remove_rmap(folio); } else { folio_remove_rmap_ptes(folio, subpage, nr_pages, vma); - folio_ref_sub(folio, nr_pages - 1); } if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); - folio_put(folio); - /* We have already batched the entire folio */ - if (nr_pages > 1) + folio_put_refs(folio, nr_pages); + + /* + * If we are sure that we batched the entire folio and cleared + * all PTEs, we can just optimize and stop right here. + */ + if (nr_pages == folio_nr_pages(folio)) goto walk_done; continue; walk_abort: _ Patches currently in -mm which might be from lance.yang(a)linux.dev are mm-rmap-fix-potential-out-of-bounds-page-table-access-during-batched-unmap.patch

1 month, 2 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror June 2025