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

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

From: Frank Li Frank.Li@nxp.com

[ Upstream commit 1b8be5ecff26201bafb0a554c74e91571299fb94 ]

When IP version >= DEV_VER_V2, gadget:sg_supported is true. So uvc gadget function driver will use sg to equeue data, first is 8bytes header, the second is 1016bytes data.

cdns3_prepare_trb: ep2in: trb 0000000000ac755f, dma buf: 0xbf455000, size: 8, burst: 128 ctrl: 0x00000415 (C=1, T=0, ISP, CHAIN, Normal) cdns3_prepare_trb: ep2in: trb 00000000a574e693, dma buf: 0xc0200fe0, size: 1016, burst: 128 ctrl: 0x00000405 (C=1, T=0, ISP, Normal)

But cdns3_ep_run_transfer() can't correctly handle this case, which only support one TRB for ISO transfer.

The controller requires duplicate the TD for each SOF if priv_ep->interval is not 1. DMA will read data from DDR to internal FIFO when get SOF. Send data to bus when receive IN token. DMA always refill FIFO when get SOF regardless host send IN token or not. If host send IN token later, some frames data will be lost.

Fixed it by below major steps:

1. Calculate numembers of TRB base on sg_nums and priv_ep->interval. 2. Remove CHAIN flags for each end TRB of TD when duplicate TD. 3. The controller requires LINK TRB must be first TRB of TD. When check there are not enough TRBs lefts, just fill LINK TRB for left TRBs.

.... CHAIN_TRB DATA_TRB, CHAIN_TRB DATA_TRB, LINK_TRB ... LINK_TRB ^End of TRB List

Cc: stable@vger.kernel.org Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver") Signed-off-by: Frank Li Frank.Li@nxp.com Link: https://lore.kernel.org/r/20231224153816.1664687-2-Frank.Li@nxp.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/cdns3/gadget.c | 51 ++++++++++++++++++++++++++++++-------- 1 file changed, 40 insertions(+), 11 deletions(-)

diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c index 82b6fd2bc890..575180a59ad4 100644 --- a/drivers/usb/cdns3/gadget.c +++ b/drivers/usb/cdns3/gadget.c @@ -1118,6 +1118,7 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, dma_addr_t trb_dma; u32 togle_pcs = 1; int sg_iter = 0; + int num_trb_req; int num_trb; int address; u32 control; @@ -1126,15 +1127,13 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, struct scatterlist *s = NULL; bool sg_supported = !!(request->num_mapped_sgs);

+ num_trb_req = sg_supported ? request->num_mapped_sgs : 1; + + /* ISO transfer require each SOF have a TD, each TD include some TRBs */ if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) - num_trb = priv_ep->interval; + num_trb = priv_ep->interval * num_trb_req; else - num_trb = sg_supported ? request->num_mapped_sgs : 1; - - if (num_trb > priv_ep->free_trbs) { - priv_ep->flags |= EP_RING_FULL; - return -ENOBUFS; - } + num_trb = num_trb_req;

priv_req = to_cdns3_request(request); address = priv_ep->endpoint.desc->bEndpointAddress; @@ -1183,14 +1182,31 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep,

link_trb->control = cpu_to_le32(((priv_ep->pcs) ? TRB_CYCLE : 0) | TRB_TYPE(TRB_LINK) | TRB_TOGGLE | ch_bit); + + if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) { + /* + * ISO require LINK TRB must be first one of TD. + * Fill LINK TRBs for left trb space to simply software process logic. + */ + while (priv_ep->enqueue) { + *trb = *link_trb; + trace_cdns3_prepare_trb(priv_ep, trb); + + cdns3_ep_inc_enq(priv_ep); + trb = priv_ep->trb_pool + priv_ep->enqueue; + priv_req->trb = trb; + } + } + } + + if (num_trb > priv_ep->free_trbs) { + priv_ep->flags |= EP_RING_FULL; + return -ENOBUFS; }

if (priv_dev->dev_ver <= DEV_VER_V2) togle_pcs = cdns3_wa1_update_guard(priv_ep, trb);

- if (sg_supported) - s = request->sg; - /* set incorrect Cycle Bit for first trb*/ control = priv_ep->pcs ? 0 : TRB_CYCLE; trb->length = 0; @@ -1208,6 +1224,9 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, do { u32 length;

+ if (!(sg_iter % num_trb_req) && sg_supported) + s = request->sg; + /* fill TRB */ control |= TRB_TYPE(TRB_NORMAL); if (sg_supported) { @@ -1249,7 +1268,7 @@ static int cdns3_ep_run_transfer(struct cdns3_endpoint *priv_ep, if (sg_supported) { trb->control |= cpu_to_le32(TRB_ISP); /* Don't set chain bit for last TRB */ - if (sg_iter < num_trb - 1) + if ((sg_iter % num_trb_req) < num_trb_req - 1) trb->control |= cpu_to_le32(TRB_CHAIN);

s = sg_next(s); @@ -1507,6 +1526,12 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev,

/* The TRB was changed as link TRB, and the request was handled at ep_dequeue */ while (TRB_FIELD_TO_TYPE(le32_to_cpu(trb->control)) == TRB_LINK) { + + /* ISO ep_traddr may stop at LINK TRB */ + if (priv_ep->dequeue == cdns3_get_dma_pos(priv_dev, priv_ep) && + priv_ep->type == USB_ENDPOINT_XFER_ISOC) + break; + trace_cdns3_complete_trb(priv_ep, trb); cdns3_ep_inc_deq(priv_ep); trb = priv_ep->trb_pool + priv_ep->dequeue; @@ -1539,6 +1564,10 @@ static void cdns3_transfer_completed(struct cdns3_device *priv_dev, }

if (request_handled) { + /* TRBs are duplicated by priv_ep->interval time for ISO IN */ + if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && priv_ep->dir) + request->actual /= priv_ep->interval; + cdns3_gadget_giveback(priv_ep, priv_req, 0); request_handled = false; transfer_end = false;

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

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

From: Frank Li Frank.Li@nxp.com

[ Upstream commit 92f02efa1d86d7dcaef7f38a5fe3396c4e88a93c ]

ISO basic transfer is ITP(SOF) Package_0 Package_1 ... Package_n

CDNS3 DMA start dma transfer from memmory to internal FIFO when get SOF, controller will transfer data to usb bus from internal FIFO when get IN token.

According USB spec defination: Maximum number of packets = (bMaxBurst + 1) * (Mult + 1)

Internal memory should be the same as (bMaxBurst + 1) * (Mult + 1). DMA don't fetch data advance when ISO transfer, so only reserve (bMaxBurst + 1) * (Mult + 1) internal memory for ISO transfer.

Need save Mult and bMaxBurst information and set it into EP_CFG register, otherwise only 1 package is sent by controller, other package will be lost.

Cc: stable@vger.kernel.org Fixes: 7733f6c32e36 ("usb: cdns3: Add Cadence USB3 DRD Driver") Signed-off-by: Frank Li Frank.Li@nxp.com Link: https://lore.kernel.org/r/20231224153816.1664687-3-Frank.Li@nxp.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/usb/cdns3/gadget.c | 59 +++++++++++++++++++++++--------------- drivers/usb/cdns3/gadget.h | 3 ++ 2 files changed, 39 insertions(+), 23 deletions(-)

diff --git a/drivers/usb/cdns3/gadget.c b/drivers/usb/cdns3/gadget.c index ee64c4ab8dd2..118c9402bb60 100644 --- a/drivers/usb/cdns3/gadget.c +++ b/drivers/usb/cdns3/gadget.c @@ -2063,11 +2063,10 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable) bool is_iso_ep = (priv_ep->type == USB_ENDPOINT_XFER_ISOC); struct cdns3_device *priv_dev = priv_ep->cdns3_dev; u32 bEndpointAddress = priv_ep->num | priv_ep->dir; - u32 max_packet_size = 0; - u8 maxburst = 0; + u32 max_packet_size = priv_ep->wMaxPacketSize; + u8 maxburst = priv_ep->bMaxBurst; u32 ep_cfg = 0; u8 buffering; - u8 mult = 0; int ret;

buffering = priv_dev->ep_buf_size - 1; @@ -2089,8 +2088,7 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable) break; default: ep_cfg = EP_CFG_EPTYPE(USB_ENDPOINT_XFER_ISOC); - mult = priv_dev->ep_iso_burst - 1; - buffering = mult + 1; + buffering = (priv_ep->bMaxBurst + 1) * (priv_ep->mult + 1) - 1; }

switch (priv_dev->gadget.speed) { @@ -2101,17 +2099,8 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable) max_packet_size = is_iso_ep ? 1024 : 512; break; case USB_SPEED_SUPER: - /* It's limitation that driver assumes in driver. */ - mult = 0; - max_packet_size = 1024; - if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) { - maxburst = priv_dev->ep_iso_burst - 1; - buffering = (mult + 1) * - (maxburst + 1); - - if (priv_ep->interval > 1) - buffering++; - } else { + if (priv_ep->type != USB_ENDPOINT_XFER_ISOC) { + max_packet_size = 1024; maxburst = priv_dev->ep_buf_size - 1; } break; @@ -2140,7 +2129,6 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable) if (priv_dev->dev_ver < DEV_VER_V2) priv_ep->trb_burst_size = 16;

- mult = min_t(u8, mult, EP_CFG_MULT_MAX); buffering = min_t(u8, buffering, EP_CFG_BUFFERING_MAX); maxburst = min_t(u8, maxburst, EP_CFG_MAXBURST_MAX);

@@ -2174,7 +2162,7 @@ int cdns3_ep_config(struct cdns3_endpoint *priv_ep, bool enable) }

ep_cfg |= EP_CFG_MAXPKTSIZE(max_packet_size) | - EP_CFG_MULT(mult) | + EP_CFG_MULT(priv_ep->mult) | /* must match EP setting */ EP_CFG_BUFFERING(buffering) | EP_CFG_MAXBURST(maxburst);

@@ -2264,6 +2252,13 @@ usb_ep *cdns3_gadget_match_ep(struct usb_gadget *gadget, priv_ep->type = usb_endpoint_type(desc); priv_ep->flags |= EP_CLAIMED; priv_ep->interval = desc->bInterval ? BIT(desc->bInterval - 1) : 0; + priv_ep->wMaxPacketSize = usb_endpoint_maxp(desc); + priv_ep->mult = USB_EP_MAXP_MULT(priv_ep->wMaxPacketSize); + priv_ep->wMaxPacketSize &= USB_ENDPOINT_MAXP_MASK; + if (priv_ep->type == USB_ENDPOINT_XFER_ISOC && comp_desc) { + priv_ep->mult = USB_SS_MULT(comp_desc->bmAttributes) - 1; + priv_ep->bMaxBurst = comp_desc->bMaxBurst; + }

spin_unlock_irqrestore(&priv_dev->lock, flags); return &priv_ep->endpoint; @@ -3033,22 +3028,40 @@ static int cdns3_gadget_check_config(struct usb_gadget *gadget) struct cdns3_endpoint *priv_ep; struct usb_ep *ep; int n_in = 0; + int iso = 0; + int out = 1; int total; + int n;

list_for_each_entry(ep, &gadget->ep_list, ep_list) { priv_ep = ep_to_cdns3_ep(ep); - if ((priv_ep->flags & EP_CLAIMED) && (ep->address & USB_DIR_IN)) - n_in++; + if (!(priv_ep->flags & EP_CLAIMED)) + continue; + + n = (priv_ep->mult + 1) * (priv_ep->bMaxBurst + 1); + if (ep->address & USB_DIR_IN) { + /* + * ISO transfer: DMA start move data when get ISO, only transfer + * data as min(TD size, iso). No benefit for allocate bigger + * internal memory than 'iso'. + */ + if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) + iso += n; + else + n_in++; + } else { + if (priv_ep->type == USB_ENDPOINT_XFER_ISOC) + out = max_t(int, out, n); + } }

/* 2KB are reserved for EP0, 1KB for out*/ - total = 2 + n_in + 1; + total = 2 + n_in + out + iso;

if (total > priv_dev->onchip_buffers) return -ENOMEM;

- priv_dev->ep_buf_size = priv_dev->ep_iso_burst = - (priv_dev->onchip_buffers - 2) / (n_in + 1); + priv_dev->ep_buf_size = (priv_dev->onchip_buffers - 2 - iso) / (n_in + out);

return 0; } diff --git a/drivers/usb/cdns3/gadget.h b/drivers/usb/cdns3/gadget.h index 32825477edd3..aeb2211228c1 100644 --- a/drivers/usb/cdns3/gadget.h +++ b/drivers/usb/cdns3/gadget.h @@ -1167,6 +1167,9 @@ struct cdns3_endpoint { u8 dir; u8 num; u8 type; + u8 mult; + u8 bMaxBurst; + u16 wMaxPacketSize; int interval;

int free_trbs;

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

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

From: qizhong cheng qizhong.cheng@mediatek.com

[ Upstream commit 4e11c29873a8a296a20f99b3e03095e65ebf897d ]

We found a failure when using the iperf tool during WiFi performance testing, where some MSIs were received while clearing the interrupt status, and these MSIs cannot be serviced.

The interrupt status can be cleared even if the MSI status remains pending. As such, given the edge-triggered interrupt type, its status should be cleared before being dispatched to the handler of the underling device.

[kwilczynski: commit log, code comment wording] Link: https://lore.kernel.org/linux-pci/20231211094923.31967-1-jianjun.wang@mediat... Fixes: 43e6409db64d ("PCI: mediatek: Add MSI support for MT2712 and MT7622") Signed-off-by: qizhong cheng qizhong.cheng@mediatek.com Signed-off-by: Jianjun Wang jianjun.wang@mediatek.com Signed-off-by: Krzysztof Wilczyński kwilczynski@kernel.org [bhelgaas: rewrap comment] Signed-off-by: Bjorn Helgaas bhelgaas@google.com Reviewed-by: AngeloGioacchino Del Regno angelogioacchino.delregno@collabora.com Cc: stable@vger.kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pci/controller/pcie-mediatek.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c index 23548b517e4b..ea91d63c8be1 100644 --- a/drivers/pci/controller/pcie-mediatek.c +++ b/drivers/pci/controller/pcie-mediatek.c @@ -620,14 +620,20 @@ static void mtk_pcie_intr_handler(struct irq_desc *desc) if (status & MSI_STATUS){ unsigned long imsi_status;

+ /* + * The interrupt status can be cleared even if the + * MSI status remains pending. As such, given the + * edge-triggered interrupt type, its status should + * be cleared before being dispatched to the + * handler of the underlying device. + */ + writel(MSI_STATUS, port->base + PCIE_INT_STATUS); while ((imsi_status = readl(port->base + PCIE_IMSI_STATUS))) { for_each_set_bit(bit, &imsi_status, MTK_MSI_IRQS_NUM) { virq = irq_find_mapping(port->inner_domain, bit); generic_handle_irq(virq); } } - /* Clear MSI interrupt status */ - writel(MSI_STATUS, port->base + PCIE_INT_STATUS); } }

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

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

From: Daniel Lezcano daniel.lezcano@linaro.org

[ Upstream commit e2c77032fcbe515194107994d12cd72ddb77b022 ]

The macros for the unit conversion for frequency are duplicated in different places.

Provide these macros in the 'units' header, so they can be reused.

Link: https://lkml.kernel.org/r/20210816114732.1834145-3-daniel.lezcano@linaro.org Signed-off-by: Daniel Lezcano daniel.lezcano@linaro.org Reviewed-by: Christian Eggers ceggers@arri.de Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Cc: Chanwoo Choi cw00.choi@samsung.com Cc: Guenter Roeck linux@roeck-us.net Cc: Jonathan Cameron jic23@kernel.org Cc: Jonathan Cameron Jonathan.Cameron@huawei.com Cc: Kyungmin Park kyungmin.park@samsung.com Cc: Lars-Peter Clausen lars@metafoo.de Cc: Lukasz Luba lukasz.luba@arm.com Cc: Maxime Coquelin mcoquelin.stm32@gmail.com Cc: Miquel Raynal miquel.raynal@bootlin.com Cc: MyungJoo Ham myungjoo.ham@samsung.com Cc: Peter Meerwald pmeerw@pmeerw.net Cc: "Rafael J. Wysocki" rafael@kernel.org Cc: Zhang Rui rui.zhang@intel.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Stable-dep-of: 3ef79cd14122 ("serial: sc16is7xx: set safe default SPI clock frequency") Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/units.h | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/include/linux/units.h b/include/linux/units.h index 62149b5082e1..b61e3f6d5099 100644 --- a/include/linux/units.h +++ b/include/linux/units.h @@ -20,6 +20,10 @@ #define PICO 1000000000000ULL #define FEMTO 1000000000000000ULL

+#define HZ_PER_KHZ 1000UL +#define KHZ_PER_MHZ 1000UL +#define HZ_PER_MHZ 1000000UL + #define MILLIWATT_PER_WATT 1000UL #define MICROWATT_PER_MILLIWATT 1000UL #define MICROWATT_PER_WATT 1000000UL

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

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

From: Oleksij Rempel o.rempel@pengutronix.de

[ Upstream commit 029b42d8519cef70c4fb5fcaccd08f1053ed2bf0 ]

Provide a macro to filter all SPI_MODE_0,1,2,3 mode in one run.

The latest SPI framework will parse the devicetree in following call sequence: of_register_spi_device() -> of_spi_parse_dt() So, driver do not need to pars the devicetree and will get prepared flags in the probe.

On one hand it is good far most drivers. On other hand some drivers need to filter flags provide by SPI framework and apply know to work flags. This drivers may use SPI_MODE_X_MASK to filter MODE flags and set own, known flags: spi->flags &= ~SPI_MODE_X_MASK; spi->flags |= SPI_MODE_0;

Signed-off-by: Oleksij Rempel o.rempel@pengutronix.de Link: https://lore.kernel.org/r/20201027095724.18654-2-o.rempel@pengutronix.de Signed-off-by: Mark Brown broonie@kernel.org Stable-dep-of: 6d710b769c1f ("serial: sc16is7xx: add check for unsupported SPI modes during probe") Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/spi/spi.h | 1 + 1 file changed, 1 insertion(+)

diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index e1d88630ff24..ab7747549d23 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -171,6 +171,7 @@ struct spi_device { #define SPI_MODE_1 (0|SPI_CPHA) #define SPI_MODE_2 (SPI_CPOL|0) #define SPI_MODE_3 (SPI_CPOL|SPI_CPHA) +#define SPI_MODE_X_MASK (SPI_CPOL|SPI_CPHA) #define SPI_CS_HIGH 0x04 /* chipselect active high? */ #define SPI_LSB_FIRST 0x08 /* per-word bits-on-wire */ #define SPI_3WIRE 0x10 /* SI/SO signals shared */

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

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

From: Marcelo Schmitt marcelo.schmitt@analog.com

[ Upstream commit 149694f5e79b0c7a36ceb76e7c0d590db8f151c1 ]

The ad7091r-base driver sets up an interrupt handler for firing events when inputs are either above or below a certain threshold. However, for the interrupt signal to come from the device it must be configured to enable the ALERT/BUSY/GPO pin to be used as ALERT, which was not being done until now. Enable interrupt signals on the ALERT/BUSY/GPO pin by setting the proper bit in the configuration register.

Signed-off-by: Marcelo Schmitt marcelo.schmitt@analog.com Link: https://lore.kernel.org/r/e8da2ee98d6df88318b14baf3dc9630e20218418.170274624... Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Stable-dep-of: 020e71c7ffc2 ("iio: adc: ad7091r: Allow users to configure device events") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iio/adc/ad7091r-base.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/drivers/iio/adc/ad7091r-base.c b/drivers/iio/adc/ad7091r-base.c index 811f04448d8d..ad089c0ff953 100644 --- a/drivers/iio/adc/ad7091r-base.c +++ b/drivers/iio/adc/ad7091r-base.c @@ -28,6 +28,7 @@ #define AD7091R_REG_RESULT_CONV_RESULT(x) ((x) & 0xfff)

/* AD7091R_REG_CONF */ +#define AD7091R_REG_CONF_ALERT_EN BIT(4) #define AD7091R_REG_CONF_AUTO BIT(8) #define AD7091R_REG_CONF_CMD BIT(10)

@@ -232,6 +233,11 @@ int ad7091r_probe(struct device *dev, const char *name, iio_dev->channels = chip_info->channels;

if (irq) { + ret = regmap_update_bits(st->map, AD7091R_REG_CONF, + AD7091R_REG_CONF_ALERT_EN, BIT(4)); + if (ret) + return ret; + ret = devm_request_threaded_irq(dev, irq, NULL, ad7091r_event_handler, IRQF_TRIGGER_FALLING | IRQF_ONESHOT, name, iio_dev);

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

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

From: Marcelo Schmitt marcelo.schmitt@analog.com

[ Upstream commit e71c5c89bcb165a02df35325aa13d1ee40112401 ]

The ADC needs a voltage reference to work correctly. Users can provide an external voltage reference or use the chip internal reference to operate the ADC. The availability of an in chip reference for the ADC saves the user from having to supply an external voltage reference, which makes the external reference an optional property as described in the device tree documentation. Though, to use the internal reference, it must be enabled by writing to the configuration register. Enable AD7091R internal voltage reference if no external vref is supplied.

Fixes: 260442cc5be4 ("iio: adc: ad7091r5: Add scale and external VREF support") Signed-off-by: Marcelo Schmitt marcelo.schmitt@analog.com Link: https://lore.kernel.org/r/b865033fa6a4fc4bf2b4a98ec51a6144e0f64f77.170301335... Cc: Stable@vger.kernel.org Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/iio/adc/ad7091r-base.c | 7 +++++++ drivers/iio/adc/ad7091r-base.h | 2 ++ 2 files changed, 9 insertions(+)

diff --git a/drivers/iio/adc/ad7091r-base.c b/drivers/iio/adc/ad7091r-base.c index 9ddda08918db..f345542e69a0 100644 --- a/drivers/iio/adc/ad7091r-base.c +++ b/drivers/iio/adc/ad7091r-base.c @@ -405,7 +405,14 @@ int ad7091r_probe(struct device *dev, const char *name, if (IS_ERR(st->vref)) { if (PTR_ERR(st->vref) == -EPROBE_DEFER) return -EPROBE_DEFER; + st->vref = NULL; + /* Enable internal vref */ + ret = regmap_set_bits(st->map, AD7091R_REG_CONF, + AD7091R_REG_CONF_INT_VREF); + if (ret) + return dev_err_probe(st->dev, ret, + "Error on enable internal reference\n"); } else { ret = regulator_enable(st->vref); if (ret) diff --git a/drivers/iio/adc/ad7091r-base.h b/drivers/iio/adc/ad7091r-base.h index 7a78976a2f80..b9e1c8bf3440 100644 --- a/drivers/iio/adc/ad7091r-base.h +++ b/drivers/iio/adc/ad7091r-base.h @@ -8,6 +8,8 @@ #ifndef __DRIVERS_IIO_ADC_AD7091R_BASE_H__ #define __DRIVERS_IIO_ADC_AD7091R_BASE_H__

+#define AD7091R_REG_CONF_INT_VREF BIT(0) + /* AD7091R_REG_CH_LIMIT */ #define AD7091R_HIGH_LIMIT 0xFFF #define AD7091R_LOW_LIMIT 0x0

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

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

From: Jonathan Cameron Jonathan.Cameron@huawei.com

commit 8a0080af84d3fb2423f0b3b55eff666f545eb097 upstream.

In order to avoid unnecessary pollution of the global symbol namespace move the core/library functions into a specific namespace and import that into the various specific device drivers that use them.

For more information see https://lwn.net/Articles/760045/

An alternative here would be to conclude that we are unlikely to see support for the other ad7091r parts in the near future and just merge the two modules into one supporting just the i2c -5 variant.

Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Cc: Paul Cercueil paul@crapouillou.net Reviewed-by: Paul Cercueil paul@crapouillou.net Reviewed-by: Andy Shevchenko andy.shevchenko@gmail.com Link: https://lore.kernel.org/r/20220130205701.334592-3-jic23@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iio/adc/ad7091r-base.c | 4 ++-- drivers/iio/adc/ad7091r5.c | 1 + 2 files changed, 3 insertions(+), 2 deletions(-)

--- a/drivers/iio/adc/ad7091r-base.c +++ b/drivers/iio/adc/ad7091r-base.c @@ -429,7 +429,7 @@ int ad7091r_probe(struct device *dev, co

return devm_iio_device_register(dev, iio_dev); } -EXPORT_SYMBOL_GPL(ad7091r_probe); +EXPORT_SYMBOL_NS_GPL(ad7091r_probe, IIO_AD7091R);

static bool ad7091r_writeable_reg(struct device *dev, unsigned int reg) { @@ -459,7 +459,7 @@ const struct regmap_config ad7091r_regma .writeable_reg = ad7091r_writeable_reg, .volatile_reg = ad7091r_volatile_reg, }; -EXPORT_SYMBOL_GPL(ad7091r_regmap_config); +EXPORT_SYMBOL_NS_GPL(ad7091r_regmap_config, IIO_AD7091R);

MODULE_AUTHOR("Beniamin Bia beniamin.bia@analog.com"); MODULE_DESCRIPTION("Analog Devices AD7091Rx multi-channel converters"); --- a/drivers/iio/adc/ad7091r5.c +++ b/drivers/iio/adc/ad7091r5.c @@ -91,3 +91,4 @@ module_i2c_driver(ad7091r5_driver); MODULE_AUTHOR("Beniamin Bia beniamin.bia@analog.com"); MODULE_DESCRIPTION("Analog Devices AD7091R5 multi-channel ADC driver"); MODULE_LICENSE("GPL v2"); +MODULE_IMPORT_NS(IIO_AD7091R);

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

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

From: Herbert Xu herbert@gondor.apana.org.au

commit 27016f75f5ed47e2d8e0ca75a8ff1f40bc1a5e27 upstream.

Disallow registration of two algorithms with identical driver names.

Cc: stable@vger.kernel.org Reported-by: Ovidiu Panait ovidiu.panait@windriver.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- crypto/algapi.c | 1 + 1 file changed, 1 insertion(+)

--- a/crypto/algapi.c +++ b/crypto/algapi.c @@ -258,6 +258,7 @@ static struct crypto_larval *__crypto_re }

if (!strcmp(q->cra_driver_name, alg->cra_name) || + !strcmp(q->cra_driver_name, alg->cra_driver_name) || !strcmp(q->cra_name, alg->cra_driver_name)) goto err; }

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

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

From: Herbert Xu herbert@gondor.apana.org.au

commit 78aafb3884f6bc6636efcc1760c891c8500b9922 upstream.

There is a dead-lock in the hwrng device read path. This triggers when the user reads from /dev/hwrng into memory also mmap-ed from /dev/hwrng. The resulting page fault triggers a recursive read which then dead-locks.

Fix this by using a stack buffer when calling copy_to_user.

Reported-by: Edward Adam Davis eadavis@qq.com Reported-by: syzbot+c52ab18308964d248092@syzkaller.appspotmail.com Fixes: 9996508b3353 ("hwrng: core - Replace u32 in driver API with byte array") Cc: stable@vger.kernel.org Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/char/hw_random/core.c | 34 +++++++++++++++++++++------------- 1 file changed, 21 insertions(+), 13 deletions(-)

--- a/drivers/char/hw_random/core.c +++ b/drivers/char/hw_random/core.c @@ -24,10 +24,13 @@ #include <linux/random.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/string.h> #include <linux/uaccess.h>

#define RNG_MODULE_NAME "hw_random"

+#define RNG_BUFFER_SIZE (SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES) + static struct hwrng *current_rng; /* the current rng has been explicitly chosen by user via sysfs */ static int cur_rng_set_by_user; @@ -59,7 +62,7 @@ static inline int rng_get_data(struct hw

static size_t rng_buffer_size(void) { - return SMP_CACHE_BYTES < 32 ? 32 : SMP_CACHE_BYTES; + return RNG_BUFFER_SIZE; }

static void add_early_randomness(struct hwrng *rng) @@ -206,6 +209,7 @@ static inline int rng_get_data(struct hw static ssize_t rng_dev_read(struct file *filp, char __user *buf, size_t size, loff_t *offp) { + u8 buffer[RNG_BUFFER_SIZE]; ssize_t ret = 0; int err = 0; int bytes_read, len; @@ -233,34 +237,37 @@ static ssize_t rng_dev_read(struct file if (bytes_read < 0) { err = bytes_read; goto out_unlock_reading; + } else if (bytes_read == 0 && + (filp->f_flags & O_NONBLOCK)) { + err = -EAGAIN; + goto out_unlock_reading; } + data_avail = bytes_read; }

- if (!data_avail) { - if (filp->f_flags & O_NONBLOCK) { - err = -EAGAIN; - goto out_unlock_reading; - } - } else { - len = data_avail; + len = data_avail; + if (len) { if (len > size) len = size;

data_avail -= len;

- if (copy_to_user(buf + ret, rng_buffer + data_avail, - len)) { + memcpy(buffer, rng_buffer + data_avail, len); + } + mutex_unlock(&reading_mutex); + put_rng(rng); + + if (len) { + if (copy_to_user(buf + ret, buffer, len)) { err = -EFAULT; - goto out_unlock_reading; + goto out; }

size -= len; ret += len; }

- mutex_unlock(&reading_mutex); - put_rng(rng);

if (need_resched()) schedule_timeout_interruptible(1); @@ -271,6 +278,7 @@ static ssize_t rng_dev_read(struct file } } out: + memzero_explicit(buffer, sizeof(buffer)); return ret ? : err;

out_unlock_reading:

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

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

From: Xiaolei Wang xiaolei.wang@windriver.com

commit d5362c37e1f8a40096452fc201c30e705750e687 upstream.

Free driver_override when rpmsg_remove(), otherwise the following memory leak will occur:

unreferenced object 0xffff0000d55d7080 (size 128): comm "kworker/u8:2", pid 56, jiffies 4294893188 (age 214.272s) hex dump (first 32 bytes): 72 70 6d 73 67 5f 6e 73 00 00 00 00 00 00 00 00 rpmsg_ns........ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<000000009c94c9c1>] __kmem_cache_alloc_node+0x1f8/0x320 [<000000002300d89b>] __kmalloc_node_track_caller+0x44/0x70 [<00000000228a60c3>] kstrndup+0x4c/0x90 [<0000000077158695>] driver_set_override+0xd0/0x164 [<000000003e9c4ea5>] rpmsg_register_device_override+0x98/0x170 [<000000001c0c89a8>] rpmsg_ns_register_device+0x24/0x30 [<000000008bbf8fa2>] rpmsg_probe+0x2e0/0x3ec [<00000000e65a68df>] virtio_dev_probe+0x1c0/0x280 [<00000000443331cc>] really_probe+0xbc/0x2dc [<00000000391064b1>] __driver_probe_device+0x78/0xe0 [<00000000a41c9a5b>] driver_probe_device+0xd8/0x160 [<000000009c3bd5df>] __device_attach_driver+0xb8/0x140 [<0000000043cd7614>] bus_for_each_drv+0x7c/0xd4 [<000000003b929a36>] __device_attach+0x9c/0x19c [<00000000a94e0ba8>] device_initial_probe+0x14/0x20 [<000000003c999637>] bus_probe_device+0xa0/0xac

Signed-off-by: Xiaolei Wang xiaolei.wang@windriver.com Fixes: b0b03b811963 ("rpmsg: Release rpmsg devices in backends") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20231215020049.78750-1-xiaolei.wang@windriver.com Signed-off-by: Mathieu Poirier mathieu.poirier@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/rpmsg/virtio_rpmsg_bus.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/rpmsg/virtio_rpmsg_bus.c +++ b/drivers/rpmsg/virtio_rpmsg_bus.c @@ -387,6 +387,7 @@ static void virtio_rpmsg_release_device( struct rpmsg_device *rpdev = to_rpmsg_device(dev); struct virtio_rpmsg_channel *vch = to_virtio_rpmsg_channel(rpdev);

+ kfree(rpdev->driver_override); kfree(vch); }

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

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

From: Helge Deller deller@gmx.de

commit 735ae74f73e55c191d48689bd11ff4a06ea0508f upstream.

When running with narrow firmware (64-bit kernel using a 32-bit firmware), extend PDC addresses into the 0xfffffff0.00000000 region instead of the 0xf0f0f0f0.00000000 region.

This fixes the power button on the C3700 machine in qemu (64-bit CPU with 32-bit firmware), and my assumption is that the previous code was really never used (because most 64-bit machines have a 64-bit firmware), or it just worked on very old machines because they may only decode 40-bit of virtual addresses.

Cc: stable@vger.kernel.org Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/parisc/kernel/firmware.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/arch/parisc/kernel/firmware.c +++ b/arch/parisc/kernel/firmware.c @@ -123,10 +123,10 @@ static unsigned long f_extend(unsigned l #ifdef CONFIG_64BIT if(unlikely(parisc_narrow_firmware)) { if((address & 0xff000000) == 0xf0000000) - return 0xf0f0f0f000000000UL | (u32)address; + return (0xfffffff0UL << 32) | (u32)address;

if((address & 0xf0000000) == 0xf0000000) - return 0xffffffff00000000UL | (u32)address; + return (0xffffffffUL << 32) | (u32)address; } #endif return address;

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

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

From: Rafael J. Wysocki rafael.j.wysocki@intel.com

commit 7d4b5d7a37bdd63a5a3371b988744b060d5bb86f upstream.

In preparation for subsequent changes, introduce a specialized variant of async_schedule_dev() that will not invoke the argument function synchronously when it cannot be scheduled for asynchronous execution.

The new function, async_schedule_dev_nocall(), will be used for fixing possible deadlocks in the system-wide power management core code.

Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Reviewed-by: Stanislaw Gruszka stanislaw.gruszka@linux.intel.com for the series. Tested-by: Youngmin Nam youngmin.nam@samsung.com Reviewed-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/async.h | 2 ++ kernel/async.c | 29 +++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+)

--- a/include/linux/async.h +++ b/include/linux/async.h @@ -90,6 +90,8 @@ async_schedule_dev(async_func_t func, st return async_schedule_node(func, dev, dev_to_node(dev)); }

+bool async_schedule_dev_nocall(async_func_t func, struct device *dev); + /** * async_schedule_dev_domain - A device specific version of async_schedule_domain * @func: function to execute asynchronously --- a/kernel/async.c +++ b/kernel/async.c @@ -244,6 +244,35 @@ async_cookie_t async_schedule_node(async EXPORT_SYMBOL_GPL(async_schedule_node);

/** + * async_schedule_dev_nocall - A simplified variant of async_schedule_dev() + * @func: function to execute asynchronously + * @dev: device argument to be passed to function + * + * @dev is used as both the argument for the function and to provide NUMA + * context for where to run the function. + * + * If the asynchronous execution of @func is scheduled successfully, return + * true. Otherwise, do nothing and return false, unlike async_schedule_dev() + * that will run the function synchronously then. + */ +bool async_schedule_dev_nocall(async_func_t func, struct device *dev) +{ + struct async_entry *entry; + + entry = kzalloc(sizeof(struct async_entry), GFP_KERNEL); + + /* Give up if there is no memory or too much work. */ + if (!entry || atomic_read(&entry_count) > MAX_WORK) { + kfree(entry); + return false; + } + + __async_schedule_node_domain(func, dev, dev_to_node(dev), + &async_dfl_domain, entry); + return true; +} + +/** * async_synchronize_full - synchronize all asynchronous function calls * * This function waits until all asynchronous function calls have been done.

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

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

From: Johan Hovold johan+linaro@kernel.org

commit 204f9ed4bad6293933179517624143b8f412347c upstream.

The USB DP/DM HS PHY interrupts need to be provided by the PDC interrupt controller in order to be able to wake the system up from low-power states and to be able to detect disconnect events, which requires triggering on falling edges.

A recent commit updated the trigger type but failed to change the interrupt provider as required. This leads to the current Linux driver failing to probe instead of printing an error during suspend and USB wakeup not working as intended.

Fixes: 84ad9ac8d9ca ("arm64: dts: qcom: sdm845: fix USB wakeup interrupt types") Fixes: ca4db2b538a1 ("arm64: dts: qcom: sdm845: Add USB-related nodes") Cc: stable@vger.kernel.org # 4.20 Signed-off-by: Johan Hovold johan+linaro@kernel.org Reviewed-by: Konrad Dybcio konrad.dybcio@linaro.org Link: https://lore.kernel.org/r/20231213173403.29544-3-johan+linaro@kernel.org Signed-off-by: Bjorn Andersson andersson@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm64/boot/dts/qcom/sdm845.dtsi | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)

--- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -3565,10 +3565,10 @@ <&gcc GCC_USB30_PRIM_MASTER_CLK>; assigned-clock-rates = <19200000>, <150000000>;

- interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 488 IRQ_TYPE_EDGE_BOTH>, - <GIC_SPI 489 IRQ_TYPE_EDGE_BOTH>; + interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>, + <&pdc_intc 8 IRQ_TYPE_EDGE_BOTH>, + <&pdc_intc 9 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq";

@@ -3613,10 +3613,10 @@ <&gcc GCC_USB30_SEC_MASTER_CLK>; assigned-clock-rates = <19200000>, <150000000>;

- interrupts = <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 487 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 490 IRQ_TYPE_EDGE_BOTH>, - <GIC_SPI 491 IRQ_TYPE_EDGE_BOTH>; + interrupts-extended = <&intc GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>, + <&intc GIC_SPI 487 IRQ_TYPE_LEVEL_HIGH>, + <&pdc_intc 10 IRQ_TYPE_EDGE_BOTH>, + <&pdc_intc 11 IRQ_TYPE_EDGE_BOTH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq";

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

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

From: Vegard Nossum vegard.nossum@oracle.com

commit 5889d6ede53bc17252f79c142387e007224aa554 upstream.

The code currently leaks the absolute path of the ABI files into the rendered documentation.

There exists code to prevent this, but it is not effective when an absolute path is passed, which it is when $srctree is used.

I consider this to be a minimal, stop-gap fix; a better fix would strip off the actual prefix instead of hacking it off with a regex.

Link: https://mastodon.social/@vegard/111677490643495163 Cc: Jani Nikula jani.nikula@intel.com Cc: stable@vger.kernel.org Signed-off-by: Vegard Nossum vegard.nossum@oracle.com Signed-off-by: Jonathan Corbet corbet@lwn.net Link: https://lore.kernel.org/r/20231231235959.3342928-1-vegard.nossum@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- scripts/get_abi.pl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/scripts/get_abi.pl +++ b/scripts/get_abi.pl @@ -75,7 +75,7 @@ sub parse_abi { $name =~ s,.*/,,;

my $fn = $file; - $fn =~ s,Documentation/ABI/,,; + $fn =~ s,.*Documentation/ABI/,,;

my $nametag = "File $fn"; $data{$nametag}->{what} = "File $name";

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

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

From: Andy Shevchenko andriy.shevchenko@linux.intel.com

commit 84a6be7db9050dd2601c9870f65eab9a665d2d5d upstream.

There is no need to duplicate what SPI core or individual controller drivers already do, i.e. mapping the buffers for DMA capable transfers.

Note, that the code, besides its redundancy, was buggy: strictly speaking there is no guarantee, while it's true for those which can use this code (see below), that the SPI host controller _is_ the device which does DMA.

Also see the Link tags below.

Additional notes. Currently only two SPI host controller drivers may use premapped (by the user) DMA buffers:

- drivers/spi/spi-au1550.c

- drivers/spi/spi-fsl-spi.c

Both of them have DMA mapping support code. I don't expect that SPI host controller code is worse than what has been done in mmc_spi. Hence I do not expect any regressions here. Otherwise, I'm pretty much sure these regressions have to be fixed in the respective drivers, and not here.

That said, remove all related pieces of DMA mapping code from mmc_spi.

Link: https://lore.kernel.org/linux-mmc/c73b9ba9-1699-2aff-e2fd-b4b4f292a3ca@raspb... Link: https://stackoverflow.com/questions/67620728/mmc-spi-issue-not-able-to-setup... Signed-off-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20231207221901.3259962-1-andriy.shevchenko@linux.i... Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/mmc/host/mmc_spi.c | 186 +-------------------------------------------- 1 file changed, 5 insertions(+), 181 deletions(-)

--- a/drivers/mmc/host/mmc_spi.c +++ b/drivers/mmc/host/mmc_spi.c @@ -15,7 +15,7 @@ #include <linux/slab.h> #include <linux/module.h> #include <linux/bio.h> -#include <linux/dma-mapping.h> +#include <linux/dma-direction.h> #include <linux/crc7.h> #include <linux/crc-itu-t.h> #include <linux/scatterlist.h> @@ -119,19 +119,14 @@ struct mmc_spi_host { struct spi_transfer status; struct spi_message readback;

- /* underlying DMA-aware controller, or null */ - struct device *dma_dev; - /* buffer used for commands and for message "overhead" */ struct scratch *data; - dma_addr_t data_dma;

/* Specs say to write ones most of the time, even when the card * has no need to read its input data; and many cards won't care. * This is our source of those ones. */ void *ones; - dma_addr_t ones_dma; };

@@ -147,11 +142,8 @@ static inline int mmc_cs_off(struct mmc_ return spi_setup(host->spi); }

-static int -mmc_spi_readbytes(struct mmc_spi_host *host, unsigned len) +static int mmc_spi_readbytes(struct mmc_spi_host *host, unsigned int len) { - int status; - if (len > sizeof(*host->data)) { WARN_ON(1); return -EIO; @@ -159,19 +151,7 @@ mmc_spi_readbytes(struct mmc_spi_host *h

host->status.len = len;

- if (host->dma_dev) - dma_sync_single_for_device(host->dma_dev, - host->data_dma, sizeof(*host->data), - DMA_FROM_DEVICE); - - status = spi_sync_locked(host->spi, &host->readback); - - if (host->dma_dev) - dma_sync_single_for_cpu(host->dma_dev, - host->data_dma, sizeof(*host->data), - DMA_FROM_DEVICE); - - return status; + return spi_sync_locked(host->spi, &host->readback); }

static int mmc_spi_skip(struct mmc_spi_host *host, unsigned long timeout, @@ -513,23 +493,11 @@ mmc_spi_command_send(struct mmc_spi_host t = &host->t; memset(t, 0, sizeof(*t)); t->tx_buf = t->rx_buf = data->status; - t->tx_dma = t->rx_dma = host->data_dma; t->len = cp - data->status; t->cs_change = 1; spi_message_add_tail(t, &host->m);

- if (host->dma_dev) { - host->m.is_dma_mapped = 1; - dma_sync_single_for_device(host->dma_dev, - host->data_dma, sizeof(*host->data), - DMA_BIDIRECTIONAL); - } status = spi_sync_locked(host->spi, &host->m); - - if (host->dma_dev) - dma_sync_single_for_cpu(host->dma_dev, - host->data_dma, sizeof(*host->data), - DMA_BIDIRECTIONAL); if (status < 0) { dev_dbg(&host->spi->dev, " ... write returned %d\n", status); cmd->error = status; @@ -547,9 +515,6 @@ mmc_spi_command_send(struct mmc_spi_host * We always provide TX data for data and CRC. The MMC/SD protocol * requires us to write ones; but Linux defaults to writing zeroes; * so we explicitly initialize it to all ones on RX paths. - * - * We also handle DMA mapping, so the underlying SPI controller does - * not need to (re)do it for each message. */ static void mmc_spi_setup_data_message( @@ -559,11 +524,8 @@ mmc_spi_setup_data_message( { struct spi_transfer *t; struct scratch *scratch = host->data; - dma_addr_t dma = host->data_dma;

spi_message_init(&host->m); - if (dma) - host->m.is_dma_mapped = 1;

/* for reads, readblock() skips 0xff bytes before finding * the token; for writes, this transfer issues that token. @@ -577,8 +539,6 @@ mmc_spi_setup_data_message( else scratch->data_token = SPI_TOKEN_SINGLE; t->tx_buf = &scratch->data_token; - if (dma) - t->tx_dma = dma + offsetof(struct scratch, data_token); spi_message_add_tail(t, &host->m); }

@@ -588,7 +548,6 @@ mmc_spi_setup_data_message( t = &host->t; memset(t, 0, sizeof(*t)); t->tx_buf = host->ones; - t->tx_dma = host->ones_dma; /* length and actual buffer info are written later */ spi_message_add_tail(t, &host->m);

@@ -598,14 +557,9 @@ mmc_spi_setup_data_message( if (direction == DMA_TO_DEVICE) { /* the actual CRC may get written later */ t->tx_buf = &scratch->crc_val; - if (dma) - t->tx_dma = dma + offsetof(struct scratch, crc_val); } else { t->tx_buf = host->ones; - t->tx_dma = host->ones_dma; t->rx_buf = &scratch->crc_val; - if (dma) - t->rx_dma = dma + offsetof(struct scratch, crc_val); } spi_message_add_tail(t, &host->m);

@@ -628,10 +582,7 @@ mmc_spi_setup_data_message( memset(t, 0, sizeof(*t)); t->len = (direction == DMA_TO_DEVICE) ? sizeof(scratch->status) : 1; t->tx_buf = host->ones; - t->tx_dma = host->ones_dma; t->rx_buf = scratch->status; - if (dma) - t->rx_dma = dma + offsetof(struct scratch, status); t->cs_change = 1; spi_message_add_tail(t, &host->m); } @@ -660,23 +611,13 @@ mmc_spi_writeblock(struct mmc_spi_host *

if (host->mmc->use_spi_crc) scratch->crc_val = cpu_to_be16(crc_itu_t(0, t->tx_buf, t->len)); - if (host->dma_dev) - dma_sync_single_for_device(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL);

status = spi_sync_locked(spi, &host->m); - if (status != 0) { dev_dbg(&spi->dev, "write error (%d)\n", status); return status; }

- if (host->dma_dev) - dma_sync_single_for_cpu(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL); - /* * Get the transmission data-response reply. It must follow * immediately after the data block we transferred. This reply @@ -725,8 +666,6 @@ mmc_spi_writeblock(struct mmc_spi_host * }

t->tx_buf += t->len; - if (host->dma_dev) - t->tx_dma += t->len;

/* Return when not busy. If we didn't collect that status yet, * we'll need some more I/O. @@ -790,30 +729,12 @@ mmc_spi_readblock(struct mmc_spi_host *h } leftover = status << 1;

- if (host->dma_dev) { - dma_sync_single_for_device(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL); - dma_sync_single_for_device(host->dma_dev, - t->rx_dma, t->len, - DMA_FROM_DEVICE); - } - status = spi_sync_locked(spi, &host->m); if (status < 0) { dev_dbg(&spi->dev, "read error %d\n", status); return status; }

- if (host->dma_dev) { - dma_sync_single_for_cpu(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL); - dma_sync_single_for_cpu(host->dma_dev, - t->rx_dma, t->len, - DMA_FROM_DEVICE); - } - if (bitshift) { /* Walk through the data and the crc and do * all the magic to get byte-aligned data. @@ -848,8 +769,6 @@ mmc_spi_readblock(struct mmc_spi_host *h }

t->rx_buf += t->len; - if (host->dma_dev) - t->rx_dma += t->len;

return 0; } @@ -864,7 +783,6 @@ mmc_spi_data_do(struct mmc_spi_host *hos struct mmc_data *data, u32 blk_size) { struct spi_device *spi = host->spi; - struct device *dma_dev = host->dma_dev; struct spi_transfer *t; enum dma_data_direction direction; struct scatterlist *sg; @@ -891,31 +809,8 @@ mmc_spi_data_do(struct mmc_spi_host *hos */ for_each_sg(data->sg, sg, data->sg_len, n_sg) { int status = 0; - dma_addr_t dma_addr = 0; void *kmap_addr; unsigned length = sg->length; - enum dma_data_direction dir = direction; - - /* set up dma mapping for controller drivers that might - * use DMA ... though they may fall back to PIO - */ - if (dma_dev) { - /* never invalidate whole *shared* pages ... */ - if ((sg->offset != 0 || length != PAGE_SIZE) - && dir == DMA_FROM_DEVICE) - dir = DMA_BIDIRECTIONAL; - - dma_addr = dma_map_page(dma_dev, sg_page(sg), 0, - PAGE_SIZE, dir); - if (dma_mapping_error(dma_dev, dma_addr)) { - data->error = -EFAULT; - break; - } - if (direction == DMA_TO_DEVICE) - t->tx_dma = dma_addr + sg->offset; - else - t->rx_dma = dma_addr + sg->offset; - }

/* allow pio too; we don't allow highmem */ kmap_addr = kmap(sg_page(sg)); @@ -951,8 +846,6 @@ mmc_spi_data_do(struct mmc_spi_host *hos if (direction == DMA_FROM_DEVICE) flush_kernel_dcache_page(sg_page(sg)); kunmap(sg_page(sg)); - if (dma_dev) - dma_unmap_page(dma_dev, dma_addr, PAGE_SIZE, dir);

if (status < 0) { data->error = status; @@ -989,21 +882,9 @@ mmc_spi_data_do(struct mmc_spi_host *hos scratch->status[0] = SPI_TOKEN_STOP_TRAN;

host->early_status.tx_buf = host->early_status.rx_buf; - host->early_status.tx_dma = host->early_status.rx_dma; host->early_status.len = statlen;

- if (host->dma_dev) - dma_sync_single_for_device(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL); - tmp = spi_sync_locked(spi, &host->m); - - if (host->dma_dev) - dma_sync_single_for_cpu(host->dma_dev, - host->data_dma, sizeof(*scratch), - DMA_BIDIRECTIONAL); - if (tmp < 0) { if (!data->error) data->error = tmp; @@ -1278,52 +1159,6 @@ mmc_spi_detect_irq(int irq, void *mmc) return IRQ_HANDLED; }

-#ifdef CONFIG_HAS_DMA -static int mmc_spi_dma_alloc(struct mmc_spi_host *host) -{ - struct spi_device *spi = host->spi; - struct device *dev; - - if (!spi->master->dev.parent->dma_mask) - return 0; - - dev = spi->master->dev.parent; - - host->ones_dma = dma_map_single(dev, host->ones, MMC_SPI_BLOCKSIZE, - DMA_TO_DEVICE); - if (dma_mapping_error(dev, host->ones_dma)) - return -ENOMEM; - - host->data_dma = dma_map_single(dev, host->data, sizeof(*host->data), - DMA_BIDIRECTIONAL); - if (dma_mapping_error(dev, host->data_dma)) { - dma_unmap_single(dev, host->ones_dma, MMC_SPI_BLOCKSIZE, - DMA_TO_DEVICE); - return -ENOMEM; - } - - dma_sync_single_for_cpu(dev, host->data_dma, sizeof(*host->data), - DMA_BIDIRECTIONAL); - - host->dma_dev = dev; - return 0; -} - -static void mmc_spi_dma_free(struct mmc_spi_host *host) -{ - if (!host->dma_dev) - return; - - dma_unmap_single(host->dma_dev, host->ones_dma, MMC_SPI_BLOCKSIZE, - DMA_TO_DEVICE); - dma_unmap_single(host->dma_dev, host->data_dma, sizeof(*host->data), - DMA_BIDIRECTIONAL); -} -#else -static inline int mmc_spi_dma_alloc(struct mmc_spi_host *host) { return 0; } -static inline void mmc_spi_dma_free(struct mmc_spi_host *host) {} -#endif - static int mmc_spi_probe(struct spi_device *spi) { void *ones; @@ -1415,24 +1250,17 @@ static int mmc_spi_probe(struct spi_devi

dev_set_drvdata(&spi->dev, mmc);

- /* preallocate dma buffers */ + /* Preallocate buffers */ host->data = kmalloc(sizeof(*host->data), GFP_KERNEL); if (!host->data) goto fail_nobuf1;

- status = mmc_spi_dma_alloc(host); - if (status) - goto fail_dma; - /* setup message for status/busy readback */ spi_message_init(&host->readback); - host->readback.is_dma_mapped = (host->dma_dev != NULL);

spi_message_add_tail(&host->status, &host->readback); host->status.tx_buf = host->ones; - host->status.tx_dma = host->ones_dma; host->status.rx_buf = &host->data->status; - host->status.rx_dma = host->data_dma + offsetof(struct scratch, status); host->status.cs_change = 1;

/* register card detect irq */ @@ -1477,9 +1305,8 @@ static int mmc_spi_probe(struct spi_devi if (!status) has_ro = true;

- dev_info(&spi->dev, "SD/MMC host %s%s%s%s%s\n", + dev_info(&spi->dev, "SD/MMC host %s%s%s%s\n", dev_name(&mmc->class_dev), - host->dma_dev ? "" : ", no DMA", has_ro ? "" : ", no WP", (host->pdata && host->pdata->setpower) ? "" : ", no poweroff", @@ -1490,8 +1317,6 @@ static int mmc_spi_probe(struct spi_devi fail_gpiod_request: mmc_remove_host(mmc); fail_glue_init: - mmc_spi_dma_free(host); -fail_dma: kfree(host->data); fail_nobuf1: mmc_free_host(mmc); @@ -1513,7 +1338,6 @@ static int mmc_spi_remove(struct spi_dev

mmc_remove_host(mmc);

- mmc_spi_dma_free(host); kfree(host->data); kfree(host->ones);

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

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

From: Dave Airlie airlied@redhat.com

commit cacea81390fd8c8c85404e5eb2adeb83d87a912e upstream.

nvif_vmm_put gets called if addr is set, but if the allocation fails we don't need to call put, otherwise we get a warning like

[523232.435671] ------------[ cut here ]------------ [523232.435674] WARNING: CPU: 8 PID: 1505697 at drivers/gpu/drm/nouveau/nvif/vmm.c:68 nvif_vmm_put+0x72/0x80 [nouveau] [523232.435795] Modules linked in: uinput rfcomm snd_seq_dummy snd_hrtimer nf_conntrack_netbios_ns nf_conntrack_broadcast nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set nf_tables nfnetlink qrtr bnep sunrpc binfmt_misc intel_rapl_msr intel_rapl_common intel_uncore_frequency intel_uncore_frequency_common isst_if_common iwlmvm nfit libnvdimm vfat fat x86_pkg_temp_thermal intel_powerclamp mac80211 snd_soc_avs snd_soc_hda_codec coretemp snd_hda_ext_core snd_soc_core snd_hda_codec_realtek kvm_intel snd_hda_codec_hdmi snd_compress snd_hda_codec_generic ac97_bus snd_pcm_dmaengine snd_hda_intel libarc4 snd_intel_dspcfg snd_intel_sdw_acpi snd_hda_codec kvm iwlwifi snd_hda_core btusb snd_hwdep btrtl snd_seq btintel irqbypass btbcm rapl snd_seq_device eeepc_wmi btmtk intel_cstate iTCO_wdt cfg80211 snd_pcm asus_wmi bluetooth intel_pmc_bxt iTCO_vendor_support snd_timer ledtrig_audio pktcdvd snd mei_me [523232.435828] sparse_keymap intel_uncore i2c_i801 platform_profile wmi_bmof mei pcspkr ioatdma soundcore i2c_smbus rfkill idma64 dca joydev acpi_tad loop zram nouveau drm_ttm_helper ttm video drm_exec drm_gpuvm gpu_sched crct10dif_pclmul i2c_algo_bit nvme crc32_pclmul crc32c_intel drm_display_helper polyval_clmulni nvme_core polyval_generic e1000e mxm_wmi cec ghash_clmulni_intel r8169 sha512_ssse3 nvme_common wmi pinctrl_sunrisepoint uas usb_storage ip6_tables ip_tables fuse [523232.435849] CPU: 8 PID: 1505697 Comm: gnome-shell Tainted: G W 6.6.0-rc7-nvk-uapi+ #12 [523232.435851] Hardware name: System manufacturer System Product Name/ROG STRIX X299-E GAMING II, BIOS 1301 09/24/2021 [523232.435852] RIP: 0010:nvif_vmm_put+0x72/0x80 [nouveau] [523232.435934] Code: 00 00 48 89 e2 be 02 00 00 00 48 c7 04 24 00 00 00 00 48 89 44 24 08 e8 fc bf ff ff 85 c0 75 0a 48 c7 43 08 00 00 00 00 eb b3 <0f> 0b eb f2 e8 f5 c9 b2 e6 0f 1f 44 00 00 90 90 90 90 90 90 90 90 [523232.435936] RSP: 0018:ffffc900077ffbd8 EFLAGS: 00010282 [523232.435937] RAX: 00000000fffffffe RBX: ffffc900077ffc00 RCX: 0000000000000010 [523232.435938] RDX: 0000000000000010 RSI: ffffc900077ffb38 RDI: ffffc900077ffbd8 [523232.435940] RBP: ffff888e1c4f2140 R08: 0000000000000000 R09: 0000000000000000 [523232.435940] R10: 0000000000000000 R11: 0000000000000000 R12: ffff888503811800 [523232.435941] R13: ffffc900077ffca0 R14: ffff888e1c4f2140 R15: ffff88810317e1e0 [523232.435942] FS: 00007f933a769640(0000) GS:ffff88905fa00000(0000) knlGS:0000000000000000 [523232.435943] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [523232.435944] CR2: 00007f930bef7000 CR3: 00000005d0322001 CR4: 00000000003706e0 [523232.435945] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [523232.435946] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [523232.435964] Call Trace: [523232.435965] <TASK> [523232.435966] ? nvif_vmm_put+0x72/0x80 [nouveau] [523232.436051] ? __warn+0x81/0x130 [523232.436055] ? nvif_vmm_put+0x72/0x80 [nouveau] [523232.436138] ? report_bug+0x171/0x1a0 [523232.436142] ? handle_bug+0x3c/0x80 [523232.436144] ? exc_invalid_op+0x17/0x70 [523232.436145] ? asm_exc_invalid_op+0x1a/0x20 [523232.436149] ? nvif_vmm_put+0x72/0x80 [nouveau] [523232.436230] ? nvif_vmm_put+0x64/0x80 [nouveau] [523232.436342] nouveau_vma_del+0x80/0xd0 [nouveau] [523232.436506] nouveau_vma_new+0x1a0/0x210 [nouveau] [523232.436671] nouveau_gem_object_open+0x1d0/0x1f0 [nouveau] [523232.436835] drm_gem_handle_create_tail+0xd1/0x180 [523232.436840] drm_prime_fd_to_handle_ioctl+0x12e/0x200 [523232.436844] ? __pfx_drm_prime_fd_to_handle_ioctl+0x10/0x10 [523232.436847] drm_ioctl_kernel+0xd3/0x180 [523232.436849] drm_ioctl+0x26d/0x4b0 [523232.436851] ? __pfx_drm_prime_fd_to_handle_ioctl+0x10/0x10 [523232.436855] nouveau_drm_ioctl+0x5a/0xb0 [nouveau] [523232.437032] __x64_sys_ioctl+0x94/0xd0 [523232.437036] do_syscall_64+0x5d/0x90 [523232.437040] ? syscall_exit_to_user_mode+0x2b/0x40 [523232.437044] ? do_syscall_64+0x6c/0x90 [523232.437046] entry_SYSCALL_64_after_hwframe+0x6e/0xd8

Reported-by: Faith Ekstrand faith.ekstrand@collabora.com Cc: stable@vger.kernel.org Signed-off-by: Dave Airlie airlied@redhat.com Link: https://patchwork.freedesktop.org/patch/msgid/20240117213852.295565-1-airlie... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/nouveau/nouveau_vmm.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/drivers/gpu/drm/nouveau/nouveau_vmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_vmm.c @@ -108,6 +108,9 @@ nouveau_vma_new(struct nouveau_bo *nvbo, } else { ret = nvif_vmm_get(&vmm->vmm, PTES, false, mem->mem.page, 0, mem->mem.size, &tmp); + if (ret) + goto done; + vma->addr = tmp.addr; }

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

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

From: Al Viro viro@zeniv.linux.org.uk

commit 22e111ed6c83dcde3037fc81176012721bc34c0b upstream.

We should never lock two subdirectories without having taken ->s_vfs_rename_mutex; inode pointer order or not, the "order" proposed in 28eceeda130f "fs: Lock moved directories" is not transitive, with the usual consequences.

The rationale for locking renamed subdirectory in all cases was the possibility of race between rename modifying .. in a subdirectory to reflect the new parent and another thread modifying the same subdirectory. For a lot of filesystems that's not a problem, but for some it can lead to trouble (e.g. the case when short directory contents is kept in the inode, but creating a file in it might push it across the size limit and copy its contents into separate data block(s)).

However, we need that only in case when the parent does change - otherwise ->rename() doesn't need to do anything with .. entry in the first place. Some instances are lazy and do a tautological update anyway, but it's really not hard to avoid.

Amended locking rules for rename(): find the parent(s) of source and target if source and target have the same parent lock the common parent else lock ->s_vfs_rename_mutex lock both parents, in ancestor-first order; if neither is an ancestor of another, lock the parent of source first. find the source and target. if source and target have the same parent if operation is an overwriting rename of a subdirectory lock the target subdirectory else if source is a subdirectory lock the source if target is a subdirectory lock the target lock non-directories involved, in inode pointer order if both source and target are such.

That way we are guaranteed that parents are locked (for obvious reasons), that any renamed non-directory is locked (nfsd relies upon that), that any victim is locked (emptiness check needs that, among other things) and subdirectory that changes parent is locked (needed to protect the update of .. entries). We are also guaranteed that any operation locking more than one directory either takes ->s_vfs_rename_mutex or locks a parent followed by its child.

Cc: stable@vger.kernel.org Fixes: 28eceeda130f "fs: Lock moved directories" Reviewed-by: Jan Kara jack@suse.cz Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/filesystems/directory-locking.rst | 29 ++++++----- Documentation/filesystems/locking.rst | 5 +- Documentation/filesystems/porting.rst | 18 +++++++ fs/namei.c | 60 ++++++++++++++---------- 4 files changed, 74 insertions(+), 38 deletions(-)

--- a/Documentation/filesystems/directory-locking.rst +++ b/Documentation/filesystems/directory-locking.rst @@ -22,13 +22,16 @@ exclusive. 3) object removal. Locking rules: caller locks parent, finds victim, locks victim and calls the method. Locks are exclusive.

-4) rename() that is _not_ cross-directory. Locking rules: caller locks the -parent and finds source and target. We lock both (provided they exist). If we -need to lock two inodes of different type (dir vs non-dir), we lock directory -first. If we need to lock two inodes of the same type, lock them in inode -pointer order. Then call the method. All locks are exclusive. -NB: we might get away with locking the source (and target in exchange -case) shared. +4) rename() that is _not_ cross-directory. Locking rules: caller locks +the parent and finds source and target. Then we decide which of the +source and target need to be locked. Source needs to be locked if it's a +non-directory; target - if it's a non-directory or about to be removed. +Take the locks that need to be taken, in inode pointer order if need +to take both (that can happen only when both source and target are +non-directories - the source because it wouldn't be locked otherwise +and the target because mixing directory and non-directory is allowed +only with RENAME_EXCHANGE, and that won't be removing the target). +After the locks had been taken, call the method. All locks are exclusive.

5) link creation. Locking rules:

@@ -44,20 +47,17 @@ rules:

* lock the filesystem * lock parents in "ancestors first" order. If one is not ancestor of - the other, lock them in inode pointer order. + the other, lock the parent of source first. * find source and target. * if old parent is equal to or is a descendent of target fail with -ENOTEMPTY * if new parent is equal to or is a descendent of source fail with -ELOOP - * Lock both the source and the target provided they exist. If we - need to lock two inodes of different type (dir vs non-dir), we lock - the directory first. If we need to lock two inodes of the same type, - lock them in inode pointer order. + * Lock subdirectories involved (source before target). + * Lock non-directories involved, in inode pointer order. * call the method.

-All ->i_rwsem are taken exclusive. Again, we might get away with locking -the source (and target in exchange case) shared. +All ->i_rwsem are taken exclusive.

The rules above obviously guarantee that all directories that are going to be read, modified or removed by method will be locked by caller. @@ -67,6 +67,7 @@ If no directory is its own ancestor, the

Proof:

+[XXX: will be updated once we are done massaging the lock_rename()] First of all, at any moment we have a linear ordering of the objects - A < B iff (A is an ancestor of B) or (B is not an ancestor of A and ptr(A) < ptr(B)). --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -95,7 +95,7 @@ symlink: exclusive mkdir: exclusive unlink: exclusive (both) rmdir: exclusive (both)(see below) -rename: exclusive (all) (see below) +rename: exclusive (both parents, some children) (see below) readlink: no get_link: no setattr: exclusive @@ -113,6 +113,9 @@ tmpfile: no Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_rwsem exclusive on victim. cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem. + ->unlink() and ->rename() have ->i_rwsem exclusive on all non-directories + involved. + ->rename() has ->i_rwsem exclusive on any subdirectory that changes parent.

See Documentation/filesystems/directory-locking.rst for more detailed discussion of the locking scheme for directory operations. --- a/Documentation/filesystems/porting.rst +++ b/Documentation/filesystems/porting.rst @@ -865,3 +865,21 @@ no matter what. Everything is handled b

clone_private_mount() returns a longterm mount now, so the proper destructor of its result is kern_unmount() or kern_unmount_array(). + +--- + +**mandatory** + +If ->rename() update of .. on cross-directory move needs an exclusion with +directory modifications, do *not* lock the subdirectory in question in your +->rename() - it's done by the caller now [that item should've been added in +28eceeda130f "fs: Lock moved directories"]. + +--- + +**mandatory** + +On same-directory ->rename() the (tautological) update of .. is not protected +by any locks; just don't do it if the old parent is the same as the new one. +We really can't lock two subdirectories in same-directory rename - not without +deadlocks. --- a/fs/namei.c +++ b/fs/namei.c @@ -2771,20 +2771,14 @@ struct dentry *lock_rename(struct dentry p = d_ancestor(p2, p1); if (p) { inode_lock_nested(p2->d_inode, I_MUTEX_PARENT); - inode_lock_nested(p1->d_inode, I_MUTEX_CHILD); + inode_lock_nested(p1->d_inode, I_MUTEX_PARENT2); return p; }

p = d_ancestor(p1, p2); - if (p) { - inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); - inode_lock_nested(p2->d_inode, I_MUTEX_CHILD); - return p; - } - - lock_two_inodes(p1->d_inode, p2->d_inode, - I_MUTEX_PARENT, I_MUTEX_PARENT2); - return NULL; + inode_lock_nested(p1->d_inode, I_MUTEX_PARENT); + inode_lock_nested(p2->d_inode, I_MUTEX_PARENT2); + return p; } EXPORT_SYMBOL(lock_rename);

@@ -4260,11 +4254,12 @@ SYSCALL_DEFINE2(link, const char __user * * a) we can get into loop creation. * b) race potential - two innocent renames can create a loop together. - * That's where 4.4 screws up. Current fix: serialization on + * That's where 4.4BSD screws up. Current fix: serialization on * sb->s_vfs_rename_mutex. We might be more accurate, but that's another * story. - * c) we have to lock _four_ objects - parents and victim (if it exists), - * and source. + * c) we may have to lock up to _four_ objects - parents and victim (if it exists), + * and source (if it's a non-directory or a subdirectory that moves to + * different parent). * And that - after we got ->i_mutex on parents (until then we don't know * whether the target exists). Solution: try to be smart with locking * order for inodes. We rely on the fact that tree topology may change @@ -4293,6 +4288,7 @@ int vfs_rename(struct inode *old_dir, st bool new_is_dir = false; unsigned max_links = new_dir->i_sb->s_max_links; struct name_snapshot old_name; + bool lock_old_subdir, lock_new_subdir;

if (source == target) return 0; @@ -4342,15 +4338,32 @@ int vfs_rename(struct inode *old_dir, st take_dentry_name_snapshot(&old_name, old_dentry); dget(new_dentry); /* - * Lock all moved children. Moved directories may need to change parent - * pointer so they need the lock to prevent against concurrent - * directory changes moving parent pointer. For regular files we've - * historically always done this. The lockdep locking subclasses are - * somewhat arbitrary but RENAME_EXCHANGE in particular can swap - * regular files and directories so it's difficult to tell which - * subclasses to use. + * Lock children. + * The source subdirectory needs to be locked on cross-directory + * rename or cross-directory exchange since its parent changes. + * The target subdirectory needs to be locked on cross-directory + * exchange due to parent change and on any rename due to becoming + * a victim. + * Non-directories need locking in all cases (for NFS reasons); + * they get locked after any subdirectories (in inode address order). + * + * NOTE: WE ONLY LOCK UNRELATED DIRECTORIES IN CROSS-DIRECTORY CASE. + * NEVER, EVER DO THAT WITHOUT ->s_vfs_rename_mutex. */ - lock_two_inodes(source, target, I_MUTEX_NORMAL, I_MUTEX_NONDIR2); + lock_old_subdir = new_dir != old_dir; + lock_new_subdir = new_dir != old_dir || !(flags & RENAME_EXCHANGE); + if (is_dir) { + if (lock_old_subdir) + inode_lock_nested(source, I_MUTEX_CHILD); + if (target && (!new_is_dir || lock_new_subdir)) + inode_lock(target); + } else if (new_is_dir) { + if (lock_new_subdir) + inode_lock_nested(target, I_MUTEX_CHILD); + inode_lock(source); + } else { + lock_two_nondirectories(source, target); + }

error = -EBUSY; if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry)) @@ -4394,8 +4407,9 @@ int vfs_rename(struct inode *old_dir, st d_exchange(old_dentry, new_dentry); } out: - inode_unlock(source); - if (target) + if (!is_dir || lock_old_subdir) + inode_unlock(source); + if (target && (!new_is_dir || lock_new_subdir)) inode_unlock(target); dput(new_dentry); if (!error) {

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

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

From: Kees Cook keescook@chromium.org

commit 3080ea5553cc909b000d1f1d964a9041962f2c5b upstream.

There are many places where kernel code wants to have several different typed trailing flexible arrays. This would normally be done with multiple flexible arrays in a union, but since GCC and Clang don't (on the surface) allow this, there have been many open-coded workarounds, usually involving neighboring 0-element arrays at the end of a structure. For example, instead of something like this:

struct thing { ... union { struct type1 foo[]; struct type2 bar[]; }; };

code works around the compiler with:

struct thing { ... struct type1 foo[0]; struct type2 bar[]; };

Another case is when a flexible array is wanted as the single member within a struct (which itself is usually in a union). For example, this would be worked around as:

union many { ... struct { struct type3 baz[0]; }; };

These kinds of work-arounds cause problems with size checks against such zero-element arrays (for example when building with -Warray-bounds and -Wzero-length-bounds, and with the coming FORTIFY_SOURCE improvements), so they must all be converted to "real" flexible arrays, avoiding warnings like this:

fs/hpfs/anode.c: In function 'hpfs_add_sector_to_btree': fs/hpfs/anode.c:209:27: warning: array subscript 0 is outside the bounds of an interior zero-length array 'struct bplus_internal_node[0]' [-Wzero-length-bounds] 209 | anode->btree.u.internal[0].down = cpu_to_le32(a); | ~~~~~~~~~~~~~~~~~~~~~~~^~~ In file included from fs/hpfs/hpfs_fn.h:26, from fs/hpfs/anode.c:10: fs/hpfs/hpfs.h:412:32: note: while referencing 'internal' 412 | struct bplus_internal_node internal[0]; /* (internal) 2-word entries giving | ^~~~~~~~

drivers/net/can/usb/etas_es58x/es58x_fd.c: In function 'es58x_fd_tx_can_msg': drivers/net/can/usb/etas_es58x/es58x_fd.c:360:35: warning: array subscript 65535 is outside the bounds of an interior zero-length array 'u8[0]' {aka 'unsigned char[]'} [-Wzero-length-bounds] 360 | tx_can_msg = (typeof(tx_can_msg))&es58x_fd_urb_cmd->raw_msg[msg_len]; | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from drivers/net/can/usb/etas_es58x/es58x_core.h:22, from drivers/net/can/usb/etas_es58x/es58x_fd.c:17: drivers/net/can/usb/etas_es58x/es58x_fd.h:231:6: note: while referencing 'raw_msg' 231 | u8 raw_msg[0]; | ^~~~~~~

However, it _is_ entirely possible to have one or more flexible arrays in a struct or union: it just has to be in another struct. And since it cannot be alone in a struct, such a struct must have at least 1 other named member -- but that member can be zero sized. Wrap all this nonsense into the new DECLARE_FLEX_ARRAY() in support of having flexible arrays in unions (or alone in a struct).

As with struct_group(), since this is needed in UAPI headers as well, implement the core there, with a non-UAPI wrapper.

Additionally update kernel-doc to understand its existence.

https://github.com/KSPP/linux/issues/137

Cc: Arnd Bergmann arnd@arndb.de Cc: "Gustavo A. R. Silva" gustavoars@kernel.org Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: Vasiliy Kovalev kovalev@altlinux.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/stddef.h | 13 +++++++++++++ include/uapi/linux/stddef.h | 16 ++++++++++++++++ scripts/kernel-doc | 3 ++- 3 files changed, 31 insertions(+), 1 deletion(-)

--- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -84,4 +84,17 @@ enum { #define struct_group_tagged(TAG, NAME, MEMBERS...) \ __struct_group(TAG, NAME, /* no attrs */, MEMBERS)

+/** + * DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union + * + * @TYPE: The type of each flexible array element + * @NAME: The name of the flexible array member + * + * In order to have a flexible array member in a union or alone in a + * struct, it needs to be wrapped in an anonymous struct with at least 1 + * named member, but that member can be empty. + */ +#define DECLARE_FLEX_ARRAY(TYPE, NAME) \ + __DECLARE_FLEX_ARRAY(TYPE, NAME) + #endif --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -28,4 +28,20 @@ struct { MEMBERS } ATTRS; \ struct TAG { MEMBERS } ATTRS NAME; \ } + +/** + * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union + * + * @TYPE: The type of each flexible array element + * @NAME: The name of the flexible array member + * + * In order to have a flexible array member in a union or alone in a + * struct, it needs to be wrapped in an anonymous struct with at least 1 + * named member, but that member can be empty. + */ +#define __DECLARE_FLEX_ARRAY(TYPE, NAME) \ + struct { \ + struct { } __empty_ ## NAME; \ + TYPE NAME[]; \ + } #endif --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1232,7 +1232,8 @@ sub dump_struct($$) { $members =~ s/DECLARE_KFIFO\s*(([^,)]+),\s*([^,)]+),\s*([^,)]+))/$2 *$1/gos; # replace DECLARE_KFIFO_PTR $members =~ s/DECLARE_KFIFO_PTR\s*(([^,)]+),\s*([^,)]+))/$2 *$1/gos; - + # replace DECLARE_FLEX_ARRAY + $members =~ s/(?:__)?DECLARE_FLEX_ARRAY\s*($args,\s*$args)/$1 $2[]/gos; my $declaration = $members;

# Split nested struct/union elements as newer ones

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

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

From: Paolo Bonzini pbonzini@redhat.com

commit a8749a35c39903120ec421ef2525acc8e0daa55c upstream.

Linux has dozens of occurrences of vmalloc(array_size()) and vzalloc(array_size()). Allow to simplify the code by providing vmalloc_array and vcalloc, as well as the underscored variants that let the caller specify the GFP flags.

Acked-by: Michal Hocko mhocko@suse.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Alexander Ofitserov oficerovas@altlinux.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/vmalloc.h | 5 ++++ mm/util.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 55 insertions(+)

--- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -112,6 +112,11 @@ extern void *__vmalloc_node_range(unsign void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller);

+extern void *__vmalloc_array(size_t n, size_t size, gfp_t flags); +extern void *vmalloc_array(size_t n, size_t size); +extern void *__vcalloc(size_t n, size_t size, gfp_t flags); +extern void *vcalloc(size_t n, size_t size); + extern void vfree(const void *addr); extern void vfree_atomic(const void *addr);

--- a/mm/util.c +++ b/mm/util.c @@ -686,6 +686,56 @@ static inline void *__page_rmapping(stru return (void *)mapping; }

+/** + * __vmalloc_array - allocate memory for a virtually contiguous array. + * @n: number of elements. + * @size: element size. + * @flags: the type of memory to allocate (see kmalloc). + */ +void *__vmalloc_array(size_t n, size_t size, gfp_t flags) +{ + size_t bytes; + + if (unlikely(check_mul_overflow(n, size, &bytes))) + return NULL; + return __vmalloc(bytes, flags); +} +EXPORT_SYMBOL(__vmalloc_array); + +/** + * vmalloc_array - allocate memory for a virtually contiguous array. + * @n: number of elements. + * @size: element size. + */ +void *vmalloc_array(size_t n, size_t size) +{ + return __vmalloc_array(n, size, GFP_KERNEL); +} +EXPORT_SYMBOL(vmalloc_array); + +/** + * __vcalloc - allocate and zero memory for a virtually contiguous array. + * @n: number of elements. + * @size: element size. + * @flags: the type of memory to allocate (see kmalloc). + */ +void *__vcalloc(size_t n, size_t size, gfp_t flags) +{ + return __vmalloc_array(n, size, flags | __GFP_ZERO); +} +EXPORT_SYMBOL(__vcalloc); + +/** + * vcalloc - allocate and zero memory for a virtually contiguous array. + * @n: number of elements. + * @size: element size. + */ +void *vcalloc(size_t n, size_t size) +{ + return __vmalloc_array(n, size, GFP_KERNEL | __GFP_ZERO); +} +EXPORT_SYMBOL(vcalloc); + /* Neutral page->mapping pointer to address_space or anon_vma or other */ void *page_rmapping(struct page *page) {

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

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

From: Wen Gu guwen@linux.alibaba.com

[ Upstream commit dbc153fd3c142909e564bb256da087e13fbf239c ]

A crash was found when dumping SMC-D connections. It can be reproduced by following steps:

- run nginx/wrk test: smc_run nginx smc_run wrk -t 16 -c 1000 -d <duration> -H 'Connection: Close' <URL>

- continuously dump SMC-D connections in parallel: watch -n 1 'smcss -D'

BUG: kernel NULL pointer dereference, address: 0000000000000030 CPU: 2 PID: 7204 Comm: smcss Kdump: loaded Tainted: G E 6.7.0+ #55 RIP: 0010:__smc_diag_dump.constprop.0+0x5e5/0x620 [smc_diag] Call Trace: <TASK> ? __die+0x24/0x70 ? page_fault_oops+0x66/0x150 ? exc_page_fault+0x69/0x140 ? asm_exc_page_fault+0x26/0x30 ? __smc_diag_dump.constprop.0+0x5e5/0x620 [smc_diag] ? __kmalloc_node_track_caller+0x35d/0x430 ? __alloc_skb+0x77/0x170 smc_diag_dump_proto+0xd0/0xf0 [smc_diag] smc_diag_dump+0x26/0x60 [smc_diag] netlink_dump+0x19f/0x320 __netlink_dump_start+0x1dc/0x300 smc_diag_handler_dump+0x6a/0x80 [smc_diag] ? __pfx_smc_diag_dump+0x10/0x10 [smc_diag] sock_diag_rcv_msg+0x121/0x140 ? __pfx_sock_diag_rcv_msg+0x10/0x10 netlink_rcv_skb+0x5a/0x110 sock_diag_rcv+0x28/0x40 netlink_unicast+0x22a/0x330 netlink_sendmsg+0x1f8/0x420 __sock_sendmsg+0xb0/0xc0 ____sys_sendmsg+0x24e/0x300 ? copy_msghdr_from_user+0x62/0x80 ___sys_sendmsg+0x7c/0xd0 ? __do_fault+0x34/0x160 ? do_read_fault+0x5f/0x100 ? do_fault+0xb0/0x110 ? __handle_mm_fault+0x2b0/0x6c0 __sys_sendmsg+0x4d/0x80 do_syscall_64+0x69/0x180 entry_SYSCALL_64_after_hwframe+0x6e/0x76

It is possible that the connection is in process of being established when we dump it. Assumed that the connection has been registered in a link group by smc_conn_create() but the rmb_desc has not yet been initialized by smc_buf_create(), thus causing the illegal access to conn->rmb_desc. So fix it by checking before dump.

Fixes: 4b1b7d3b30a6 ("net/smc: add SMC-D diag support") Signed-off-by: Wen Gu guwen@linux.alibaba.com Reviewed-by: Dust Li dust.li@linux.alibaba.com Reviewed-by: Wenjia Zhang wenjia@linux.ibm.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/smc/smc_diag.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index f15fca59b4b2..7c921760dce7 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -177,7 +177,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, } if (smc->conn.lgr && smc->conn.lgr->is_smcd && (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) && - !list_empty(&smc->conn.lgr->list)) { + !list_empty(&smc->conn.lgr->list) && smc->conn.rmb_desc) { struct smc_connection *conn = &smc->conn; struct smcd_diag_dmbinfo dinfo;

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

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

From: Michael Chan michael.chan@broadcom.com

[ Upstream commit 3c1069fa42872f95cf3c6fedf80723d391e12d57 ]

The first message to firmware may fail if the device is undergoing FLR. The driver has some recovery logic for this failure scenario but we must wait 100 msec for FLR to complete before proceeding. Otherwise the recovery will always fail.

Fixes: ba02629ff6cb ("bnxt_en: log firmware status on firmware init failure") Reviewed-by: Damodharam Ammepalli damodharam.ammepalli@broadcom.com Signed-off-by: Michael Chan michael.chan@broadcom.com Link: https://lore.kernel.org/r/20240117234515.226944-2-michael.chan@broadcom.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 584f365de563..059552f4154d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11331,6 +11331,11 @@ static int bnxt_fw_init_one_p1(struct bnxt *bp)

bp->fw_cap = 0; rc = bnxt_hwrm_ver_get(bp); + /* FW may be unresponsive after FLR. FLR must complete within 100 msec + * so wait before continuing with recovery. + */ + if (rc) + msleep(100); bnxt_try_map_fw_health_reg(bp); if (rc) { if (bp->fw_health && bp->fw_health->status_reliable) {

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

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

From: Eric Dumazet edumazet@google.com

[ Upstream commit dad555c816a50c6a6a8a86be1f9177673918c647 ]

syzbot was able to trick llc_ui_sendmsg(), allocating an skb with no headroom, but subsequently trying to push 14 bytes of Ethernet header [1]

Like some others, llc_ui_sendmsg() releases the socket lock before calling sock_alloc_send_skb(). Then it acquires it again, but does not redo all the sanity checks that were performed.

This fix:

- Uses LL_RESERVED_SPACE() to reserve space. - Check all conditions again after socket lock is held again. - Do not account Ethernet header for mtu limitation.

[1]

skbuff: skb_under_panic: text:ffff800088baa334 len:1514 put:14 head:ffff0000c9c37000 data:ffff0000c9c36ff2 tail:0x5dc end:0x6c0 dev:bond0

kernel BUG at net/core/skbuff.c:193 ! Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP Modules linked in: CPU: 0 PID: 6875 Comm: syz-executor.0 Not tainted 6.7.0-rc8-syzkaller-00101-g0802e17d9aca-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/17/2023 pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : skb_panic net/core/skbuff.c:189 [inline] pc : skb_under_panic+0x13c/0x140 net/core/skbuff.c:203 lr : skb_panic net/core/skbuff.c:189 [inline] lr : skb_under_panic+0x13c/0x140 net/core/skbuff.c:203 sp : ffff800096f97000 x29: ffff800096f97010 x28: ffff80008cc8d668 x27: dfff800000000000 x26: ffff0000cb970c90 x25: 00000000000005dc x24: ffff0000c9c36ff2 x23: ffff0000c9c37000 x22: 00000000000005ea x21: 00000000000006c0 x20: 000000000000000e x19: ffff800088baa334 x18: 1fffe000368261ce x17: ffff80008e4ed000 x16: ffff80008a8310f8 x15: 0000000000000001 x14: 1ffff00012df2d58 x13: 0000000000000000 x12: 0000000000000000 x11: 0000000000000001 x10: 0000000000ff0100 x9 : e28a51f1087e8400 x8 : e28a51f1087e8400 x7 : ffff80008028f8d0 x6 : 0000000000000000 x5 : 0000000000000001 x4 : 0000000000000001 x3 : ffff800082b78714 x2 : 0000000000000001 x1 : 0000000100000000 x0 : 0000000000000089 Call trace: skb_panic net/core/skbuff.c:189 [inline] skb_under_panic+0x13c/0x140 net/core/skbuff.c:203 skb_push+0xf0/0x108 net/core/skbuff.c:2451 eth_header+0x44/0x1f8 net/ethernet/eth.c:83 dev_hard_header include/linux/netdevice.h:3188 [inline] llc_mac_hdr_init+0x110/0x17c net/llc/llc_output.c:33 llc_sap_action_send_xid_c+0x170/0x344 net/llc/llc_s_ac.c:85 llc_exec_sap_trans_actions net/llc/llc_sap.c:153 [inline] llc_sap_next_state net/llc/llc_sap.c:182 [inline] llc_sap_state_process+0x1ec/0x774 net/llc/llc_sap.c:209 llc_build_and_send_xid_pkt+0x12c/0x1c0 net/llc/llc_sap.c:270 llc_ui_sendmsg+0x7bc/0xb1c net/llc/af_llc.c:997 sock_sendmsg_nosec net/socket.c:730 [inline] __sock_sendmsg net/socket.c:745 [inline] sock_sendmsg+0x194/0x274 net/socket.c:767 splice_to_socket+0x7cc/0xd58 fs/splice.c:881 do_splice_from fs/splice.c:933 [inline] direct_splice_actor+0xe4/0x1c0 fs/splice.c:1142 splice_direct_to_actor+0x2a0/0x7e4 fs/splice.c:1088 do_splice_direct+0x20c/0x348 fs/splice.c:1194 do_sendfile+0x4bc/0xc70 fs/read_write.c:1254 __do_sys_sendfile64 fs/read_write.c:1322 [inline] __se_sys_sendfile64 fs/read_write.c:1308 [inline] __arm64_sys_sendfile64+0x160/0x3b4 fs/read_write.c:1308 __invoke_syscall arch/arm64/kernel/syscall.c:37 [inline] invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:51 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:136 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:155 el0_svc+0x54/0x158 arch/arm64/kernel/entry-common.c:678 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:696 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:595 Code: aa1803e6 aa1903e7 a90023f5 94792f6a (d4210000)

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-and-tested-by: syzbot+2a7024e9502df538e8ef@syzkaller.appspotmail.com Signed-off-by: Eric Dumazet edumazet@google.com Reviewed-by: Kuniyuki Iwashima kuniyu@amazon.com Link: https://lore.kernel.org/r/20240118183625.4007013-1-edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/llc/af_llc.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 01e26698285a..f9785150bfcc 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -927,14 +927,15 @@ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, */ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { + DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); - DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); int flags = msg->msg_flags; int noblock = flags & MSG_DONTWAIT; + int rc = -EINVAL, copied = 0, hdrlen, hh_len; struct sk_buff *skb = NULL; + struct net_device *dev; size_t size = 0; - int rc = -EINVAL, copied = 0, hdrlen;

dprintk("%s: sending from %02X to %02X\n", __func__, llc->laddr.lsap, llc->daddr.lsap); @@ -954,22 +955,29 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (rc) goto out; } - hdrlen = llc->dev->hard_header_len + llc_ui_header_len(sk, addr); + dev = llc->dev; + hh_len = LL_RESERVED_SPACE(dev); + hdrlen = llc_ui_header_len(sk, addr); size = hdrlen + len; - if (size > llc->dev->mtu) - size = llc->dev->mtu; + size = min_t(size_t, size, READ_ONCE(dev->mtu)); copied = size - hdrlen; rc = -EINVAL; if (copied < 0) goto out; release_sock(sk); - skb = sock_alloc_send_skb(sk, size, noblock, &rc); + skb = sock_alloc_send_skb(sk, hh_len + size, noblock, &rc); lock_sock(sk); if (!skb) goto out; - skb->dev = llc->dev; + if (sock_flag(sk, SOCK_ZAPPED) || + llc->dev != dev || + hdrlen != llc_ui_header_len(sk, addr) || + hh_len != LL_RESERVED_SPACE(dev) || + size > READ_ONCE(dev->mtu)) + goto out; + skb->dev = dev; skb->protocol = llc_proto_type(addr->sllc_arphrd); - skb_reserve(skb, hdrlen); + skb_reserve(skb, hh_len + hdrlen); rc = memcpy_from_msg(skb_put(skb, copied), msg, copied); if (rc) goto out;

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

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

From: Sharath Srinivasan sharath.srinivasan@oracle.com

[ Upstream commit 13e788deb7348cc88df34bed736c3b3b9927ea52 ]

Syzcaller UBSAN crash occurs in rds_cmsg_recv(), which reads inc->i_rx_lat_trace[j + 1] with index 4 (3 + 1), but with array size of 4 (RDS_RX_MAX_TRACES). Here 'j' is assigned from rs->rs_rx_trace[i] and in-turn from trace.rx_trace_pos[i] in rds_recv_track_latency(), with both arrays sized 3 (RDS_MSG_RX_DGRAM_TRACE_MAX). So fix the off-by-one bounds check in rds_recv_track_latency() to prevent a potential crash in rds_cmsg_recv().

Found by syzcaller: ================================================================= UBSAN: array-index-out-of-bounds in net/rds/recv.c:585:39 index 4 is out of range for type 'u64 [4]' CPU: 1 PID: 8058 Comm: syz-executor228 Not tainted 6.6.0-gd2f51b3516da #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x136/0x150 lib/dump_stack.c:106 ubsan_epilogue lib/ubsan.c:217 [inline] __ubsan_handle_out_of_bounds+0xd5/0x130 lib/ubsan.c:348 rds_cmsg_recv+0x60d/0x700 net/rds/recv.c:585 rds_recvmsg+0x3fb/0x1610 net/rds/recv.c:716 sock_recvmsg_nosec net/socket.c:1044 [inline] sock_recvmsg+0xe2/0x160 net/socket.c:1066 __sys_recvfrom+0x1b6/0x2f0 net/socket.c:2246 __do_sys_recvfrom net/socket.c:2264 [inline] __se_sys_recvfrom net/socket.c:2260 [inline] __x64_sys_recvfrom+0xe0/0x1b0 net/socket.c:2260 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x40/0x110 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x63/0x6b ==================================================================

Fixes: 3289025aedc0 ("RDS: add receive message trace used by application") Reported-by: Chenyuan Yang chenyuan0y@gmail.com Closes: https://lore.kernel.org/linux-rdma/CALGdzuoVdq-wtQ4Az9iottBqC5cv9ZhcE5q8N7Lf... Signed-off-by: Sharath Srinivasan sharath.srinivasan@oracle.com Reviewed-by: Simon Horman horms@kernel.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/rds/af_rds.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index b239120dd9ca..0ec0ae148349 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -419,7 +419,7 @@ static int rds_recv_track_latency(struct rds_sock *rs, sockptr_t optval,

rs->rs_rx_traces = trace.rx_traces; for (i = 0; i < rs->rs_rx_traces; i++) { - if (trace.rx_trace_pos[i] > RDS_MSG_RX_DGRAM_TRACE_MAX) { + if (trace.rx_trace_pos[i] >= RDS_MSG_RX_DGRAM_TRACE_MAX) { rs->rs_rx_traces = 0; return -EFAULT; }

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

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

From: David Howells dhowells@redhat.com

[ Upstream commit 57e9d49c54528c49b8bffe6d99d782ea051ea534 ]

There appears to be a race between silly-rename files being created/removed and various userspace tools iterating over the contents of a directory, leading to such errors as:

find: './kernel/.tmp_cpio_dir/include/dt-bindings/reset/.__afs2080': No such file or directory tar: ./include/linux/greybus/.__afs3C95: File removed before we read it

when building a kernel.

Fix afs_readdir() so that it doesn't return .__afsXXXX silly-rename files to userspace. This doesn't stop them being looked up directly by name as we need to be able to look them up from within the kernel as part of the silly-rename algorithm.

Fixes: 79ddbfa500b3 ("afs: Implement sillyrename for unlink and rename") Signed-off-by: David Howells dhowells@redhat.com cc: Marc Dionne marc.dionne@auristor.com cc: linux-afs@lists.infradead.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/afs/dir.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/fs/afs/dir.c b/fs/afs/dir.c index a59d6293a32b..0b927736ca72 100644 --- a/fs/afs/dir.c +++ b/fs/afs/dir.c @@ -418,6 +418,14 @@ static int afs_dir_iterate_block(struct afs_vnode *dvnode, continue; }

+ /* Don't expose silly rename entries to userspace. */ + if (nlen > 6 && + dire->u.name[0] == '.' && + ctx->actor != afs_lookup_filldir && + ctx->actor != afs_lookup_one_filldir && + memcmp(dire->u.name, ".__afs", 6) == 0) + continue; + /* found the next entry */ if (!dir_emit(ctx, dire->u.name, nlen, ntohl(dire->u.vnode),

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

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

From: Zhengchao Shao shaozhengchao@huawei.com

[ Upstream commit 234ec0b6034b16869d45128b8cd2dc6ffe596f04 ]

I analyze the potential sleeping issue of the following processes: Thread A Thread B ... netlink_create //ref = 1 do_mq_notify ... sock = netlink_getsockbyfilp ... //ref = 2 info->notify_sock = sock; ... ... netlink_sendmsg ... skb = netlink_alloc_large_skb //skb->head is vmalloced ... netlink_unicast ... sk = netlink_getsockbyportid //ref = 3 ... netlink_sendskb ... __netlink_sendskb ... skb_queue_tail //put skb to sk_receive_queue ... sock_put //ref = 2 ... ... ... netlink_release ... deferred_put_nlk_sk //ref = 1 mqueue_flush_file spin_lock remove_notification netlink_sendskb sock_put //ref = 0 sk_free ... __sk_destruct netlink_sock_destruct skb_queue_purge //get skb from sk_receive_queue ... __skb_queue_purge_reason kfree_skb_reason __kfree_skb ... skb_release_all skb_release_head_state netlink_skb_destructor vfree(skb->head) //sleeping while holding spinlock

In netlink_sendmsg, if the memory pointed to by skb->head is allocated by vmalloc, and is put to sk_receive_queue queue, also the skb is not freed. When the mqueue executes flush, the sleeping bug will occur. Use vfree_atomic instead of vfree in netlink_skb_destructor to solve the issue.

Fixes: c05cdb1b864f ("netlink: allow large data transfers from user-space") Signed-off-by: Zhengchao Shao shaozhengchao@huawei.com Link: https://lore.kernel.org/r/20240122011807.2110357-1-shaozhengchao@huawei.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/netlink/af_netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 901358a5b593..359f07a53ecc 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -366,7 +366,7 @@ static void netlink_skb_destructor(struct sk_buff *skb) if (is_vmalloc_addr(skb->head)) { if (!skb->cloned || !atomic_dec_return(&(skb_shinfo(skb)->dataref))) - vfree(skb->head); + vfree_atomic(skb->head);

skb->head = NULL; }

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

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

From: Yevgeny Kliteynik kliteyn@nvidia.com

[ Upstream commit 5665954293f13642f9c052ead83c1e9d8cff186f ]

When FW provides ICM addresses for drop RX/TX, the provided capability is 64 bits that contain its GVMI as well as the ICM address itself. In case of TX DROP this GVMI is different from the GVMI that the domain is operating on.

This patch fixes the action to use these GVMI IDs, as provided by FW.

Fixes: 9db810ed2d37 ("net/mlx5: DR, Expose steering action functionality") Signed-off-by: Yevgeny Kliteynik kliteyn@nvidia.com Signed-off-by: Saeed Mahameed saeedm@nvidia.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c index df1363a34a42..9721fe58eb7b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -667,6 +667,7 @@ int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, switch (action_type) { case DR_ACTION_TYP_DROP: attr.final_icm_addr = nic_dmn->drop_icm_addr; + attr.hit_gvmi = nic_dmn->drop_icm_addr >> 48; break; case DR_ACTION_TYP_FT: dest_action = action;

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

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

From: Florian Westphal fw@strlen.de

[ Upstream commit b462579b2b86a8f5230543cadd3a4836be27baf7 ]

nftables has two types of sets/maps, one where userspace defines the name, and anonymous sets/maps, where userspace defines a template name.

For the latter, kernel requires presence of exactly one "%d". nftables uses "__set%d" and "__map%d" for this. The kernel will expand the format specifier and replaces it with the smallest unused number.

As-is, userspace could define a template name that allows to move the set name past the 256 bytes upperlimit (post-expansion).

I don't see how this could be a problem, but I would prefer if userspace cannot do this, so add a limit of 16 bytes for the '%d' template name.

16 bytes is the old total upper limit for set names that existed when nf_tables was merged initially.

Fixes: 387454901bd6 ("netfilter: nf_tables: Allow set names of up to 255 chars") Signed-off-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_tables_api.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fca8f9a36063..0d0b76a5ddfa 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -25,6 +25,7 @@ #include <net/sock.h>

#define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-")) +#define NFT_SET_MAX_ANONLEN 16

unsigned int nf_tables_net_id __read_mostly;

@@ -3930,6 +3931,9 @@ static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set, if (p[1] != 'd' || strchr(p + 2, '%')) return -EINVAL;

+ if (strnlen(name, NFT_SET_MAX_ANONLEN) >= NFT_SET_MAX_ANONLEN) + return -EINVAL; + inuse = (unsigned long *)get_zeroed_page(GFP_KERNEL); if (inuse == NULL) return -ENOMEM;

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

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

From: Jenishkumar Maheshbhai Patel jpatel2@marvell.com

[ Upstream commit 9f538b415db862e74b8c5d3abbccfc1b2b6caa38 ]

Register value persist after booting the kernel using kexec which results in kernel panic. Thus clear the BM pool registers before initialisation to fix the issue.

Fixes: 3f518509dedc ("ethernet: Add new driver for Marvell Armada 375 network unit") Signed-off-by: Jenishkumar Maheshbhai Patel jpatel2@marvell.com Reviewed-by: Maxime Chevallier maxime.chevallier@bootlin.com Link: https://lore.kernel.org/r/20240119035914.2595665-1-jpatel2@marvell.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/marvell/mvpp2/mvpp2_main.c | 27 ++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index e0e6275b3e20..e4e80c2b1ce4 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -581,12 +581,38 @@ static int mvpp2_bm_pools_init(struct device *dev, struct mvpp2 *priv) return err; }

+/* Cleanup pool before actual initialization in the OS */ +static void mvpp2_bm_pool_cleanup(struct mvpp2 *priv, int pool_id) +{ + unsigned int thread = mvpp2_cpu_to_thread(priv, get_cpu()); + u32 val; + int i; + + /* Drain the BM from all possible residues left by firmware */ + for (i = 0; i < MVPP2_BM_POOL_SIZE_MAX; i++) + mvpp2_thread_read(priv, thread, MVPP2_BM_PHY_ALLOC_REG(pool_id)); + + put_cpu(); + + /* Stop the BM pool */ + val = mvpp2_read(priv, MVPP2_BM_POOL_CTRL_REG(pool_id)); + val |= MVPP2_BM_STOP_MASK; + mvpp2_write(priv, MVPP2_BM_POOL_CTRL_REG(pool_id), val); +} + static int mvpp2_bm_init(struct device *dev, struct mvpp2 *priv) { enum dma_data_direction dma_dir = DMA_FROM_DEVICE; int i, err, poolnum = MVPP2_BM_POOLS_NUM; struct mvpp2_port *port;

+ if (priv->percpu_pools) + poolnum = mvpp2_get_nrxqs(priv) * 2; + + /* Clean up the pool state in case it contains stale state */ + for (i = 0; i < poolnum; i++) + mvpp2_bm_pool_cleanup(priv, i); + if (priv->percpu_pools) { for (i = 0; i < priv->port_count; i++) { port = priv->port_list[i]; @@ -596,7 +622,6 @@ static int mvpp2_bm_init(struct device *dev, struct mvpp2 *priv) } }

- poolnum = mvpp2_get_nrxqs(priv) * 2; for (i = 0; i < poolnum; i++) { /* the pool in use */ int pn = i / (poolnum / 2);

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

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

From: Zhipeng Lu alexious@zju.edu.cn

[ Upstream commit f6cc4b6a3ae53df425771000e9c9540cce9b7bb1 ]

In fjes_hw_setup, it allocates several memory and delay the deallocation to the fjes_hw_exit in fjes_probe through the following call chain:

fjes_probe |-> fjes_hw_init |-> fjes_hw_setup |-> fjes_hw_exit

However, when fjes_hw_setup fails, fjes_hw_exit won't be called and thus all the resources allocated in fjes_hw_setup will be leaked. In this patch, we free those resources in fjes_hw_setup and prevents such leaks.

Fixes: 2fcbca687702 ("fjes: platform_driver's .probe and .remove routine") Signed-off-by: Zhipeng Lu alexious@zju.edu.cn Reviewed-by: Simon Horman horms@kernel.org Link: https://lore.kernel.org/r/20240122172445.3841883-1-alexious@zju.edu.cn Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/fjes/fjes_hw.c | 37 ++++++++++++++++++++++++++++++------- 1 file changed, 30 insertions(+), 7 deletions(-)

diff --git a/drivers/net/fjes/fjes_hw.c b/drivers/net/fjes/fjes_hw.c index 065bb0a40b1d..a1405a3e294c 100644 --- a/drivers/net/fjes/fjes_hw.c +++ b/drivers/net/fjes/fjes_hw.c @@ -220,21 +220,25 @@ static int fjes_hw_setup(struct fjes_hw *hw)

mem_size = FJES_DEV_REQ_BUF_SIZE(hw->max_epid); hw->hw_info.req_buf = kzalloc(mem_size, GFP_KERNEL); - if (!(hw->hw_info.req_buf)) - return -ENOMEM; + if (!(hw->hw_info.req_buf)) { + result = -ENOMEM; + goto free_ep_info; + }

hw->hw_info.req_buf_size = mem_size;

mem_size = FJES_DEV_RES_BUF_SIZE(hw->max_epid); hw->hw_info.res_buf = kzalloc(mem_size, GFP_KERNEL); - if (!(hw->hw_info.res_buf)) - return -ENOMEM; + if (!(hw->hw_info.res_buf)) { + result = -ENOMEM; + goto free_req_buf; + }

hw->hw_info.res_buf_size = mem_size;

result = fjes_hw_alloc_shared_status_region(hw); if (result) - return result; + goto free_res_buf;

hw->hw_info.buffer_share_bit = 0; hw->hw_info.buffer_unshare_reserve_bit = 0; @@ -245,11 +249,11 @@ static int fjes_hw_setup(struct fjes_hw *hw)

result = fjes_hw_alloc_epbuf(&buf_pair->tx); if (result) - return result; + goto free_epbuf;

result = fjes_hw_alloc_epbuf(&buf_pair->rx); if (result) - return result; + goto free_epbuf;

spin_lock_irqsave(&hw->rx_status_lock, flags); fjes_hw_setup_epbuf(&buf_pair->tx, mac, @@ -272,6 +276,25 @@ static int fjes_hw_setup(struct fjes_hw *hw) fjes_hw_init_command_registers(hw, &param);

return 0; + +free_epbuf: + for (epidx = 0; epidx < hw->max_epid ; epidx++) { + if (epidx == hw->my_epid) + continue; + fjes_hw_free_epbuf(&hw->ep_shm_info[epidx].tx); + fjes_hw_free_epbuf(&hw->ep_shm_info[epidx].rx); + } + fjes_hw_free_shared_status_region(hw); +free_res_buf: + kfree(hw->hw_info.res_buf); + hw->hw_info.res_buf = NULL; +free_req_buf: + kfree(hw->hw_info.req_buf); + hw->hw_info.req_buf = NULL; +free_ep_info: + kfree(hw->ep_shm_info); + hw->ep_shm_info = NULL; + return result; }

static void fjes_hw_cleanup(struct fjes_hw *hw)

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

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

From: Fedor Pchelkin pchelkin@ispras.ru

commit f03e274a8b29d1d1c1bbd7f764766cb5ca537ab7 upstream.

As clearing REF_VERIFY mount option indicates there were some errors in a ref-verify process, a ref cache is not relevant anymore and should be freed.

btrfs_free_ref_cache() requires REF_VERIFY option being set so call it just before clearing the mount option.

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Reported-by: syzbot+be14ed7728594dc8bd42@syzkaller.appspotmail.com Fixes: fd708b81d972 ("Btrfs: add a extent ref verify tool") CC: stable@vger.kernel.org # 5.4+ Closes: https://lore.kernel.org/lkml/000000000000e5a65c05ee832054@google.com/ Reported-by: syzbot+c563a3c79927971f950f@syzkaller.appspotmail.com Closes: https://lore.kernel.org/lkml/0000000000007fe09705fdc6086c@google.com/ Reviewed-by: Anand Jain anand.jain@oracle.com Signed-off-by: Fedor Pchelkin pchelkin@ispras.ru Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/ref-verify.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -899,8 +899,10 @@ int btrfs_ref_tree_mod(struct btrfs_fs_i out_unlock: spin_unlock(&fs_info->ref_verify_lock); out: - if (ret) + if (ret) { + btrfs_free_ref_cache(fs_info); btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); + } return ret; }

@@ -1029,8 +1031,8 @@ int btrfs_build_ref_tree(struct btrfs_fs } } if (ret) { - btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); btrfs_free_ref_cache(fs_info); + btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); } btrfs_free_path(path); return ret;

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

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

From: David Sterba dsterba@suse.com

commit a208b3f132b48e1f94f620024e66fea635925877 upstream.

There's a warning in btrfs_issue_discard() when the range is not aligned to 512 bytes, originally added in 4d89d377bbb0 ("btrfs: btrfs_issue_discard ensure offset/length are aligned to sector boundaries"). We can't do sub-sector writes anyway so the adjustment is the only thing that we can do and the warning is unnecessary.

CC: stable@vger.kernel.org # 4.19+ Reported-by: syzbot+4a4f1eba14eb5c3417d1@syzkaller.appspotmail.com Reviewed-by: Johannes Thumshirn johannes.thumshirn@wdc.com Reviewed-by: Anand Jain anand.jain@oracle.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/extent-tree.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1202,7 +1202,8 @@ static int btrfs_issue_discard(struct bl u64 bytes_left, end; u64 aligned_start = ALIGN(start, 1 << 9);

- if (WARN_ON(start != aligned_start)) { + /* Adjust the range to be aligned to 512B sectors if necessary. */ + if (start != aligned_start) { len -= aligned_start - start; len = round_down(len, 1 << 9); start = aligned_start;

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

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

From: Omar Sandoval osandov@fb.com

commit 7081929ab2572920e94d70be3d332e5c9f97095a upstream.

If the source file descriptor to the snapshot ioctl refers to a deleted subvolume, we get the following abort:

BTRFS: Transaction aborted (error -2) WARNING: CPU: 0 PID: 833 at fs/btrfs/transaction.c:1875 create_pending_snapshot+0x1040/0x1190 [btrfs] Modules linked in: pata_acpi btrfs ata_piix libata scsi_mod virtio_net blake2b_generic xor net_failover virtio_rng failover scsi_common rng_core raid6_pq libcrc32c CPU: 0 PID: 833 Comm: t_snapshot_dele Not tainted 6.7.0-rc6 #2 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-1.fc39 04/01/2014 RIP: 0010:create_pending_snapshot+0x1040/0x1190 [btrfs] RSP: 0018:ffffa09c01337af8 EFLAGS: 00010282 RAX: 0000000000000000 RBX: ffff9982053e7c78 RCX: 0000000000000027 RDX: ffff99827dc20848 RSI: 0000000000000001 RDI: ffff99827dc20840 RBP: ffffa09c01337c00 R08: 0000000000000000 R09: ffffa09c01337998 R10: 0000000000000003 R11: ffffffffb96da248 R12: fffffffffffffffe R13: ffff99820535bb28 R14: ffff99820b7bd000 R15: ffff99820381ea80 FS: 00007fe20aadabc0(0000) GS:ffff99827dc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000559a120b502f CR3: 00000000055b6000 CR4: 00000000000006f0 Call Trace: <TASK> ? create_pending_snapshot+0x1040/0x1190 [btrfs] ? __warn+0x81/0x130 ? create_pending_snapshot+0x1040/0x1190 [btrfs] ? report_bug+0x171/0x1a0 ? handle_bug+0x3a/0x70 ? exc_invalid_op+0x17/0x70 ? asm_exc_invalid_op+0x1a/0x20 ? create_pending_snapshot+0x1040/0x1190 [btrfs] ? create_pending_snapshot+0x1040/0x1190 [btrfs] create_pending_snapshots+0x92/0xc0 [btrfs] btrfs_commit_transaction+0x66b/0xf40 [btrfs] btrfs_mksubvol+0x301/0x4d0 [btrfs] btrfs_mksnapshot+0x80/0xb0 [btrfs] __btrfs_ioctl_snap_create+0x1c2/0x1d0 [btrfs] btrfs_ioctl_snap_create_v2+0xc4/0x150 [btrfs] btrfs_ioctl+0x8a6/0x2650 [btrfs] ? kmem_cache_free+0x22/0x340 ? do_sys_openat2+0x97/0xe0 __x64_sys_ioctl+0x97/0xd0 do_syscall_64+0x46/0xf0 entry_SYSCALL_64_after_hwframe+0x6e/0x76 RIP: 0033:0x7fe20abe83af RSP: 002b:00007ffe6eff1360 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 00007fe20abe83af RDX: 00007ffe6eff23c0 RSI: 0000000050009417 RDI: 0000000000000003 RBP: 0000000000000003 R08: 0000000000000000 R09: 00007fe20ad16cd0 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007ffe6eff13c0 R14: 00007fe20ad45000 R15: 0000559a120b6d58 </TASK> ---[ end trace 0000000000000000 ]--- BTRFS: error (device vdc: state A) in create_pending_snapshot:1875: errno=-2 No such entry BTRFS info (device vdc: state EA): forced readonly BTRFS warning (device vdc: state EA): Skipping commit of aborted transaction. BTRFS: error (device vdc: state EA) in cleanup_transaction:2055: errno=-2 No such entry

This happens because create_pending_snapshot() initializes the new root item as a copy of the source root item. This includes the refs field, which is 0 for a deleted subvolume. The call to btrfs_insert_root() therefore inserts a root with refs == 0. btrfs_get_new_fs_root() then finds the root and returns -ENOENT if refs == 0, which causes create_pending_snapshot() to abort.

Fix it by checking the source root's refs before attempting the snapshot, but after locking subvol_sem to avoid racing with deletion.

CC: stable@vger.kernel.org # 4.14+ Reviewed-by: Sweet Tea Dorminy sweettea-kernel@dorminy.me Reviewed-by: Anand Jain anand.jain@oracle.com Signed-off-by: Omar Sandoval osandov@fb.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/ioctl.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -798,6 +798,9 @@ static int create_snapshot(struct btrfs_ struct btrfs_trans_handle *trans; int ret;

+ if (btrfs_root_refs(&root->root_item) == 0) + return -ENOENT; + if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) return -EINVAL;

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

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

From: Bernd Edlinger bernd.edlinger@hotmail.de

commit 84c39ec57d409e803a9bb6e4e85daf1243e0e80b upstream.

If get_unused_fd_flags() fails, the error handling is incomplete because bprm->cred is already set to NULL, and therefore free_bprm will not unlock the cred_guard_mutex. Note there are two error conditions which end up here, one before and one after bprm->cred is cleared.

Fixes: b8a61c9e7b4a ("exec: Generic execfd support") Signed-off-by: Bernd Edlinger bernd.edlinger@hotmail.de Acked-by: Eric W. Biederman ebiederm@xmission.com Link: https://lore.kernel.org/r/AS8P193MB128517ADB5EFF29E04389EDAE4752@AS8P193MB12... Cc: stable@vger.kernel.org Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/exec.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/fs/exec.c +++ b/fs/exec.c @@ -1392,6 +1392,9 @@ int begin_new_exec(struct linux_binprm *

out_unlock: up_write(&me->signal->exec_update_lock); + if (!bprm->cred) + mutex_unlock(&me->signal->cred_guard_mutex); + out: return retval; }

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

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

From: Pablo Neira Ayuso pablo@netfilter.org

commit 01acb2e8666a6529697141a6017edbf206921913 upstream.

Remove netdevice from inet/ingress basechain in case NETDEV_UNREGISTER event is reported, otherwise a stale reference to netdevice remains in the hook list.

Fixes: 60a3815da702 ("netfilter: add inet ingress support") Cc: stable@vger.kernel.org Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/netfilter/nft_chain_filter.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)

--- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -358,9 +358,10 @@ static int nf_tables_netdev_event(struct unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct nft_base_chain *basechain; struct nftables_pernet *nft_net; - struct nft_table *table; struct nft_chain *chain, *nr; + struct nft_table *table; struct nft_ctx ctx = { .net = dev_net(dev), }; @@ -372,7 +373,8 @@ static int nf_tables_netdev_event(struct nft_net = net_generic(ctx.net, nf_tables_net_id); mutex_lock(&nft_net->commit_mutex); list_for_each_entry(table, &nft_net->tables, list) { - if (table->family != NFPROTO_NETDEV) + if (table->family != NFPROTO_NETDEV && + table->family != NFPROTO_INET) continue;

ctx.family = table->family; @@ -381,6 +383,11 @@ static int nf_tables_netdev_event(struct if (!nft_is_base_chain(chain)) continue;

+ basechain = nft_base_chain(chain); + if (table->family == NFPROTO_INET && + basechain->ops.hooknum != NF_INET_INGRESS) + continue; + ctx.chain = chain; nft_netdev_event(event, dev, &ctx); }

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

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

From: Mario Limonciello mario.limonciello@amd.com

commit 805c74eac8cb306dc69b87b6b066ab4da77ceaf1 upstream.

Spurious wakeups are reported on the GPD G1619-04 which can be absolved by programming the GPIO to ignore wakeups.

Cc: stable@vger.kernel.org Reported-and-tested-by: George Melikov mail@gmelikov.ru Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3073 Signed-off-by: Mario Limonciello mario.limonciello@amd.com Reviewed-by: Andy Shevchenko andriy.shevchenko@linux.intel.com Signed-off-by: Bartosz Golaszewski bartosz.golaszewski@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpio/gpiolib-acpi.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)

--- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -1479,6 +1479,20 @@ static const struct dmi_system_id gpioli .ignore_wake = "INT33FF:01@0", }, }, + { + /* + * Spurious wakeups from TP_ATTN# pin + * Found in BIOS 0.35 + * https://gitlab.freedesktop.org/drm/amd/-/issues/3073 + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "GPD"), + DMI_MATCH(DMI_PRODUCT_NAME, "G1619-04"), + }, + .driver_data = &(struct acpi_gpiolib_dmi_quirk) { + .ignore_wake = "PNP0C50:00@8", + }, + }, {} /* Terminating entry */ };

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

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

From: Dan Carpenter dan.carpenter@linaro.org

commit 914437992876838662c968cb416f832110fb1093 upstream.

The i2c_master_send/recv() functions return negative error codes or the number of bytes that were able to be sent/received. This code has two problems. 1) Instead of checking if all the bytes were sent or received, it checks that at least one byte was sent or received. 2) If there was a partial send/receive then we should return a negative error code but this code returns success.

Fixes: a9fe713d7d45 ("drm/bridge: Add PTN3460 bridge driver") Cc: stable@vger.kernel.org Signed-off-by: Dan Carpenter dan.carpenter@linaro.org Reviewed-by: Robert Foss rfoss@kernel.org Signed-off-by: Robert Foss rfoss@kernel.org Link: https://patchwork.freedesktop.org/patch/msgid/0cdc2dce-ca89-451a-9774-1482ab... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/bridge/nxp-ptn3460.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

--- a/drivers/gpu/drm/bridge/nxp-ptn3460.c +++ b/drivers/gpu/drm/bridge/nxp-ptn3460.c @@ -56,13 +56,13 @@ static int ptn3460_read_bytes(struct ptn ret = i2c_master_send(ptn_bridge->client, &addr, 1); if (ret <= 0) { DRM_ERROR("Failed to send i2c command, ret=%d\n", ret); - return ret; + return ret ?: -EIO; }

ret = i2c_master_recv(ptn_bridge->client, buf, len); - if (ret <= 0) { + if (ret != len) { DRM_ERROR("Failed to recv i2c data, ret=%d\n", ret); - return ret; + return ret < 0 ? ret : -EIO; }

return 0; @@ -78,9 +78,9 @@ static int ptn3460_write_byte(struct ptn buf[1] = val;

ret = i2c_master_send(ptn_bridge->client, buf, ARRAY_SIZE(buf)); - if (ret <= 0) { + if (ret != ARRAY_SIZE(buf)) { DRM_ERROR("Failed to send i2c command, ret=%d\n", ret); - return ret; + return ret < 0 ? ret : -EIO; }

return 0;

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

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

From: Dan Carpenter dan.carpenter@linaro.org

commit 28d3d0696688154cc04983f343011d07bf0508e4 upstream.

The i2c_master_send/recv() functions return negative error codes or they return "len" on success. So the error handling here can be written as just normal checks for "if (ret < 0) return ret;". No need to complicate things.

Btw, in this code the "len" parameter can never be zero, but even if it were, then I feel like this would still be the best way to write it.

Fixes: 914437992876 ("drm/bridge: nxp-ptn3460: fix i2c_master_send() error checking") Suggested-by: Neil Armstrong neil.armstrong@linaro.org Signed-off-by: Dan Carpenter dan.carpenter@linaro.org Reviewed-by: Robert Foss rfoss@kernel.org Signed-off-by: Robert Foss rfoss@kernel.org Link: https://patchwork.freedesktop.org/patch/msgid/04242630-42d8-4920-8c67-24ac9d... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/bridge/nxp-ptn3460.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)

--- a/drivers/gpu/drm/bridge/nxp-ptn3460.c +++ b/drivers/gpu/drm/bridge/nxp-ptn3460.c @@ -54,15 +54,15 @@ static int ptn3460_read_bytes(struct ptn int ret;

ret = i2c_master_send(ptn_bridge->client, &addr, 1); - if (ret <= 0) { + if (ret < 0) { DRM_ERROR("Failed to send i2c command, ret=%d\n", ret); - return ret ?: -EIO; + return ret; }

ret = i2c_master_recv(ptn_bridge->client, buf, len); - if (ret != len) { + if (ret < 0) { DRM_ERROR("Failed to recv i2c data, ret=%d\n", ret); - return ret < 0 ? ret : -EIO; + return ret; }

return 0; @@ -78,9 +78,9 @@ static int ptn3460_write_byte(struct ptn buf[1] = val;

ret = i2c_master_send(ptn_bridge->client, buf, ARRAY_SIZE(buf)); - if (ret != ARRAY_SIZE(buf)) { + if (ret < 0) { DRM_ERROR("Failed to send i2c command, ret=%d\n", ret); - return ret < 0 ? ret : -EIO; + return ret; }

return 0;

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

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

From: Rafael J. Wysocki rafael.j.wysocki@intel.com

[ Upstream commit 2aa36604e8243698ff22bd5fef0dd0c6bb07ba92 ]

It is generally unsafe to call put_device() with dpm_list_mtx held, because the given device's release routine may carry out an action depending on that lock which then may deadlock, so modify the system-wide suspend and resume of devices to always drop dpm_list_mtx before calling put_device() (and adjust white space somewhat while at it).

For instance, this prevents the following splat from showing up in the kernel log after a system resume in certain configurations:

[ 3290.969514] ====================================================== [ 3290.969517] WARNING: possible circular locking dependency detected [ 3290.969519] 5.15.0+ #2420 Tainted: G S [ 3290.969523] ------------------------------------------------------ [ 3290.969525] systemd-sleep/4553 is trying to acquire lock: [ 3290.969529] ffff888117ab1138 ((wq_completion)hci0#2){+.+.}-{0:0}, at: flush_workqueue+0x87/0x4a0 [ 3290.969554] but task is already holding lock: [ 3290.969556] ffffffff8280fca8 (dpm_list_mtx){+.+.}-{3:3}, at: dpm_resume+0x12e/0x3e0 [ 3290.969571] which lock already depends on the new lock.

[ 3290.969573] the existing dependency chain (in reverse order) is: [ 3290.969575] -> #3 (dpm_list_mtx){+.+.}-{3:3}: [ 3290.969583] __mutex_lock+0x9d/0xa30 [ 3290.969591] device_pm_add+0x2e/0xe0 [ 3290.969597] device_add+0x4d5/0x8f0 [ 3290.969605] hci_conn_add_sysfs+0x43/0xb0 [bluetooth] [ 3290.969689] hci_conn_complete_evt.isra.71+0x124/0x750 [bluetooth] [ 3290.969747] hci_event_packet+0xd6c/0x28a0 [bluetooth] [ 3290.969798] hci_rx_work+0x213/0x640 [bluetooth] [ 3290.969842] process_one_work+0x2aa/0x650 [ 3290.969851] worker_thread+0x39/0x400 [ 3290.969859] kthread+0x142/0x170 [ 3290.969865] ret_from_fork+0x22/0x30 [ 3290.969872] -> #2 (&hdev->lock){+.+.}-{3:3}: [ 3290.969881] __mutex_lock+0x9d/0xa30 [ 3290.969887] hci_event_packet+0xba/0x28a0 [bluetooth] [ 3290.969935] hci_rx_work+0x213/0x640 [bluetooth] [ 3290.969978] process_one_work+0x2aa/0x650 [ 3290.969985] worker_thread+0x39/0x400 [ 3290.969993] kthread+0x142/0x170 [ 3290.969999] ret_from_fork+0x22/0x30 [ 3290.970004] -> #1 ((work_completion)(&hdev->rx_work)){+.+.}-{0:0}: [ 3290.970013] process_one_work+0x27d/0x650 [ 3290.970020] worker_thread+0x39/0x400 [ 3290.970028] kthread+0x142/0x170 [ 3290.970033] ret_from_fork+0x22/0x30 [ 3290.970038] -> #0 ((wq_completion)hci0#2){+.+.}-{0:0}: [ 3290.970047] __lock_acquire+0x15cb/0x1b50 [ 3290.970054] lock_acquire+0x26c/0x300 [ 3290.970059] flush_workqueue+0xae/0x4a0 [ 3290.970066] drain_workqueue+0xa1/0x130 [ 3290.970073] destroy_workqueue+0x34/0x1f0 [ 3290.970081] hci_release_dev+0x49/0x180 [bluetooth] [ 3290.970130] bt_host_release+0x1d/0x30 [bluetooth] [ 3290.970195] device_release+0x33/0x90 [ 3290.970201] kobject_release+0x63/0x160 [ 3290.970211] dpm_resume+0x164/0x3e0 [ 3290.970215] dpm_resume_end+0xd/0x20 [ 3290.970220] suspend_devices_and_enter+0x1a4/0xba0 [ 3290.970229] pm_suspend+0x26b/0x310 [ 3290.970236] state_store+0x42/0x90 [ 3290.970243] kernfs_fop_write_iter+0x135/0x1b0 [ 3290.970251] new_sync_write+0x125/0x1c0 [ 3290.970257] vfs_write+0x360/0x3c0 [ 3290.970263] ksys_write+0xa7/0xe0 [ 3290.970269] do_syscall_64+0x3a/0x80 [ 3290.970276] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 3290.970284] other info that might help us debug this:

[ 3290.970285] Chain exists of: (wq_completion)hci0#2 --> &hdev->lock --> dpm_list_mtx

[ 3290.970297] Possible unsafe locking scenario:

[ 3290.970299] CPU0 CPU1 [ 3290.970300] ---- ---- [ 3290.970302] lock(dpm_list_mtx); [ 3290.970306] lock(&hdev->lock); [ 3290.970310] lock(dpm_list_mtx); [ 3290.970314] lock((wq_completion)hci0#2); [ 3290.970319] *** DEADLOCK ***

[ 3290.970321] 7 locks held by systemd-sleep/4553: [ 3290.970325] #0: ffff888103bcd448 (sb_writers#4){.+.+}-{0:0}, at: ksys_write+0xa7/0xe0 [ 3290.970341] #1: ffff888115a14488 (&of->mutex){+.+.}-{3:3}, at: kernfs_fop_write_iter+0x103/0x1b0 [ 3290.970355] #2: ffff888100f719e0 (kn->active#233){.+.+}-{0:0}, at: kernfs_fop_write_iter+0x10c/0x1b0 [ 3290.970369] #3: ffffffff82661048 (autosleep_lock){+.+.}-{3:3}, at: state_store+0x12/0x90 [ 3290.970384] #4: ffffffff82658ac8 (system_transition_mutex){+.+.}-{3:3}, at: pm_suspend+0x9f/0x310 [ 3290.970399] #5: ffffffff827f2a48 (acpi_scan_lock){+.+.}-{3:3}, at: acpi_suspend_begin+0x4c/0x80 [ 3290.970416] #6: ffffffff8280fca8 (dpm_list_mtx){+.+.}-{3:3}, at: dpm_resume+0x12e/0x3e0 [ 3290.970428] stack backtrace: [ 3290.970431] CPU: 3 PID: 4553 Comm: systemd-sleep Tainted: G S 5.15.0+ #2420 [ 3290.970438] Hardware name: Dell Inc. XPS 13 9380/0RYJWW, BIOS 1.5.0 06/03/2019 [ 3290.970441] Call Trace: [ 3290.970446] dump_stack_lvl+0x44/0x57 [ 3290.970454] check_noncircular+0x105/0x120 [ 3290.970468] ? __lock_acquire+0x15cb/0x1b50 [ 3290.970474] __lock_acquire+0x15cb/0x1b50 [ 3290.970487] lock_acquire+0x26c/0x300 [ 3290.970493] ? flush_workqueue+0x87/0x4a0 [ 3290.970503] ? __raw_spin_lock_init+0x3b/0x60 [ 3290.970510] ? lockdep_init_map_type+0x58/0x240 [ 3290.970519] flush_workqueue+0xae/0x4a0 [ 3290.970526] ? flush_workqueue+0x87/0x4a0 [ 3290.970544] ? drain_workqueue+0xa1/0x130 [ 3290.970552] drain_workqueue+0xa1/0x130 [ 3290.970561] destroy_workqueue+0x34/0x1f0 [ 3290.970572] hci_release_dev+0x49/0x180 [bluetooth] [ 3290.970624] bt_host_release+0x1d/0x30 [bluetooth] [ 3290.970687] device_release+0x33/0x90 [ 3290.970695] kobject_release+0x63/0x160 [ 3290.970705] dpm_resume+0x164/0x3e0 [ 3290.970710] ? dpm_resume_early+0x251/0x3b0 [ 3290.970718] dpm_resume_end+0xd/0x20 [ 3290.970723] suspend_devices_and_enter+0x1a4/0xba0 [ 3290.970737] pm_suspend+0x26b/0x310 [ 3290.970746] state_store+0x42/0x90 [ 3290.970755] kernfs_fop_write_iter+0x135/0x1b0 [ 3290.970764] new_sync_write+0x125/0x1c0 [ 3290.970777] vfs_write+0x360/0x3c0 [ 3290.970785] ksys_write+0xa7/0xe0 [ 3290.970794] do_syscall_64+0x3a/0x80 [ 3290.970803] entry_SYSCALL_64_after_hwframe+0x44/0xae [ 3290.970811] RIP: 0033:0x7f41b1328164 [ 3290.970819] Code: 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b7 0f 1f 80 00 00 00 00 8b 05 4a d2 2c 00 48 63 ff 85 c0 75 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 f3 c3 66 90 55 53 48 89 d5 48 89 f3 48 83 [ 3290.970824] RSP: 002b:00007ffe6ae21b28 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 3290.970831] RAX: ffffffffffffffda RBX: 0000000000000004 RCX: 00007f41b1328164 [ 3290.970836] RDX: 0000000000000004 RSI: 000055965e651070 RDI: 0000000000000004 [ 3290.970839] RBP: 000055965e651070 R08: 000055965e64f390 R09: 00007f41b1e3d1c0 [ 3290.970843] R10: 000000000000000a R11: 0000000000000246 R12: 0000000000000004 [ 3290.970846] R13: 0000000000000001 R14: 000055965e64f2b0 R15: 0000000000000004

Cc: All applicable stable@vger.kernel.org Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Stable-dep-of: 7839d0078e0d ("PM: sleep: Fix possible deadlocks in core system-wide PM code") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/base/power/main.c | 84 ++++++++++++++++++++++++++------------- 1 file changed, 57 insertions(+), 27 deletions(-)

diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index a4714a025315..6c334a65644c 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -714,6 +714,7 @@ static void dpm_noirq_resume_devices(pm_message_t state) dev = to_device(dpm_noirq_list.next); get_device(dev); list_move_tail(&dev->power.entry, &dpm_late_early_list); + mutex_unlock(&dpm_list_mtx);

if (!is_async(dev)) { @@ -728,8 +729,9 @@ static void dpm_noirq_resume_devices(pm_message_t state) } }

- mutex_lock(&dpm_list_mtx); put_device(dev); + + mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); @@ -855,6 +857,7 @@ void dpm_resume_early(pm_message_t state) dev = to_device(dpm_late_early_list.next); get_device(dev); list_move_tail(&dev->power.entry, &dpm_suspended_list); + mutex_unlock(&dpm_list_mtx);

if (!is_async(dev)) { @@ -868,8 +871,10 @@ void dpm_resume_early(pm_message_t state) pm_dev_err(dev, state, " early", error); } } - mutex_lock(&dpm_list_mtx); + put_device(dev); + + mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); @@ -1032,7 +1037,12 @@ void dpm_resume(pm_message_t state) } if (!list_empty(&dev->power.entry)) list_move_tail(&dev->power.entry, &dpm_prepared_list); + + mutex_unlock(&dpm_list_mtx); + put_device(dev); + + mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); async_synchronize_full(); @@ -1110,14 +1120,16 @@ void dpm_complete(pm_message_t state) get_device(dev); dev->power.is_prepared = false; list_move(&dev->power.entry, &list); + mutex_unlock(&dpm_list_mtx);

trace_device_pm_callback_start(dev, "", state.event); device_complete(dev, state); trace_device_pm_callback_end(dev, 0);

- mutex_lock(&dpm_list_mtx); put_device(dev); + + mutex_lock(&dpm_list_mtx); } list_splice(&list, &dpm_list); mutex_unlock(&dpm_list_mtx); @@ -1302,17 +1314,21 @@ static int dpm_noirq_suspend_devices(pm_message_t state) error = device_suspend_noirq(dev);

mutex_lock(&dpm_list_mtx); + if (error) { pm_dev_err(dev, state, " noirq", error); dpm_save_failed_dev(dev_name(dev)); - put_device(dev); - break; - } - if (!list_empty(&dev->power.entry)) + } else if (!list_empty(&dev->power.entry)) { list_move(&dev->power.entry, &dpm_noirq_list); + } + + mutex_unlock(&dpm_list_mtx); + put_device(dev);

- if (async_error) + mutex_lock(&dpm_list_mtx); + + if (error || async_error) break; } mutex_unlock(&dpm_list_mtx); @@ -1479,23 +1495,28 @@ int dpm_suspend_late(pm_message_t state) struct device *dev = to_device(dpm_suspended_list.prev);

get_device(dev); + mutex_unlock(&dpm_list_mtx);

error = device_suspend_late(dev);

mutex_lock(&dpm_list_mtx); + if (!list_empty(&dev->power.entry)) list_move(&dev->power.entry, &dpm_late_early_list);

if (error) { pm_dev_err(dev, state, " late", error); dpm_save_failed_dev(dev_name(dev)); - put_device(dev); - break; } + + mutex_unlock(&dpm_list_mtx); + put_device(dev);

- if (async_error) + mutex_lock(&dpm_list_mtx); + + if (error || async_error) break; } mutex_unlock(&dpm_list_mtx); @@ -1755,21 +1776,27 @@ int dpm_suspend(pm_message_t state) struct device *dev = to_device(dpm_prepared_list.prev);

get_device(dev); + mutex_unlock(&dpm_list_mtx);

error = device_suspend(dev);

mutex_lock(&dpm_list_mtx); + if (error) { pm_dev_err(dev, state, "", error); dpm_save_failed_dev(dev_name(dev)); - put_device(dev); - break; - } - if (!list_empty(&dev->power.entry)) + } else if (!list_empty(&dev->power.entry)) { list_move(&dev->power.entry, &dpm_suspended_list); + } + + mutex_unlock(&dpm_list_mtx); + put_device(dev); - if (async_error) + + mutex_lock(&dpm_list_mtx); + + if (error || async_error) break; } mutex_unlock(&dpm_list_mtx); @@ -1886,6 +1913,7 @@ int dpm_prepare(pm_message_t state) struct device *dev = to_device(dpm_list.next);

get_device(dev); + mutex_unlock(&dpm_list_mtx);

trace_device_pm_callback_start(dev, "", state.event); @@ -1893,21 +1921,23 @@ int dpm_prepare(pm_message_t state) trace_device_pm_callback_end(dev, error);

mutex_lock(&dpm_list_mtx); - if (error) { - if (error == -EAGAIN) { - put_device(dev); - error = 0; - continue; - } + + if (!error) { + dev->power.is_prepared = true; + if (!list_empty(&dev->power.entry)) + list_move_tail(&dev->power.entry, &dpm_prepared_list); + } else if (error == -EAGAIN) { + error = 0; + } else { dev_info(dev, "not prepared for power transition: code %d\n", error); - put_device(dev); - break; } - dev->power.is_prepared = true; - if (!list_empty(&dev->power.entry)) - list_move_tail(&dev->power.entry, &dpm_prepared_list); + + mutex_unlock(&dpm_list_mtx); + put_device(dev); + + mutex_lock(&dpm_list_mtx); } mutex_unlock(&dpm_list_mtx); trace_suspend_resume(TPS("dpm_prepare"), state.event, false);

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

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

From: Rafael J. Wysocki rafael.j.wysocki@intel.com

[ Upstream commit 7839d0078e0d5e6cc2fa0b0dfbee71de74f1e557 ]

It is reported that in low-memory situations the system-wide resume core code deadlocks, because async_schedule_dev() executes its argument function synchronously if it cannot allocate memory (and not only in that case) and that function attempts to acquire a mutex that is already held. Executing the argument function synchronously from within dpm_async_fn() may also be problematic for ordering reasons (it may cause a consumer device's resume callback to be invoked before a requisite supplier device's one, for example).

Address this by changing the code in question to use async_schedule_dev_nocall() for scheduling the asynchronous execution of device suspend and resume functions and to directly run them synchronously if async_schedule_dev_nocall() returns false.

Link: https://lore.kernel.org/linux-pm/ZYvjiqX6EsL15moe@perf/ Reported-by: Youngmin Nam youngmin.nam@samsung.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Reviewed-by: Stanislaw Gruszka stanislaw.gruszka@linux.intel.com Tested-by: Youngmin Nam youngmin.nam@samsung.com Reviewed-by: Ulf Hansson ulf.hansson@linaro.org Cc: 5.7+ stable@vger.kernel.org # 5.7+: 6aa09a5bccd8 async: Split async_schedule_node_domain() Cc: 5.7+ stable@vger.kernel.org # 5.7+: 7d4b5d7a37bd async: Introduce async_schedule_dev_nocall() Cc: 5.7+ stable@vger.kernel.org # 5.7+ Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/base/power/main.c | 148 ++++++++++++++++++-------------------- 1 file changed, 68 insertions(+), 80 deletions(-)

diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c index 402f3c4e3668..c493e48e420f 100644 --- a/drivers/base/power/main.c +++ b/drivers/base/power/main.c @@ -583,7 +583,7 @@ bool dev_pm_skip_resume(struct device *dev) }

/** - * device_resume_noirq - Execute a "noirq resume" callback for given device. + * __device_resume_noirq - Execute a "noirq resume" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. @@ -591,7 +591,7 @@ bool dev_pm_skip_resume(struct device *dev) * The driver of @dev will not receive interrupts while this function is being * executed. */ -static int device_resume_noirq(struct device *dev, pm_message_t state, bool async) +static void __device_resume_noirq(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; @@ -659,7 +659,13 @@ static int device_resume_noirq(struct device *dev, pm_message_t state, bool asyn Out: complete_all(&dev->power.completion); TRACE_RESUME(error); - return error; + + if (error) { + suspend_stats.failed_resume_noirq++; + dpm_save_failed_step(SUSPEND_RESUME_NOIRQ); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async noirq" : " noirq", error); + } }

static bool is_async(struct device *dev) @@ -672,11 +678,15 @@ static bool dpm_async_fn(struct device *dev, async_func_t func) { reinit_completion(&dev->power.completion);

- if (is_async(dev)) { - get_device(dev); - async_schedule_dev(func, dev); + if (!is_async(dev)) + return false; + + get_device(dev); + + if (async_schedule_dev_nocall(func, dev)) return true; - } + + put_device(dev);

return false; } @@ -684,15 +694,19 @@ static bool dpm_async_fn(struct device *dev, async_func_t func) static void async_resume_noirq(void *data, async_cookie_t cookie) { struct device *dev = data; - int error; - - error = device_resume_noirq(dev, pm_transition, true); - if (error) - pm_dev_err(dev, pm_transition, " async", error);

+ __device_resume_noirq(dev, pm_transition, true); put_device(dev); }

+static void device_resume_noirq(struct device *dev) +{ + if (dpm_async_fn(dev, async_resume_noirq)) + return; + + __device_resume_noirq(dev, pm_transition, false); +} + static void dpm_noirq_resume_devices(pm_message_t state) { struct device *dev; @@ -702,14 +716,6 @@ static void dpm_noirq_resume_devices(pm_message_t state) mutex_lock(&dpm_list_mtx); pm_transition = state;

- /* - * Advanced the async threads upfront, - * in case the starting of async threads is - * delayed by non-async resuming devices. - */ - list_for_each_entry(dev, &dpm_noirq_list, power.entry) - dpm_async_fn(dev, async_resume_noirq); - while (!list_empty(&dpm_noirq_list)) { dev = to_device(dpm_noirq_list.next); get_device(dev); @@ -717,17 +723,7 @@ static void dpm_noirq_resume_devices(pm_message_t state)

mutex_unlock(&dpm_list_mtx);

- if (!is_async(dev)) { - int error; - - error = device_resume_noirq(dev, state, false); - if (error) { - suspend_stats.failed_resume_noirq++; - dpm_save_failed_step(SUSPEND_RESUME_NOIRQ); - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, state, " noirq", error); - } - } + device_resume_noirq(dev);

put_device(dev);

@@ -757,14 +753,14 @@ void dpm_resume_noirq(pm_message_t state) }

/** - * device_resume_early - Execute an "early resume" callback for given device. + * __device_resume_early - Execute an "early resume" callback for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. * * Runtime PM is disabled for @dev while this function is being executed. */ -static int device_resume_early(struct device *dev, pm_message_t state, bool async) +static void __device_resume_early(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; @@ -817,21 +813,31 @@ static int device_resume_early(struct device *dev, pm_message_t state, bool asyn

pm_runtime_enable(dev); complete_all(&dev->power.completion); - return error; + + if (error) { + suspend_stats.failed_resume_early++; + dpm_save_failed_step(SUSPEND_RESUME_EARLY); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async early" : " early", error); + } }

static void async_resume_early(void *data, async_cookie_t cookie) { struct device *dev = data; - int error; - - error = device_resume_early(dev, pm_transition, true); - if (error) - pm_dev_err(dev, pm_transition, " async", error);

+ __device_resume_early(dev, pm_transition, true); put_device(dev); }

+static void device_resume_early(struct device *dev) +{ + if (dpm_async_fn(dev, async_resume_early)) + return; + + __device_resume_early(dev, pm_transition, false); +} + /** * dpm_resume_early - Execute "early resume" callbacks for all devices. * @state: PM transition of the system being carried out. @@ -845,14 +851,6 @@ void dpm_resume_early(pm_message_t state) mutex_lock(&dpm_list_mtx); pm_transition = state;

- /* - * Advanced the async threads upfront, - * in case the starting of async threads is - * delayed by non-async resuming devices. - */ - list_for_each_entry(dev, &dpm_late_early_list, power.entry) - dpm_async_fn(dev, async_resume_early); - while (!list_empty(&dpm_late_early_list)) { dev = to_device(dpm_late_early_list.next); get_device(dev); @@ -860,17 +858,7 @@ void dpm_resume_early(pm_message_t state)

mutex_unlock(&dpm_list_mtx);

- if (!is_async(dev)) { - int error; - - error = device_resume_early(dev, state, false); - if (error) { - suspend_stats.failed_resume_early++; - dpm_save_failed_step(SUSPEND_RESUME_EARLY); - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, state, " early", error); - } - } + device_resume_early(dev);

put_device(dev);

@@ -894,12 +882,12 @@ void dpm_resume_start(pm_message_t state) EXPORT_SYMBOL_GPL(dpm_resume_start);

/** - * device_resume - Execute "resume" callbacks for given device. + * __device_resume - Execute "resume" callbacks for given device. * @dev: Device to handle. * @state: PM transition of the system being carried out. * @async: If true, the device is being resumed asynchronously. */ -static int device_resume(struct device *dev, pm_message_t state, bool async) +static void __device_resume(struct device *dev, pm_message_t state, bool async) { pm_callback_t callback = NULL; const char *info = NULL; @@ -981,20 +969,30 @@ static int device_resume(struct device *dev, pm_message_t state, bool async)

TRACE_RESUME(error);

- return error; + if (error) { + suspend_stats.failed_resume++; + dpm_save_failed_step(SUSPEND_RESUME); + dpm_save_failed_dev(dev_name(dev)); + pm_dev_err(dev, state, async ? " async" : "", error); + } }

static void async_resume(void *data, async_cookie_t cookie) { struct device *dev = data; - int error;

- error = device_resume(dev, pm_transition, true); - if (error) - pm_dev_err(dev, pm_transition, " async", error); + __device_resume(dev, pm_transition, true); put_device(dev); }

+static void device_resume(struct device *dev) +{ + if (dpm_async_fn(dev, async_resume)) + return; + + __device_resume(dev, pm_transition, false); +} + /** * dpm_resume - Execute "resume" callbacks for non-sysdev devices. * @state: PM transition of the system being carried out. @@ -1014,27 +1012,17 @@ void dpm_resume(pm_message_t state) pm_transition = state; async_error = 0;

- list_for_each_entry(dev, &dpm_suspended_list, power.entry) - dpm_async_fn(dev, async_resume); - while (!list_empty(&dpm_suspended_list)) { dev = to_device(dpm_suspended_list.next); + get_device(dev); - if (!is_async(dev)) { - int error;

- mutex_unlock(&dpm_list_mtx); + mutex_unlock(&dpm_list_mtx); + + device_resume(dev);

- error = device_resume(dev, state, false); - if (error) { - suspend_stats.failed_resume++; - dpm_save_failed_step(SUSPEND_RESUME); - dpm_save_failed_dev(dev_name(dev)); - pm_dev_err(dev, state, "", error); - } + mutex_lock(&dpm_list_mtx);

- mutex_lock(&dpm_list_mtx); - } if (!list_empty(&dev->power.entry)) list_move_tail(&dev->power.entry, &dpm_prepared_list);

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

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

From: Lukas Schauer lukas@schauer.dev

[ Upstream commit e95aada4cb93d42e25c30a0ef9eb2923d9711d4a ]

Commit c73be61cede5 ("pipe: Add general notification queue support") a regression was introduced that would lock up resized pipes under certain conditions. See the reproducer in [1].

The commit resizing the pipe ring size was moved to a different function, doing that moved the wakeup for pipe->wr_wait before actually raising pipe->max_usage. If a pipe was full before the resize occured it would result in the wakeup never actually triggering pipe_write.

Set @max_usage and @nr_accounted before waking writers if this isn't a watch queue.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=212295 [1] Link: https://lore.kernel.org/r/20231201-orchideen-modewelt-e009de4562c6@brauner Fixes: c73be61cede5 ("pipe: Add general notification queue support") Reviewed-by: David Howells dhowells@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Lukas Schauer lukas@schauer.dev [Christian Brauner brauner@kernel.org: rewrite to account for watch queues] Signed-off-by: Christian Brauner brauner@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- fs/pipe.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/fs/pipe.c b/fs/pipe.c index 7b3e94baba21..588fe37d8d95 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1300,6 +1300,11 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) pipe->tail = tail; pipe->head = head;

+ if (!pipe_has_watch_queue(pipe)) { + pipe->max_usage = nr_slots; + pipe->nr_accounted = nr_slots; + } + spin_unlock_irq(&pipe->rd_wait.lock);

/* This might have made more room for writers */ @@ -1351,8 +1356,6 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) if (ret < 0) goto out_revert_acct;

- pipe->max_usage = nr_slots; - pipe->nr_accounted = nr_slots; return pipe->max_usage * PAGE_SIZE;

out_revert_acct:

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

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

From: Sandeep Maheswaram sanm@codeaurora.org

[ Upstream commit 1e6e6e7a080ca3c1e807473e067ef04d4d005097 ]

Using pdc interrupts for USB instead of GIC interrupts to support wake up in case xo shutdown.

Reviewed-by: Stephen Boyd swboyd@chromium.org Signed-off-by: Sandeep Maheswaram sanm@codeaurora.org Link: https://lore.kernel.org/r/1594235417-23066-4-git-send-email-sanm@codeaurora.... Signed-off-by: Bjorn Andersson bjorn.andersson@linaro.org Stable-dep-of: 9b956999bf72 ("arm64: dts: qcom: sc7180: fix USB wakeup interrupt types") Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/boot/dts/qcom/sc7180.dtsi | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi index eb07a882d43b..6eb82699a4a1 100644 --- a/arch/arm64/boot/dts/qcom/sc7180.dtsi +++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi @@ -2688,10 +2688,10 @@ usb_1: usb@a6f8800 { <&gcc GCC_USB30_PRIM_MASTER_CLK>; assigned-clock-rates = <19200000>, <150000000>;

- interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 486 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 488 IRQ_TYPE_LEVEL_HIGH>, - <GIC_SPI 489 IRQ_TYPE_LEVEL_HIGH>; + interrupts-extended = <&intc GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 6 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 8 IRQ_TYPE_LEVEL_HIGH>, + <&pdc 9 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "hs_phy_irq", "ss_phy_irq", "dm_hs_phy_irq", "dp_hs_phy_irq";

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

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

From: Zheng Wang zyytlz.wz@163.com

[ Upstream commit 206c857dd17d4d026de85866f1b5f0969f2a109e ]

In mtk_jpeg_probe, &jpeg->job_timeout_work is bound with mtk_jpeg_job_timeout_work.

In mtk_jpeg_dec_device_run, if error happens in mtk_jpeg_set_dec_dst, it will finally start the worker while mark the job as finished by invoking v4l2_m2m_job_finish.

There are two methods to trigger the bug. If we remove the module, it which will call mtk_jpeg_remove to make cleanup. The possible sequence is as follows, which will cause a use-after-free bug.

CPU0 CPU1 mtk_jpeg_dec_... | start worker | |mtk_jpeg_job_timeout_work mtk_jpeg_remove | v4l2_m2m_release | kfree(m2m_dev); | | | v4l2_m2m_get_curr_priv | m2m_dev->curr_ctx //use

If we close the file descriptor, which will call mtk_jpeg_release, it will have a similar sequence.

Fix this bug by starting timeout worker only if started jpegdec worker successfully. Then v4l2_m2m_job_finish will only be called in either mtk_jpeg_job_timeout_work or mtk_jpeg_dec_device_run.

Fixes: b2f0d2724ba4 ("[media] vcodec: mediatek: Add Mediatek JPEG Decoder Driver") Signed-off-by: Zheng Wang zyytlz.wz@163.com Signed-off-by: Dmitry Osipenko dmitry.osipenko@collabora.com Cc: stable@vger.kernel.org Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c b/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c index 36109c324cb6..3519c2252ae8 100644 --- a/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c +++ b/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c @@ -977,13 +977,13 @@ static void mtk_jpeg_dec_device_run(void *priv) if (ret < 0) goto dec_end;

- schedule_delayed_work(&jpeg->job_timeout_work, - msecs_to_jiffies(MTK_JPEG_HW_TIMEOUT_MSEC)); - mtk_jpeg_set_dec_src(ctx, &src_buf->vb2_buf, &bs); if (mtk_jpeg_set_dec_dst(ctx, &jpeg_src_buf->dec_param, &dst_buf->vb2_buf, &fb)) goto dec_end;

+ schedule_delayed_work(&jpeg->job_timeout_work, + msecs_to_jiffies(MTK_JPEG_HW_TIMEOUT_MSEC)); + spin_lock_irqsave(&jpeg->hw_lock, flags); mtk_jpeg_dec_reset(jpeg->reg_base); mtk_jpeg_dec_set_config(jpeg->reg_base,

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

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

From: Charan Teja Kalla quic_charante@quicinc.com

[ Upstream commit 5ec8e8ea8b7783fab150cf86404fc38cb4db8800 ]

The below race is observed on a PFN which falls into the device memory region with the system memory configuration where PFN's are such that [ZONE_NORMAL ZONE_DEVICE ZONE_NORMAL]. Since normal zone start and end pfn contains the device memory PFN's as well, the compaction triggered will try on the device memory PFN's too though they end up in NOP(because pfn_to_online_page() returns NULL for ZONE_DEVICE memory sections). When from other core, the section mappings are being removed for the ZONE_DEVICE region, that the PFN in question belongs to, on which compaction is currently being operated is resulting into the kernel crash with CONFIG_SPASEMEM_VMEMAP enabled. The crash logs can be seen at [1].

compact_zone() memunmap_pages ------------- --------------- __pageblock_pfn_to_page ...... (a)pfn_valid(): valid_section()//return true (b)__remove_pages()-> sparse_remove_section()-> section_deactivate(): [Free the array ms->usage and set ms->usage = NULL] pfn_section_valid() [Access ms->usage which is NULL]

NOTE: From the above it can be said that the race is reduced to between the pfn_valid()/pfn_section_valid() and the section deactivate with SPASEMEM_VMEMAP enabled.

The commit b943f045a9af("mm/sparse: fix kernel crash with pfn_section_valid check") tried to address the same problem by clearing the SECTION_HAS_MEM_MAP with the expectation of valid_section() returns false thus ms->usage is not accessed.

Fix this issue by the below steps:

a) Clear SECTION_HAS_MEM_MAP before freeing the ->usage.

b) RCU protected read side critical section will either return NULL when SECTION_HAS_MEM_MAP is cleared or can successfully access ->usage.

c) Free the ->usage with kfree_rcu() and set ms->usage = NULL. No attempt will be made to access ->usage after this as the SECTION_HAS_MEM_MAP is cleared thus valid_section() return false.

Thanks to David/Pavan for their inputs on this patch.

[1] https://lore.kernel.org/linux-mm/994410bb-89aa-d987-1f50-f514903c55aa@quicin...

On Snapdragon SoC, with the mentioned memory configuration of PFN's as [ZONE_NORMAL ZONE_DEVICE ZONE_NORMAL], we are able to see bunch of issues daily while testing on a device farm.

For this particular issue below is the log. Though the below log is not directly pointing to the pfn_section_valid(){ ms->usage;}, when we loaded this dump on T32 lauterbach tool, it is pointing.

[ 540.578056] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 540.578068] Mem abort info: [ 540.578070] ESR = 0x0000000096000005 [ 540.578073] EC = 0x25: DABT (current EL), IL = 32 bits [ 540.578077] SET = 0, FnV = 0 [ 540.578080] EA = 0, S1PTW = 0 [ 540.578082] FSC = 0x05: level 1 translation fault [ 540.578085] Data abort info: [ 540.578086] ISV = 0, ISS = 0x00000005 [ 540.578088] CM = 0, WnR = 0 [ 540.579431] pstate: 82400005 (Nzcv daif +PAN -UAO +TCO -DIT -SSBSBTYPE=--) [ 540.579436] pc : __pageblock_pfn_to_page+0x6c/0x14c [ 540.579454] lr : compact_zone+0x994/0x1058 [ 540.579460] sp : ffffffc03579b510 [ 540.579463] x29: ffffffc03579b510 x28: 0000000000235800 x27:000000000000000c [ 540.579470] x26: 0000000000235c00 x25: 0000000000000068 x24:ffffffc03579b640 [ 540.579477] x23: 0000000000000001 x22: ffffffc03579b660 x21:0000000000000000 [ 540.579483] x20: 0000000000235bff x19: ffffffdebf7e3940 x18:ffffffdebf66d140 [ 540.579489] x17: 00000000739ba063 x16: 00000000739ba063 x15:00000000009f4bff [ 540.579495] x14: 0000008000000000 x13: 0000000000000000 x12:0000000000000001 [ 540.579501] x11: 0000000000000000 x10: 0000000000000000 x9 :ffffff897d2cd440 [ 540.579507] x8 : 0000000000000000 x7 : 0000000000000000 x6 :ffffffc03579b5b4 [ 540.579512] x5 : 0000000000027f25 x4 : ffffffc03579b5b8 x3 :0000000000000001 [ 540.579518] x2 : ffffffdebf7e3940 x1 : 0000000000235c00 x0 :0000000000235800 [ 540.579524] Call trace: [ 540.579527] __pageblock_pfn_to_page+0x6c/0x14c [ 540.579533] compact_zone+0x994/0x1058 [ 540.579536] try_to_compact_pages+0x128/0x378 [ 540.579540] __alloc_pages_direct_compact+0x80/0x2b0 [ 540.579544] __alloc_pages_slowpath+0x5c0/0xe10 [ 540.579547] __alloc_pages+0x250/0x2d0 [ 540.579550] __iommu_dma_alloc_noncontiguous+0x13c/0x3fc [ 540.579561] iommu_dma_alloc+0xa0/0x320 [ 540.579565] dma_alloc_attrs+0xd4/0x108

[quic_charante@quicinc.com: use kfree_rcu() in place of synchronize_rcu(), per David] Link: https://lkml.kernel.org/r/1698403778-20938-1-git-send-email-quic_charante@qu... Link: https://lkml.kernel.org/r/1697202267-23600-1-git-send-email-quic_charante@qu... Fixes: f46edbd1b151 ("mm/sparsemem: add helpers track active portions of a section at boot") Signed-off-by: Charan Teja Kalla quic_charante@quicinc.com Cc: Aneesh Kumar K.V aneesh.kumar@linux.ibm.com Cc: Dan Williams dan.j.williams@intel.com Cc: David Hildenbrand david@redhat.com Cc: Mel Gorman mgorman@techsingularity.net Cc: Oscar Salvador osalvador@suse.de Cc: Vlastimil Babka vbabka@suse.cz Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/mmzone.h | 14 +++++++++++--- mm/sparse.c | 17 +++++++++-------- 2 files changed, 20 insertions(+), 11 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 11fa11c31fda..ffae2b330818 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1188,6 +1188,7 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec) #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK)

struct mem_section_usage { + struct rcu_head rcu; #ifdef CONFIG_SPARSEMEM_VMEMMAP DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION); #endif @@ -1353,7 +1354,7 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) { int idx = subsection_map_index(pfn);

- return test_bit(idx, ms->usage->subsection_map); + return test_bit(idx, READ_ONCE(ms->usage)->subsection_map); } #else static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) @@ -1366,17 +1367,24 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn) static inline int pfn_valid(unsigned long pfn) { struct mem_section *ms; + int ret;

if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; ms = __pfn_to_section(pfn); - if (!valid_section(ms)) + rcu_read_lock(); + if (!valid_section(ms)) { + rcu_read_unlock(); return 0; + } /* * Traditionally early sections always returned pfn_valid() for * the entire section-sized span. */ - return early_section(ms) || pfn_section_valid(ms, pfn); + ret = early_section(ms) || pfn_section_valid(ms, pfn); + rcu_read_unlock(); + + return ret; } #endif

diff --git a/mm/sparse.c b/mm/sparse.c index 33406ea2ecc4..db0a7c53775b 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -809,6 +809,13 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages, if (empty) { unsigned long section_nr = pfn_to_section_nr(pfn);

+ /* + * Mark the section invalid so that valid_section() + * return false. This prevents code from dereferencing + * ms->usage array. + */ + ms->section_mem_map &= ~SECTION_HAS_MEM_MAP; + /* * When removing an early section, the usage map is kept (as the * usage maps of other sections fall into the same page). It @@ -817,16 +824,10 @@ static void section_deactivate(unsigned long pfn, unsigned long nr_pages, * was allocated during boot. */ if (!PageReserved(virt_to_page(ms->usage))) { - kfree(ms->usage); - ms->usage = NULL; + kfree_rcu(ms->usage, rcu); + WRITE_ONCE(ms->usage, NULL); } memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr); - /* - * Mark the section invalid so that valid_section() - * return false. This prevents code from dereferencing - * ms->usage array. - */ - ms->section_mem_map &= ~SECTION_HAS_MEM_MAP; }

/*

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

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

From: Omar Sandoval osandov@fb.com

[ Upstream commit 3324d0547861b16cf436d54abba7052e0c8aa9de ]

Sweet Tea spotted a race between subvolume deletion and snapshotting that can result in the root item for the snapshot having the BTRFS_ROOT_SUBVOL_DEAD flag set. The race is:

Thread 1 | Thread 2 ----------------------------------------------|---------- btrfs_delete_subvolume | btrfs_set_root_flags(BTRFS_ROOT_SUBVOL_DEAD)| |btrfs_mksubvol | down_read(subvol_sem) | create_snapshot | ... | create_pending_snapshot | copy root item from source down_write(subvol_sem) |

This flag is only checked in send and swap activate, which this would cause to fail mysteriously.

create_snapshot() now checks the root refs to reject a deleted subvolume, so we can fix this by locking subvol_sem earlier so that the BTRFS_ROOT_SUBVOL_DEAD flag and the root refs are updated atomically.

CC: stable@vger.kernel.org # 4.14+ Reported-by: Sweet Tea Dorminy sweettea-kernel@dorminy.me Reviewed-by: Sweet Tea Dorminy sweettea-kernel@dorminy.me Reviewed-by: Anand Jain anand.jain@oracle.com Signed-off-by: Omar Sandoval osandov@fb.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/btrfs/inode.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c6b861f5bcfe..250b6064876d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4008,6 +4008,8 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) u64 root_flags; int ret;

+ down_write(&fs_info->subvol_sem); + /* * Don't allow to delete a subvolume with send in progress. This is * inside the inode lock so the error handling that has to drop the bit @@ -4019,25 +4021,25 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) btrfs_warn(fs_info, "attempt to delete subvolume %llu during send", dest->root_key.objectid); - return -EPERM; + ret = -EPERM; + goto out_up_write; } if (atomic_read(&dest->nr_swapfiles)) { spin_unlock(&dest->root_item_lock); btrfs_warn(fs_info, "attempt to delete subvolume %llu with active swapfile", root->root_key.objectid); - return -EPERM; + ret = -EPERM; + goto out_up_write; } root_flags = btrfs_root_flags(&dest->root_item); btrfs_set_root_flags(&dest->root_item, root_flags | BTRFS_ROOT_SUBVOL_DEAD); spin_unlock(&dest->root_item_lock);

- down_write(&fs_info->subvol_sem); - ret = may_destroy_subvol(dest); if (ret) - goto out_up_write; + goto out_undead;

btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP); /* @@ -4047,7 +4049,7 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) */ ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true); if (ret) - goto out_up_write; + goto out_undead;

trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { @@ -4109,15 +4111,17 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) inode->i_flags |= S_DEAD; out_release: btrfs_subvolume_release_metadata(root, &block_rsv); -out_up_write: - up_write(&fs_info->subvol_sem); +out_undead: if (ret) { spin_lock(&dest->root_item_lock); root_flags = btrfs_root_flags(&dest->root_item); btrfs_set_root_flags(&dest->root_item, root_flags & ~BTRFS_ROOT_SUBVOL_DEAD); spin_unlock(&dest->root_item_lock); - } else { + } +out_up_write: + up_write(&fs_info->subvol_sem); + if (!ret) { d_invalidate(dentry); btrfs_prune_dentries(dest); ASSERT(dest->send_in_progress == 0);

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

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

From: Chuck Lever chuck.lever@oracle.com

[ Upstream commit 043862b09cc00273e35e6c3a6389957953a34207 ]

And return explicit nfserr values that match what is documented in the new comment / API contract.

Signed-off-by: Chuck Lever chuck.lever@oracle.com Stable-dep-of: edcf9725150e ("nfsd: fix RELEASE_LOCKOWNER") Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfsd/nfs4state.c | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 1b40b2197ce6..b6480be7b5e6 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -7107,6 +7107,23 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) return status; }

+/** + * nfsd4_release_lockowner - process NFSv4.0 RELEASE_LOCKOWNER operations + * @rqstp: RPC transaction + * @cstate: NFSv4 COMPOUND state + * @u: RELEASE_LOCKOWNER arguments + * + * The lockowner's so_count is bumped when a lock record is added + * or when copying a conflicting lock. The latter case is brief, + * but can lead to fleeting false positives when looking for + * locks-in-use. + * + * Return values: + * %nfs_ok: lockowner released or not found + * %nfserr_locks_held: lockowner still in use + * %nfserr_stale_clientid: clientid no longer active + * %nfserr_expired: clientid not recognized + */ __be32 nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, @@ -7133,7 +7150,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, lo = find_lockowner_str_locked(clp, &rlockowner->rl_owner); if (!lo) { spin_unlock(&clp->cl_lock); - return status; + return nfs_ok; } if (atomic_read(&lo->lo_owner.so_count) != 2) { spin_unlock(&clp->cl_lock); @@ -7149,11 +7166,11 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp, put_ol_stateid_locked(stp, &reaplist); } spin_unlock(&clp->cl_lock); + free_ol_stateid_reaplist(&reaplist); remove_blocked_locks(lo); nfs4_put_stateowner(&lo->lo_owner); - - return status; + return nfs_ok; }

static inline struct nfs4_client_reclaim *

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

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

From: Arnd Bergmann arnd@arndb.de

[ Upstream commit 960b537e91725bcb17dd1b19e48950e62d134078 ]

gcc rightfully complains about excessive stack usage in the fimd_win_set_pixfmt() function:

drivers/gpu/drm/exynos/exynos_drm_fimd.c: In function 'fimd_win_set_pixfmt': drivers/gpu/drm/exynos/exynos_drm_fimd.c:750:1: error: the frame size of 1032 bytes is larger than 1024 byte drivers/gpu/drm/exynos/exynos5433_drm_decon.c: In function 'decon_win_set_pixfmt': drivers/gpu/drm/exynos/exynos5433_drm_decon.c:381:1: error: the frame size of 1032 bytes is larger than 1024 bytes

There is really no reason to copy the large exynos_drm_plane structure to the stack before using one of its members, so just use a pointer instead.

Fixes: 6f8ee5c21722 ("drm/exynos: fimd: Make plane alpha configurable") Signed-off-by: Arnd Bergmann arnd@arndb.de Reviewed-by: Marek Szyprowski m.szyprowski@samsung.com Signed-off-by: Inki Dae inki.dae@samsung.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/exynos/exynos5433_drm_decon.c | 4 ++-- drivers/gpu/drm/exynos/exynos_drm_fimd.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index c277d2fc50c6..e43dfea09527 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -318,9 +318,9 @@ static void decon_win_set_bldmod(struct decon_context *ctx, unsigned int win, static void decon_win_set_pixfmt(struct decon_context *ctx, unsigned int win, struct drm_framebuffer *fb) { - struct exynos_drm_plane plane = ctx->planes[win]; + struct exynos_drm_plane *plane = &ctx->planes[win]; struct exynos_drm_plane_state *state = - to_exynos_plane_state(plane.base.state); + to_exynos_plane_state(plane->base.state); unsigned int alpha = state->base.alpha; unsigned int pixel_alpha; unsigned long val; diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c index bb67cad8371f..c045330f9c48 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c @@ -637,9 +637,9 @@ static void fimd_win_set_bldmod(struct fimd_context *ctx, unsigned int win, static void fimd_win_set_pixfmt(struct fimd_context *ctx, unsigned int win, struct drm_framebuffer *fb, int width) { - struct exynos_drm_plane plane = ctx->planes[win]; + struct exynos_drm_plane *plane = &ctx->planes[win]; struct exynos_drm_plane_state *state = - to_exynos_plane_state(plane.base.state); + to_exynos_plane_state(plane->base.state); uint32_t pixel_format = fb->format->format; unsigned int alpha = state->base.alpha; u32 val = WINCONx_ENWIN;

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

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

From: Wenhua Lin Wenhua.Lin@unisoc.com

[ Upstream commit 84aef4ed59705585d629e81d633a83b7d416f5fb ]

The raw interrupt status of eic maybe set before the interrupt is enabled, since the eic interrupt has a latch function, which would trigger the interrupt event once enabled it from user side. To solve this problem, interrupts generated before setting the interrupt trigger type are ignored.

Fixes: 25518e024e3a ("gpio: Add Spreadtrum EIC driver support") Acked-by: Chunyan Zhang zhang.lyra@gmail.com Signed-off-by: Wenhua Lin Wenhua.Lin@unisoc.com Signed-off-by: Bartosz Golaszewski bartosz.golaszewski@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpio/gpio-eic-sprd.c | 32 ++++++++++++++++++++++++++++---- 1 file changed, 28 insertions(+), 4 deletions(-)

diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c index 865ab2b34fdd..3dfb8b6c6c71 100644 --- a/drivers/gpio/gpio-eic-sprd.c +++ b/drivers/gpio/gpio-eic-sprd.c @@ -318,20 +318,27 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) switch (flow_type) { case IRQ_TYPE_LEVEL_HIGH: sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 1); + sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IC, 1); break; case IRQ_TYPE_LEVEL_LOW: sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 0); + sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IC, 1); break; case IRQ_TYPE_EDGE_RISING: case IRQ_TYPE_EDGE_FALLING: case IRQ_TYPE_EDGE_BOTH: state = sprd_eic_get(chip, offset); - if (state) + if (state) { sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 0); - else + sprd_eic_update(chip, offset, + SPRD_EIC_DBNC_IC, 1); + } else { sprd_eic_update(chip, offset, SPRD_EIC_DBNC_IEV, 1); + sprd_eic_update(chip, offset, + SPRD_EIC_DBNC_IC, 1); + } break; default: return -ENOTSUPP; @@ -343,20 +350,27 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) switch (flow_type) { case IRQ_TYPE_LEVEL_HIGH: sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTCLR, 1); break; case IRQ_TYPE_LEVEL_LOW: sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTCLR, 1); break; case IRQ_TYPE_EDGE_RISING: case IRQ_TYPE_EDGE_FALLING: case IRQ_TYPE_EDGE_BOTH: state = sprd_eic_get(chip, offset); - if (state) + if (state) { sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 0); - else + sprd_eic_update(chip, offset, + SPRD_EIC_LATCH_INTCLR, 1); + } else { sprd_eic_update(chip, offset, SPRD_EIC_LATCH_INTPOL, 1); + sprd_eic_update(chip, offset, + SPRD_EIC_LATCH_INTCLR, 1); + } break; default: return -ENOTSUPP; @@ -370,29 +384,34 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_FALLING: sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_BOTH: sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 1); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_LEVEL_HIGH: sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 1); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_level_irq); break; case IRQ_TYPE_LEVEL_LOW: sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 1); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTCLR, 1); irq_set_handler_locked(data, handle_level_irq); break; default: @@ -405,29 +424,34 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_FALLING: sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_BOTH: sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 1); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_LEVEL_HIGH: sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 1); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 1); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_level_irq); break; case IRQ_TYPE_LEVEL_LOW: sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTBOTH, 0); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTMODE, 1); sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTPOL, 0); + sprd_eic_update(chip, offset, SPRD_EIC_SYNC_INTCLR, 1); irq_set_handler_locked(data, handle_level_irq); break; default:

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

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

From: Xi Ruoyao xry111@xry111.site

commit 59be5c35850171e307ca5d3d703ee9ff4096b948 upstream.

If we still own the FPU after initializing fcr31, when we are preempted the dirty value in the FPU will be read out and stored into fcr31, clobbering our setting. This can cause an improper floating-point environment after execve(). For example:

zsh% cat measure.c #include <fenv.h> int main() { return fetestexcept(FE_INEXACT); } zsh% cc measure.c -o measure -lm zsh% echo $((1.0/3)) # raising FE_INEXACT 0.33333333333333331 zsh% while ./measure; do ; done (stopped in seconds)

Call lose_fpu(0) before setting fcr31 to prevent this.

Closes: https://lore.kernel.org/linux-mips/7a6aa1bbdbbe2e63ae96ff163fab0349f58f1b9e.... Fixes: 9b26616c8d9d ("MIPS: Respect the ISA level in FCSR handling") Cc: stable@vger.kernel.org Signed-off-by: Xi Ruoyao xry111@xry111.site Signed-off-by: Thomas Bogendoerfer tsbogend@alpha.franken.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/mips/kernel/elf.c | 6 ++++++ 1 file changed, 6 insertions(+)

--- a/arch/mips/kernel/elf.c +++ b/arch/mips/kernel/elf.c @@ -11,6 +11,7 @@

#include <asm/cpu-features.h> #include <asm/cpu-info.h> +#include <asm/fpu.h>

#ifdef CONFIG_MIPS_FP_SUPPORT

@@ -309,6 +310,11 @@ void mips_set_personality_nan(struct arc struct cpuinfo_mips *c = &boot_cpu_data; struct task_struct *t = current;

+ /* Do this early so t->thread.fpu.fcr31 won't be clobbered in case + * we are preempted before the lose_fpu(0) in start_thread. + */ + lose_fpu(0); + t->thread.fpu.fcr31 = c->fpu_csr31; switch (state->nan_2008) { case 0:

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

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

From: Richard Palethorpe rpalethorpe@suse.com

commit 56062d60f117dccfb5281869e0ab61e090baf864 upstream.

Presently ia32 registers stored in ptregs are unconditionally cast to unsigned int by the ia32 stub. They are then cast to long when passed to __se_sys*, but will not be sign extended.

This takes the sign of the syscall argument into account in the ia32 stub. It still casts to unsigned int to avoid implementation specific behavior. However then casts to int or unsigned int as necessary. So that the following cast to long sign extends the value.

This fixes the io_pgetevents02 LTP test when compiled with -m32. Presently the systemcall io_pgetevents_time64() unexpectedly accepts -1 for the maximum number of events.

It doesn't appear other systemcalls with signed arguments are effected because they all have compat variants defined and wired up.

Fixes: ebeb8c82ffaf ("syscalls/x86: Use 'struct pt_regs' based syscall calling for IA32_EMULATION and x32") Suggested-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Richard Palethorpe rpalethorpe@suse.com Signed-off-by: Nikolay Borisov nik.borisov@suse.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Reviewed-by: Arnd Bergmann arnd@arndb.de Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240110130122.3836513-1-nik.borisov@suse.com Link: https://lore.kernel.org/ltp/20210921130127.24131-1-rpalethorpe@suse.com/ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/syscall_wrapper.h | 25 +++++++++++++++++++++---- include/linux/syscalls.h | 1 + 2 files changed, 22 insertions(+), 4 deletions(-)

--- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -58,12 +58,29 @@ extern long __ia32_sys_ni_syscall(const ,,regs->di,,regs->si,,regs->dx \ ,,regs->r10,,regs->r8,,regs->r9) \

+ +/* SYSCALL_PT_ARGS is Adapted from s390x */ +#define SYSCALL_PT_ARG6(m, t1, t2, t3, t4, t5, t6) \ + SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5), m(t6, (regs->bp)) +#define SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5) \ + SYSCALL_PT_ARG4(m, t1, t2, t3, t4), m(t5, (regs->di)) +#define SYSCALL_PT_ARG4(m, t1, t2, t3, t4) \ + SYSCALL_PT_ARG3(m, t1, t2, t3), m(t4, (regs->si)) +#define SYSCALL_PT_ARG3(m, t1, t2, t3) \ + SYSCALL_PT_ARG2(m, t1, t2), m(t3, (regs->dx)) +#define SYSCALL_PT_ARG2(m, t1, t2) \ + SYSCALL_PT_ARG1(m, t1), m(t2, (regs->cx)) +#define SYSCALL_PT_ARG1(m, t1) m(t1, (regs->bx)) +#define SYSCALL_PT_ARGS(x, ...) SYSCALL_PT_ARG##x(__VA_ARGS__) + +#define __SC_COMPAT_CAST(t, a) \ + (__typeof(__builtin_choose_expr(__TYPE_IS_L(t), 0, 0U))) \ + (unsigned int)a + /* Mapping of registers to parameters for syscalls on i386 */ #define SC_IA32_REGS_TO_ARGS(x, ...) \ - __MAP(x,__SC_ARGS \ - ,,(unsigned int)regs->bx,,(unsigned int)regs->cx \ - ,,(unsigned int)regs->dx,,(unsigned int)regs->si \ - ,,(unsigned int)regs->di,,(unsigned int)regs->bp) + SYSCALL_PT_ARGS(x, __SC_COMPAT_CAST, \ + __MAP(x, __SC_TYPE, __VA_ARGS__)) \

#define __SYS_STUB0(abi, name) \ long __##abi##_##name(const struct pt_regs *regs); \ --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -119,6 +119,7 @@ struct open_how; #define __TYPE_IS_LL(t) (__TYPE_AS(t, 0LL) || __TYPE_AS(t, 0ULL)) #define __SC_LONG(t, a) __typeof(__builtin_choose_expr(__TYPE_IS_LL(t), 0LL, 0L)) a #define __SC_CAST(t, a) (__force t) a +#define __SC_TYPE(t, a) t #define __SC_ARGS(t, a) a #define __SC_TEST(t, a) (void)BUILD_BUG_ON_ZERO(!__TYPE_IS_LL(t) && sizeof(t) > sizeof(long))

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

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

From: Mark Rutland mark.rutland@arm.com

[ Upstream commit ca6f537e459e2da4b331fe8928d1a0b0f9301f42 ]

The SW_INCR event is somewhat unusual, and depends on the specific HW counter that it is programmed into. When programmed into PMEVCNTR<n>, SW_INCR will count any writes to PMSWINC_EL0 with bit n set, ignoring writes to SW_INCR with bit n clear.

Event rotation means that there's no fixed relationship between perf_events and HW counters, so this isn't all that useful.

Further, we program PMUSERENR.{SW,EN}=={0,0}, which causes EL0 writes to PMSWINC_EL0 to be trapped and handled as UNDEFINED, resulting in a SIGILL to userspace.

Given that, it's not a good idea to expose SW_INCR in sysfs. Hide it as we did for CHAIN back in commit:

4ba2578fa7b55701 ("arm64: perf: don't expose CHAIN event in sysfs")

Signed-off-by: Mark Rutland mark.rutland@arm.com Cc: Will Deacon will@kernel.org Link: https://lore.kernel.org/r/20231204115847.2993026-1-mark.rutland@arm.com Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm64/kernel/perf_event.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c index cdb3d4549b3a..8e428f8dd108 100644 --- a/arch/arm64/kernel/perf_event.c +++ b/arch/arm64/kernel/perf_event.c @@ -171,7 +171,11 @@ armv8pmu_events_sysfs_show(struct device *dev, }).attr.attr)

static struct attribute *armv8_pmuv3_event_attrs[] = { - ARMV8_EVENT_ATTR(sw_incr, ARMV8_PMUV3_PERFCTR_SW_INCR), + /* + * Don't expose the sw_incr event in /sys. It's not usable as writes to + * PMSWINC_EL0 will trap as PMUSERENR.{SW,EN}=={0,0} and event rotation + * means we don't have a fixed event<->counter relationship regardless. + */ ARMV8_EVENT_ATTR(l1i_cache_refill, ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL), ARMV8_EVENT_ATTR(l1i_tlb_refill, ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL), ARMV8_EVENT_ATTR(l1d_cache_refill, ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL),

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

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

From: Michael Ellerman mpe@ellerman.id.au

[ Upstream commit d8c3f243d4db24675b653f0568bb65dae34e6455 ]

With NUMA=n and FA_DUMP=y or PRESERVE_FA_DUMP=y the build fails with:

arch/powerpc/kernel/fadump.c:1739:22: error: no previous prototype for ‘arch_reserved_kernel_pages’ [-Werror=missing-prototypes] 1739 | unsigned long __init arch_reserved_kernel_pages(void) | ^~~~~~~~~~~~~~~~~~~~~~~~~~

The prototype for arch_reserved_kernel_pages() is in include/linux/mm.h, but it's guarded by __HAVE_ARCH_RESERVED_KERNEL_PAGES. The powerpc headers define __HAVE_ARCH_RESERVED_KERNEL_PAGES in asm/mmzone.h, which is not included into the generic headers when NUMA=n.

Move the definition of __HAVE_ARCH_RESERVED_KERNEL_PAGES into asm/mmu.h which is included regardless of NUMA=n.

Additionally the ifdef around __HAVE_ARCH_RESERVED_KERNEL_PAGES needs to also check for CONFIG_PRESERVE_FA_DUMP.

Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://msgid.link/20231130114433.3053544-1-mpe@ellerman.id.au Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/include/asm/mmu.h | 4 ++++ arch/powerpc/include/asm/mmzone.h | 3 --- 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/mmu.h b/arch/powerpc/include/asm/mmu.h index 255a1837e9f7..3a5a27318a0e 100644 --- a/arch/powerpc/include/asm/mmu.h +++ b/arch/powerpc/include/asm/mmu.h @@ -390,5 +390,9 @@ extern void *abatron_pteptrs[2]; #include <asm/nohash/mmu.h> #endif

+#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP) +#define __HAVE_ARCH_RESERVED_KERNEL_PAGES +#endif + #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_MMU_H_ */ diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h index 6cda76b57c5d..bd1a8d7256ff 100644 --- a/arch/powerpc/include/asm/mmzone.h +++ b/arch/powerpc/include/asm/mmzone.h @@ -42,9 +42,6 @@ u64 memory_hotplug_max(void); #else #define memory_hotplug_max() memblock_end_of_DRAM() #endif /* CONFIG_NEED_MULTIPLE_NODES */ -#ifdef CONFIG_FA_DUMP -#define __HAVE_ARCH_RESERVED_KERNEL_PAGES -#endif

#ifdef CONFIG_MEMORY_HOTPLUG extern int create_section_mapping(unsigned long start, unsigned long end,

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

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

From: Stephen Rothwell sfr@canb.auug.org.au

[ Upstream commit 0d555b57ee660d8a871781c0eebf006e855e918d ]

The linux-next build of powerpc64 allnoconfig fails with:

arch/powerpc/mm/book3s64/pgtable.c:557:5: error: no previous prototype for 'pmd_move_must_withdraw' 557 | int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, | ^~~~~~~~~~~~~~~~~~~~~~

Caused by commit:

c6345dfa6e3e ("Makefile.extrawarn: turn on missing-prototypes globally")

Fix it by moving the function definition under CONFIG_TRANSPARENT_HUGEPAGE like the prototype. The function is only called when CONFIG_TRANSPARENT_HUGEPAGE=y.

Signed-off-by: Stephen Rothwell sfr@canb.auug.org.au [mpe: Flesh out change log from linux-next patch] Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://msgid.link/20231127132809.45c2b398@canb.auug.org.au Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/mm/book3s64/pgtable.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c index e18ae50a275c..a86d932a7c30 100644 --- a/arch/powerpc/mm/book3s64/pgtable.c +++ b/arch/powerpc/mm/book3s64/pgtable.c @@ -446,6 +446,7 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, set_pte_at(vma->vm_mm, addr, ptep, pte); }

+#ifdef CONFIG_TRANSPARENT_HUGEPAGE /* * For hash translation mode, we use the deposited table to store hash slot * information and they are stored at PTRS_PER_PMD offset from related pmd @@ -467,6 +468,7 @@ int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,

return true; } +#endif

/* * Does the CPU support tlbie?

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

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

From: Zhiquan Li zhiquan1.li@intel.com

[ Upstream commit 9f3b130048bfa2e44a8cfb1b616f826d9d5d8188 ]

Memory errors don't happen very often, especially fatal ones. However, in large-scale scenarios such as data centers, that probability increases with the amount of machines present.

When a fatal machine check happens, mce_panic() is called based on the severity grading of that error. The page containing the error is not marked as poison.

However, when kexec is enabled, tools like makedumpfile understand when pages are marked as poison and do not touch them so as not to cause a fatal machine check exception again while dumping the previous kernel's memory.

Therefore, mark the page containing the error as poisoned so that the kexec'ed kernel can avoid accessing the page.

[ bp: Rewrite commit message and comment. ]

Co-developed-by: Youquan Song youquan.song@intel.com Signed-off-by: Youquan Song youquan.song@intel.com Signed-off-by: Zhiquan Li zhiquan1.li@intel.com Signed-off-by: Borislav Petkov (AMD) bp@alien8.de Reviewed-by: Naoya Horiguchi naoya.horiguchi@nec.com Link: https://lore.kernel.org/r/20231014051754.3759099-1-zhiquan1.li@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/kernel/cpu/mce/core.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 0b7c81389c50..18a6ed2afca0 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -44,6 +44,7 @@ #include <linux/sync_core.h> #include <linux/task_work.h> #include <linux/hardirq.h> +#include <linux/kexec.h>

#include <asm/intel-family.h> #include <asm/processor.h> @@ -274,6 +275,7 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) struct llist_node *pending; struct mce_evt_llist *l; int apei_err = 0; + struct page *p;

/* * Allow instrumentation around external facilities usage. Not that it @@ -329,6 +331,20 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) if (!fake_panic) { if (panic_timeout == 0) panic_timeout = mca_cfg.panic_timeout; + + /* + * Kdump skips the poisoned page in order to avoid + * touching the error bits again. Poison the page even + * if the error is fatal and the machine is about to + * panic. + */ + if (kexec_crash_loaded()) { + if (final && (final->status & MCI_STATUS_ADDRV)) { + p = pfn_to_online_page(final->addr >> PAGE_SHIFT); + if (p) + SetPageHWPoison(p); + } + } panic(msg); } else pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg);

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

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

From: Andrzej Hajda andrzej.hajda@intel.com

[ Upstream commit 9bb6362652f3f4d74a87d572a91ee1b38e673ef6 ]

After release of the hashbucket lock the tracking object can be modified or freed by a concurrent thread. Using it in such a case is error prone, even for printing the object state:

1. T1 tries to deactivate destroyed object, debugobjects detects it, hash bucket lock is released.

2. T2 preempts T1 and frees the tracking object.

3. The freed tracking object is allocated and initialized for a different to be tracked kernel object.

4. T1 resumes and reports error for wrong kernel object.

Create a local copy of the tracking object before releasing the hash bucket lock and use the local copy for reporting and fixups to prevent this.

Signed-off-by: Andrzej Hajda andrzej.hajda@intel.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Link: https://lore.kernel.org/r/20231025-debugobjects_fix-v3-1-2bc3bf7084c2@intel.... Signed-off-by: Sasha Levin sashal@kernel.org --- lib/debugobjects.c | 200 ++++++++++++++++++--------------------------- 1 file changed, 78 insertions(+), 122 deletions(-)

diff --git a/lib/debugobjects.c b/lib/debugobjects.c index 4dd9283f6fea..b055741a5a4d 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -612,9 +612,8 @@ static void debug_objects_fill_pool(void) static void __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack) { - enum debug_obj_state state; + struct debug_obj *obj, o; struct debug_bucket *db; - struct debug_obj *obj; unsigned long flags;

debug_objects_fill_pool(); @@ -635,24 +634,18 @@ __debug_object_init(void *addr, const struct debug_obj_descr *descr, int onstack case ODEBUG_STATE_INIT: case ODEBUG_STATE_INACTIVE: obj->state = ODEBUG_STATE_INIT; - break; - - case ODEBUG_STATE_ACTIVE: - state = obj->state; - raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "init"); - debug_object_fixup(descr->fixup_init, addr, state); - return; - - case ODEBUG_STATE_DESTROYED: raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "init"); return; default: break; }

+ o = *obj; raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(&o, "init"); + + if (o.state == ODEBUG_STATE_ACTIVE) + debug_object_fixup(descr->fixup_init, addr, o.state); }

/** @@ -693,11 +686,9 @@ EXPORT_SYMBOL_GPL(debug_object_init_on_stack); int debug_object_activate(void *addr, const struct debug_obj_descr *descr) { struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr }; - enum debug_obj_state state; struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; - int ret;

if (!debug_objects_enabled) return 0; @@ -709,49 +700,38 @@ int debug_object_activate(void *addr, const struct debug_obj_descr *descr) raw_spin_lock_irqsave(&db->lock, flags);

obj = lookup_object_or_alloc(addr, db, descr, false, true); - if (likely(!IS_ERR_OR_NULL(obj))) { - bool print_object = false; - + if (unlikely(!obj)) { + raw_spin_unlock_irqrestore(&db->lock, flags); + debug_objects_oom(); + return 0; + } else if (likely(!IS_ERR(obj))) { switch (obj->state) { - case ODEBUG_STATE_INIT: - case ODEBUG_STATE_INACTIVE: - obj->state = ODEBUG_STATE_ACTIVE; - ret = 0; - break; - case ODEBUG_STATE_ACTIVE: - state = obj->state; - raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "activate"); - ret = debug_object_fixup(descr->fixup_activate, addr, state); - return ret ? 0 : -EINVAL; - case ODEBUG_STATE_DESTROYED: - print_object = true; - ret = -EINVAL; + o = *obj; break; + case ODEBUG_STATE_INIT: + case ODEBUG_STATE_INACTIVE: + obj->state = ODEBUG_STATE_ACTIVE; + fallthrough; default: - ret = 0; - break; + raw_spin_unlock_irqrestore(&db->lock, flags); + return 0; } - raw_spin_unlock_irqrestore(&db->lock, flags); - if (print_object) - debug_print_object(obj, "activate"); - return ret; }

raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(&o, "activate");

- /* If NULL the allocation has hit OOM */ - if (!obj) { - debug_objects_oom(); - return 0; + switch (o.state) { + case ODEBUG_STATE_ACTIVE: + case ODEBUG_STATE_NOTAVAILABLE: + if (debug_object_fixup(descr->fixup_activate, addr, o.state)) + return 0; + fallthrough; + default: + return -EINVAL; } - - /* Object is neither static nor tracked. It's not initialized */ - debug_print_object(&o, "activate"); - ret = debug_object_fixup(descr->fixup_activate, addr, ODEBUG_STATE_NOTAVAILABLE); - return ret ? 0 : -EINVAL; } EXPORT_SYMBOL_GPL(debug_object_activate);

@@ -762,10 +742,10 @@ EXPORT_SYMBOL_GPL(debug_object_activate); */ void debug_object_deactivate(void *addr, const struct debug_obj_descr *descr) { + struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr }; struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; - bool print_object = false;

if (!debug_objects_enabled) return; @@ -777,33 +757,24 @@ void debug_object_deactivate(void *addr, const struct debug_obj_descr *descr) obj = lookup_object(addr, db); if (obj) { switch (obj->state) { + case ODEBUG_STATE_DESTROYED: + break; case ODEBUG_STATE_INIT: case ODEBUG_STATE_INACTIVE: case ODEBUG_STATE_ACTIVE: - if (!obj->astate) - obj->state = ODEBUG_STATE_INACTIVE; - else - print_object = true; - break; - - case ODEBUG_STATE_DESTROYED: - print_object = true; - break; + if (obj->astate) + break; + obj->state = ODEBUG_STATE_INACTIVE; + fallthrough; default: - break; + raw_spin_unlock_irqrestore(&db->lock, flags); + return; } + o = *obj; }

raw_spin_unlock_irqrestore(&db->lock, flags); - if (!obj) { - struct debug_obj o = { .object = addr, - .state = ODEBUG_STATE_NOTAVAILABLE, - .descr = descr }; - - debug_print_object(&o, "deactivate"); - } else if (print_object) { - debug_print_object(obj, "deactivate"); - } + debug_print_object(&o, "deactivate"); } EXPORT_SYMBOL_GPL(debug_object_deactivate);

@@ -814,11 +785,9 @@ EXPORT_SYMBOL_GPL(debug_object_deactivate); */ void debug_object_destroy(void *addr, const struct debug_obj_descr *descr) { - enum debug_obj_state state; + struct debug_obj *obj, o; struct debug_bucket *db; - struct debug_obj *obj; unsigned long flags; - bool print_object = false;

if (!debug_objects_enabled) return; @@ -828,32 +797,31 @@ void debug_object_destroy(void *addr, const struct debug_obj_descr *descr) raw_spin_lock_irqsave(&db->lock, flags);

obj = lookup_object(addr, db); - if (!obj) - goto out_unlock; + if (!obj) { + raw_spin_unlock_irqrestore(&db->lock, flags); + return; + }

switch (obj->state) { + case ODEBUG_STATE_ACTIVE: + case ODEBUG_STATE_DESTROYED: + break; case ODEBUG_STATE_NONE: case ODEBUG_STATE_INIT: case ODEBUG_STATE_INACTIVE: obj->state = ODEBUG_STATE_DESTROYED; - break; - case ODEBUG_STATE_ACTIVE: - state = obj->state; + fallthrough; + default: raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "destroy"); - debug_object_fixup(descr->fixup_destroy, addr, state); return; - - case ODEBUG_STATE_DESTROYED: - print_object = true; - break; - default: - break; } -out_unlock: + + o = *obj; raw_spin_unlock_irqrestore(&db->lock, flags); - if (print_object) - debug_print_object(obj, "destroy"); + debug_print_object(&o, "destroy"); + + if (o.state == ODEBUG_STATE_ACTIVE) + debug_object_fixup(descr->fixup_destroy, addr, o.state); } EXPORT_SYMBOL_GPL(debug_object_destroy);

@@ -864,9 +832,8 @@ EXPORT_SYMBOL_GPL(debug_object_destroy); */ void debug_object_free(void *addr, const struct debug_obj_descr *descr) { - enum debug_obj_state state; + struct debug_obj *obj, o; struct debug_bucket *db; - struct debug_obj *obj; unsigned long flags;

if (!debug_objects_enabled) @@ -877,24 +844,26 @@ void debug_object_free(void *addr, const struct debug_obj_descr *descr) raw_spin_lock_irqsave(&db->lock, flags);

obj = lookup_object(addr, db); - if (!obj) - goto out_unlock; + if (!obj) { + raw_spin_unlock_irqrestore(&db->lock, flags); + return; + }

switch (obj->state) { case ODEBUG_STATE_ACTIVE: - state = obj->state; - raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "free"); - debug_object_fixup(descr->fixup_free, addr, state); - return; + break; default: hlist_del(&obj->node); raw_spin_unlock_irqrestore(&db->lock, flags); free_object(obj); return; } -out_unlock: + + o = *obj; raw_spin_unlock_irqrestore(&db->lock, flags); + debug_print_object(&o, "free"); + + debug_object_fixup(descr->fixup_free, addr, o.state); } EXPORT_SYMBOL_GPL(debug_object_free);

@@ -946,10 +915,10 @@ void debug_object_active_state(void *addr, const struct debug_obj_descr *descr, unsigned int expect, unsigned int next) { + struct debug_obj o = { .object = addr, .state = ODEBUG_STATE_NOTAVAILABLE, .descr = descr }; struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; - bool print_object = false;

if (!debug_objects_enabled) return; @@ -962,28 +931,19 @@ debug_object_active_state(void *addr, const struct debug_obj_descr *descr, if (obj) { switch (obj->state) { case ODEBUG_STATE_ACTIVE: - if (obj->astate == expect) - obj->astate = next; - else - print_object = true; - break; - + if (obj->astate != expect) + break; + obj->astate = next; + raw_spin_unlock_irqrestore(&db->lock, flags); + return; default: - print_object = true; break; } + o = *obj; }

raw_spin_unlock_irqrestore(&db->lock, flags); - if (!obj) { - struct debug_obj o = { .object = addr, - .state = ODEBUG_STATE_NOTAVAILABLE, - .descr = descr }; - - debug_print_object(&o, "active_state"); - } else if (print_object) { - debug_print_object(obj, "active_state"); - } + debug_print_object(&o, "active_state"); } EXPORT_SYMBOL_GPL(debug_object_active_state);

@@ -991,12 +951,10 @@ EXPORT_SYMBOL_GPL(debug_object_active_state); static void __debug_check_no_obj_freed(const void *address, unsigned long size) { unsigned long flags, oaddr, saddr, eaddr, paddr, chunks; - const struct debug_obj_descr *descr; - enum debug_obj_state state; + int cnt, objs_checked = 0; + struct debug_obj *obj, o; struct debug_bucket *db; struct hlist_node *tmp; - struct debug_obj *obj; - int cnt, objs_checked = 0;

saddr = (unsigned long) address; eaddr = saddr + size; @@ -1018,12 +976,10 @@ static void __debug_check_no_obj_freed(const void *address, unsigned long size)

switch (obj->state) { case ODEBUG_STATE_ACTIVE: - descr = obj->descr; - state = obj->state; + o = *obj; raw_spin_unlock_irqrestore(&db->lock, flags); - debug_print_object(obj, "free"); - debug_object_fixup(descr->fixup_free, - (void *) oaddr, state); + debug_print_object(&o, "free"); + debug_object_fixup(o.descr->fixup_free, (void *)oaddr, o.state); goto repeat; default: hlist_del(&obj->node);

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

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

From: Chris Riches chris.riches@nutanix.com

[ Upstream commit 022732e3d846e197539712e51ecada90ded0572a ]

When auditd_set sets the auditd_conn pointer, audit messages can immediately be put on the socket by other kernel threads. If the backlog is large or the rate is high, this can immediately fill the socket buffer. If the audit daemon requested an ACK for this operation, a full socket buffer causes the ACK to get dropped, also setting ENOBUFS on the socket.

To avoid this race and ensure ACKs get through, fast-track the ACK in this specific case to ensure it is sent before auditd_conn is set.

Signed-off-by: Chris Riches chris.riches@nutanix.com [PM: fix some tab vs space damage] Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/audit.c | 31 ++++++++++++++++++++++++------- 1 file changed, 24 insertions(+), 7 deletions(-)

diff --git a/kernel/audit.c b/kernel/audit.c index aeec86ed4708..2ab04e0a7441 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -490,15 +490,19 @@ static void auditd_conn_free(struct rcu_head *rcu) * @pid: auditd PID * @portid: auditd netlink portid * @net: auditd network namespace pointer + * @skb: the netlink command from the audit daemon + * @ack: netlink ack flag, cleared if ack'd here * * Description: * This function will obtain and drop network namespace references as * necessary. Returns zero on success, negative values on failure. */ -static int auditd_set(struct pid *pid, u32 portid, struct net *net) +static int auditd_set(struct pid *pid, u32 portid, struct net *net, + struct sk_buff *skb, bool *ack) { unsigned long flags; struct auditd_connection *ac_old, *ac_new; + struct nlmsghdr *nlh;

if (!pid || !net) return -EINVAL; @@ -510,6 +514,13 @@ static int auditd_set(struct pid *pid, u32 portid, struct net *net) ac_new->portid = portid; ac_new->net = get_net(net);

+ /* send the ack now to avoid a race with the queue backlog */ + if (*ack) { + nlh = nlmsg_hdr(skb); + netlink_ack(skb, nlh, 0, NULL); + *ack = false; + } + spin_lock_irqsave(&auditd_conn_lock, flags); ac_old = rcu_dereference_protected(auditd_conn, lockdep_is_held(&auditd_conn_lock)); @@ -1203,7 +1214,8 @@ static int audit_replace(struct pid *pid) return auditd_send_unicast_skb(skb); }

-static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) +static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, + bool *ack) { u32 seq; void *data; @@ -1296,7 +1308,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) /* register a new auditd connection */ err = auditd_set(req_pid, NETLINK_CB(skb).portid, - sock_net(NETLINK_CB(skb).sk)); + sock_net(NETLINK_CB(skb).sk), + skb, ack); if (audit_enabled != AUDIT_OFF) audit_log_config_change("audit_pid", new_pid, @@ -1541,9 +1554,10 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) * Parse the provided skb and deal with any messages that may be present, * malformed skbs are discarded. */ -static void audit_receive(struct sk_buff *skb) +static void audit_receive(struct sk_buff *skb) { struct nlmsghdr *nlh; + bool ack; /* * len MUST be signed for nlmsg_next to be able to dec it below 0 * if the nlmsg_len was not aligned @@ -1556,9 +1570,12 @@ static void audit_receive(struct sk_buff *skb)

audit_ctl_lock(); while (nlmsg_ok(nlh, len)) { - err = audit_receive_msg(skb, nlh); - /* if err or if this message says it wants a response */ - if (err || (nlh->nlmsg_flags & NLM_F_ACK)) + ack = nlh->nlmsg_flags & NLM_F_ACK; + err = audit_receive_msg(skb, nlh, &ack); + + /* send an ack if the user asked for one and audit_receive_msg + * didn't already do it, or if there was an error. */ + if (ack || err) netlink_ack(skb, nlh, err, NULL);

nlh = nlmsg_next(nlh, &len);

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

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

From: Dmitry Antipov dmantipov@yandex.ru

[ Upstream commit ba3f5058db437d919f8468db50483dd9028ff688 ]

When compiling with gcc version 14.0.0 20231126 (experimental) and CONFIG_FORTIFY_SOURCE=y, I've noticed the following:

In file included from ./include/linux/string.h:295, from ./include/linux/bitmap.h:12, from ./include/linux/cpumask.h:12, from ./arch/x86/include/asm/paravirt.h:17, from ./arch/x86/include/asm/cpuid.h:62, from ./arch/x86/include/asm/processor.h:19, from ./arch/x86/include/asm/cpufeature.h:5, from ./arch/x86/include/asm/thread_info.h:53, from ./include/linux/thread_info.h:60, from ./arch/x86/include/asm/preempt.h:9, from ./include/linux/preempt.h:79, from ./include/linux/spinlock.h:56, from ./include/linux/mmzone.h:8, from ./include/linux/gfp.h:7, from ./include/linux/slab.h:16, from ./include/linux/resource_ext.h:11, from ./include/linux/acpi.h:13, from drivers/pnp/pnpacpi/rsparser.c:11: In function 'fortify_memcpy_chk', inlined from 'pnpacpi_parse_allocated_vendor' at drivers/pnp/pnpacpi/rsparser.c:158:3, inlined from 'pnpacpi_allocated_resource' at drivers/pnp/pnpacpi/rsparser.c:249:3: ./include/linux/fortify-string.h:588:25: warning: call to '__read_overflow2_field' declared with attribute warning: detected read beyond size of field (2nd parameter); maybe use struct_group()? [-Wattribute-warning] 588 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

According to the comments in include/linux/fortify-string.h, 'memcpy()', 'memmove()' and 'memset()' must not be used beyond individual struct members to ensure that the compiler can enforce protection against buffer overflows, and, IIUC, this also applies to partial copies from the particular member ('vendor->byte_data' in this case). So it should be better (and safer) to do both copies at once (and 'byte_data' of 'struct acpi_resource_vendor_typed' seems to be a good candidate for '__counted_by(byte_length)' as well).

Signed-off-by: Dmitry Antipov dmantipov@yandex.ru Reviewed-by: Kees Cook keescook@chromium.org Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/pnp/pnpacpi/rsparser.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/pnp/pnpacpi/rsparser.c b/drivers/pnp/pnpacpi/rsparser.c index da78dc77aed3..9879deb4dc0b 100644 --- a/drivers/pnp/pnpacpi/rsparser.c +++ b/drivers/pnp/pnpacpi/rsparser.c @@ -151,13 +151,13 @@ static int vendor_resource_matches(struct pnp_dev *dev, static void pnpacpi_parse_allocated_vendor(struct pnp_dev *dev, struct acpi_resource_vendor_typed *vendor) { - if (vendor_resource_matches(dev, vendor, &hp_ccsr_uuid, 16)) { - u64 start, length; + struct { u64 start, length; } range;

- memcpy(&start, vendor->byte_data, sizeof(start)); - memcpy(&length, vendor->byte_data + 8, sizeof(length)); - - pnp_add_mem_resource(dev, start, start + length - 1, 0); + if (vendor_resource_matches(dev, vendor, &hp_ccsr_uuid, + sizeof(range))) { + memcpy(&range, vendor->byte_data, sizeof(range)); + pnp_add_mem_resource(dev, range.start, range.start + + range.length - 1, 0); } }

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

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

From: Mukesh Ojha quic_mojha@quicinc.com

[ Upstream commit aed5ed595960c6d301dcd4ed31aeaa7a8054c0c6 ]

There is a chance if a frequent switch of the governor done in a loop result in timer list corruption where timer cancel being done from two place one from cancel_delayed_work_sync() and followed by expire_timers() can be seen from the traces[1].

while true do echo "simple_ondemand" > /sys/class/devfreq/1d84000.ufshc/governor echo "performance" > /sys/class/devfreq/1d84000.ufshc/governor done

It looks to be issue with devfreq driver where device_monitor_[start/stop] need to synchronized so that delayed work should get corrupted while it is either being queued or running or being cancelled.

Let's use polling flag and devfreq lock to synchronize the queueing the timer instance twice and work data being corrupted.

[1] ... .. <idle>-0 [003] 9436.209662: timer_cancel timer=0xffffff80444f0428 <idle>-0 [003] 9436.209664: timer_expire_entry timer=0xffffff80444f0428 now=0x10022da1c function=__typeid__ZTSFvP10timer_listE_global_addr baseclk=0x10022da1c <idle>-0 [003] 9436.209718: timer_expire_exit timer=0xffffff80444f0428 kworker/u16:6-14217 [003] 9436.209863: timer_start timer=0xffffff80444f0428 function=__typeid__ZTSFvP10timer_listE_global_addr expires=0x10022da2b now=0x10022da1c flags=182452227 vendor.xxxyyy.ha-1593 [004] 9436.209888: timer_cancel timer=0xffffff80444f0428 vendor.xxxyyy.ha-1593 [004] 9436.216390: timer_init timer=0xffffff80444f0428 vendor.xxxyyy.ha-1593 [004] 9436.216392: timer_start timer=0xffffff80444f0428 function=__typeid__ZTSFvP10timer_listE_global_addr expires=0x10022da2c now=0x10022da1d flags=186646532 vendor.xxxyyy.ha-1593 [005] 9436.220992: timer_cancel timer=0xffffff80444f0428 xxxyyyTraceManag-7795 [004] 9436.261641: timer_cancel timer=0xffffff80444f0428

[2]

9436.261653][ C4] Unable to handle kernel paging request at virtual address dead00000000012a [ 9436.261664][ C4] Mem abort info: [ 9436.261666][ C4] ESR = 0x96000044 [ 9436.261669][ C4] EC = 0x25: DABT (current EL), IL = 32 bits [ 9436.261671][ C4] SET = 0, FnV = 0 [ 9436.261673][ C4] EA = 0, S1PTW = 0 [ 9436.261675][ C4] Data abort info: [ 9436.261677][ C4] ISV = 0, ISS = 0x00000044 [ 9436.261680][ C4] CM = 0, WnR = 1 [ 9436.261682][ C4] [dead00000000012a] address between user and kernel address ranges [ 9436.261685][ C4] Internal error: Oops: 96000044 [#1] PREEMPT SMP [ 9436.261701][ C4] Skip md ftrace buffer dump for: 0x3a982d0 ...

[ 9436.262138][ C4] CPU: 4 PID: 7795 Comm: TraceManag Tainted: G S W O 5.10.149-android12-9-o-g17f915d29d0c #1 [ 9436.262141][ C4] Hardware name: Qualcomm Technologies, Inc. (DT) [ 9436.262144][ C4] pstate: 22400085 (nzCv daIf +PAN -UAO +TCO BTYPE=--) [ 9436.262161][ C4] pc : expire_timers+0x9c/0x438 [ 9436.262164][ C4] lr : expire_timers+0x2a4/0x438 [ 9436.262168][ C4] sp : ffffffc010023dd0 [ 9436.262171][ C4] x29: ffffffc010023df0 x28: ffffffd0636fdc18 [ 9436.262178][ C4] x27: ffffffd063569dd0 x26: ffffffd063536008 [ 9436.262182][ C4] x25: 0000000000000001 x24: ffffff88f7c69280 [ 9436.262185][ C4] x23: 00000000000000e0 x22: dead000000000122 [ 9436.262188][ C4] x21: 000000010022da29 x20: ffffff8af72b4e80 [ 9436.262191][ C4] x19: ffffffc010023e50 x18: ffffffc010025038 [ 9436.262195][ C4] x17: 0000000000000240 x16: 0000000000000201 [ 9436.262199][ C4] x15: ffffffffffffffff x14: ffffff889f3c3100 [ 9436.262203][ C4] x13: ffffff889f3c3100 x12: 00000000049f56b8 [ 9436.262207][ C4] x11: 00000000049f56b8 x10: 00000000ffffffff [ 9436.262212][ C4] x9 : ffffffc010023e50 x8 : dead000000000122 [ 9436.262216][ C4] x7 : ffffffffffffffff x6 : ffffffc0100239d8 [ 9436.262220][ C4] x5 : 0000000000000000 x4 : 0000000000000101 [ 9436.262223][ C4] x3 : 0000000000000080 x2 : ffffff889edc155c [ 9436.262227][ C4] x1 : ffffff8001005200 x0 : ffffff80444f0428 [ 9436.262232][ C4] Call trace: [ 9436.262236][ C4] expire_timers+0x9c/0x438 [ 9436.262240][ C4] __run_timers+0x1f0/0x330 [ 9436.262245][ C4] run_timer_softirq+0x28/0x58 [ 9436.262255][ C4] efi_header_end+0x168/0x5ec [ 9436.262265][ C4] __irq_exit_rcu+0x108/0x124 [ 9436.262274][ C4] __handle_domain_irq+0x118/0x1e4 [ 9436.262282][ C4] gic_handle_irq.30369+0x6c/0x2bc [ 9436.262286][ C4] el0_irq_naked+0x60/0x6c

Link: https://lore.kernel.org/all/1700860318-4025-1-git-send-email-quic_mojha@quic... Reported-by: Joyyoung Huang huangzaiyang@oppo.com Acked-by: MyungJoo Ham myungjoo.ham@samsung.com Signed-off-by: Mukesh Ojha quic_mojha@quicinc.com Signed-off-by: Chanwoo Choi cw00.choi@samsung.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/devfreq/devfreq.c | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-)

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c index 42c1eed44529..216594b86119 100644 --- a/drivers/devfreq/devfreq.c +++ b/drivers/devfreq/devfreq.c @@ -438,10 +438,14 @@ static void devfreq_monitor(struct work_struct *work) if (err) dev_err(&devfreq->dev, "dvfs failed with (%d) error\n", err);

+ if (devfreq->stop_polling) + goto out; + queue_delayed_work(devfreq_wq, &devfreq->work, msecs_to_jiffies(devfreq->profile->polling_ms)); - mutex_unlock(&devfreq->lock);

+out: + mutex_unlock(&devfreq->lock); trace_devfreq_monitor(devfreq); }

@@ -459,6 +463,10 @@ void devfreq_monitor_start(struct devfreq *devfreq) if (devfreq->governor->interrupt_driven) return;

+ mutex_lock(&devfreq->lock); + if (delayed_work_pending(&devfreq->work)) + goto out; + switch (devfreq->profile->timer) { case DEVFREQ_TIMER_DEFERRABLE: INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor); @@ -467,12 +475,16 @@ void devfreq_monitor_start(struct devfreq *devfreq) INIT_DELAYED_WORK(&devfreq->work, devfreq_monitor); break; default: - return; + goto out; }

if (devfreq->profile->polling_ms) queue_delayed_work(devfreq_wq, &devfreq->work, msecs_to_jiffies(devfreq->profile->polling_ms)); + +out: + devfreq->stop_polling = false; + mutex_unlock(&devfreq->lock); } EXPORT_SYMBOL(devfreq_monitor_start);

@@ -489,6 +501,14 @@ void devfreq_monitor_stop(struct devfreq *devfreq) if (devfreq->governor->interrupt_driven) return;

+ mutex_lock(&devfreq->lock); + if (devfreq->stop_polling) { + mutex_unlock(&devfreq->lock); + return; + } + + devfreq->stop_polling = true; + mutex_unlock(&devfreq->lock); cancel_delayed_work_sync(&devfreq->work); } EXPORT_SYMBOL(devfreq_monitor_stop);

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

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

From: Osama Muhammad osmtendev@gmail.com

[ Upstream commit 9862ec7ac1cbc6eb5ee4a045b5d5b8edbb2f7e68 ]

Syzkaller reported the following issue:

UBSAN: array-index-out-of-bounds in fs/jfs/jfs_dmap.c:2867:6 index 196694 is out of range for type 's8[1365]' (aka 'signed char[1365]') CPU: 1 PID: 109 Comm: jfsCommit Not tainted 6.6.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/04/2023 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1e7/0x2d0 lib/dump_stack.c:106 ubsan_epilogue lib/ubsan.c:217 [inline] __ubsan_handle_out_of_bounds+0x11c/0x150 lib/ubsan.c:348 dbAdjTree+0x474/0x4f0 fs/jfs/jfs_dmap.c:2867 dbJoin+0x210/0x2d0 fs/jfs/jfs_dmap.c:2834 dbFreeBits+0x4eb/0xda0 fs/jfs/jfs_dmap.c:2331 dbFreeDmap fs/jfs/jfs_dmap.c:2080 [inline] dbFree+0x343/0x650 fs/jfs/jfs_dmap.c:402 txFreeMap+0x798/0xd50 fs/jfs/jfs_txnmgr.c:2534 txUpdateMap+0x342/0x9e0 txLazyCommit fs/jfs/jfs_txnmgr.c:2664 [inline] jfs_lazycommit+0x47a/0xb70 fs/jfs/jfs_txnmgr.c:2732 kthread+0x2d3/0x370 kernel/kthread.c:388 ret_from_fork+0x48/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:304 </TASK> ================================================================================ Kernel panic - not syncing: UBSAN: panic_on_warn set ... CPU: 1 PID: 109 Comm: jfsCommit Not tainted 6.6.0-rc3-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/04/2023 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1e7/0x2d0 lib/dump_stack.c:106 panic+0x30f/0x770 kernel/panic.c:340 check_panic_on_warn+0x82/0xa0 kernel/panic.c:236 ubsan_epilogue lib/ubsan.c:223 [inline] __ubsan_handle_out_of_bounds+0x13c/0x150 lib/ubsan.c:348 dbAdjTree+0x474/0x4f0 fs/jfs/jfs_dmap.c:2867 dbJoin+0x210/0x2d0 fs/jfs/jfs_dmap.c:2834 dbFreeBits+0x4eb/0xda0 fs/jfs/jfs_dmap.c:2331 dbFreeDmap fs/jfs/jfs_dmap.c:2080 [inline] dbFree+0x343/0x650 fs/jfs/jfs_dmap.c:402 txFreeMap+0x798/0xd50 fs/jfs/jfs_txnmgr.c:2534 txUpdateMap+0x342/0x9e0 txLazyCommit fs/jfs/jfs_txnmgr.c:2664 [inline] jfs_lazycommit+0x47a/0xb70 fs/jfs/jfs_txnmgr.c:2732 kthread+0x2d3/0x370 kernel/kthread.c:388 ret_from_fork+0x48/0x80 arch/x86/kernel/process.c:147 ret_from_fork_asm+0x11/0x20 arch/x86/entry/entry_64.S:304 </TASK> Kernel Offset: disabled Rebooting in 86400 seconds..

The issue is caused when the value of lp becomes greater than CTLTREESIZE which is the max size of stree. Adding a simple check solves this issue.

Dave: As the function returns a void, good error handling would require a more intrusive code reorganization, so I modified Osama's patch at use WARN_ON_ONCE for lack of a cleaner option.

The patch is tested via syzbot.

Reported-by: syzbot+39ba34a099ac2e9bd3cb@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=39ba34a099ac2e9bd3cb Signed-off-by: Osama Muhammad osmtendev@gmail.com Signed-off-by: Dave Kleikamp dave.kleikamp@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/jfs/jfs_dmap.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c index 72eb5ed54c2a..985beb1c654d 100644 --- a/fs/jfs/jfs_dmap.c +++ b/fs/jfs/jfs_dmap.c @@ -2935,6 +2935,9 @@ static void dbAdjTree(dmtree_t * tp, int leafno, int newval) /* is the current value the same as the old value ? if so, * there is nothing to do. */ + if (WARN_ON_ONCE(lp >= CTLTREESIZE)) + return; + if (tp->dmt_stree[lp] == newval) return;

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

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

From: Manas Ghandat ghandatmanas@gmail.com

[ Upstream commit fa5492ee89463a7590a1449358002ff7ef63529f ]

Currently while searching for current page in the sorted entry table of the page there is a out of bound access. Added a bound check to fix the error.

Dave: Set return code to -EIO

Reported-by: kernel test robot lkp@intel.com Reported-by: Dan Carpenter dan.carpenter@linaro.org Closes: https://lore.kernel.org/r/202310241724.Ed02yUz9-lkp@intel.com/ Signed-off-by: Manas Ghandat ghandatmanas@gmail.com Signed-off-by: Dave Kleikamp dave.kleikamp@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/jfs/jfs_dtree.c | 5 +++++ 1 file changed, 5 insertions(+)

diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c index fafcb90219cf..a222a9d71887 100644 --- a/fs/jfs/jfs_dtree.c +++ b/fs/jfs/jfs_dtree.c @@ -633,6 +633,11 @@ int dtSearch(struct inode *ip, struct component_name * key, ino_t * data, for (base = 0, lim = p->header.nextindex; lim; lim >>= 1) { index = base + (lim >> 1);

+ if (stbl[index] < 0) { + rc = -EIO; + goto out; + } + if (p->header.flag & BT_LEAF) { /* uppercase leaf name to compare */ cmp =

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

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

From: Edward Adam Davis eadavis@qq.com

[ Upstream commit e0e1958f4c365e380b17ccb35617345b31ef7bf3 ]

When the execution of diMount(ipimap) fails, the object ipimap that has been released may be accessed in diFreeSpecial(). Asynchronous ipimap release occurs when rcu_core() calls jfs_free_node().

Therefore, when diMount(ipimap) fails, sbi->ipimap should not be initialized as ipimap.

Reported-and-tested-by: syzbot+01cf2dbcbe2022454388@syzkaller.appspotmail.com Signed-off-by: Edward Adam Davis eadavis@qq.com Signed-off-by: Dave Kleikamp dave.kleikamp@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/jfs/jfs_mount.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c index aa4ff7bcaff2..55702b31ab3c 100644 --- a/fs/jfs/jfs_mount.c +++ b/fs/jfs/jfs_mount.c @@ -172,15 +172,15 @@ int jfs_mount(struct super_block *sb) } jfs_info("jfs_mount: ipimap:0x%p", ipimap);

- /* map further access of per fileset inodes by the fileset inode */ - sbi->ipimap = ipimap; - /* initialize fileset inode allocation map */ if ((rc = diMount(ipimap))) { jfs_err("jfs_mount: diMount failed w/rc = %d", rc); goto err_ipimap; }

+ /* map further access of per fileset inodes by the fileset inode */ + sbi->ipimap = ipimap; + return rc;

/*

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

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

From: Thomas Bourgoin thomas.bourgoin@foss.st.com

[ Upstream commit 0eaef675b94c746900dcea7f6c41b9a103ed5d53 ]

smatch warnings: drivers/crypto/stm32/stm32-crc32.c:108 stm32_crc_get_next_crc() warn: can 'crc' even be NULL?

Use list_first_entry_or_null instead of list_first_entry to retrieve the first device registered. The function list_first_entry always return a non NULL pointer even if the list is empty. Hence checking if the pointer returned is NULL does not tell if the list is empty or not.

Reported-by: kernel test robot lkp@intel.com Closes: https://lore.kernel.org/r/202311281111.ou2oUL2i-lkp@intel.com/ Reported-by: Dan Carpenter error27@gmail.com Closes: https://lore.kernel.org/r/202311281111.ou2oUL2i-lkp@intel.com/ Signed-off-by: Thomas Bourgoin thomas.bourgoin@foss.st.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/crypto/stm32/stm32-crc32.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/crypto/stm32/stm32-crc32.c b/drivers/crypto/stm32/stm32-crc32.c index 90a920e7f664..c439be1650c8 100644 --- a/drivers/crypto/stm32/stm32-crc32.c +++ b/drivers/crypto/stm32/stm32-crc32.c @@ -104,7 +104,7 @@ static struct stm32_crc *stm32_crc_get_next_crc(void) struct stm32_crc *crc;

spin_lock_bh(&crc_list.lock); - crc = list_first_entry(&crc_list.dev_list, struct stm32_crc, list); + crc = list_first_entry_or_null(&crc_list.dev_list, struct stm32_crc, list); if (crc) list_move_tail(&crc->list, &crc_list.dev_list); spin_unlock_bh(&crc_list.lock);

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

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

From: Oleg Nesterov oleg@redhat.com

[ Upstream commit 1702e0654ca9a7bcd7c7619c8a5004db58945b71 ]

David Howells says:

(5) afs_find_server().

There could be a lot of servers in the list and each server can have multiple addresses, so I think this would be better with an exclusive second pass.

The server list isn't likely to change all that often, but when it does change, there's a good chance several servers are going to be added/removed one after the other. Further, this is only going to be used for incoming cache management/callback requests from the server, which hopefully aren't going to happen too often - but it is remotely drivable.

(6) afs_find_server_by_uuid().

Similarly to (5), there could be a lot of servers to search through, but they are in a tree not a flat list, so it should be faster to process. Again, it's not likely to change that often and, again, when it does change it's likely to involve multiple changes. This can be driven remotely by an incoming cache management request but is mostly going to be driven by setting up or reconfiguring a volume's server list - something that also isn't likely to happen often.

Make the "seq" counter odd on the 2nd pass, otherwise read_seqbegin_or_lock() never takes the lock.

Signed-off-by: Oleg Nesterov oleg@redhat.com Signed-off-by: David Howells dhowells@redhat.com cc: Marc Dionne marc.dionne@auristor.com cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/20231130115614.GA21581@redhat.com/ Signed-off-by: Sasha Levin sashal@kernel.org --- fs/afs/server.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/afs/server.c b/fs/afs/server.c index 684a2b02b9ff..733e3c470f7e 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -27,7 +27,7 @@ struct afs_server *afs_find_server(struct afs_net *net, const struct afs_addr_list *alist; struct afs_server *server = NULL; unsigned int i; - int seq = 0, diff; + int seq = 1, diff;

rcu_read_lock();

@@ -35,6 +35,7 @@ struct afs_server *afs_find_server(struct afs_net *net, if (server) afs_unuse_server_notime(net, server, afs_server_trace_put_find_rsq); server = NULL; + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&net->fs_addr_lock, &seq);

if (srx->transport.family == AF_INET6) { @@ -90,7 +91,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu { struct afs_server *server = NULL; struct rb_node *p; - int diff, seq = 0; + int diff, seq = 1;

_enter("%pU", uuid);

@@ -102,7 +103,7 @@ struct afs_server *afs_find_server_by_uuid(struct afs_net *net, const uuid_t *uu if (server) afs_unuse_server(net, server, afs_server_trace_put_uuid_rsq); server = NULL; - + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&net->fs_lock, &seq);

p = net->fs_servers.rb_node;

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

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

From: Edward Adam Davis eadavis@qq.com

[ Upstream commit 49f9637aafa6e63ba686c13cb8549bf5e6920402 ]

[Syz report] UBSAN: array-index-out-of-bounds in fs/jfs/jfs_imap.c:2360:2 index -878706688 is out of range for type 'struct iagctl[128]' CPU: 1 PID: 5065 Comm: syz-executor282 Not tainted 6.7.0-rc4-syzkaller-00009-gbee0e7762ad2 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 11/10/2023 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1e7/0x2d0 lib/dump_stack.c:106 ubsan_epilogue lib/ubsan.c:217 [inline] __ubsan_handle_out_of_bounds+0x11c/0x150 lib/ubsan.c:348 diNewExt+0x3cf3/0x4000 fs/jfs/jfs_imap.c:2360 diAllocExt fs/jfs/jfs_imap.c:1949 [inline] diAllocAG+0xbe8/0x1e50 fs/jfs/jfs_imap.c:1666 diAlloc+0x1d3/0x1760 fs/jfs/jfs_imap.c:1587 ialloc+0x8f/0x900 fs/jfs/jfs_inode.c:56 jfs_mkdir+0x1c5/0xb90 fs/jfs/namei.c:225 vfs_mkdir+0x2f1/0x4b0 fs/namei.c:4106 do_mkdirat+0x264/0x3a0 fs/namei.c:4129 __do_sys_mkdir fs/namei.c:4149 [inline] __se_sys_mkdir fs/namei.c:4147 [inline] __x64_sys_mkdir+0x6e/0x80 fs/namei.c:4147 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x45/0x110 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x63/0x6b RIP: 0033:0x7fcb7e6a0b57 Code: ff ff 77 07 31 c0 c3 0f 1f 40 00 48 c7 c2 b8 ff ff ff f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 b8 53 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffd83023038 EFLAGS: 00000286 ORIG_RAX: 0000000000000053 RAX: ffffffffffffffda RBX: 00000000ffffffff RCX: 00007fcb7e6a0b57 RDX: 00000000000a1020 RSI: 00000000000001ff RDI: 0000000020000140 RBP: 0000000020000140 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000286 R12: 00007ffd830230d0 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000

[Analysis] When the agstart is too large, it can cause agno overflow.

[Fix] After obtaining agno, if the value is invalid, exit the subsequent process.

Reported-and-tested-by: syzbot+553d90297e6d2f50dbc7@syzkaller.appspotmail.com Signed-off-by: Edward Adam Davis eadavis@qq.com

Modified the test from agno > MAXAG to agno >= MAXAG based on linux-next report by kernel test robot (Dan Carpenter).

Signed-off-by: Dave Kleikamp dave.kleikamp@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/jfs/jfs_imap.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c index 14f918a4831d..b0965f3ef186 100644 --- a/fs/jfs/jfs_imap.c +++ b/fs/jfs/jfs_imap.c @@ -2181,6 +2181,9 @@ static int diNewExt(struct inomap * imap, struct iag * iagp, int extno) /* get the ag and iag numbers for this iag. */ agno = BLKTOAG(le64_to_cpu(iagp->agstart), sbi); + if (agno >= MAXAG || agno < 0) + return -EIO; + iagno = le32_to_cpu(iagp->iagnum);

/* check if this is the last free extent within the

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

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

From: Heiko Carstens hca@linux.ibm.com

[ Upstream commit b988b1bb0053c0dcd26187d29ef07566a565cf55 ]

kvm_arch_vcpu_ioctl_set_fpu() allows to set the floating point control (fpc) register of a guest cpu. The new value is tested for validity by temporarily loading it into the fpc register.

This may lead to corruption of the fpc register of the host process: if an interrupt happens while the value is temporarily loaded into the fpc register, and within interrupt context floating point or vector registers are used, the current fp/vx registers are saved with save_fpu_regs() assuming they belong to user space and will be loaded into fp/vx registers when returning to user space.

test_fp_ctl() restores the original user space / host process fpc register value, however it will be discarded, when returning to user space.

In result the host process will incorrectly continue to run with the value that was supposed to be used for a guest cpu.

Fix this by simply removing the test. There is another test right before the SIE context is entered which will handles invalid values.

This results in a change of behaviour: invalid values will now be accepted instead of that the ioctl fails with -EINVAL. This seems to be acceptable, given that this interface is most likely not used anymore, and this is in addition the same behaviour implemented with the memory mapped interface (replace invalid values with zero) - see sync_regs() in kvm-s390.c.

Reviewed-by: Christian Borntraeger borntraeger@linux.ibm.com Reviewed-by: Claudio Imbrenda imbrenda@linux.ibm.com Signed-off-by: Heiko Carstens hca@linux.ibm.com Signed-off-by: Alexander Gordeev agordeev@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/kvm/kvm-s390.c | 5 ----- 1 file changed, 5 deletions(-)

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 7a326d03087a..f6c27b44766f 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -3649,10 +3649,6 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)

vcpu_load(vcpu);

- if (test_fp_ctl(fpu->fpc)) { - ret = -EINVAL; - goto out; - } vcpu->run->s.regs.fpc = fpu->fpc; if (MACHINE_HAS_VX) convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs, @@ -3660,7 +3656,6 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) else memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs));

-out: vcpu_put(vcpu); return ret; }

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

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

From: Gabriel Krisman Bertazi krisman@suse.de

[ Upstream commit cd72c7ef5fed44272272a105b1da22810c91be69 ]

Even though it seems to be able to resolve some names of case-insensitive directories, the lack of d_hash and d_compare means we end up with a broken state in the d_cache. Considering it was never a goal to support these two together, and we are preparing to use d_revalidate in case-insensitive filesystems, which would make the combination even more broken, reject any attempt to get a casefolded inode from ecryptfs.

Signed-off-by: Gabriel Krisman Bertazi krisman@suse.de Reviewed-by: Eric Biggers ebiggers@google.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ecryptfs/inode.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index e23752d9a79f..c867a0d62f36 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -76,6 +76,14 @@ static struct inode *__ecryptfs_get_inode(struct inode *lower_inode,

if (lower_inode->i_sb != ecryptfs_superblock_to_lower(sb)) return ERR_PTR(-EXDEV); + + /* Reject dealing with casefold directories. */ + if (IS_CASEFOLDED(lower_inode)) { + pr_err_ratelimited("%s: Can't handle casefolded directory.\n", + __func__); + return ERR_PTR(-EREMOTE); + } + if (!igrab(lower_inode)) return ERR_PTR(-ESTALE); inode = iget5_locked(sb, (unsigned long)lower_inode,

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

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

From: Baokun Li libaokun1@huawei.com

[ Upstream commit 658a52344fb139f9531e7543a6e0015b630feb38 ]

The maximum value of flexbg_size is 2^31, but the maximum value of int is (2^31 - 1), so overflow may occur when the type of flexbg_size is declared as int.

For example, when uninit_mask is initialized in ext4_alloc_group_tables(), if flexbg_size == 2^31, the initialized uninit_mask is incorrect, and this may causes set_flexbg_block_bitmap() to trigger a BUG_ON().

Therefore, the flexbg_size type is declared as unsigned int to avoid overflow and memory waste.

Signed-off-by: Baokun Li libaokun1@huawei.com Reviewed-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20231023013057.2117948-2-libaokun1@huawei.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/resize.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 9b4199a1e039..96d278688fd7 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -237,7 +237,7 @@ struct ext4_new_flex_group_data { * * Returns NULL on failure otherwise address of the allocated structure. */ -static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size) +static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned int flexbg_size) { struct ext4_new_flex_group_data *flex_gd;

@@ -292,7 +292,7 @@ static void free_flex_gd(struct ext4_new_flex_group_data *flex_gd) */ static int ext4_alloc_group_tables(struct super_block *sb, struct ext4_new_flex_group_data *flex_gd, - int flexbg_size) + unsigned int flexbg_size) { struct ext4_new_group_data *group_data = flex_gd->groups; ext4_fsblk_t start_blk; @@ -393,12 +393,12 @@ static int ext4_alloc_group_tables(struct super_block *sb, group = group_data[0].group;

printk(KERN_DEBUG "EXT4-fs: adding a flex group with " - "%d groups, flexbg size is %d:\n", flex_gd->count, + "%u groups, flexbg size is %u:\n", flex_gd->count, flexbg_size);

for (i = 0; i < flex_gd->count; i++) { ext4_debug( - "adding %s group %u: %u blocks (%d free, %d mdata blocks)\n", + "adding %s group %u: %u blocks (%u free, %u mdata blocks)\n", ext4_bg_has_super(sb, group + i) ? "normal" : "no-super", group + i, group_data[i].blocks_count, @@ -1563,7 +1563,7 @@ static int ext4_flex_group_add(struct super_block *sb, static int ext4_setup_next_flex_gd(struct super_block *sb, struct ext4_new_flex_group_data *flex_gd, ext4_fsblk_t n_blocks_count, - unsigned long flexbg_size) + unsigned int flexbg_size) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; @@ -1941,8 +1941,9 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) ext4_fsblk_t o_blocks_count; ext4_fsblk_t n_blocks_count_retry = 0; unsigned long last_update_time = 0; - int err = 0, flexbg_size = 1 << sbi->s_log_groups_per_flex; + int err = 0; int meta_bg; + unsigned int flexbg_size = ext4_flex_bg_size(sbi);

/* See if the device is actually as big as what was requested */ bh = ext4_sb_bread(sb, n_blocks_count - 1, 0);

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

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

From: Baokun Li libaokun1@huawei.com

[ Upstream commit 5d1935ac02ca5aee364a449a35e2977ea84509b0 ]

When we online resize an ext4 filesystem with a oversized flexbg_size,

mkfs.ext4 -F -G 67108864 $dev -b 4096 100M mount $dev $dir resize2fs $dev 16G

the following WARN_ON is triggered: ================================================================== WARNING: CPU: 0 PID: 427 at mm/page_alloc.c:4402 __alloc_pages+0x411/0x550 Modules linked in: sg(E) CPU: 0 PID: 427 Comm: resize2fs Tainted: G E 6.6.0-rc5+ #314 RIP: 0010:__alloc_pages+0x411/0x550 Call Trace: <TASK> __kmalloc_large_node+0xa2/0x200 __kmalloc+0x16e/0x290 ext4_resize_fs+0x481/0xd80 __ext4_ioctl+0x1616/0x1d90 ext4_ioctl+0x12/0x20 __x64_sys_ioctl+0xf0/0x150 do_syscall_64+0x3b/0x90 ==================================================================

This is because flexbg_size is too large and the size of the new_group_data array to be allocated exceeds MAX_ORDER. Currently, the minimum value of MAX_ORDER is 8, the minimum value of PAGE_SIZE is 4096, the corresponding maximum number of groups that can be allocated is:

(PAGE_SIZE << MAX_ORDER) / sizeof(struct ext4_new_group_data) ≈ 21845

And the value that is down-aligned to the power of 2 is 16384. Therefore, this value is defined as MAX_RESIZE_BG, and the number of groups added each time does not exceed this value during resizing, and is added multiple times to complete the online resizing. The difference is that the metadata in a flex_bg may be more dispersed.

Signed-off-by: Baokun Li libaokun1@huawei.com Reviewed-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20231023013057.2117948-4-libaokun1@huawei.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/resize.c | 25 +++++++++++++++++-------- 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index 66ce3d118203..06e0eaf2ea4e 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -227,10 +227,17 @@ struct ext4_new_flex_group_data { in the flex group */ __u16 *bg_flags; /* block group flags of groups in @groups */ + ext4_group_t resize_bg; /* number of allocated + new_group_data */ ext4_group_t count; /* number of groups in @groups */ };

+/* + * Avoiding memory allocation failures due to too many groups added each time. + */ +#define MAX_RESIZE_BG 16384 + /* * alloc_flex_gd() allocates a ext4_new_flex_group_data with size of * @flexbg_size. @@ -245,14 +252,18 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned int flexbg_size) if (flex_gd == NULL) goto out3;

- flex_gd->count = flexbg_size; - flex_gd->groups = kmalloc_array(flexbg_size, + if (unlikely(flexbg_size > MAX_RESIZE_BG)) + flex_gd->resize_bg = MAX_RESIZE_BG; + else + flex_gd->resize_bg = flexbg_size; + + flex_gd->groups = kmalloc_array(flex_gd->resize_bg, sizeof(struct ext4_new_group_data), GFP_NOFS); if (flex_gd->groups == NULL) goto out2;

- flex_gd->bg_flags = kmalloc_array(flexbg_size, sizeof(__u16), + flex_gd->bg_flags = kmalloc_array(flex_gd->resize_bg, sizeof(__u16), GFP_NOFS); if (flex_gd->bg_flags == NULL) goto out1; @@ -1559,8 +1570,7 @@ static int ext4_flex_group_add(struct super_block *sb,

static int ext4_setup_next_flex_gd(struct super_block *sb, struct ext4_new_flex_group_data *flex_gd, - ext4_fsblk_t n_blocks_count, - unsigned int flexbg_size) + ext4_fsblk_t n_blocks_count) { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; @@ -1584,7 +1594,7 @@ static int ext4_setup_next_flex_gd(struct super_block *sb, BUG_ON(last); ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &last);

- last_group = group | (flexbg_size - 1); + last_group = group | (flex_gd->resize_bg - 1); if (last_group > n_group) last_group = n_group;

@@ -2081,8 +2091,7 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count) /* Add flex groups. Note that a regular group is a * flex group with 1 group. */ - while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count, - flexbg_size)) { + while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count)) { if (jiffies - last_update_time > HZ * 10) { if (last_update_time) ext4_msg(sb, KERN_INFO,

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

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

From: Andrii Nakryiko andrii@kernel.org

[ Upstream commit f4c7e887324f5776eef6e6e47a90e0ac8058a7a8 ]

Some compilers complain about get_pprint_mapv_size() not returning value in some code paths. Fix with explicit return.

Signed-off-by: Andrii Nakryiko andrii@kernel.org Link: https://lore.kernel.org/r/20231102033759.2541186-3-andrii@kernel.org Signed-off-by: Alexei Starovoitov ast@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/bpf/prog_tests/btf.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index 28d22265b825..cbdc2839904e 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -4611,6 +4611,7 @@ static size_t get_pprint_mapv_size(enum pprint_mapv_kind_t mapv_kind) #endif

assert(0); + return 0; }

static void set_pprint_mapv(enum pprint_mapv_kind_t mapv_kind,

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

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

From: Justin Tee justin.tee@broadcom.com

[ Upstream commit f5779b529240b715f0e358489ad0ed933bf77c97 ]

Because file_name and phba->ModelName are both declared a size 80 bytes, the extra ".grp" file extension could cause an overflow into file_name.

Define a ELX_FW_NAME_SIZE macro with value 84. 84 incorporates the 4 extra characters from ".grp". file_name is changed to be declared as a char and initialized to zeros i.e. null chars.

Signed-off-by: Justin Tee justin.tee@broadcom.com Link: https://lore.kernel.org/r/20231031191224.150862-3-justintee8345@gmail.com Reviewed-by: Himanshu Madhani himanshu.madhani@oracle.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/lpfc/lpfc.h | 1 + drivers/scsi/lpfc/lpfc_init.c | 4 ++-- 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index 03bc472f302a..cf69f831a725 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -32,6 +32,7 @@ struct lpfc_sli2_slim;

#define ELX_MODEL_NAME_SIZE 80 +#define ELX_FW_NAME_SIZE 84

#define LPFC_PCI_DEV_LP 0x1 #define LPFC_PCI_DEV_OC 0x2 diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c index 1bb3c96a04bd..5f2009327a59 100644 --- a/drivers/scsi/lpfc/lpfc_init.c +++ b/drivers/scsi/lpfc/lpfc_init.c @@ -13026,7 +13026,7 @@ lpfc_write_firmware(const struct firmware *fw, void *context) int lpfc_sli4_request_firmware_update(struct lpfc_hba *phba, uint8_t fw_upgrade) { - uint8_t file_name[ELX_MODEL_NAME_SIZE]; + char file_name[ELX_FW_NAME_SIZE] = {0}; int ret; const struct firmware *fw;

@@ -13035,7 +13035,7 @@ lpfc_sli4_request_firmware_update(struct lpfc_hba *phba, uint8_t fw_upgrade) LPFC_SLI_INTF_IF_TYPE_2) return -EPERM;

- snprintf(file_name, ELX_MODEL_NAME_SIZE, "%s.grp", phba->ModelName); + scnprintf(file_name, sizeof(file_name), "%s.grp", phba->ModelName);

if (fw_upgrade == INT_FW_UPGRADE) { ret = request_firmware_nowait(THIS_MODULE, FW_ACTION_HOTPLUG,

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

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

From: Zhengchao Shao shaozhengchao@huawei.com

[ Upstream commit d6b83f1e3707c4d60acfa58afd3515e17e5d5384 ]

If failed to allocate "tags" or could not find the final upper device from start_dev's upper list in bond_verify_device_path(), only the loopback detection of the current upper device should be affected, and the system is no need to be panic. So return -ENOMEM in alb_upper_dev_walk to stop walking, print some warn information when failed to allocate memory for vlan tags in bond_verify_device_path.

I also think that the following function calls netdev_walk_all_upper_dev_rcu ---->>>alb_upper_dev_walk ---------->>>bond_verify_device_path

From this way, "end device" can eventually be obtained from "start device"

in bond_verify_device_path, IS_ERR(tags) could be instead of IS_ERR_OR_NULL(tags) in alb_upper_dev_walk.

Signed-off-by: Zhengchao Shao shaozhengchao@huawei.com Acked-by: Jay Vosburgh jay.vosburgh@canonical.com Link: https://lore.kernel.org/r/20231118081653.1481260-1-shaozhengchao@huawei.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/bonding/bond_alb.c | 3 ++- drivers/net/bonding/bond_main.c | 5 ++++- 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 64ba465741a7..81a5e7622ea7 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -971,7 +971,8 @@ static int alb_upper_dev_walk(struct net_device *upper, if (netif_is_macvlan(upper) && !strict_match) { tags = bond_verify_device_path(bond->dev, upper, 0); if (IS_ERR_OR_NULL(tags)) - BUG(); + return -ENOMEM; + alb_send_lp_vid(slave, upper->dev_addr, tags[0].vlan_proto, tags[0].vlan_id); kfree(tags); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 50fabba04248..506d6fdbfacc 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2777,8 +2777,11 @@ struct bond_vlan_tag *bond_verify_device_path(struct net_device *start_dev,

if (start_dev == end_dev) { tags = kcalloc(level + 1, sizeof(*tags), GFP_ATOMIC); - if (!tags) + if (!tags) { + net_err_ratelimited("%s: %s: Failed to allocate tags\n", + __func__, start_dev->name); return ERR_PTR(-ENOMEM); + } tags[level].vlan_proto = VLAN_N_VID; return tags; }

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

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

From: Alexander Stein alexander.stein@ew.tq-group.com

[ Upstream commit 0d4ac04fa7c3f6dc263dba6f575a2ec7a2d4eca8 ]

imx7d uses two ports for 'in-ports', so the syntax port@<num> has to be used. imx7d has both port and port@1 nodes present, raising these error: funnel@30041000: in-ports: More than one condition true in oneOf schema funnel@30041000: Unevaluated properties are not allowed ('in-ports' was unexpected)

Fix this by also using port@0 for imx7s as well.

Signed-off-by: Alexander Stein alexander.stein@ew.tq-group.com Signed-off-by: Shawn Guo shawnguo@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/boot/dts/imx7d.dtsi | 3 --- arch/arm/boot/dts/imx7s.dtsi | 6 +++++- 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/arm/boot/dts/imx7d.dtsi b/arch/arm/boot/dts/imx7d.dtsi index b0bcfa9094a3..8ad3e60fd7d1 100644 --- a/arch/arm/boot/dts/imx7d.dtsi +++ b/arch/arm/boot/dts/imx7d.dtsi @@ -209,9 +209,6 @@ };

&ca_funnel_in_ports { - #address-cells = <1>; - #size-cells = <0>; - port@1 { reg = <1>; ca_funnel_in_port1: endpoint { diff --git a/arch/arm/boot/dts/imx7s.dtsi b/arch/arm/boot/dts/imx7s.dtsi index 03bde2fb9bb1..622c60bd8b75 100644 --- a/arch/arm/boot/dts/imx7s.dtsi +++ b/arch/arm/boot/dts/imx7s.dtsi @@ -173,7 +173,11 @@ clock-names = "apb_pclk";

ca_funnel_in_ports: in-ports { - port { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; ca_funnel_in_port0: endpoint { remote-endpoint = <&etm0_out_port>; };