From: Takashi Iwai tiwai@suse.de

commit 97d917879d7f92df09c3f21fd54609a8bcd654b2 upstream.

We took sound_oss_mutex around the calls of unregister_sound_special() at unregistering OSS devices. This may, however, lead to a deadlock, because we manage the card release via the card's device object, and the release may happen at unregister_sound_special() call -- which will take sound_oss_mutex again in turn.

Although the deadlock might be fixed by relaxing the rawmidi mutex in the previous commit, it's safer to move unregister_sound_special() calls themselves out of the sound_oss_mutex, too. The call is race-safe as the function has a spinlock protection by itself.

Link: https://lore.kernel.org/r/CAB7eexJP7w1B0mVgDF0dQ+gWor7UdkiwPczmL7pn91xx8xpzO... Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221011070147.7611-2-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/core/sound_oss.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-)

--- a/sound/core/sound_oss.c +++ b/sound/core/sound_oss.c @@ -162,7 +162,6 @@ int snd_unregister_oss_device(int type, mutex_unlock(&sound_oss_mutex); return -ENOENT; } - unregister_sound_special(minor); switch (SNDRV_MINOR_OSS_DEVICE(minor)) { case SNDRV_MINOR_OSS_PCM: track2 = SNDRV_MINOR_OSS(cidx, SNDRV_MINOR_OSS_AUDIO); @@ -174,12 +173,18 @@ int snd_unregister_oss_device(int type, track2 = SNDRV_MINOR_OSS(cidx, SNDRV_MINOR_OSS_DMMIDI1); break; } - if (track2 >= 0) { - unregister_sound_special(track2); + if (track2 >= 0) snd_oss_minors[track2] = NULL; - } snd_oss_minors[minor] = NULL; mutex_unlock(&sound_oss_mutex); + + /* call unregister_sound_special() outside sound_oss_mutex; + * otherwise may deadlock, as it can trigger the release of a card + */ + unregister_sound_special(minor); + if (track2 >= 0) + unregister_sound_special(track2); + kfree(mptr); return 0; }

From: Takashi Iwai tiwai@suse.de

commit 6382da0828995af87aa8b8bef28cc61aceb4aff3 upstream.

When the driver hits -ENOMEM at allocating a URB or a buffer, it aborts and goes to the error path that releases the all previously allocated resources. However, when -ENOMEM hits at the middle of the sync EP URB allocation loop, the partially allocated URBs might be left without released, because ep->nurbs is still zero at that point.

Fix it by setting ep->nurbs at first, so that the error handler loops over the full URB list.

Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220930100151.19461-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/usb/endpoint.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

--- a/sound/usb/endpoint.c +++ b/sound/usb/endpoint.c @@ -1223,6 +1223,7 @@ static int sync_ep_set_params(struct snd if (!ep->syncbuf) return -ENOMEM;

+ ep->nurbs = SYNC_URBS; for (i = 0; i < SYNC_URBS; i++) { struct snd_urb_ctx *u = &ep->urb[i]; u->index = i; @@ -1242,8 +1243,6 @@ static int sync_ep_set_params(struct snd u->urb->complete = snd_complete_urb; }

- ep->nurbs = SYNC_URBS; - return 0;

out_of_memory:

From: Callum Osmotherly callum.osmotherly@gmail.com

commit 417b9c51f59734d852e47252476fadc293ad994a upstream.

After some feedback from users with Dell Precision 5530 machines, this patch reverts the previous change to add ALC289_FIXUP_DUAL_SPK. While it improved the speaker output quality, it caused the headphone jack to have an audible "pop" sound when power saving was toggled.

Fixes: 1885ff13d4c4 ("ALSA: hda/realtek: Enable 4-speaker output Dell Precision 5530 laptop") Signed-off-by: Callum Osmotherly callum.osmotherly@gmail.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/Yz0uyN1zwZhnyRD6@piranha Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/patch_realtek.c | 1 - 1 file changed, 1 deletion(-)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -8847,7 +8847,6 @@ static const struct snd_pci_quirk alc269 SND_PCI_QUIRK(0x1028, 0x0871, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0872, "Dell Precision 3630", ALC255_FIXUP_DELL_HEADSET_MIC), SND_PCI_QUIRK(0x1028, 0x0873, "Dell Precision 3930", ALC255_FIXUP_DUMMY_LINEOUT_VERB), - SND_PCI_QUIRK(0x1028, 0x087d, "Dell Precision 5530", ALC289_FIXUP_DUAL_SPK), SND_PCI_QUIRK(0x1028, 0x08ad, "Dell WYSE AIO", ALC225_FIXUP_DELL_WYSE_AIO_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x08ae, "Dell WYSE NB", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x0935, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB),

From: Luke D. Jones luke@ljones.dev

commit 2ea8e1297801f7b0220ebf6ae61a5b74ca83981e upstream.

The ASUS ROG X16 (GV601R) series laptop has the same node-to-DAC pairs as early models and the G14, this includes bass speakers which are by default mapped incorrectly to the 0x06 node.

Add a quirk to use the same DAC pairs as the G14.

Signed-off-by: Luke D. Jones luke@ljones.dev Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221010070347.36883-1-luke@ljones.dev Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/patch_realtek.c | 1 + 1 file changed, 1 insertion(+)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9047,6 +9047,7 @@ static const struct snd_pci_quirk alc269 SND_PCI_QUIRK(0x1043, 0x1e8e, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1c52, "ASUS Zephyrus G15 2022", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1f11, "ASUS Zephyrus G14", ALC289_FIXUP_ASUS_GA401), + SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2), SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC), SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC),

From: Tudor Ambarus tudor.ambarus@microchip.com

commit 1161703c9bd664da5e3b2eb1a3bb40c210e026ea upstream.

Every dma_map_single() call should have its dma_unmap_single() counterpart, because the DMA address space is a shared resource and one could render the machine unusable by consuming all DMA addresses.

Link: https://lore.kernel.org/lkml/13c6c9a2-6db5-c3bf-349b-4c127ad3496a@axentia.se... Cc: stable@vger.kernel.org Fixes: f88fc122cc34 ("mtd: nand: Cleanup/rework the atmel_nand driver") Signed-off-by: Tudor Ambarus tudor.ambarus@microchip.com Acked-by: Alexander Dahl ada@thorsis.com Reported-by: Peter Rosin peda@axentia.se Tested-by: Alexander Dahl ada@thorsis.com Reviewed-by: Boris Brezillon boris.brezillon@collabora.com Tested-by: Peter Rosin peda@axentia.se Signed-off-by: Miquel Raynal miquel.raynal@bootlin.com Link: https://lore.kernel.org/linux-mtd/20220728074014.145406-1-tudor.ambarus@micr... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/mtd/nand/raw/atmel/nand-controller.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/mtd/nand/raw/atmel/nand-controller.c +++ b/drivers/mtd/nand/raw/atmel/nand-controller.c @@ -405,6 +405,7 @@ static int atmel_nand_dma_transfer(struc

dma_async_issue_pending(nc->dmac); wait_for_completion(&finished); + dma_unmap_single(nc->dev, buf_dma, len, dir);

return 0;

From: Gaurav Kohli gauravkohli@linux.microsoft.com

commit 365e1ececb2905f94cc10a5817c5b644a32a3ae2 upstream.

During vm boot, there might be possibility that vf registration call comes before the vf association from host to vm.

And this might break netvsc vf path, To prevent the same block vf registration until vf bind message comes from host.

Cc: stable@vger.kernel.org Fixes: 00d7ddba11436 ("hv_netvsc: pair VF based on serial number") Reviewed-by: Haiyang Zhang haiyangz@microsoft.com Signed-off-by: Gaurav Kohli gauravkohli@linux.microsoft.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/hyperv/hyperv_net.h | 3 ++- drivers/net/hyperv/netvsc.c | 4 ++++ drivers/net/hyperv/netvsc_drv.c | 19 +++++++++++++++++++ 3 files changed, 25 insertions(+), 1 deletion(-)

--- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -1037,7 +1037,8 @@ struct net_device_context { u32 vf_alloc; /* Serial number of the VF to team with */ u32 vf_serial; - + /* completion variable to confirm vf association */ + struct completion vf_add; /* Is the current data path through the VF NIC? */ bool data_path_is_vf;

--- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1450,6 +1450,10 @@ static void netvsc_send_vf(struct net_de

net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated; net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial; + + if (net_device_ctx->vf_alloc) + complete(&net_device_ctx->vf_add); + netdev_info(ndev, "VF slot %u %s\n", net_device_ctx->vf_serial, net_device_ctx->vf_alloc ? "added" : "removed"); --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2336,6 +2336,18 @@ static struct net_device *get_netvsc_bys

}

+ /* Fallback path to check synthetic vf with + * help of mac addr + */ + list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) { + ndev = hv_get_drvdata(ndev_ctx->device_ctx); + if (ether_addr_equal(vf_netdev->perm_addr, ndev->perm_addr)) { + netdev_notice(vf_netdev, + "falling back to mac addr based matching\n"); + return ndev; + } + } + netdev_notice(vf_netdev, "no netdev found for vf serial:%u\n", serial); return NULL; @@ -2432,6 +2444,11 @@ static int netvsc_vf_changed(struct net_ if (net_device_ctx->data_path_is_vf == vf_is_up) return NOTIFY_OK;

+ if (vf_is_up && !net_device_ctx->vf_alloc) { + netdev_info(ndev, "Waiting for the VF association from host\n"); + wait_for_completion(&net_device_ctx->vf_add); + } + ret = netvsc_switch_datapath(ndev, vf_is_up);

if (ret) { @@ -2463,6 +2480,7 @@ static int netvsc_unregister_vf(struct n

netvsc_vf_setxdp(vf_netdev, NULL);

+ reinit_completion(&net_device_ctx->vf_add); netdev_rx_handler_unregister(vf_netdev); netdev_upper_dev_unlink(vf_netdev, ndev); RCU_INIT_POINTER(net_device_ctx->vf_netdev, NULL); @@ -2502,6 +2520,7 @@ static int netvsc_probe(struct hv_device

INIT_DELAYED_WORK(&net_device_ctx->dwork, netvsc_link_change);

+ init_completion(&net_device_ctx->vf_add); spin_lock_init(&net_device_ctx->lock); INIT_LIST_HEAD(&net_device_ctx->reconfig_events); INIT_DELAYED_WORK(&net_device_ctx->vf_takeover, netvsc_vf_setup);

From: Zhang Xiaoxu zhangxiaoxu5@huawei.com

commit e98ecc6e94f4e6d21c06660b0f336df02836694f upstream.

Commit d5c7076b772a ("smb3: add smb3.1.1 to default dialect list") extend the dialects from 3 to 4, but forget to decrease the extended length when specific the dialect, then the message length is larger than expected.

This maybe leak some info through network because not initialize the message body.

After apply this patch, the VALIDATE_NEGOTIATE_INFO message length is reduced from 28 bytes to 26 bytes.

Fixes: d5c7076b772a ("smb3: add smb3.1.1 to default dialect list") Signed-off-by: Zhang Xiaoxu zhangxiaoxu5@huawei.com Cc: stable@vger.kernel.org Acked-by: Paulo Alcantara (SUSE) pc@cjr.nz Reviewed-by: Tom Talpey tom@talpey.com Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/cifs/smb2pdu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1137,9 +1137,9 @@ int smb3_validate_negotiate(const unsign pneg_inbuf->Dialects[0] = cpu_to_le16(server->vals->protocol_id); pneg_inbuf->DialectCount = cpu_to_le16(1); - /* structure is big enough for 3 dialects, sending only 1 */ + /* structure is big enough for 4 dialects, sending only 1 */ inbuflen = sizeof(*pneg_inbuf) - - sizeof(pneg_inbuf->Dialects[0]) * 2; + sizeof(pneg_inbuf->Dialects[0]) * 3; }

rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,

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

commit 7f4f1096d5921f5d90547596f9ce80e0b924f887 upstream.

After the result of the previous conversion is read the chip automatically starts a new conversion and doesn't accept new i2c transfers until this conversion is completed which makes the function return failure.

So add an early return iff the programming of the new address isn't needed. Note this will not fix the problem in general, but all cases that are currently used. Once this changes we get the failure back, but this can be addressed when the need arises.

Fixes: 69548b7c2c4f ("iio: adc: ltc2497: split protocol independent part in a separate module ") Reported-by: Meng Li Meng.Li@windriver.com Signed-off-by: Uwe Kleine-König u.kleine-koenig@pengutronix.de Tested-by: Denys Zagorui dzagorui@cisco.com Cc: Stable@vger.kernel.org Link: https://lore.kernel.org/r/20220815091647.1523532-1-dzagorui@cisco.com Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iio/adc/ltc2497.c | 13 +++++++++++++ 1 file changed, 13 insertions(+)

--- a/drivers/iio/adc/ltc2497.c +++ b/drivers/iio/adc/ltc2497.c @@ -41,6 +41,19 @@ static int ltc2497_result_and_measure(st }

*val = (be32_to_cpu(st->buf) >> 14) - (1 << 17); + + /* + * The part started a new conversion at the end of the above i2c + * transfer, so if the address didn't change since the last call + * everything is fine and we can return early. + * If not (which should only happen when some sort of bulk + * conversion is implemented) we have to program the new + * address. Note that this probably fails as the conversion that + * was triggered above is like not complete yet and the two + * operations have to be done in a single transfer. + */ + if (ddata->addr_prev == address) + return 0; }

ret = i2c_smbus_write_byte(st->client,

From: Eddie James eajames@linux.ibm.com

commit c2329717bdd3fa62f8a2f3d8d85ad0bee4556bd7 upstream.

Move the startup procedure into a function, and correct a missing check on the return code for writing the PRS_CFG register.

Cc: stable@vger.kernel.org Signed-off-by: Eddie James eajames@linux.ibm.com Reviewed-by: Joel Stanley joel@jms.id.au Reviewed-by: Andy Shevchenko andy.shevchenko@gmail.com Link: https://lore.kernel.org/r/20220915195719.136812-2-eajames@linux.ibm.com Signed-off-by: Jonathan Cameron Jonathan.Cameron@huawei.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/iio/pressure/dps310.c | 188 ++++++++++++++++++++++-------------------- 1 file changed, 99 insertions(+), 89 deletions(-)

--- a/drivers/iio/pressure/dps310.c +++ b/drivers/iio/pressure/dps310.c @@ -159,6 +159,102 @@ static int dps310_get_coefs(struct dps31 return 0; }

+/* + * Some versions of the chip will read temperatures in the ~60C range when + * it's actually ~20C. This is the manufacturer recommended workaround + * to correct the issue. The registers used below are undocumented. + */ +static int dps310_temp_workaround(struct dps310_data *data) +{ + int rc; + int reg; + + rc = regmap_read(data->regmap, 0x32, &reg); + if (rc) + return rc; + + /* + * If bit 1 is set then the device is okay, and the workaround does not + * need to be applied + */ + if (reg & BIT(1)) + return 0; + + rc = regmap_write(data->regmap, 0x0e, 0xA5); + if (rc) + return rc; + + rc = regmap_write(data->regmap, 0x0f, 0x96); + if (rc) + return rc; + + rc = regmap_write(data->regmap, 0x62, 0x02); + if (rc) + return rc; + + rc = regmap_write(data->regmap, 0x0e, 0x00); + if (rc) + return rc; + + return regmap_write(data->regmap, 0x0f, 0x00); +} + +static int dps310_startup(struct dps310_data *data) +{ + int rc; + int ready; + + /* + * Set up pressure sensor in single sample, one measurement per second + * mode + */ + rc = regmap_write(data->regmap, DPS310_PRS_CFG, 0); + if (rc) + return rc; + + /* + * Set up external (MEMS) temperature sensor in single sample, one + * measurement per second mode + */ + rc = regmap_write(data->regmap, DPS310_TMP_CFG, DPS310_TMP_EXT); + if (rc) + return rc; + + /* Temp and pressure shifts are disabled when PRC <= 8 */ + rc = regmap_write_bits(data->regmap, DPS310_CFG_REG, + DPS310_PRS_SHIFT_EN | DPS310_TMP_SHIFT_EN, 0); + if (rc) + return rc; + + /* MEAS_CFG doesn't update correctly unless first written with 0 */ + rc = regmap_write_bits(data->regmap, DPS310_MEAS_CFG, + DPS310_MEAS_CTRL_BITS, 0); + if (rc) + return rc; + + /* Turn on temperature and pressure measurement in the background */ + rc = regmap_write_bits(data->regmap, DPS310_MEAS_CFG, + DPS310_MEAS_CTRL_BITS, DPS310_PRS_EN | + DPS310_TEMP_EN | DPS310_BACKGROUND); + if (rc) + return rc; + + /* + * Calibration coefficients required for reporting temperature. + * They are available 40ms after the device has started + */ + rc = regmap_read_poll_timeout(data->regmap, DPS310_MEAS_CFG, ready, + ready & DPS310_COEF_RDY, 10000, 40000); + if (rc) + return rc; + + rc = dps310_get_coefs(data); + if (rc) + return rc; + + return dps310_temp_workaround(data); +} + static int dps310_get_pres_precision(struct dps310_data *data) { int rc; @@ -677,52 +773,12 @@ static const struct iio_info dps310_info .write_raw = dps310_write_raw, };

-/* - * Some verions of chip will read temperatures in the ~60C range when - * its actually ~20C. This is the manufacturer recommended workaround - * to correct the issue. The registers used below are undocumented. - */ -static int dps310_temp_workaround(struct dps310_data *data) -{ - int rc; - int reg; - - rc = regmap_read(data->regmap, 0x32, &reg); - if (rc < 0) - return rc; - - /* - * If bit 1 is set then the device is okay, and the workaround does not - * need to be applied - */ - if (reg & BIT(1)) - return 0; - - rc = regmap_write(data->regmap, 0x0e, 0xA5); - if (rc < 0) - return rc; - - rc = regmap_write(data->regmap, 0x0f, 0x96); - if (rc < 0) - return rc; - - rc = regmap_write(data->regmap, 0x62, 0x02); - if (rc < 0) - return rc; - - rc = regmap_write(data->regmap, 0x0e, 0x00); - if (rc < 0) - return rc; - - return regmap_write(data->regmap, 0x0f, 0x00); -} - static int dps310_probe(struct i2c_client *client, const struct i2c_device_id *id) { struct dps310_data *data; struct iio_dev *iio; - int rc, ready; + int rc;

iio = devm_iio_device_alloc(&client->dev, sizeof(*data)); if (!iio) @@ -747,54 +803,8 @@ static int dps310_probe(struct i2c_clien if (rc) return rc;

- /* - * Set up pressure sensor in single sample, one measurement per second - * mode - */ - rc = regmap_write(data->regmap, DPS310_PRS_CFG, 0); - - /* - * Set up external (MEMS) temperature sensor in single sample, one - * measurement per second mode - */ - rc = regmap_write(data->regmap, DPS310_TMP_CFG, DPS310_TMP_EXT); - if (rc < 0) - return rc; - - /* Temp and pressure shifts are disabled when PRC <= 8 */ - rc = regmap_write_bits(data->regmap, DPS310_CFG_REG, - DPS310_PRS_SHIFT_EN | DPS310_TMP_SHIFT_EN, 0); - if (rc < 0) - return rc; - - /* MEAS_CFG doesn't update correctly unless first written with 0 */ - rc = regmap_write_bits(data->regmap, DPS310_MEAS_CFG, - DPS310_MEAS_CTRL_BITS, 0); - if (rc < 0) - return rc; - - /* Turn on temperature and pressure measurement in the background */ - rc = regmap_write_bits(data->regmap, DPS310_MEAS_CFG, - DPS310_MEAS_CTRL_BITS, DPS310_PRS_EN | - DPS310_TEMP_EN | DPS310_BACKGROUND); - if (rc < 0) - return rc; - - /* - * Calibration coefficients required for reporting temperature. - * They are available 40ms after the device has started - */ - rc = regmap_read_poll_timeout(data->regmap, DPS310_MEAS_CFG, ready, - ready & DPS310_COEF_RDY, 10000, 40000); - if (rc < 0) - return rc; - - rc = dps310_get_coefs(data); - if (rc < 0) - return rc; - - rc = dps310_temp_workaround(data); - if (rc < 0) + rc = dps310_startup(data); + if (rc) return rc;

rc = devm_iio_device_register(&client->dev, iio);

From: Rafael Mendonca rafaelmendsr@gmail.com

commit d591b32e519603524a35b172156db71df9116902 upstream.

If DbC is already in use, then the allocated memory for the xhci_dbc struct doesn't get freed before returning NULL, which leads to a memleak.

Fixes: 534675942e90 ("xhci: dbc: refactor xhci_dbc_init()") Cc: stable@vger.kernel.org Signed-off-by: Rafael Mendonca rafaelmendsr@gmail.com Signed-off-by: Mathias Nyman mathias.nyman@linux.intel.com Link: https://lore.kernel.org/r/20220921123450.671459-3-mathias.nyman@linux.intel.... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/host/xhci-dbgcap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/usb/host/xhci-dbgcap.c +++ b/drivers/usb/host/xhci-dbgcap.c @@ -988,7 +988,7 @@ xhci_alloc_dbc(struct device *dev, void dbc->driver = driver;

if (readl(&dbc->regs->control) & DBC_CTRL_DBC_ENABLE) - return NULL; + goto err;

INIT_DELAYED_WORK(&dbc->event_work, xhci_dbc_handle_events); spin_lock_init(&dbc->lock);

From: Anssi Hannula anssi.hannula@bitwise.fi

commit cd7f30e174d09a02ca2afa5ef093fb0f0352e0d8 upstream.

flush_comp is initialized when CMD_FLUSH_QUEUE is sent to the device and completed when the device sends CMD_FLUSH_QUEUE_RESP.

This causes completion of uninitialized completion if the device sends CMD_FLUSH_QUEUE_RESP before CMD_FLUSH_QUEUE is ever sent (e.g. as a response to a flush by a previously bound driver, or a misbehaving device).

Fix that by initializing flush_comp in kvaser_usb_init_one() like the other completions.

This issue is only triggerable after RX URBs have been set up, i.e. the interface has been opened at least once.

Cc: stable@vger.kernel.org Fixes: aec5fb2268b7 ("can: kvaser_usb: Add support for Kvaser USB hydra family") Tested-by: Jimmy Assarsson extja@kvaser.com Signed-off-by: Anssi Hannula anssi.hannula@bitwise.fi Signed-off-by: Jimmy Assarsson extja@kvaser.com Link: https://lore.kernel.org/all/20221010150829.199676-3-extja@kvaser.com Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c | 1 + drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -717,6 +717,7 @@ static int kvaser_usb_init_one(struct kv init_usb_anchor(&priv->tx_submitted); init_completion(&priv->start_comp); init_completion(&priv->stop_comp); + init_completion(&priv->flush_comp); priv->can.ctrlmode_supported = 0;

priv->dev = dev; --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c @@ -1914,7 +1914,7 @@ static int kvaser_usb_hydra_flush_queue( { int err;

- init_completion(&priv->flush_comp); + reinit_completion(&priv->flush_comp);

err = kvaser_usb_hydra_send_simple_cmd(priv->dev, CMD_FLUSH_QUEUE, priv->channel);

From: Anssi Hannula anssi.hannula@bitwise.fi

commit 455561fb618fde40558776b5b8435f9420f335db upstream.

The TX queue seems to be implicitly flushed by the hardware during bus-off or bus-off recovery, but the driver does not reset the TX bookkeeping.

Despite not resetting TX bookkeeping the driver still re-enables TX queue unconditionally, leading to "cannot find free context" / NETDEV_TX_BUSY errors if the TX queue was full at bus-off time.

Fix that by resetting TX bookkeeping on CAN restart.

Tested with 0bfd:0124 Kvaser Mini PCI Express 2xHS FW 4.18.778.

Cc: stable@vger.kernel.org Fixes: 080f40a6fa28 ("can: kvaser_usb: Add support for Kvaser CAN/USB devices") Tested-by: Jimmy Assarsson extja@kvaser.com Signed-off-by: Anssi Hannula anssi.hannula@bitwise.fi Signed-off-by: Jimmy Assarsson extja@kvaser.com Link: https://lore.kernel.org/all/20221010150829.199676-4-extja@kvaser.com Signed-off-by: Marc Kleine-Budde mkl@pengutronix.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/can/usb/kvaser_usb/kvaser_usb.h | 2 ++ drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c | 2 +- drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 2 ++ 3 files changed, 5 insertions(+), 1 deletion(-)

--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h @@ -178,6 +178,8 @@ struct kvaser_usb_dev_cfg { extern const struct kvaser_usb_dev_ops kvaser_usb_hydra_dev_ops; extern const struct kvaser_usb_dev_ops kvaser_usb_leaf_dev_ops;

+void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv); + int kvaser_usb_recv_cmd(const struct kvaser_usb *dev, void *cmd, int len, int *actual_len);

--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -480,7 +480,7 @@ static void kvaser_usb_reset_tx_urb_cont /* This method might sleep. Do not call it in the atomic context * of URB completions. */ -static void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv) +void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv) { usb_kill_anchored_urbs(&priv->tx_submitted); kvaser_usb_reset_tx_urb_contexts(priv); --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c @@ -1430,6 +1430,8 @@ static int kvaser_usb_leaf_set_mode(stru

switch (mode) { case CAN_MODE_START: + kvaser_usb_unlink_tx_urbs(priv); + err = kvaser_usb_leaf_simple_cmd_async(priv, CMD_START_CHIP); if (err) return err;

From: Wenchao Chen wenchao.chen@unisoc.com

commit 6e141772e6465f937458b35ddcfd0a981b6f5280 upstream.

The Spreadtrum controller supports 100KHz minimal clock rate, which means that the current value 400KHz is wrong.

Unfortunately this has also lead to fail to initialize some cards, which are allowed to require 100KHz to work. So, let's fix the problem by changing the minimal supported clock rate to 100KHz.

Signed-off-by: Wenchao Chen wenchao.chen@unisoc.com Acked-by: Adrian Hunter adrian.hunter@intel.com Fixes: fb8bd90f83c4 ("mmc: sdhci-sprd: Add Spreadtrum's initial host controller") Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20221011104935.10980-1-wenchao.chen666@gmail.com [Ulf: Clarified to commit-message] Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/mmc/host/sdhci-sprd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/mmc/host/sdhci-sprd.c +++ b/drivers/mmc/host/sdhci-sprd.c @@ -296,7 +296,7 @@ static unsigned int sdhci_sprd_get_max_c

static unsigned int sdhci_sprd_get_min_clock(struct sdhci_host *host) { - return 400000; + return 100000; }

static void sdhci_sprd_set_uhs_signaling(struct sdhci_host *host,

From: Alexander Aring aahringo@redhat.com

commit eef6ec9bf390e836a6c4029f3620fe49528aa1fe upstream.

This patch fixes a race by using ls_cb_mutex around the bit operations and conditional code blocks for LSFL_CB_DELAY.

The function dlm_callback_stop() expects to stop all callbacks and flush all currently queued onces. The set_bit() is not enough because there can still be queue_work() after the workqueue was flushed. To avoid queue_work() after set_bit(), surround both by ls_cb_mutex.

Cc: stable@vger.kernel.org Signed-off-by: Alexander Aring aahringo@redhat.com Signed-off-by: David Teigland teigland@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/dlm/ast.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/fs/dlm/ast.c +++ b/fs/dlm/ast.c @@ -198,13 +198,13 @@ void dlm_add_cb(struct dlm_lkb *lkb, uin if (!prev_seq) { kref_get(&lkb->lkb_ref);

+ mutex_lock(&ls->ls_cb_mutex); if (test_bit(LSFL_CB_DELAY, &ls->ls_flags)) { - mutex_lock(&ls->ls_cb_mutex); list_add(&lkb->lkb_cb_list, &ls->ls_cb_delay); - mutex_unlock(&ls->ls_cb_mutex); } else { queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work); } + mutex_unlock(&ls->ls_cb_mutex); } out: mutex_unlock(&lkb->lkb_cb_mutex); @@ -284,7 +284,9 @@ void dlm_callback_stop(struct dlm_ls *ls

void dlm_callback_suspend(struct dlm_ls *ls) { + mutex_lock(&ls->ls_cb_mutex); set_bit(LSFL_CB_DELAY, &ls->ls_flags); + mutex_unlock(&ls->ls_cb_mutex);

if (ls->ls_callback_wq) flush_workqueue(ls->ls_callback_wq);

From: Andri Yngvason andri@yngvason.is

commit be6e2b5734a425941fcdcdbd2a9337be498ce2cf upstream.

This fixes broken atomic checks which cause a race between the release-timer and processing of hid input.

I noticed that contacts were sometimes sticking, even with the "sticky fingers" quirk enabled. This fixes that problem.

Cc: stable@vger.kernel.org Fixes: 9609827458c3 ("HID: multitouch: optimize the sticky fingers timer") Signed-off-by: Andri Yngvason andri@yngvason.is Signed-off-by: Benjamin Tissoires benjamin.tissoires@redhat.com Link: https://lore.kernel.org/r/20220907150159.2285460-1-andri@yngvason.is Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/hid/hid-multitouch.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)

--- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1186,7 +1186,7 @@ static void mt_touch_report(struct hid_d int contact_count = -1;

/* sticky fingers release in progress, abort */ - if (test_and_set_bit(MT_IO_FLAGS_RUNNING, &td->mt_io_flags)) + if (test_and_set_bit_lock(MT_IO_FLAGS_RUNNING, &td->mt_io_flags)) return;

scantime = *app->scantime; @@ -1267,7 +1267,7 @@ static void mt_touch_report(struct hid_d del_timer(&td->release_timer); }

- clear_bit(MT_IO_FLAGS_RUNNING, &td->mt_io_flags); + clear_bit_unlock(MT_IO_FLAGS_RUNNING, &td->mt_io_flags); }

static int mt_touch_input_configured(struct hid_device *hdev, @@ -1702,11 +1702,11 @@ static void mt_expired_timeout(struct ti * An input report came in just before we release the sticky fingers, * it will take care of the sticky fingers. */ - if (test_and_set_bit(MT_IO_FLAGS_RUNNING, &td->mt_io_flags)) + if (test_and_set_bit_lock(MT_IO_FLAGS_RUNNING, &td->mt_io_flags)) return; if (test_bit(MT_IO_FLAGS_PENDING_SLOTS, &td->mt_io_flags)) mt_release_contacts(hdev); - clear_bit(MT_IO_FLAGS_RUNNING, &td->mt_io_flags); + clear_bit_unlock(MT_IO_FLAGS_RUNNING, &td->mt_io_flags); }

static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id)

From: Patryk Duda pdk@semihalf.com

commit f74c7557ed0d321947e8bb4e9d47c1013f8b2227 upstream.

Some EC based devices (e.g. Fingerpint MCU) can jump to RO part of the firmware (intentionally or due to device reboot). The RO part doesn't change during the device lifecycle, so it won't support newer version of EC_CMD_GET_NEXT_EVENT command.

Function cros_ec_query_all() is responsible for finding maximum supported MKBP event version. It's usually called when the device is running RW part of the firmware, so the command version can be potentially higher than version supported by the RO.

The problem was fixed by updating maximum supported version when the device returns EC_RES_INVALID_VERSION (mapped to -ENOPROTOOPT). That way the kernel will use highest common version supported by RO and RW.

Fixes: 3300fdd630d4 ("platform/chrome: cros_ec: handle MKBP more events flag") Cc: stable@vger.kernel.org # 5.10+ Reviewed-by: Guenter Roeck groeck@chromium.org Signed-off-by: Patryk Duda pdk@semihalf.com Signed-off-by: Tzung-Bi Shih tzungbi@kernel.org Link: https://lore.kernel.org/r/20220802154128.21175-1-pdk@semihalf.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/platform/chrome/cros_ec_proto.c | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+)

--- a/drivers/platform/chrome/cros_ec_proto.c +++ b/drivers/platform/chrome/cros_ec_proto.c @@ -748,6 +748,7 @@ int cros_ec_get_next_event(struct cros_e u8 event_type; u32 host_event; int ret; + u32 ver_mask;

/* * Default value for wake_event. @@ -769,6 +770,37 @@ int cros_ec_get_next_event(struct cros_e return get_keyboard_state_event(ec_dev);

ret = get_next_event(ec_dev); + /* + * -ENOPROTOOPT is returned when EC returns EC_RES_INVALID_VERSION. + * This can occur when EC based device (e.g. Fingerprint MCU) jumps to + * the RO image which doesn't support newer version of the command. In + * this case we will attempt to update maximum supported version of the + * EC_CMD_GET_NEXT_EVENT. + */ + if (ret == -ENOPROTOOPT) { + dev_dbg(ec_dev->dev, + "GET_NEXT_EVENT returned invalid version error.\n"); + ret = cros_ec_get_host_command_version_mask(ec_dev, + EC_CMD_GET_NEXT_EVENT, + &ver_mask); + if (ret < 0 || ver_mask == 0) + /* + * Do not change the MKBP supported version if we can't + * obtain supported version correctly. Please note that + * calling EC_CMD_GET_NEXT_EVENT returned + * EC_RES_INVALID_VERSION which means that the command + * is present. + */ + return -ENOPROTOOPT; + + ec_dev->mkbp_event_supported = fls(ver_mask); + dev_dbg(ec_dev->dev, "MKBP support version changed to %u\n", + ec_dev->mkbp_event_supported - 1); + + /* Try to get next event with new MKBP support version set. */ + ret = get_next_event(ec_dev); + } + if (ret <= 0) return ret;

From: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org

commit e96bca7eaa5747633ec638b065630ff83728982a upstream.

Slimbus streams are first prepared and then enabled, so the cleanup path should reverse it. The unprepare sets stream->num_ports to 0 and frees the stream->ports. Calling disable after unprepare was not really effective (channels was not deactivated) and could lead to further issues due to making transfers on unprepared stream.

Fixes: a61f3b4f476e ("ASoC: wcd934x: add support to wcd9340/wcd9341 codec") Cc: stable@vger.kernel.org Signed-off-by: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org Reviewed-by: Srinivas Kandagatla srinivas.kandagatla@linaro.org Link: https://lore.kernel.org/r/20220921145354.1683791-2-krzysztof.kozlowski@linar... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/soc/codecs/wcd934x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/sound/soc/codecs/wcd934x.c +++ b/sound/soc/codecs/wcd934x.c @@ -1913,8 +1913,8 @@ static int wcd934x_trigger(struct snd_pc case SNDRV_PCM_TRIGGER_STOP: case SNDRV_PCM_TRIGGER_SUSPEND: case SNDRV_PCM_TRIGGER_PAUSE_PUSH: - slim_stream_unprepare(dai_data->sruntime); slim_stream_disable(dai_data->sruntime); + slim_stream_unprepare(dai_data->sruntime); break; default: break;

From: Mika Westerberg mika.westerberg@linux.intel.com

commit ff7cd07f306406493f7b78890475e85b6d0811ed upstream.

If the other host starts sending packets early on it is possible that we are still in the middle of populating the initial Rx ring packets to the ring. This causes the tbnet_poll() to mess over the queue and causes list corruption. This happens specifically when connected with macOS as it seems start sending various IP discovery packets as soon as its side of the paths are configured.

To prevent this we move the DMA path enabling to happen after we have primed the Rx ring. This makes sure no incoming packets can arrive before we are ready to handle them.

Fixes: e69b6c02b4c3 ("net: Add support for networking over Thunderbolt cable") Cc: stable@vger.kernel.org Signed-off-by: Mika Westerberg mika.westerberg@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/thunderbolt.c | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-)

--- a/drivers/net/thunderbolt.c +++ b/drivers/net/thunderbolt.c @@ -612,18 +612,13 @@ static void tbnet_connected_work(struct return; }

- /* Both logins successful so enable the high-speed DMA paths and - * start the network device queue. + /* Both logins successful so enable the rings, high-speed DMA + * paths and start the network device queue. + * + * Note we enable the DMA paths last to make sure we have primed + * the Rx ring before any incoming packets are allowed to + * arrive. */ - ret = tb_xdomain_enable_paths(net->xd, net->local_transmit_path, - net->rx_ring.ring->hop, - net->remote_transmit_path, - net->tx_ring.ring->hop); - if (ret) { - netdev_err(net->dev, "failed to enable DMA paths\n"); - return; - } - tb_ring_start(net->tx_ring.ring); tb_ring_start(net->rx_ring.ring);

@@ -635,10 +630,21 @@ static void tbnet_connected_work(struct if (ret) goto err_free_rx_buffers;

+ ret = tb_xdomain_enable_paths(net->xd, net->local_transmit_path, + net->rx_ring.ring->hop, + net->remote_transmit_path, + net->tx_ring.ring->hop); + if (ret) { + netdev_err(net->dev, "failed to enable DMA paths\n"); + goto err_free_tx_buffers; + } + netif_carrier_on(net->dev); netif_start_queue(net->dev); return;

+err_free_tx_buffers: + tbnet_free_buffers(&net->tx_ring); err_free_rx_buffers: tbnet_free_buffers(&net->rx_ring); err_stop_rings:

From: Conor Dooley conor.dooley@microchip.com

commit 456797da792fa7cbf6698febf275fe9b36691f78 upstream.

arm64's method of defining a default cpu topology requires only minimal changes to apply to RISC-V also. The current arm64 implementation exits early in a uniprocessor configuration by reading MPIDR & claiming that uniprocessor can rely on the default values.

This is appears to be a hangover from prior to '3102bc0e6ac7 ("arm64: topology: Stop using MPIDR for topology information")', because the current code just assigns default values for multiprocessor systems.

With the MPIDR references removed, store_cpu_topolgy() can be moved to the common arch_topology code.

Reviewed-by: Sudeep Holla sudeep.holla@arm.com Acked-by: Catalin Marinas catalin.marinas@arm.com Reviewed-by: Atish Patra atishp@rivosinc.com Signed-off-by: Conor Dooley conor.dooley@microchip.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm64/kernel/topology.c | 40 ---------------------------------------- drivers/base/arch_topology.c | 19 +++++++++++++++++++ 2 files changed, 19 insertions(+), 40 deletions(-)

--- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -22,46 +22,6 @@ #include <asm/cputype.h> #include <asm/topology.h>

-void store_cpu_topology(unsigned int cpuid) -{ - struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; - u64 mpidr; - - if (cpuid_topo->package_id != -1) - goto topology_populated; - - mpidr = read_cpuid_mpidr(); - - /* Uniprocessor systems can rely on default topology values */ - if (mpidr & MPIDR_UP_BITMASK) - return; - - /* - * This would be the place to create cpu topology based on MPIDR. - * - * However, it cannot be trusted to depict the actual topology; some - * pieces of the architecture enforce an artificial cap on Aff0 values - * (e.g. GICv3's ICC_SGI1R_EL1 limits it to 15), leading to an - * artificial cycling of Aff1, Aff2 and Aff3 values. IOW, these end up - * having absolutely no relationship to the actual underlying system - * topology, and cannot be reasonably used as core / package ID. - * - * If the MT bit is set, Aff0 *could* be used to define a thread ID, but - * we still wouldn't be able to obtain a sane core ID. This means we - * need to entirely ignore MPIDR for any topology deduction. - */ - cpuid_topo->thread_id = -1; - cpuid_topo->core_id = cpuid; - cpuid_topo->package_id = cpu_to_node(cpuid); - - pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n", - cpuid, cpuid_topo->package_id, cpuid_topo->core_id, - cpuid_topo->thread_id, mpidr); - -topology_populated: - update_siblings_masks(cpuid); -} - #ifdef CONFIG_ACPI static bool __init acpi_cpu_is_threaded(int cpu) { --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -690,4 +690,23 @@ void __init init_cpu_topology(void) else if (of_have_populated_dt() && parse_dt_topology()) reset_cpu_topology(); } + +void store_cpu_topology(unsigned int cpuid) +{ + struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; + + if (cpuid_topo->package_id != -1) + goto topology_populated; + + cpuid_topo->thread_id = -1; + cpuid_topo->core_id = cpuid; + cpuid_topo->package_id = cpu_to_node(cpuid); + + pr_debug("CPU%u: package %d core %d thread %d\n", + cpuid, cpuid_topo->package_id, cpuid_topo->core_id, + cpuid_topo->thread_id); + +topology_populated: + update_siblings_masks(cpuid); +} #endif

From: Maciej W. Rozycki macro@orcam.me.uk

commit 9cc205e3c17d5716da7ebb7fa0c985555e95d009 upstream.

Fix port I/O string accessors such as `insb', `outsb', etc. which use the physical PCI port I/O address rather than the corresponding memory mapping to get at the requested location, which in turn breaks at least accesses made by our parport driver to a PCIe parallel port such as:

PCI parallel port detected: 1415:c118, I/O at 0x1000(0x1008), IRQ 20 parport0: PC-style at 0x1000 (0x1008), irq 20, using FIFO [PCSPP,TRISTATE,COMPAT,EPP,ECP]

causing a memory access fault:

Unable to handle kernel access to user memory without uaccess routines at virtual address 0000000000001008 Oops [#1] Modules linked in: CPU: 1 PID: 350 Comm: cat Not tainted 6.0.0-rc2-00283-g10d4879f9ef0-dirty #23 Hardware name: SiFive HiFive Unmatched A00 (DT) epc : parport_pc_fifo_write_block_pio+0x266/0x416 ra : parport_pc_fifo_write_block_pio+0xb4/0x416 epc : ffffffff80542c3e ra : ffffffff80542a8c sp : ffffffd88899fc60 gp : ffffffff80fa2700 tp : ffffffd882b1e900 t0 : ffffffd883d0b000 t1 : ffffffffff000002 t2 : 4646393043330a38 s0 : ffffffd88899fcf0 s1 : 0000000000001000 a0 : 0000000000000010 a1 : 0000000000000000 a2 : ffffffd883d0a010 a3 : 0000000000000023 a4 : 00000000ffff8fbb a5 : ffffffd883d0a001 a6 : 0000000100000000 a7 : ffffffc800000000 s2 : ffffffffff000002 s3 : ffffffff80d28880 s4 : ffffffff80fa1f50 s5 : 0000000000001008 s6 : 0000000000000008 s7 : ffffffd883d0a000 s8 : 0004000000000000 s9 : ffffffff80dc1d80 s10: ffffffd8807e4000 s11: 0000000000000000 t3 : 00000000000000ff t4 : 393044410a303930 t5 : 0000000000001000 t6 : 0000000000040000 status: 0000000200000120 badaddr: 0000000000001008 cause: 000000000000000f [<ffffffff80543212>] parport_pc_compat_write_block_pio+0xfe/0x200 [<ffffffff8053bbc0>] parport_write+0x46/0xf8 [<ffffffff8050530e>] lp_write+0x158/0x2d2 [<ffffffff80185716>] vfs_write+0x8e/0x2c2 [<ffffffff80185a74>] ksys_write+0x52/0xc2 [<ffffffff80185af2>] sys_write+0xe/0x16 [<ffffffff80003770>] ret_from_syscall+0x0/0x2 ---[ end trace 0000000000000000 ]---

For simplicity address the problem by adding PCI_IOBASE to the physical address requested in the respective wrapper macros only, observing that the raw accessors such as `__insb', `__outsb', etc. are not supposed to be used other than by said macros. Remove the cast to `long' that is no longer needed on `addr' now that it is used as an offset from PCI_IOBASE and add parentheses around `addr' needed for predictable evaluation in macro expansion. No need to make said adjustments in separate changes given that current code is gravely broken and does not ever work.

Signed-off-by: Maciej W. Rozycki macro@orcam.me.uk Fixes: fab957c11efe2 ("RISC-V: Atomic and Locking Code") Cc: stable@vger.kernel.org # v4.15+ Reviewed-by: Arnd Bergmann arnd@arndb.de Link: https://lore.kernel.org/r/alpine.DEB.2.21.2209220223080.29493@angie.orcam.me... Signed-off-by: Palmer Dabbelt palmer@rivosinc.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/riscv/include/asm/io.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)

--- a/arch/riscv/include/asm/io.h +++ b/arch/riscv/include/asm/io.h @@ -101,9 +101,9 @@ __io_reads_ins(reads, u32, l, __io_br(), __io_reads_ins(ins, u8, b, __io_pbr(), __io_par(addr)) __io_reads_ins(ins, u16, w, __io_pbr(), __io_par(addr)) __io_reads_ins(ins, u32, l, __io_pbr(), __io_par(addr)) -#define insb(addr, buffer, count) __insb((void __iomem *)(long)addr, buffer, count) -#define insw(addr, buffer, count) __insw((void __iomem *)(long)addr, buffer, count) -#define insl(addr, buffer, count) __insl((void __iomem *)(long)addr, buffer, count) +#define insb(addr, buffer, count) __insb(PCI_IOBASE + (addr), buffer, count) +#define insw(addr, buffer, count) __insw(PCI_IOBASE + (addr), buffer, count) +#define insl(addr, buffer, count) __insl(PCI_IOBASE + (addr), buffer, count)

__io_writes_outs(writes, u8, b, __io_bw(), __io_aw()) __io_writes_outs(writes, u16, w, __io_bw(), __io_aw()) @@ -115,22 +115,22 @@ __io_writes_outs(writes, u32, l, __io_bw __io_writes_outs(outs, u8, b, __io_pbw(), __io_paw()) __io_writes_outs(outs, u16, w, __io_pbw(), __io_paw()) __io_writes_outs(outs, u32, l, __io_pbw(), __io_paw()) -#define outsb(addr, buffer, count) __outsb((void __iomem *)(long)addr, buffer, count) -#define outsw(addr, buffer, count) __outsw((void __iomem *)(long)addr, buffer, count) -#define outsl(addr, buffer, count) __outsl((void __iomem *)(long)addr, buffer, count) +#define outsb(addr, buffer, count) __outsb(PCI_IOBASE + (addr), buffer, count) +#define outsw(addr, buffer, count) __outsw(PCI_IOBASE + (addr), buffer, count) +#define outsl(addr, buffer, count) __outsl(PCI_IOBASE + (addr), buffer, count)

#ifdef CONFIG_64BIT __io_reads_ins(reads, u64, q, __io_br(), __io_ar(addr)) #define readsq(addr, buffer, count) __readsq(addr, buffer, count)

__io_reads_ins(ins, u64, q, __io_pbr(), __io_par(addr)) -#define insq(addr, buffer, count) __insq((void __iomem *)addr, buffer, count) +#define insq(addr, buffer, count) __insq(PCI_IOBASE + (addr), buffer, count)

__io_writes_outs(writes, u64, q, __io_bw(), __io_aw()) #define writesq(addr, buffer, count) __writesq(addr, buffer, count)

__io_writes_outs(outs, u64, q, __io_pbr(), __io_paw()) -#define outsq(addr, buffer, count) __outsq((void __iomem *)addr, buffer, count) +#define outsq(addr, buffer, count) __outsq(PCI_IOBASE + (addr), buffer, count) #endif

#include <asm-generic/io.h>

From: Andrew Bresticker abrestic@rivosinc.com

commit 9e2e6042a7ec6504fe8e366717afa2f40cf16488 upstream.

Commit 2139619bcad7 ("riscv: mmap with PROT_WRITE but no PROT_READ is invalid") made mmap() return EINVAL if PROT_WRITE was set wihtout PROT_READ with the justification that a write-only PTE is considered a reserved PTE permission bit pattern in the privileged spec. This check is unnecessary since we let VM_WRITE imply VM_READ on RISC-V, and it is inconsistent with other architectures that don't support write-only PTEs, creating a potential software portability issue. Just remove the check altogether and let PROT_WRITE imply PROT_READ as is the case on other architectures.

Note that this also allows PROT_WRITE|PROT_EXEC mappings which were disallowed prior to the aforementioned commit; PROT_READ is implied in such mappings as well.

Fixes: 2139619bcad7 ("riscv: mmap with PROT_WRITE but no PROT_READ is invalid") Reviewed-by: Atish Patra atishp@rivosinc.com Signed-off-by: Andrew Bresticker abrestic@rivosinc.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220915193702.2201018-3-abrestic@rivosinc.com/ Signed-off-by: Palmer Dabbelt palmer@rivosinc.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/riscv/kernel/sys_riscv.c | 3 --- 1 file changed, 3 deletions(-)

--- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -18,9 +18,6 @@ static long riscv_sys_mmap(unsigned long if (unlikely(offset & (~PAGE_MASK >> page_shift_offset))) return -EINVAL;

- if (unlikely((prot & PROT_WRITE) && !(prot & PROT_READ))) - return -EINVAL; - return ksys_mmap_pgoff(addr, len, prot, flags, fd, offset >> (PAGE_SHIFT - page_shift_offset)); }

From: Wenting Zhang zephray@outlook.com

commit 10f6913c548b32ecb73801a16b120e761c6957ea upstream.

When CONFIG_CMDLINE_FORCE is enabled, cmdline provided by CONFIG_CMDLINE are always used. This allows CONFIG_CMDLINE to be used regardless of the result of device tree scanning.

This especially fixes the case where a device tree without the chosen node is supplied to the kernel. In such cases, early_init_dt_scan would return true. But inside early_init_dt_scan_chosen, the cmdline won't be updated as there is no chosen node in the device tree. As a result, CONFIG_CMDLINE is not copied into boot_command_line even if CONFIG_CMDLINE_FORCE is enabled. This commit allows properly update boot_command_line in this situation.

Fixes: 8fd6e05c7463 ("arch: riscv: support kernel command line forcing when no DTB passed") Signed-off-by: Wenting Zhang zephray@outlook.com Reviewed-by: Björn Töpel bjorn@kernel.org Reviewed-by: Conor Dooley conor.dooley@microchip.com Link: https://lore.kernel.org/r/PSBPR04MB399135DFC54928AB958D0638B1829@PSBPR04MB39... Cc: stable@vger.kernel.org Signed-off-by: Palmer Dabbelt palmer@rivosinc.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/riscv/kernel/setup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -260,10 +260,10 @@ static void __init parse_dtb(void) pr_info("Machine model: %s\n", name); dump_stack_set_arch_desc("%s (DT)", name); } - return; + } else { + pr_err("No DTB passed to the kernel\n"); }

- pr_err("No DTB passed to the kernel\n"); #ifdef CONFIG_CMDLINE_FORCE strscpy(boot_command_line, CONFIG_CMDLINE, COMMAND_LINE_SIZE); pr_info("Forcing kernel command line to: %s\n", boot_command_line);

From: Huacai Chen chenhuacai@loongson.cn

commit 16c546e148fa6d14a019431436a6f7b4087dbccd upstream.

When CONFIG_CPUMASK_OFFSTACK and CONFIG_DEBUG_PER_CPU_MAPS is selected, cpu_max_bits_warn() generates a runtime warning similar as below while we show /proc/cpuinfo. Fix this by using nr_cpu_ids (the runtime limit) instead of NR_CPUS to iterate CPUs.

[ 3.052463] ------------[ cut here ]------------ [ 3.059679] WARNING: CPU: 3 PID: 1 at include/linux/cpumask.h:108 show_cpuinfo+0x5e8/0x5f0 [ 3.070072] Modules linked in: efivarfs autofs4 [ 3.076257] CPU: 0 PID: 1 Comm: systemd Not tainted 5.19-rc5+ #1052 [ 3.099465] Stack : 9000000100157b08 9000000000f18530 9000000000cf846c 9000000100154000 [ 3.109127] 9000000100157a50 0000000000000000 9000000100157a58 9000000000ef7430 [ 3.118774] 90000001001578e8 0000000000000040 0000000000000020 ffffffffffffffff [ 3.128412] 0000000000aaaaaa 1ab25f00eec96a37 900000010021de80 900000000101c890 [ 3.138056] 0000000000000000 0000000000000000 0000000000000000 0000000000aaaaaa [ 3.147711] ffff8000339dc220 0000000000000001 0000000006ab4000 0000000000000000 [ 3.157364] 900000000101c998 0000000000000004 9000000000ef7430 0000000000000000 [ 3.167012] 0000000000000009 000000000000006c 0000000000000000 0000000000000000 [ 3.176641] 9000000000d3de08 9000000001639390 90000000002086d8 00007ffff0080286 [ 3.186260] 00000000000000b0 0000000000000004 0000000000000000 0000000000071c1c [ 3.195868] ... [ 3.199917] Call Trace: [ 3.203941] [<90000000002086d8>] show_stack+0x38/0x14c [ 3.210666] [<9000000000cf846c>] dump_stack_lvl+0x60/0x88 [ 3.217625] [<900000000023d268>] __warn+0xd0/0x100 [ 3.223958] [<9000000000cf3c90>] warn_slowpath_fmt+0x7c/0xcc [ 3.231150] [<9000000000210220>] show_cpuinfo+0x5e8/0x5f0 [ 3.238080] [<90000000004f578c>] seq_read_iter+0x354/0x4b4 [ 3.245098] [<90000000004c2e90>] new_sync_read+0x17c/0x1c4 [ 3.252114] [<90000000004c5174>] vfs_read+0x138/0x1d0 [ 3.258694] [<90000000004c55f8>] ksys_read+0x70/0x100 [ 3.265265] [<9000000000cfde9c>] do_syscall+0x7c/0x94 [ 3.271820] [<9000000000202fe4>] handle_syscall+0xc4/0x160 [ 3.281824] ---[ end trace 8b484262b4b8c24c ]---

Cc: stable@vger.kernel.org Signed-off-by: Huacai Chen chenhuacai@loongson.cn Signed-off-by: Richard Weinberger richard@nod.at Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/um/kernel/um_arch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -94,7 +94,7 @@ static int show_cpuinfo(struct seq_file

static void *c_start(struct seq_file *m, loff_t *pos) { - return *pos < NR_CPUS ? cpu_data + *pos : NULL; + return *pos < nr_cpu_ids ? cpu_data + *pos : NULL; }

static void *c_next(struct seq_file *m, void *v, loff_t *pos)

From: Sagi Grimberg sagi@grimberg.me

commit 72e3b8883a36e80ebfa41015c7b6926ce31ace05 upstream.

When we revalidate paths as part of ns size change (as of commit e7d65803e2bb), it is possible that during the path revalidation, the only paths that is IO capable (i.e. optimized/non-optimized) are the ones that ns resize was not yet informed to the host, which will cause inflight requests to be requeued (as we have available paths but none are IO capable). These requests on the requeue list are waiting for someone to resubmit them at some point.

The IO capable paths will eventually notify the ns resize change to the host, but there is nothing that will kick the requeue list to resubmit the queued requests.

Fix this by always kicking the requeue list, and if no IO capable path exists, these requests will be queued again.

A typical log that indicates that IOs are requeued: -- nvme nvme1: creating 4 I/O queues. nvme nvme1: new ctrl: "testnqn1" nvme nvme2: creating 4 I/O queues. nvme nvme2: mapped 4/0/0 default/read/poll queues. nvme nvme2: new ctrl: NQN "testnqn1", addr 127.0.0.1:8009 nvme nvme1: rescanning namespaces. nvme1n1: detected capacity change from 2097152 to 4194304 block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O block nvme1n1: no usable path - requeuing I/O nvme nvme2: rescanning namespaces. --

Reported-by: Yogev Cohen yogev@lightbitslabs.com Fixes: e7d65803e2bb ("nvme-multipath: revalidate paths during rescan") Signed-off-by: Sagi Grimberg sagi@grimberg.me Cc: stable@vger.kernel.org # v5.15+ Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/nvme/host/multipath.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -159,6 +159,7 @@ void nvme_mpath_revalidate_paths(struct

for_each_node(node) rcu_assign_pointer(head->current_path[node], NULL); + kblockd_schedule_work(&head->requeue_work); }

static bool nvme_path_is_disabled(struct nvme_ns *ns)

From: Hamza Mahfooz hamza.mahfooz@amd.com

commit 17d819e2828cacca2e4c909044eb9798ed379cd2 upstream.

This reverts commit 66f99628eb24409cb8feb5061f78283c8b65f820.

Unfortunately, that commit causes performance regressions on non-PSR setups. So, just revert it until FB_DAMAGE_CLIPS support can be added.

Cc: stable@vger.kernel.org Link: https://gitlab.freedesktop.org/drm/amd/-/issues/2189 Link: https://bugzilla.kernel.org/show_bug.cgi?id=216554 Fixes: 66f99628eb2440 ("drm/amdgpu: use dirty framebuffer helper") Fixes: abbc7a3dafb91b ("drm/amdgpu: don't register a dirty callback for non-atomic") Signed-off-by: Hamza Mahfooz hamza.mahfooz@amd.com Acked-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-)

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -35,8 +35,6 @@ #include <linux/pci.h> #include <linux/pm_runtime.h> #include <drm/drm_crtc_helper.h> -#include <drm/drm_damage_helper.h> -#include <drm/drm_drv.h> #include <drm/drm_edid.h> #include <drm/drm_gem_framebuffer_helper.h> #include <drm/drm_fb_helper.h> @@ -494,12 +492,6 @@ static const struct drm_framebuffer_func .create_handle = drm_gem_fb_create_handle, };

-static const struct drm_framebuffer_funcs amdgpu_fb_funcs_atomic = { - .destroy = drm_gem_fb_destroy, - .create_handle = drm_gem_fb_create_handle, - .dirty = drm_atomic_helper_dirtyfb, -}; - uint32_t amdgpu_display_supported_domains(struct amdgpu_device *adev, uint64_t bo_flags) { @@ -1117,10 +1109,8 @@ int amdgpu_display_gem_fb_verify_and_ini if (ret) goto err;

- if (drm_drv_uses_atomic_modeset(dev)) - ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs_atomic); - else - ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs); + ret = drm_framebuffer_init(dev, &rfb->base, &amdgpu_fb_funcs); + if (ret) goto err;

From: Dmitry Osipenko dmitry.osipenko@collabora.com

commit e473216b42aa1fd9fc6b94b608b42c210c655908 upstream.

Transferred 2D BO always must be a shmem BO. Add check for that to prevent NULL dereference if userspace passes a VRAM BO.

Cc: stable@vger.kernel.org Reviewed-by: Emil Velikov emil.l.velikov@gmail.com Signed-off-by: Dmitry Osipenko dmitry.osipenko@collabora.com Link: http://patchwork.freedesktop.org/patch/msgid/20220630200726.1884320-3-dmitry... Signed-off-by: Gerd Hoffmann kraxel@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/virtio/virtgpu_vq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -604,7 +604,7 @@ void virtio_gpu_cmd_transfer_to_host_2d( bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); struct virtio_gpu_object_shmem *shmem = to_virtio_gpu_shmem(bo);

- if (use_dma_api) + if (virtio_gpu_is_shmem(bo) && use_dma_api) dma_sync_sgtable_for_device(vgdev->vdev->dev.parent, shmem->pages, DMA_TO_DEVICE);

From: Dmitry Osipenko dmitry.osipenko@collabora.com

commit 4656b3a26a9e9fe5f04bfd2ab55b066266ba7f4d upstream.

Make virtio_gpu_plane_cleanup_fb() to clean the state which DRM core wants to clean up and not the current plane's state. Normally the older atomic state is cleaned up, but the newer state could also be cleaned up in case of aborted commits.

Cc: stable@vger.kernel.org Signed-off-by: Dmitry Osipenko dmitry.osipenko@collabora.com Link: http://patchwork.freedesktop.org/patch/msgid/20220630200726.1884320-6-dmitry... Signed-off-by: Gerd Hoffmann kraxel@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/virtio/virtgpu_plane.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/drivers/gpu/drm/virtio/virtgpu_plane.c +++ b/drivers/gpu/drm/virtio/virtgpu_plane.c @@ -265,14 +265,14 @@ static int virtio_gpu_plane_prepare_fb(s }

static void virtio_gpu_plane_cleanup_fb(struct drm_plane *plane, - struct drm_plane_state *old_state) + struct drm_plane_state *state) { struct virtio_gpu_framebuffer *vgfb;

- if (!plane->state->fb) + if (!state->fb) return;

- vgfb = to_virtio_gpu_framebuffer(plane->state->fb); + vgfb = to_virtio_gpu_framebuffer(state->fb); if (vgfb->fence) { dma_fence_put(&vgfb->fence->f); vgfb->fence = NULL;

From: James Morse james.morse@arm.com

commit 171df58028bf4649460fb146a56a58dcb0c8f75a upstream.

Cortex-A55 is affected by an erratum where in rare circumstances the CPUs may not handle a race between a break-before-make sequence on one CPU, and another CPU accessing the same page. This could allow a store to a page that has been unmapped.

Work around this by adding the affected CPUs to the list that needs TLB sequences to be done twice.

Signed-off-by: James Morse james.morse@arm.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220930131959.3082594-1-james.morse@arm.com Signed-off-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/arm64/silicon-errata.rst | 2 ++ arch/arm64/Kconfig | 17 +++++++++++++++++ arch/arm64/kernel/cpu_errata.c | 5 +++++ 3 files changed, 24 insertions(+)

--- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -68,6 +68,8 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A55 | #1530923 | ARM64_ERRATUM_1530923 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A55 | #2441007 | ARM64_ERRATUM_2441007 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A57 | #832075 | ARM64_ERRATUM_832075 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A57 | #852523 | N/A | --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -596,6 +596,23 @@ config ARM64_ERRATUM_1530923 config ARM64_WORKAROUND_REPEAT_TLBI bool

+config ARM64_ERRATUM_2441007 + bool "Cortex-A55: Completion of affected memory accesses might not be guaranteed by completion of a TLBI" + default y + select ARM64_WORKAROUND_REPEAT_TLBI + help + This option adds a workaround for ARM Cortex-A55 erratum #2441007. + + Under very rare circumstances, affected Cortex-A55 CPUs + may not handle a race between a break-before-make sequence on one + CPU, and another CPU accessing the same page. This could allow a + store to a page that has been unmapped. + + Work around this by adding the affected CPUs to the list that needs + TLB sequences to be done twice. + + If unsure, say Y. + config ARM64_ERRATUM_1286807 bool "Cortex-A76: Modification of the translation table for a virtual address might lead to read-after-read ordering violation" default y --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -214,6 +214,11 @@ static const struct arm64_cpu_capabiliti ERRATA_MIDR_RANGE(MIDR_QCOM_KRYO_4XX_GOLD, 0xc, 0xe, 0xf, 0xe), }, #endif +#ifdef CONFIG_ARM64_ERRATUM_2441007 + { + ERRATA_MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), + }, +#endif #ifdef CONFIG_ARM64_ERRATUM_2441009 { /* Cortex-A510 r0p0 -> r1p1. Fixed in r1p2 */

From: Carlos Llamas cmllamas@google.com

commit deb0f6562884b5b4beb883d73e66a7d3a1b96d99 upstream.

Commit c462ac288f2c ("mm: Introduce arch_validate_flags()") added a late check in mmap_region() to let architectures validate vm_flags. The check needs to happen after calling ->mmap() as the flags can potentially be modified during this callback.

If arch_validate_flags() check fails we unmap and free the vma. However, the error path fails to undo the ->mmap() call that previously succeeded and depending on the specific ->mmap() implementation this translates to reference increments, memory allocations and other operations what will not be cleaned up.

There are several places (mainly device drivers) where this is an issue. However, one specific example is bpf_map_mmap() which keeps count of the mappings in map->writecnt. The count is incremented on ->mmap() and then decremented on vm_ops->close(). When arch_validate_flags() fails this count is off since bpf_map_mmap_close() is never called.

One can reproduce this issue in arm64 devices with MTE support. Here the vm_flags are checked to only allow VM_MTE if VM_MTE_ALLOWED has been set previously. From userspace then is enough to pass the PROT_MTE flag to mmap() syscall to trigger the arch_validate_flags() failure.

The following program reproduces this issue:

#include <stdio.h> #include <unistd.h> #include <linux/unistd.h> #include <linux/bpf.h> #include <sys/mman.h>

int main(void) { union bpf_attr attr = { .map_type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(int), .value_size = sizeof(long long), .max_entries = 256, .map_flags = BPF_F_MMAPABLE, }; int fd;

fd = syscall(__NR_bpf, BPF_MAP_CREATE, &attr, sizeof(attr)); mmap(NULL, 4096, PROT_WRITE | PROT_MTE, MAP_SHARED, fd, 0);

return 0; }

By manually adding some log statements to the vm_ops callbacks we can confirm that when passing PROT_MTE to mmap() the map->writecnt is off upon ->release():

With PROT_MTE flag: root@debian:~# ./bpf-test [ 111.263874] bpf_map_write_active_inc: map=9 writecnt=1 [ 111.288763] bpf_map_release: map=9 writecnt=1

Without PROT_MTE flag: root@debian:~# ./bpf-test [ 157.816912] bpf_map_write_active_inc: map=10 writecnt=1 [ 157.830442] bpf_map_write_active_dec: map=10 writecnt=0 [ 157.832396] bpf_map_release: map=10 writecnt=0

This patch fixes the above issue by calling vm_ops->close() when the arch_validate_flags() check fails, after this we can proceed to unmap and free the vma on the error path.

Link: https://lkml.kernel.org/r/20220930003844.1210987-1-cmllamas@google.com Fixes: c462ac288f2c ("mm: Introduce arch_validate_flags()") Signed-off-by: Carlos Llamas cmllamas@google.com Reviewed-by: Catalin Marinas catalin.marinas@arm.com Acked-by: Andrii Nakryiko andrii@kernel.org Reviewed-by: Liam Howlett liam.howlett@oracle.com Cc: Christian Brauner (Microsoft) brauner@kernel.org Cc: Michal Hocko mhocko@suse.com Cc: Suren Baghdasaryan surenb@google.com Cc: stable@vger.kernel.org [5.10+] Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/mmap.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

--- a/mm/mmap.c +++ b/mm/mmap.c @@ -1836,7 +1836,7 @@ unsigned long mmap_region(struct file *f if (!arch_validate_flags(vma->vm_flags)) { error = -EINVAL; if (file) - goto unmap_and_free_vma; + goto close_and_free_vma; else goto free_vma; } @@ -1876,6 +1876,9 @@ out:

return addr;

+close_and_free_vma: + if (vma->vm_ops && vma->vm_ops->close) + vma->vm_ops->close(vma); unmap_and_free_vma: fput(vma->vm_file); vma->vm_file = NULL;

From: M. Vefa Bicakci m.v.b@runbox.com

commit 5c13a4a0291b30191eff9ead8d010e1ca43a4d0c upstream.

Prior to this commit, the gntdev driver code did not handle the following scenario correctly with paravirtualized (PV) Xen domains:

* User process sets up a gntdev mapping composed of two grant mappings (i.e., two pages shared by another Xen domain). * User process munmap()s one of the pages. * User process munmap()s the remaining page. * User process exits.

In the scenario above, the user process would cause the kernel to log the following messages in dmesg for the first munmap(), and the second munmap() call would result in similar log messages:

BUG: Bad page map in process doublemap.test pte:... pmd:... page:0000000057c97bff refcount:1 mapcount:-1 \ mapping:0000000000000000 index:0x0 pfn:... ... page dumped because: bad pte ... file:gntdev fault:0x0 mmap:gntdev_mmap [xen_gntdev] readpage:0x0 ... Call Trace: <TASK> dump_stack_lvl+0x46/0x5e print_bad_pte.cold+0x66/0xb6 unmap_page_range+0x7e5/0xdc0 unmap_vmas+0x78/0xf0 unmap_region+0xa8/0x110 __do_munmap+0x1ea/0x4e0 __vm_munmap+0x75/0x120 __x64_sys_munmap+0x28/0x40 do_syscall_64+0x38/0x90 entry_SYSCALL_64_after_hwframe+0x61/0xcb ...

For each munmap() call, the Xen hypervisor (if built with CONFIG_DEBUG) would print out the following and trigger a general protection fault in the affected Xen PV domain:

(XEN) d0v... Attempt to implicitly unmap d0's grant PTE ... (XEN) d0v... Attempt to implicitly unmap d0's grant PTE ...

As of this writing, gntdev_grant_map structure's vma field (referred to as map->vma below) is mainly used for checking the start and end addresses of mappings. However, with split VMAs, these may change, and there could be more than one VMA associated with a gntdev mapping. Hence, remove the use of map->vma and rely on map->pages_vm_start for the original start address and on (map->count << PAGE_SHIFT) for the original mapping size. Let the invalidate() and find_special_page() hooks use these.

Also, given that there can be multiple VMAs associated with a gntdev mapping, move the "mmu_interval_notifier_remove(&map->notifier)" call to the end of gntdev_put_map, so that the MMU notifier is only removed after the closing of the last remaining VMA.

Finally, use an atomic to prevent inadvertent gntdev mapping re-use, instead of using the map->live_grants atomic counter and/or the map->vma pointer (the latter of which is now removed). This prevents the userspace from mmap()'ing (with MAP_FIXED) a gntdev mapping over the same address range as a previously set up gntdev mapping. This scenario can be summarized with the following call-trace, which was valid prior to this commit:

mmap gntdev_mmap mmap (repeat mmap with MAP_FIXED over the same address range) gntdev_invalidate unmap_grant_pages (sets 'being_removed' entries to true) gnttab_unmap_refs_async unmap_single_vma gntdev_mmap (maps the shared pages again) munmap gntdev_invalidate unmap_grant_pages (no-op because 'being_removed' entries are true) unmap_single_vma (For PV domains, Xen reports that a granted page is being unmapped and triggers a general protection fault in the affected domain, if Xen was built with CONFIG_DEBUG)

The fix for this last scenario could be worth its own commit, but we opted for a single commit, because removing the gntdev_grant_map structure's vma field requires guarding the entry to gntdev_mmap(), and the live_grants atomic counter is not sufficient on its own to prevent the mmap() over a pre-existing mapping.

Link: https://github.com/QubesOS/qubes-issues/issues/7631 Fixes: ab31523c2fca ("xen/gntdev: allow usermode to map granted pages") Cc: stable@vger.kernel.org Signed-off-by: M. Vefa Bicakci m.v.b@runbox.com Reviewed-by: Juergen Gross jgross@suse.com Link: https://lore.kernel.org/r/20221002222006.2077-3-m.v.b@runbox.com Signed-off-by: Juergen Gross jgross@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/xen/gntdev-common.h | 3 +- drivers/xen/gntdev.c | 58 ++++++++++++++++++-------------------------- 2 files changed, 27 insertions(+), 34 deletions(-)

--- a/drivers/xen/gntdev-common.h +++ b/drivers/xen/gntdev-common.h @@ -44,9 +44,10 @@ struct gntdev_unmap_notify { };

struct gntdev_grant_map { + atomic_t in_use; struct mmu_interval_notifier notifier; + bool notifier_init; struct list_head next; - struct vm_area_struct *vma; int index; int count; int flags; --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -286,6 +286,9 @@ void gntdev_put_map(struct gntdev_priv * */ }

+ if (use_ptemod && map->notifier_init) + mmu_interval_notifier_remove(&map->notifier); + if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT) { notify_remote_via_evtchn(map->notify.event); evtchn_put(map->notify.event); @@ -298,7 +301,7 @@ void gntdev_put_map(struct gntdev_priv * static int find_grant_ptes(pte_t *pte, unsigned long addr, void *data) { struct gntdev_grant_map *map = data; - unsigned int pgnr = (addr - map->vma->vm_start) >> PAGE_SHIFT; + unsigned int pgnr = (addr - map->pages_vm_start) >> PAGE_SHIFT; int flags = map->flags | GNTMAP_application_map | GNTMAP_contains_pte | (1 << _GNTMAP_guest_avail0); u64 pte_maddr; @@ -508,11 +511,7 @@ static void gntdev_vma_close(struct vm_a struct gntdev_priv *priv = file->private_data;

pr_debug("gntdev_vma_close %p\n", vma); - if (use_ptemod) { - WARN_ON(map->vma != vma); - mmu_interval_notifier_remove(&map->notifier); - map->vma = NULL; - } + vma->vm_private_data = NULL; gntdev_put_map(priv, map); } @@ -540,29 +539,30 @@ static bool gntdev_invalidate(struct mmu struct gntdev_grant_map *map = container_of(mn, struct gntdev_grant_map, notifier); unsigned long mstart, mend; + unsigned long map_start, map_end;

if (!mmu_notifier_range_blockable(range)) return false;

+ map_start = map->pages_vm_start; + map_end = map->pages_vm_start + (map->count << PAGE_SHIFT); + /* * If the VMA is split or otherwise changed the notifier is not * updated, but we don't want to process VA's outside the modified * VMA. FIXME: It would be much more understandable to just prevent * modifying the VMA in the first place. */ - if (map->vma->vm_start >= range->end || - map->vma->vm_end <= range->start) + if (map_start >= range->end || map_end <= range->start) return true;

- mstart = max(range->start, map->vma->vm_start); - mend = min(range->end, map->vma->vm_end); + mstart = max(range->start, map_start); + mend = min(range->end, map_end); pr_debug("map %d+%d (%lx %lx), range %lx %lx, mrange %lx %lx\n", - map->index, map->count, - map->vma->vm_start, map->vma->vm_end, - range->start, range->end, mstart, mend); - unmap_grant_pages(map, - (mstart - map->vma->vm_start) >> PAGE_SHIFT, - (mend - mstart) >> PAGE_SHIFT); + map->index, map->count, map_start, map_end, + range->start, range->end, mstart, mend); + unmap_grant_pages(map, (mstart - map_start) >> PAGE_SHIFT, + (mend - mstart) >> PAGE_SHIFT);

return true; } @@ -1042,18 +1042,15 @@ static int gntdev_mmap(struct file *flip return -EINVAL;

pr_debug("map %d+%d at %lx (pgoff %lx)\n", - index, count, vma->vm_start, vma->vm_pgoff); + index, count, vma->vm_start, vma->vm_pgoff);

mutex_lock(&priv->lock); map = gntdev_find_map_index(priv, index, count); if (!map) goto unlock_out; - if (use_ptemod && map->vma) - goto unlock_out; - if (atomic_read(&map->live_grants)) { - err = -EAGAIN; + if (!atomic_add_unless(&map->in_use, 1, 1)) goto unlock_out; - } + refcount_inc(&map->users);

vma->vm_ops = &gntdev_vmops; @@ -1074,15 +1071,16 @@ static int gntdev_mmap(struct file *flip map->flags |= GNTMAP_readonly; }

+ map->pages_vm_start = vma->vm_start; + if (use_ptemod) { - map->vma = vma; err = mmu_interval_notifier_insert_locked( &map->notifier, vma->vm_mm, vma->vm_start, vma->vm_end - vma->vm_start, &gntdev_mmu_ops); - if (err) { - map->vma = NULL; + if (err) goto out_unlock_put; - } + + map->notifier_init = true; } mutex_unlock(&priv->lock);

@@ -1099,7 +1097,6 @@ static int gntdev_mmap(struct file *flip */ mmu_interval_read_begin(&map->notifier);

- map->pages_vm_start = vma->vm_start; err = apply_to_page_range(vma->vm_mm, vma->vm_start, vma->vm_end - vma->vm_start, find_grant_ptes, map); @@ -1128,13 +1125,8 @@ unlock_out: out_unlock_put: mutex_unlock(&priv->lock); out_put_map: - if (use_ptemod) { + if (use_ptemod) unmap_grant_pages(map, 0, map->count); - if (map->vma) { - mmu_interval_notifier_remove(&map->notifier); - map->vma = NULL; - } - } gntdev_put_map(priv, map); return err; }

From: Maciej W. Rozycki macro@orcam.me.uk

commit 9906890c89e4dbd900ed87ad3040080339a7f411 upstream.

A SERIAL_8250_16550A_VARIANTS configuration option has been recently defined that lets one request the 8250 driver not to probe for 16550A device features so as to reduce the driver's device startup time in virtual machines.

Some actual hardware devices require these features to have been fully determined however for their driver to work correctly, so define a flag to let drivers request full 16550A feature probing on a device-by-device basis if required regardless of the SERIAL_8250_16550A_VARIANTS option setting chosen.

Fixes: dc56ecb81a0a ("serial: 8250: Support disabling mdelay-filled probes of 16550A variants") Cc: stable@vger.kernel.org # v5.6+ Reported-by: Anders Blomdell anders.blomdell@control.lth.se Signed-off-by: Maciej W. Rozycki macro@orcam.me.uk Link: https://lore.kernel.org/r/alpine.DEB.2.21.2209202357520.41633@angie.orcam.me... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/tty/serial/8250/8250_port.c | 3 ++- include/linux/serial_core.h | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-)

--- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1029,7 +1029,8 @@ static void autoconfig_16550a(struct uar up->port.type = PORT_16550A; up->capabilities |= UART_CAP_FIFO;

- if (!IS_ENABLED(CONFIG_SERIAL_8250_16550A_VARIANTS)) + if (!IS_ENABLED(CONFIG_SERIAL_8250_16550A_VARIANTS) && + !(up->port.flags & UPF_FULL_PROBE)) return;

/* --- a/include/linux/serial_core.h +++ b/include/linux/serial_core.h @@ -100,7 +100,7 @@ struct uart_icount { __u32 buf_overrun; };

-typedef unsigned int __bitwise upf_t; +typedef u64 __bitwise upf_t; typedef unsigned int __bitwise upstat_t;

struct uart_port { @@ -207,6 +207,7 @@ struct uart_port { #define UPF_FIXED_PORT ((__force upf_t) (1 << 29)) #define UPF_DEAD ((__force upf_t) (1 << 30)) #define UPF_IOREMAP ((__force upf_t) (1 << 31)) +#define UPF_FULL_PROBE ((__force upf_t) (1ULL << 32))

#define __UPF_CHANGE_MASK 0x17fff #define UPF_CHANGE_MASK ((__force upf_t) __UPF_CHANGE_MASK)

From: Chuck Lever chuck.lever@oracle.com

commit 640f87c190e0d1b2a0fcb2ecf6d2cd53b1c41991 upstream.

Since before the git era, NFSD has conserved the number of pages held by each nfsd thread by combining the RPC receive and send buffers into a single array of pages. This works because there are no cases where an operation needs a large RPC Call message and a large RPC Reply message at the same time.

Once an RPC Call has been received, svc_process() updates svc_rqst::rq_res to describe the part of rq_pages that can be used for constructing the Reply. This means that the send buffer (rq_res) shrinks when the received RPC record containing the RPC Call is large.

A client can force this shrinkage on TCP by sending a correctly- formed RPC Call header contained in an RPC record that is excessively large. The full maximum payload size cannot be constructed in that case.

Thanks to Aleksi Illikainen and Kari Hulkko for uncovering this issue.

Reported-by: Ben Ronallo Benjamin.Ronallo@synopsys.com Cc: stable@vger.kernel.org Signed-off-by: Chuck Lever chuck.lever@oracle.com Reviewed-by: Jeff Layton jlayton@kernel.org Signed-off-by: Chuck Lever chuck.lever@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/nfsd/nfs3proc.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

--- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -447,13 +447,14 @@ static void nfsd3_init_dirlist_pages(str { struct xdr_buf *buf = &resp->dirlist; struct xdr_stream *xdr = &resp->xdr; - - count = clamp(count, (u32)(XDR_UNIT * 2), svc_max_payload(rqstp)); + unsigned int sendbuf = min_t(unsigned int, rqstp->rq_res.buflen, + svc_max_payload(rqstp));

memset(buf, 0, sizeof(*buf));

/* Reserve room for the NULL ptr & eof flag (-2 words) */ - buf->buflen = count - XDR_UNIT * 2; + buf->buflen = clamp(count, (u32)(XDR_UNIT * 2), sendbuf); + buf->buflen -= XDR_UNIT * 2; buf->pages = rqstp->rq_next_page; rqstp->rq_next_page += (buf->buflen + PAGE_SIZE - 1) >> PAGE_SHIFT;

From: Chuck Lever chuck.lever@oracle.com

commit fa6be9cc6e80ec79892ddf08a8c10cabab9baf38 upstream.

Since before the git era, NFSD has conserved the number of pages held by each nfsd thread by combining the RPC receive and send buffers into a single array of pages. This works because there are no cases where an operation needs a large RPC Call message and a large RPC Reply at the same time.

Once an RPC Call has been received, svc_process() updates svc_rqst::rq_res to describe the part of rq_pages that can be used for constructing the Reply. This means that the send buffer (rq_res) shrinks when the received RPC record containing the RPC Call is large.

A client can force this shrinkage on TCP by sending a correctly- formed RPC Call header contained in an RPC record that is excessively large. The full maximum payload size cannot be constructed in that case.

Cc: stable@vger.kernel.org Signed-off-by: Chuck Lever chuck.lever@oracle.com Reviewed-by: Jeff Layton jlayton@kernel.org Signed-off-by: Chuck Lever chuck.lever@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/nfsd/nfs3proc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -146,7 +146,6 @@ nfsd3_proc_read(struct svc_rqst *rqstp) { struct nfsd3_readargs *argp = rqstp->rq_argp; struct nfsd3_readres *resp = rqstp->rq_resp; - u32 max_blocksize = svc_max_payload(rqstp); unsigned int len; int v;

@@ -155,7 +154,8 @@ nfsd3_proc_read(struct svc_rqst *rqstp) (unsigned long) argp->count, (unsigned long long) argp->offset);

- argp->count = min_t(u32, argp->count, max_blocksize); + argp->count = min_t(u32, argp->count, svc_max_payload(rqstp)); + argp->count = min_t(u32, argp->count, rqstp->rq_res.buflen); if (argp->offset > (u64)OFFSET_MAX) argp->offset = (u64)OFFSET_MAX; if (argp->offset + argp->count > (u64)OFFSET_MAX)

From: Pali Rohár pali@kernel.org

commit 110a58b9f91c66f743c01a2c217243d94c899c23 upstream.

uImage boot wrapper should not use SPE instructions, like kernel itself. Boot wrapper has already disabled Altivec and VSX instructions but not SPE. Options -mno-spe and -mspe=no already set when compilation of kernel, but not when compiling uImage wrapper yet. Fix it.

Cc: stable@vger.kernel.org Signed-off-by: Pali Rohár pali@kernel.org Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20220827134454.17365-1-pali@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/powerpc/boot/Makefile | 1 + 1 file changed, 1 insertion(+)

--- a/arch/powerpc/boot/Makefile +++ b/arch/powerpc/boot/Makefile @@ -34,6 +34,7 @@ endif

BOOTCFLAGS := -Wall -Wundef -Wstrict-prototypes -Wno-trigraphs \ -fno-strict-aliasing -O2 -msoft-float -mno-altivec -mno-vsx \ + $(call cc-option,-mno-spe) $(call cc-option,-mspe=no) \ -pipe -fomit-frame-pointer -fno-builtin -fPIC -nostdinc \ $(LINUXINCLUDE)

From: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org

commit 16f14551d0df9e7cd283545d7d748829594d912f upstream.

Add proper error path in probe() to cleanup resources previously acquired/allocated to fix warnings visible during probe deferral:

notifier callback qcom_slim_ngd_ssr_notify already registered WARNING: CPU: 6 PID: 70 at kernel/notifier.c:28 notifier_chain_register+0x5c/0x90 Modules linked in: CPU: 6 PID: 70 Comm: kworker/u16:1 Not tainted 6.0.0-rc3-next-20220830 #380 Call trace: notifier_chain_register+0x5c/0x90 srcu_notifier_chain_register+0x44/0x90 qcom_register_ssr_notifier+0x38/0x4c qcom_slim_ngd_ctrl_probe+0xd8/0x400 platform_probe+0x6c/0xe0 really_probe+0xbc/0x2d4 __driver_probe_device+0x78/0xe0 driver_probe_device+0x3c/0x12c __device_attach_driver+0xb8/0x120 bus_for_each_drv+0x78/0xd0 __device_attach+0xa8/0x1c0 device_initial_probe+0x18/0x24 bus_probe_device+0xa0/0xac deferred_probe_work_func+0x88/0xc0 process_one_work+0x1d4/0x320 worker_thread+0x2cc/0x44c kthread+0x110/0x114 ret_from_fork+0x10/0x20

Fixes: e1ae85e1830e ("slimbus: qcom-ngd-ctrl: add Protection Domain Restart Support") Cc: stable@vger.kernel.org Signed-off-by: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org Signed-off-by: Srinivas Kandagatla srinivas.kandagatla@linaro.org Link: https://lore.kernel.org/r/20220916122910.170730-3-srinivas.kandagatla@linaro... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/slimbus/qcom-ngd-ctrl.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-)

--- a/drivers/slimbus/qcom-ngd-ctrl.c +++ b/drivers/slimbus/qcom-ngd-ctrl.c @@ -1567,18 +1567,27 @@ static int qcom_slim_ngd_ctrl_probe(stru ctrl->pdr = pdr_handle_alloc(slim_pd_status, ctrl); if (IS_ERR(ctrl->pdr)) { dev_err(dev, "Failed to init PDR handle\n"); - return PTR_ERR(ctrl->pdr); + ret = PTR_ERR(ctrl->pdr); + goto err_pdr_alloc; }

pds = pdr_add_lookup(ctrl->pdr, "avs/audio", "msm/adsp/audio_pd"); if (IS_ERR(pds) && PTR_ERR(pds) != -EALREADY) { ret = PTR_ERR(pds); dev_err(dev, "pdr add lookup failed: %d\n", ret); - return ret; + goto err_pdr_lookup; }

platform_driver_register(&qcom_slim_ngd_driver); return of_qcom_slim_ngd_register(dev, ctrl); + +err_pdr_alloc: + qcom_unregister_ssr_notifier(ctrl->notifier, &ctrl->nb); + +err_pdr_lookup: + pdr_handle_release(ctrl->pdr); + + return ret; }

static int qcom_slim_ngd_ctrl_remove(struct platform_device *pdev)

From: Quentin Schulz quentin.schulz@theobroma-systems.com

commit 8ea8af6c8469156ac2042d83d73f6b74eb4b4b45 upstream.

Before the split of gpio and pinctrl sections in their own driver, rockchip_set_mux was called in pinmux_ops.gpio_set_direction for configuring a pin in its GPIO function.

This is essential for cases where pinctrl is "bypassed" by gpio consumers otherwise the GPIO function is not configured for the pin and it does not work. Such was the case for the sysfs/libgpiod userspace GPIO handling.

Let's call pinctrl_gpio_direction_input/output when setting the direction of a GPIO so that the pinctrl core requests from the rockchip pinctrl driver to put the pin in its GPIO function.

Fixes: 9ce9a02039de ("pinctrl/rockchip: drop the gpio related codes") Fixes: 936ee2675eee ("gpio/rockchip: add driver for rockchip gpio") Cc: stable@vger.kernel.org Reviewed-by: Heiko Stuebner heiko@sntech.de Signed-off-by: Quentin Schulz quentin.schulz@theobroma-systems.com Link: https://lore.kernel.org/r/20220930132033.4003377-3-foss+kernel@0leil.net Signed-off-by: Linus Walleij linus.walleij@linaro.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpio/gpio-rockchip.c | 7 +++++++ 1 file changed, 7 insertions(+)

--- a/drivers/gpio/gpio-rockchip.c +++ b/drivers/gpio/gpio-rockchip.c @@ -19,6 +19,7 @@ #include <linux/of_address.h> #include <linux/of_device.h> #include <linux/of_irq.h> +#include <linux/pinctrl/consumer.h> #include <linux/pinctrl/pinconf-generic.h> #include <linux/regmap.h>

@@ -155,6 +156,12 @@ static int rockchip_gpio_set_direction(s unsigned long flags; u32 data = input ? 0 : 1;

+ + if (input) + pinctrl_gpio_direction_input(bank->pin_base + offset); + else + pinctrl_gpio_direction_output(bank->pin_base + offset); + raw_spin_lock_irqsave(&bank->slock, flags); rockchip_gpio_writel_bit(bank, offset, data, bank->gpio_regs->port_ddr); raw_spin_unlock_irqrestore(&bank->slock, flags);

From: Hyunwoo Kim imv4bel@gmail.com

commit 5610bcfe8693c02e2e4c8b31427f1bdbdecc839c upstream.

A race condition may occur if the user physically removes the USB device while calling open() for this device node.

This is a race condition between the ufx_ops_open() function and the ufx_usb_disconnect() function, which may eventually result in UAF.

So, add a mutex to the ufx_ops_open() and ufx_usb_disconnect() functions to avoid race contidion of krefs.

Signed-off-by: Hyunwoo Kim imv4bel@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Helge Deller deller@gmx.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/video/fbdev/smscufx.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-)

--- a/drivers/video/fbdev/smscufx.c +++ b/drivers/video/fbdev/smscufx.c @@ -137,6 +137,8 @@ static int ufx_submit_urb(struct ufx_dat static int ufx_alloc_urb_list(struct ufx_data *dev, int count, size_t size); static void ufx_free_urb_list(struct ufx_data *dev);

+static DEFINE_MUTEX(disconnect_mutex); + /* reads a control register */ static int ufx_reg_read(struct ufx_data *dev, u32 index, u32 *data) { @@ -1070,9 +1072,13 @@ static int ufx_ops_open(struct fb_info * if (user == 0 && !console) return -EBUSY;

+ mutex_lock(&disconnect_mutex); + /* If the USB device is gone, we don't accept new opens */ - if (dev->virtualized) + if (dev->virtualized) { + mutex_unlock(&disconnect_mutex); return -ENODEV; + }

dev->fb_count++;

@@ -1096,6 +1102,8 @@ static int ufx_ops_open(struct fb_info * pr_debug("open /dev/fb%d user=%d fb_info=%p count=%d", info->node, user, info, dev->fb_count);

+ mutex_unlock(&disconnect_mutex); + return 0; }

@@ -1740,6 +1748,8 @@ static void ufx_usb_disconnect(struct us { struct ufx_data *dev;

+ mutex_lock(&disconnect_mutex); + dev = usb_get_intfdata(interface);

pr_debug("USB disconnect starting\n"); @@ -1760,6 +1770,8 @@ static void ufx_usb_disconnect(struct us kref_put(&dev->kref, ufx_free);

/* consider ufx_data freed */ + + mutex_unlock(&disconnect_mutex); }

static struct usb_driver ufx_driver = {

From: Zhang Xiaoxu zhangxiaoxu5@huawei.com

commit b1763d265af62800ec96eeb79803c4c537dcef3a upstream.

Commit c7803b05f74b ("smb3: fix ksmbd bigendian bug in oplock break, and move its struct to smbfs_common") use the defination of 'struct validate_negotiate_info_req' in smbfs_common, the array length of 'Dialects' changed from 1 to 4, but the protocol does not require the client to send all 4. This lead the request which satisfied with protocol and server to fail.

So just ensure the request payload has the 'DialectCount' in smb2_ioctl(), then fsctl_validate_negotiate_info() will use it to validate the payload length and each dialect.

Also when the {in, out}_buf_len is less than the required, should goto out to initialize the status in the response header.

Fixes: f7db8fd03a4b ("ksmbd: add validation in smb2_ioctl") Cc: stable@vger.kernel.org Signed-off-by: Zhang Xiaoxu zhangxiaoxu5@huawei.com Acked-by: Namjae Jeon linkinjeon@kernel.org Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ksmbd/smb2pdu.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-)

--- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -7617,11 +7617,16 @@ int smb2_ioctl(struct ksmbd_work *work) goto out; }

- if (in_buf_len < sizeof(struct validate_negotiate_info_req)) - return -EINVAL; + if (in_buf_len < offsetof(struct validate_negotiate_info_req, + Dialects)) { + ret = -EINVAL; + goto out; + }

- if (out_buf_len < sizeof(struct validate_negotiate_info_rsp)) - return -EINVAL; + if (out_buf_len < sizeof(struct validate_negotiate_info_rsp)) { + ret = -EINVAL; + goto out; + }

ret = fsctl_validate_negotiate_info(conn, (struct validate_negotiate_info_req *)&req->Buffer[0],

From: Lukas Czerner lczerner@redhat.com

commit cbfecb927f429a6fa613d74b998496bd71e4438a upstream.

Currently the I_DIRTY_TIME will never get set if the inode already has I_DIRTY_INODE with assumption that it supersedes I_DIRTY_TIME. That's true, however ext4 will only update the on-disk inode in ->dirty_inode(), not on actual writeback. As a result if the inode already has I_DIRTY_INODE state by the time we get to __mark_inode_dirty() only with I_DIRTY_TIME, the time was already filled into on-disk inode and will not get updated until the next I_DIRTY_INODE update, which might never come if we crash or get a power failure.

The problem can be reproduced on ext4 by running xfstest generic/622 with -o iversion mount option.

Fix it by allowing I_DIRTY_TIME to be set even if the inode already has I_DIRTY_INODE. Also make sure that the case is properly handled in writeback_single_inode() as well. Additionally changes in xfs_fs_dirty_inode() was made to accommodate for I_DIRTY_TIME in flag.

Thanks Jan Kara for suggestions on how to make this work properly.

Cc: Dave Chinner david@fromorbit.com Cc: Christoph Hellwig hch@infradead.org Cc: stable@kernel.org Signed-off-by: Lukas Czerner lczerner@redhat.com Suggested-by: Jan Kara jack@suse.cz Reviewed-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20220825100657.44217-1-lczerner@redhat.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/filesystems/vfs.rst | 3 +++ fs/fs-writeback.c | 37 +++++++++++++++++++++++++------------ fs/xfs/xfs_super.c | 10 ++++++++-- include/linux/fs.h | 9 +++++---- 4 files changed, 41 insertions(+), 18 deletions(-)

--- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -274,6 +274,9 @@ or bottom half). This is specifically for the inode itself being marked dirty, not its data. If the update needs to be persisted by fdatasync(), then I_DIRTY_DATASYNC will be set in the flags argument. + I_DIRTY_TIME will be set in the flags in case lazytime is enabled + and struct inode has times updated since the last ->dirty_inode + call.

``write_inode`` this method is called when the VFS needs to write an inode to --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1745,9 +1745,14 @@ static int writeback_single_inode(struct */ if (!(inode->i_state & I_DIRTY_ALL)) inode_cgwb_move_to_attached(inode, wb); - else if (!(inode->i_state & I_SYNC_QUEUED) && - (inode->i_state & I_DIRTY)) - redirty_tail_locked(inode, wb); + else if (!(inode->i_state & I_SYNC_QUEUED)) { + if ((inode->i_state & I_DIRTY)) + redirty_tail_locked(inode, wb); + else if (inode->i_state & I_DIRTY_TIME) { + inode->dirtied_when = jiffies; + inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); + } + }

spin_unlock(&wb->list_lock); inode_sync_complete(inode); @@ -2401,6 +2406,20 @@ void __mark_inode_dirty(struct inode *in

if (flags & I_DIRTY_INODE) { /* + * Inode timestamp update will piggback on this dirtying. + * We tell ->dirty_inode callback that timestamps need to + * be updated by setting I_DIRTY_TIME in flags. + */ + if (inode->i_state & I_DIRTY_TIME) { + spin_lock(&inode->i_lock); + if (inode->i_state & I_DIRTY_TIME) { + inode->i_state &= ~I_DIRTY_TIME; + flags |= I_DIRTY_TIME; + } + spin_unlock(&inode->i_lock); + } + + /* * Notify the filesystem about the inode being dirtied, so that * (if needed) it can update on-disk fields and journal the * inode. This is only needed when the inode itself is being @@ -2409,7 +2428,8 @@ void __mark_inode_dirty(struct inode *in */ trace_writeback_dirty_inode_start(inode, flags); if (sb->s_op->dirty_inode) - sb->s_op->dirty_inode(inode, flags & I_DIRTY_INODE); + sb->s_op->dirty_inode(inode, + flags & (I_DIRTY_INODE | I_DIRTY_TIME)); trace_writeback_dirty_inode(inode, flags);

/* I_DIRTY_INODE supersedes I_DIRTY_TIME. */ @@ -2430,21 +2450,15 @@ void __mark_inode_dirty(struct inode *in */ smp_mb();

- if (((inode->i_state & flags) == flags) || - (dirtytime && (inode->i_state & I_DIRTY_INODE))) + if ((inode->i_state & flags) == flags) return;

spin_lock(&inode->i_lock); - if (dirtytime && (inode->i_state & I_DIRTY_INODE)) - goto out_unlock_inode; if ((inode->i_state & flags) != flags) { const int was_dirty = inode->i_state & I_DIRTY;

inode_attach_wb(inode, NULL);

- /* I_DIRTY_INODE supersedes I_DIRTY_TIME. */ - if (flags & I_DIRTY_INODE) - inode->i_state &= ~I_DIRTY_TIME; inode->i_state |= flags;

/* @@ -2517,7 +2531,6 @@ void __mark_inode_dirty(struct inode *in out_unlock: if (wb) spin_unlock(&wb->list_lock); -out_unlock_inode: spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(__mark_inode_dirty); --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -642,7 +642,7 @@ xfs_fs_destroy_inode( static void xfs_fs_dirty_inode( struct inode *inode, - int flag) + int flags) { struct xfs_inode *ip = XFS_I(inode); struct xfs_mount *mp = ip->i_mount; @@ -650,7 +650,13 @@ xfs_fs_dirty_inode(

if (!(inode->i_sb->s_flags & SB_LAZYTIME)) return; - if (flag != I_DIRTY_SYNC || !(inode->i_state & I_DIRTY_TIME)) + + /* + * Only do the timestamp update if the inode is dirty (I_DIRTY_SYNC) + * and has dirty timestamp (I_DIRTY_TIME). I_DIRTY_TIME can be passed + * in flags possibly together with I_DIRTY_SYNC. + */ + if ((flags & ~I_DIRTY_TIME) != I_DIRTY_SYNC || !(flags & I_DIRTY_TIME)) return;

if (xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp)) --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2288,13 +2288,14 @@ static inline void kiocb_clone(struct ki * don't have to write inode on fdatasync() when only * e.g. the timestamps have changed. * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. - * I_DIRTY_TIME The inode itself only has dirty timestamps, and the + * I_DIRTY_TIME The inode itself has dirty timestamps, and the * lazytime mount option is enabled. We keep track of this * separately from I_DIRTY_SYNC in order to implement * lazytime. This gets cleared if I_DIRTY_INODE - * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. I.e. - * either I_DIRTY_TIME *or* I_DIRTY_INODE can be set in - * i_state, but not both. I_DIRTY_PAGES may still be set. + * (I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But + * I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already + * in place because writeback might already be in progress + * and we don't want to lose the time update * I_NEW Serves as both a mutex and completion notification. * New inodes set I_NEW. If two processes both create * the same inode, one of them will release its inode and

From: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp

commit cbddcc4fa3443fe8cfb2ff8e210deb1f6a0eea38 upstream.

syzbot is reporting uninit-value in btrfs_clean_tree_block() [1], for commit bc877d285ca3dba2 ("btrfs: Deduplicate extent_buffer init code") missed that btrfs_set_header_generation() in btrfs_init_new_buffer() must not be moved to after clean_tree_block() because clean_tree_block() is calling btrfs_header_generation() since commit 55c69072d6bd5be1 ("Btrfs: Fix extent_buffer usage when nodesize != leafsize").

Since memzero_extent_buffer() will reset "struct btrfs_header" part, we can't move btrfs_set_header_generation() to before memzero_extent_buffer(). Just re-add btrfs_set_header_generation() before btrfs_clean_tree_block().

Link: https://syzkaller.appspot.com/bug?extid=fba8e2116a12609b6c59 [1] Reported-by: syzbot syzbot+fba8e2116a12609b6c59@syzkaller.appspotmail.com Fixes: bc877d285ca3dba2 ("btrfs: Deduplicate extent_buffer init code") CC: stable@vger.kernel.org # 4.19+ Signed-off-by: Tetsuo Handa penguin-kernel@I-love.SAKURA.ne.jp 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, 3 insertions(+)

--- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4802,6 +4802,9 @@ btrfs_init_new_buffer(struct btrfs_trans !test_bit(BTRFS_ROOT_RESET_LOCKDEP_CLASS, &root->state)) lockdep_owner = BTRFS_FS_TREE_OBJECTID;

+ /* btrfs_clean_tree_block() accesses generation field. */ + btrfs_set_header_generation(buf, trans->transid); + /* * This needs to stay, because we could allocate a freed block from an * old tree into a new tree, so we need to make sure this new block is

From: Jaegeuk Kim jaegeuk@kernel.org

commit c7b58576370147833999fd4cc874d0f918bdf9ca upstream.

This avoids -EINVAL when trying to freeze f2fs.

Cc: stable@vger.kernel.org Reviewed-by: Chao Yu chao@kernel.org Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/checkpoint.c | 24 ++++++++++++++++++------ fs/f2fs/f2fs.h | 1 + fs/f2fs/super.c | 5 ++--- 3 files changed, 21 insertions(+), 9 deletions(-)

--- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -1892,15 +1892,27 @@ int f2fs_start_ckpt_thread(struct f2fs_s void f2fs_stop_ckpt_thread(struct f2fs_sb_info *sbi) { struct ckpt_req_control *cprc = &sbi->cprc_info; + struct task_struct *ckpt_task;

- if (cprc->f2fs_issue_ckpt) { - struct task_struct *ckpt_task = cprc->f2fs_issue_ckpt; + if (!cprc->f2fs_issue_ckpt) + return;

- cprc->f2fs_issue_ckpt = NULL; - kthread_stop(ckpt_task); + ckpt_task = cprc->f2fs_issue_ckpt; + cprc->f2fs_issue_ckpt = NULL; + kthread_stop(ckpt_task);

- flush_remained_ckpt_reqs(sbi, NULL); - } + f2fs_flush_ckpt_thread(sbi); +} + +void f2fs_flush_ckpt_thread(struct f2fs_sb_info *sbi) +{ + struct ckpt_req_control *cprc = &sbi->cprc_info; + + flush_remained_ckpt_reqs(sbi, NULL); + + /* Let's wait for the previous dispatched checkpoint. */ + while (atomic_read(&cprc->queued_ckpt)) + io_schedule_timeout(DEFAULT_IO_TIMEOUT); }

void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi) --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -3540,6 +3540,7 @@ unsigned int f2fs_usable_blks_in_seg(str * checkpoint.c */ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io); +void f2fs_flush_ckpt_thread(struct f2fs_sb_info *sbi); struct page *f2fs_grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index); struct page *f2fs_get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index); struct page *f2fs_get_meta_page_retry(struct f2fs_sb_info *sbi, pgoff_t index); --- a/fs/f2fs/super.c +++ b/fs/f2fs/super.c @@ -1661,9 +1661,8 @@ static int f2fs_freeze(struct super_bloc if (is_sbi_flag_set(F2FS_SB(sb), SBI_IS_DIRTY)) return -EINVAL;

- /* ensure no checkpoint required */ - if (!llist_empty(&F2FS_SB(sb)->cprc_info.issue_list)) - return -EINVAL; + /* Let's flush checkpoints and stop the thread. */ + f2fs_flush_ckpt_thread(F2FS_SB(sb));

/* to avoid deadlock on f2fs_evict_inode->SB_FREEZE_FS */ set_sbi_flag(F2FS_SB(sb), SBI_IS_FREEZING);

From: Chao Yu chao@kernel.org

commit 0ef4ca04a3f9223ff8bc440041c524b2123e09a3 upstream.

As Wenqing Liu reported in bugzilla:

https://bugzilla.kernel.org/show_bug.cgi?id=216456

loop5: detected capacity change from 0 to 131072 F2FS-fs (loop5): recover_inode: ino = 6, name = hln, inline = 1 F2FS-fs (loop5): recover_data: ino = 6 (i_size: recover) err = 0 F2FS-fs (loop5): recover_inode: ino = 6, name = hln, inline = 1 F2FS-fs (loop5): recover_data: ino = 6 (i_size: recover) err = 0 F2FS-fs (loop5): recover_inode: ino = 6, name = hln, inline = 1 F2FS-fs (loop5): recover_data: ino = 6 (i_size: recover) err = 0 F2FS-fs (loop5): Bitmap was wrongly set, blk:5634 ------------[ cut here ]------------ WARNING: CPU: 3 PID: 1013 at fs/f2fs/segment.c:2198 RIP: 0010:update_sit_entry+0xa55/0x10b0 [f2fs] Call Trace: <TASK> f2fs_do_replace_block+0xa98/0x1890 [f2fs] f2fs_replace_block+0xeb/0x180 [f2fs] recover_data+0x1a69/0x6ae0 [f2fs] f2fs_recover_fsync_data+0x120d/0x1fc0 [f2fs] f2fs_fill_super+0x4665/0x61e0 [f2fs] mount_bdev+0x2cf/0x3b0 legacy_get_tree+0xed/0x1d0 vfs_get_tree+0x81/0x2b0 path_mount+0x47e/0x19d0 do_mount+0xce/0xf0 __x64_sys_mount+0x12c/0x1a0 do_syscall_64+0x38/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd

If we enable CONFIG_F2FS_CHECK_FS config, it will trigger a kernel panic instead of warning.

The root cause is: in fuzzed image, SIT table is inconsistent with inode mapping table, result in triggering such warning during SIT table update.

This patch introduces a new flag DATA_GENERIC_ENHANCE_UPDATE, w/ this flag, data block recovery flow can check destination blkaddr's validation in SIT table, and skip f2fs_replace_block() to avoid inconsistent status.

Cc: stable@vger.kernel.org Reported-by: Wenqing Liu wenqingliu0120@gmail.com Signed-off-by: Chao Yu chao@kernel.org Signed-off-by: Jaegeuk Kim jaegeuk@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/f2fs/checkpoint.c | 10 +++++++++- fs/f2fs/f2fs.h | 4 ++++ fs/f2fs/recovery.c | 8 ++++++++ 3 files changed, 21 insertions(+), 1 deletion(-)

--- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -139,7 +139,7 @@ static bool __is_bitmap_valid(struct f2f unsigned int segno, offset; bool exist;

- if (type != DATA_GENERIC_ENHANCE && type != DATA_GENERIC_ENHANCE_READ) + if (type == DATA_GENERIC) return true;

segno = GET_SEGNO(sbi, blkaddr); @@ -147,6 +147,13 @@ static bool __is_bitmap_valid(struct f2f se = get_seg_entry(sbi, segno);

exist = f2fs_test_bit(offset, se->cur_valid_map); + if (exist && type == DATA_GENERIC_ENHANCE_UPDATE) { + f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d", + blkaddr, exist); + set_sbi_flag(sbi, SBI_NEED_FSCK); + return exist; + } + if (!exist && type == DATA_GENERIC_ENHANCE) { f2fs_err(sbi, "Inconsistent error blkaddr:%u, sit bitmap:%d", blkaddr, exist); @@ -184,6 +191,7 @@ bool f2fs_is_valid_blkaddr(struct f2fs_s case DATA_GENERIC: case DATA_GENERIC_ENHANCE: case DATA_GENERIC_ENHANCE_READ: + case DATA_GENERIC_ENHANCE_UPDATE: if (unlikely(blkaddr >= MAX_BLKADDR(sbi) || blkaddr < MAIN_BLKADDR(sbi))) { f2fs_warn(sbi, "access invalid blkaddr:%u", --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -249,6 +249,10 @@ enum { * condition of read on truncated area * by extent_cache */ + DATA_GENERIC_ENHANCE_UPDATE, /* + * strong check on range and segment + * bitmap for update case + */ META_GENERIC, };

--- a/fs/f2fs/recovery.c +++ b/fs/f2fs/recovery.c @@ -677,6 +677,14 @@ retry_prev: goto err; }

+ if (f2fs_is_valid_blkaddr(sbi, dest, + DATA_GENERIC_ENHANCE_UPDATE)) { + f2fs_err(sbi, "Inconsistent dest blkaddr:%u, ino:%lu, ofs:%u", + dest, inode->i_ino, dn.ofs_in_node); + err = -EFSCORRUPTED; + goto err; + } + /* write dummy data page */ f2fs_replace_block(sbi, &dn, src, dest, ni.version, false, false);

From: Kees Cook keescook@chromium.org

commit f02003c860d921171be4a27e2893766eb3bc6871 upstream.

Currently under Clang, CC_HAS_AUTO_VAR_INIT_ZERO requires an extra -enable flag compared to CC_HAS_AUTO_VAR_INIT_PATTERN. GCC 12[1] will not, and will happily ignore the Clang-specific flag. However, its presence on the command-line is both cumbersome and confusing. Due to GCC's tolerant behavior, though, we can continue to use a single Kconfig cc-option test for the feature on both compilers, but then drop the Clang-specific option in the Makefile.

In other words, this patch does not change anything other than making the compiler command line shorter once GCC supports -ftrivial-auto-var-init=zero.

[1] https://gcc.gnu.org/git/?p=gcc.git%3Ba=commitdiff%3Bh=a25e0b5e6ac8a77a71c229...

Cc: Greg Kroah-Hartman gregkh@linuxfoundation.org Cc: Masahiro Yamada masahiroy@kernel.org Cc: llvm@lists.linux.dev Fixes: dcb7c0b9461c ("hardening: Clarify Kconfig text for auto-var-init") Suggested-by: Will Deacon will@kernel.org Link: https://lore.kernel.org/lkml/20210914102837.6172-1-will@kernel.org/ Reviewed-by: Nick Desaulniers ndesaulniers@google.com Reviewed-by: Nathan Chancellor nathan@kernel.org Acked-by: Will Deacon will@kernel.org Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: Nathan Chancellor nathan@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Makefile | 6 +++--- security/Kconfig.hardening | 5 ++++- 2 files changed, 7 insertions(+), 4 deletions(-)

--- a/Makefile +++ b/Makefile @@ -844,12 +844,12 @@ endif

# Initialize all stack variables with a zero value. ifdef CONFIG_INIT_STACK_ALL_ZERO -# Future support for zero initialization is still being debated, see -# https://bugs.llvm.org/show_bug.cgi?id=45497. These flags are subject to being -# renamed or dropped. KBUILD_CFLAGS += -ftrivial-auto-var-init=zero +ifdef CONFIG_CC_IS_CLANG +# https://bugs.llvm.org/show_bug.cgi?id=45497 KBUILD_CFLAGS += -enable-trivial-auto-var-init-zero-knowing-it-will-be-removed-from-clang endif +endif

# While VLAs have been removed, GCC produces unreachable stack probes # for the randomize_kstack_offset feature. Disable it for all compilers. --- a/security/Kconfig.hardening +++ b/security/Kconfig.hardening @@ -23,13 +23,16 @@ config CC_HAS_AUTO_VAR_INIT_PATTERN def_bool $(cc-option,-ftrivial-auto-var-init=pattern)

config CC_HAS_AUTO_VAR_INIT_ZERO + # GCC ignores the -enable flag, so we can test for the feature with + # a single invocation using the flag, but drop it as appropriate in + # the Makefile, depending on the presence of Clang. def_bool $(cc-option,-ftrivial-auto-var-init=zero -enable-trivial-auto-var-init-zero-knowing-it-will-be-removed-from-clang)

choice prompt "Initialize kernel stack variables at function entry" default GCC_PLUGIN_STRUCTLEAK_BYREF_ALL if COMPILE_TEST && GCC_PLUGINS default INIT_STACK_ALL_PATTERN if COMPILE_TEST && CC_HAS_AUTO_VAR_INIT_PATTERN - default INIT_STACK_ALL_ZERO if CC_HAS_AUTO_VAR_INIT_PATTERN + default INIT_STACK_ALL_ZERO if CC_HAS_AUTO_VAR_INIT_ZERO default INIT_STACK_NONE help This option enables initialization of stack variables at

From: Andrew Perepechko anserper@ya.ru

commit 34fc8768ec6089565d6d73bad26724083cecf7bd upstream.

LIFO wakeup order is unfair and sometimes leads to a journal user not being able to get a journal handle for hundreds of transactions in a row.

FIFO wakeup can make things more fair.

Cc: stable@kernel.org Signed-off-by: Alexey Lyashkov alexey.lyashkov@gmail.com Reviewed-by: Ritesh Harjani (IBM) ritesh.list@gmail.com Link: https://lore.kernel.org/r/20220907165959.1137482-1-alexey.lyashkov@gmail.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/jbd2/commit.c | 2 +- fs/jbd2/transaction.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-)

--- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -581,7 +581,7 @@ void jbd2_journal_commit_transaction(jou journal->j_running_transaction = NULL; start_time = ktime_get(); commit_transaction->t_log_start = journal->j_head; - wake_up(&journal->j_wait_transaction_locked); + wake_up_all(&journal->j_wait_transaction_locked); write_unlock(&journal->j_state_lock);

jbd_debug(3, "JBD2: commit phase 2a\n"); --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -173,7 +173,7 @@ static void wait_transaction_locked(jour int need_to_start; tid_t tid = journal->j_running_transaction->t_tid;

- prepare_to_wait(&journal->j_wait_transaction_locked, &wait, + prepare_to_wait_exclusive(&journal->j_wait_transaction_locked, &wait, TASK_UNINTERRUPTIBLE); need_to_start = !tid_geq(journal->j_commit_request, tid); read_unlock(&journal->j_state_lock); @@ -199,7 +199,7 @@ static void wait_transaction_switching(j read_unlock(&journal->j_state_lock); return; } - prepare_to_wait(&journal->j_wait_transaction_locked, &wait, + prepare_to_wait_exclusive(&journal->j_wait_transaction_locked, &wait, TASK_UNINTERRUPTIBLE); read_unlock(&journal->j_state_lock); /* @@ -911,7 +911,7 @@ void jbd2_journal_unlock_updates (journa write_lock(&journal->j_state_lock); --journal->j_barrier_count; write_unlock(&journal->j_state_lock); - wake_up(&journal->j_wait_transaction_locked); + wake_up_all(&journal->j_wait_transaction_locked); }

static void warn_dirty_buffer(struct buffer_head *bh)

From: Ye Bin yebin10@huawei.com

commit 243d1a5d505d0b0460c9af0ad56ed4a56ef0bebd upstream.

In 'jbd2_fc_wait_bufs' use 'bh' after put buffer head reference count which may lead to use-after-free. So judge buffer if uptodate before put buffer head reference count.

Cc: stable@kernel.org Signed-off-by: Ye Bin yebin10@huawei.com Reviewed-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20220914100812.1414768-3-yebin10@huawei.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/jbd2/journal.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)

--- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -924,16 +924,16 @@ int jbd2_fc_wait_bufs(journal_t *journal for (i = j_fc_off - 1; i >= j_fc_off - num_blks; i--) { bh = journal->j_fc_wbuf[i]; wait_on_buffer(bh); - put_bh(bh); - journal->j_fc_wbuf[i] = NULL; /* * Update j_fc_off so jbd2_fc_release_bufs can release remain * buffer head. */ if (unlikely(!buffer_uptodate(bh))) { - journal->j_fc_off = i; + journal->j_fc_off = i + 1; return -EIO; } + put_bh(bh); + journal->j_fc_wbuf[i] = NULL; }

return 0;

From: Jan Kara jack@suse.cz

commit 4bb26f2885ac6930984ee451b952c5a6042f2c0e upstream.

When inode is created and written to using direct IO, there is nothing to clear the EXT4_STATE_MAY_INLINE_DATA flag. Thus when inode gets truncated later to say 1 byte and written using normal write, we will try to store the data as inline data. This confuses the code later because the inode now has both normal block and inline data allocated and the confusion manifests for example as:

kernel BUG at fs/ext4/inode.c:2721! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 0 PID: 359 Comm: repro Not tainted 5.19.0-rc8-00001-g31ba1e3b8305-dirty #15 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.0-1.fc36 04/01/2014 RIP: 0010:ext4_writepages+0x363d/0x3660 RSP: 0018:ffffc90000ccf260 EFLAGS: 00010293 RAX: ffffffff81e1abcd RBX: 0000008000000000 RCX: ffff88810842a180 RDX: 0000000000000000 RSI: 0000008000000000 RDI: 0000000000000000 RBP: ffffc90000ccf650 R08: ffffffff81e17d58 R09: ffffed10222c680b R10: dfffe910222c680c R11: 1ffff110222c680a R12: ffff888111634128 R13: ffffc90000ccf880 R14: 0000008410000000 R15: 0000000000000001 FS: 00007f72635d2640(0000) GS:ffff88811b000000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000565243379180 CR3: 000000010aa74000 CR4: 0000000000150eb0 Call Trace: <TASK> do_writepages+0x397/0x640 filemap_fdatawrite_wbc+0x151/0x1b0 file_write_and_wait_range+0x1c9/0x2b0 ext4_sync_file+0x19e/0xa00 vfs_fsync_range+0x17b/0x190 ext4_buffered_write_iter+0x488/0x530 ext4_file_write_iter+0x449/0x1b90 vfs_write+0xbcd/0xf40 ksys_write+0x198/0x2c0 __x64_sys_write+0x7b/0x90 do_syscall_64+0x3d/0x90 entry_SYSCALL_64_after_hwframe+0x63/0xcd </TASK>

Fix the problem by clearing EXT4_STATE_MAY_INLINE_DATA when we are doing direct IO write to a file.

Cc: stable@kernel.org Reported-by: Tadeusz Struk tadeusz.struk@linaro.org Reported-by: syzbot+bd13648a53ed6933ca49@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=a1e89d09bbbcbd5c4cb45db230ee28c82295398... Signed-off-by: Jan Kara jack@suse.cz Reviewed-by: Lukas Czerner lczerner@redhat.com Tested-by: Tadeusz Struktadeusz.struk@linaro.org Link: https://lore.kernel.org/r/20220727155753.13969-1-jack@suse.cz Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/file.c | 6 ++++++ 1 file changed, 6 insertions(+)

--- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -528,6 +528,12 @@ static ssize_t ext4_dio_write_iter(struc ret = -EAGAIN; goto out; } + /* + * Make sure inline data cannot be created anymore since we are going + * to allocate blocks for DIO. We know the inode does not have any + * inline data now because ext4_dio_supported() checked for that. + */ + ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);

offset = iocb->ki_pos; count = ret;

From: Lalith Rajendran lalithkraj@google.com

commit 3b575495ab8dbb4dbe85b4ac7f991693c3668ff5 upstream.

ext4_lazyinit_thread is not set freezable. Hence when the thread calls try_to_freeze it doesn't freeze during suspend and continues to send requests to the storage during suspend, resulting in suspend failures.

Cc: stable@kernel.org Signed-off-by: Lalith Rajendran lalithkraj@google.com Link: https://lore.kernel.org/r/20220818214049.1519544-1-lalithkraj@google.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/super.c | 1 + 1 file changed, 1 insertion(+)

--- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3377,6 +3377,7 @@ static int ext4_lazyinit_thread(void *ar unsigned long next_wakeup, cur;

BUG_ON(NULL == eli); + set_freezable();

cont_thread: while (true) {

From: Lukas Czerner lczerner@redhat.com

commit 50f094a5580e6297bf10a807d16f0ee23fa576cf upstream.

ea_inodes are using i_version for storing part of the reference count so we really need to leave it alone.

The problem can be reproduced by xfstest ext4/026 when iversion is enabled. Fix it by not calling inode_inc_iversion() for EXT4_EA_INODE_FL inodes in ext4_mark_iloc_dirty().

Cc: stable@kernel.org Signed-off-by: Lukas Czerner lczerner@redhat.com Reviewed-by: Jan Kara jack@suse.cz Reviewed-by: Jeff Layton jlayton@kernel.org Reviewed-by: Christian Brauner (Microsoft) brauner@kernel.org Link: https://lore.kernel.org/r/20220824160349.39664-1-lczerner@redhat.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/inode.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

--- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -5701,7 +5701,12 @@ int ext4_mark_iloc_dirty(handle_t *handl } ext4_fc_track_inode(handle, inode);

- if (IS_I_VERSION(inode)) + /* + * ea_inodes are using i_version for storing reference count, don't + * mess with it + */ + if (IS_I_VERSION(inode) && + !(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) inode_inc_iversion(inode);

/* the do_update_inode consumes one bh->b_count */

From: Jinke Han hanjinke.666@bytedance.com

commit d1052d236eddf6aa851434db1897b942e8db9921 upstream.

In our product environment, we encounter some jbd hung waiting handles to stop while several writters were doing memory reclaim for buffer head allocation in delay alloc write path. Ext4 do buffer head allocation with holding transaction handle which may be blocked too long if the reclaim works not so smooth. According to our bcc trace, the reclaim time in buffer head allocation can reach 258s and the jbd transaction commit also take almost the same time meanwhile. Except for these extreme cases, we often see several seconds delays for cgroup memory reclaim on our servers. This is more likely to happen considering docker environment.

One thing to note, the allocation of buffer heads is as often as page allocation or more often when blocksize less than page size. Just like page cache allocation, we should also place the buffer head allocation before startting the handle.

Cc: stable@kernel.org Signed-off-by: Jinke Han hanjinke.666@bytedance.com Link: https://lore.kernel.org/r/20220903012429.22555-1-hanjinke.666@bytedance.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/inode.c | 7 +++++++ 1 file changed, 7 insertions(+)

--- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1177,6 +1177,13 @@ retry_grab: page = grab_cache_page_write_begin(mapping, index, flags); if (!page) return -ENOMEM; + /* + * The same as page allocation, we prealloc buffer heads before + * starting the handle. + */ + if (!page_has_buffers(page)) + create_empty_buffers(page, inode->i_sb->s_blocksize, 0); + unlock_page(page);

retry_journal:

From: Ye Bin yebin10@huawei.com

commit ccbf8eeb39f2ff00b54726a2b20b35d788c4ecb5 upstream.

In 'ext4_fc_write_inode' function first call 'ext4_get_inode_loc' get 'iloc', after use it miss release 'iloc.bh'. So just release 'iloc.bh' before 'ext4_fc_write_inode' return.

Cc: stable@kernel.org Signed-off-by: Ye Bin yebin10@huawei.com Reviewed-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20220914100859.1415196-1-yebin10@huawei.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/fast_commit.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)

--- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -794,22 +794,25 @@ static int ext4_fc_write_inode(struct in tl.fc_tag = cpu_to_le16(EXT4_FC_TAG_INODE); tl.fc_len = cpu_to_le16(inode_len + sizeof(fc_inode.fc_ino));

+ ret = -ECANCELED; dst = ext4_fc_reserve_space(inode->i_sb, sizeof(tl) + inode_len + sizeof(fc_inode.fc_ino), crc); if (!dst) - return -ECANCELED; + goto err;

if (!ext4_fc_memcpy(inode->i_sb, dst, &tl, sizeof(tl), crc)) - return -ECANCELED; + goto err; dst += sizeof(tl); if (!ext4_fc_memcpy(inode->i_sb, dst, &fc_inode, sizeof(fc_inode), crc)) - return -ECANCELED; + goto err; dst += sizeof(fc_inode); if (!ext4_fc_memcpy(inode->i_sb, dst, (u8 *)ext4_raw_inode(&iloc), inode_len, crc)) - return -ECANCELED; - - return 0; + goto err; + ret = 0; +err: + brelse(iloc.bh); + return ret; }

/*

From: Ye Bin yebin10@huawei.com

commit 7069d105c1f15c442b68af43f7fde784f3126739 upstream.

As krealloc may return NULL, in this case 'state->fc_regions' may not be freed by krealloc, but 'state->fc_regions' already set NULL. Then will lead to 'state->fc_regions' memory leak.

Cc: stable@kernel.org Signed-off-by: Ye Bin yebin10@huawei.com Reviewed-by: Jan Kara jack@suse.cz Link: https://lore.kernel.org/r/20220921064040.3693255-3-yebin10@huawei.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/ext4/fast_commit.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-)

--- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -1607,15 +1607,17 @@ int ext4_fc_record_regions(struct super_ if (replay && state->fc_regions_used != state->fc_regions_valid) state->fc_regions_used = state->fc_regions_valid; if (state->fc_regions_used == state->fc_regions_size) { + struct ext4_fc_alloc_region *fc_regions; + state->fc_regions_size += EXT4_FC_REPLAY_REALLOC_INCREMENT; - state->fc_regions = krealloc( - state->fc_regions, - state->fc_regions_size * - sizeof(struct ext4_fc_alloc_region), - GFP_KERNEL); - if (!state->fc_regions) + fc_regions = krealloc(state->fc_regions, + state->fc_regions_size * + sizeof(struct ext4_fc_alloc_region), + GFP_KERNEL); + if (!fc_regions) return -ENOMEM; + state->fc_regions = fc_regions; } region = &state->fc_regions[state->fc_regions_used++]; region->ino = ino;

From: Rik van Riel riel@surriel.com

commit 747f7a2901174c9afa805dddfb7b24db6f65e985 upstream.

The KLP transition code depends on the TIF_PATCH_PENDING and the task->patch_state to stay in sync. On a normal (forward) transition, TIF_PATCH_PENDING will be set on every task in the system, while on a reverse transition (after a failed forward one) first TIF_PATCH_PENDING will be cleared from every task, followed by it being set on tasks that need to be transitioned back to the original code.

However, the fork code copies over the TIF_PATCH_PENDING flag from the parent to the child early on, in dup_task_struct and setup_thread_stack. Much later, klp_copy_process will set child->patch_state to match that of the parent.

However, the parent's patch_state may have been changed by KLP loading or unloading since it was initially copied over into the child.

This results in the KLP code occasionally hitting this warning in klp_complete_transition:

for_each_process_thread(g, task) { WARN_ON_ONCE(test_tsk_thread_flag(task, TIF_PATCH_PENDING)); task->patch_state = KLP_UNDEFINED; }

Set, or clear, the TIF_PATCH_PENDING flag in the child task depending on whether or not it is needed at the time klp_copy_process is called, at a point in copy_process where the tasklist_lock is held exclusively, preventing races with the KLP code.

The KLP code does have a few places where the state is changed without the tasklist_lock held, but those should not cause problems because klp_update_patch_state(current) cannot be called while the current task is in the middle of fork, klp_check_and_switch_task() which is called under the pi_lock, which prevents rescheduling, and manipulation of the patch state of idle tasks, which do not fork.

This should prevent this warning from triggering again in the future, and close the race for both normal and reverse transitions.

Signed-off-by: Rik van Riel riel@surriel.com Reported-by: Breno Leitao leitao@debian.org Reviewed-by: Petr Mladek pmladek@suse.com Acked-by: Josh Poimboeuf jpoimboe@kernel.org Fixes: d83a7cb375ee ("livepatch: change to a per-task consistency model") Cc: stable@kernel.org Signed-off-by: Petr Mladek pmladek@suse.com Link: https://lore.kernel.org/r/20220808150019.03d6a67b@imladris.surriel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/livepatch/transition.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-)

--- a/kernel/livepatch/transition.c +++ b/kernel/livepatch/transition.c @@ -610,9 +610,23 @@ void klp_reverse_transition(void) /* Called from copy_process() during fork */ void klp_copy_process(struct task_struct *child) { - child->patch_state = current->patch_state;

- /* TIF_PATCH_PENDING gets copied in setup_thread_stack() */ + /* + * The parent process may have gone through a KLP transition since + * the thread flag was copied in setup_thread_stack earlier. Bring + * the task flag up to date with the parent here. + * + * The operation is serialized against all klp_*_transition() + * operations by the tasklist_lock. The only exception is + * klp_update_patch_state(current), but we cannot race with + * that because we are current. + */ + if (test_tsk_thread_flag(current, TIF_PATCH_PENDING)) + set_tsk_thread_flag(child, TIF_PATCH_PENDING); + else + clear_tsk_thread_flag(child, TIF_PATCH_PENDING); + + child->patch_state = current->patch_state; }

/*

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

commit fa8f4a89736b654125fb254b0db753ac68a5fced upstream.

If a page is partially read, and then the splice system call is run against the ring buffer, it will always fail to read, no matter how much is in the ring buffer. That's because the code path for a partial read of the page does will fail if the "full" flag is set.

The splice system call wants full pages, so if the read of the ring buffer is not yet full, it should return zero, and the splice will block. But if a previous read was done, where the beginning has been consumed, it should still be given to the splice caller if the rest of the page has been written to.

This caused the splice command to never consume data in this scenario, and let the ring buffer just fill up and lose events.

Link: https://lkml.kernel.org/r/20220927144317.46be6b80@gandalf.local.home

Cc: stable@vger.kernel.org Fixes: 8789a9e7df6bf ("ring-buffer: read page interface") Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/ring_buffer.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-)

--- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -5574,7 +5574,15 @@ int ring_buffer_read_page(struct trace_b unsigned int pos = 0; unsigned int size;

- if (full) + /* + * If a full page is expected, this can still be returned + * if there's been a previous partial read and the + * rest of the page can be read and the commit page is off + * the reader page. + */ + if (full && + (!read || (len < (commit - read)) || + cpu_buffer->reader_page == cpu_buffer->commit_page)) goto out_unlock;

if (len > (commit - read))

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

commit ec0bbc5ec5664dcee344f79373852117dc672c86 upstream.

The wake up waiters only checks the "wakeup_full" variable and not the "full_waiters_pending". The full_waiters_pending is set when a waiter is added to the wait queue. The wakeup_full is only set when an event is triggered, and it clears the full_waiters_pending to avoid multiple calls to irq_work_queue().

The irq_work callback really needs to check both wakeup_full as well as full_waiters_pending such that this code can be used to wake up waiters when a file is closed that represents the ring buffer and the waiters need to be woken up.

Link: https://lkml.kernel.org/r/20220927231824.209460321@goodmis.org

Cc: stable@vger.kernel.org Cc: Ingo Molnar mingo@kernel.org Cc: Andrew Morton akpm@linux-foundation.org Fixes: 15693458c4bc0 ("tracing/ring-buffer: Move poll wake ups into ring buffer code") Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/ring_buffer.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -881,8 +881,9 @@ static void rb_wake_up_waiters(struct ir struct rb_irq_work *rbwork = container_of(work, struct rb_irq_work, work);

wake_up_all(&rbwork->waiters); - if (rbwork->wakeup_full) { + if (rbwork->full_waiters_pending || rbwork->wakeup_full) { rbwork->wakeup_full = false; + rbwork->full_waiters_pending = false; wake_up_all(&rbwork->full_waiters); } }

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

commit a0fcaaed0c46cf9399d3a2d6e0c87ddb3df0e044 upstream.

The ring buffer is broken up into sub buffers (currently of page size). Each sub buffer has a pointer to its "tail" (the last event written to the sub buffer). When a new event is requested, the tail is locally incremented to cover the size of the new event. This is done in a way that there is no need for locking.

If the tail goes past the end of the sub buffer, the process of moving to the next sub buffer takes place. After setting the current sub buffer to the next one, the previous one that had the tail go passed the end of the sub buffer needs to be reset back to the original tail location (before the new event was requested) and the rest of the sub buffer needs to be "padded".

The race happens when a reader takes control of the sub buffer. As readers do a "swap" of sub buffers from the ring buffer to get exclusive access to the sub buffer, it replaces the "head" sub buffer with an empty sub buffer that goes back into the writable portion of the ring buffer. This swap can happen as soon as the writer moves to the next sub buffer and before it updates the last sub buffer with padding.

Because the sub buffer can be released to the reader while the writer is still updating the padding, it is possible for the reader to see the event that goes past the end of the sub buffer. This can cause obvious issues.

To fix this, add a few memory barriers so that the reader definitely sees the updates to the sub buffer, and also waits until the writer has put back the "tail" of the sub buffer back to the last event that was written on it.

To be paranoid, it will only spin for 1 second, otherwise it will warn and shutdown the ring buffer code. 1 second should be enough as the writer does have preemption disabled. If the writer doesn't move within 1 second (with preemption disabled) something is horribly wrong. No interrupt should last 1 second!

Link: https://lore.kernel.org/all/20220830120854.7545-1-jiazi.li@transsion.com/ Link: https://bugzilla.kernel.org/show_bug.cgi?id=216369 Link: https://lkml.kernel.org/r/20220929104909.0650a36c@gandalf.local.home

Cc: Ingo Molnar mingo@kernel.org Cc: Andrew Morton akpm@linux-foundation.org Cc: stable@vger.kernel.org Fixes: c7b0930857e22 ("ring-buffer: prevent adding write in discarded area") Reported-by: Jiazi.Li jiazi.li@transsion.com Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/ring_buffer.c | 33 +++++++++++++++++++++++++++++++++ 1 file changed, 33 insertions(+)

--- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -2612,6 +2612,9 @@ rb_reset_tail(struct ring_buffer_per_cpu /* Mark the rest of the page with padding */ rb_event_set_padding(event);

+ /* Make sure the padding is visible before the write update */ + smp_wmb(); + /* Set the write back to the previous setting */ local_sub(length, &tail_page->write); return; @@ -2623,6 +2626,9 @@ rb_reset_tail(struct ring_buffer_per_cpu /* time delta must be non zero */ event->time_delta = 1;

+ /* Make sure the padding is visible before the tail_page->write update */ + smp_wmb(); + /* Set write to end of buffer */ length = (tail + length) - BUF_PAGE_SIZE; local_sub(length, &tail_page->write); @@ -4587,6 +4593,33 @@ rb_get_reader_page(struct ring_buffer_pe arch_spin_unlock(&cpu_buffer->lock); local_irq_restore(flags);

+ /* + * The writer has preempt disable, wait for it. But not forever + * Although, 1 second is pretty much "forever" + */ +#define USECS_WAIT 1000000 + for (nr_loops = 0; nr_loops < USECS_WAIT; nr_loops++) { + /* If the write is past the end of page, a writer is still updating it */ + if (likely(!reader || rb_page_write(reader) <= BUF_PAGE_SIZE)) + break; + + udelay(1); + + /* Get the latest version of the reader write value */ + smp_rmb(); + } + + /* The writer is not moving forward? Something is wrong */ + if (RB_WARN_ON(cpu_buffer, nr_loops == USECS_WAIT)) + reader = NULL; + + /* + * Make sure we see any padding after the write update + * (see rb_reset_tail()) + */ + smp_rmb(); + + return reader; }

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

commit f3ddb74ad0790030c9592229fb14d8c451f4e9a8 upstream.

When the file that represents the ring buffer is closed, there may be waiters waiting on more input from the ring buffer. Call ring_buffer_wake_waiters() to wake up any waiters when the file is closed.

Link: https://lkml.kernel.org/r/20220927231825.182416969@goodmis.org

Cc: stable@vger.kernel.org Cc: Ingo Molnar mingo@kernel.org Cc: Andrew Morton akpm@linux-foundation.org Fixes: e30f53aad2202 ("tracing: Do not busy wait in buffer splice") Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/trace_events.h | 1 + kernel/trace/trace.c | 15 +++++++++++++++ 2 files changed, 16 insertions(+)

--- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -91,6 +91,7 @@ struct trace_iterator { unsigned int temp_size; char *fmt; /* modified format holder */ unsigned int fmt_size; + long wait_index;

/* trace_seq for __print_flags() and __print_symbolic() etc. */ struct trace_seq tmp_seq; --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8117,6 +8117,12 @@ static int tracing_buffers_release(struc

__trace_array_put(iter->tr);

+ iter->wait_index++; + /* Make sure the waiters see the new wait_index */ + smp_wmb(); + + ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); + if (info->spare) ring_buffer_free_read_page(iter->array_buffer->buffer, info->spare_cpu, info->spare); @@ -8270,6 +8276,8 @@ tracing_buffers_splice_read(struct file

/* did we read anything? */ if (!spd.nr_pages) { + long wait_index; + if (ret) goto out;

@@ -8277,10 +8285,17 @@ tracing_buffers_splice_read(struct file if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) goto out;

+ wait_index = READ_ONCE(iter->wait_index); + ret = wait_on_pipe(iter, iter->tr->buffer_percent); if (ret) goto out;

+ /* Make sure we see the new wait_index */ + smp_rmb(); + if (wait_index != iter->wait_index) + goto out; + goto again; }

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

commit 01b2a52171735c6eea80ee2f355f32bea6c41418 upstream.

If a process is waiting on the ring buffer for data, there currently isn't a clean way to force it to wake up. Add an ioctl call that will force any tasks that are waiting on the trace_pipe_raw file to wake up.

Link: https://lkml.kernel.org/r/20220929095029.117f913f@gandalf.local.home

Cc: stable@vger.kernel.org Cc: Ingo Molnar mingo@kernel.org Cc: Andrew Morton akpm@linux-foundation.org Fixes: e30f53aad2202 ("tracing: Do not busy wait in buffer splice") Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/trace.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+)

--- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -8310,12 +8310,34 @@ out: return ret; }

+/* An ioctl call with cmd 0 to the ring buffer file will wake up all waiters */ +static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct ftrace_buffer_info *info = file->private_data; + struct trace_iterator *iter = &info->iter; + + if (cmd) + return -ENOIOCTLCMD; + + mutex_lock(&trace_types_lock); + + iter->wait_index++; + /* Make sure the waiters see the new wait_index */ + smp_wmb(); + + ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); + + mutex_unlock(&trace_types_lock); + return 0; +} + static const struct file_operations tracing_buffers_fops = { .open = tracing_buffers_open, .read = tracing_buffers_read, .poll = tracing_buffers_poll, .release = tracing_buffers_release, .splice_read = tracing_buffers_splice_read, + .unlocked_ioctl = tracing_buffers_ioctl, .llseek = no_llseek, };

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

commit 2e9906f84fc7c99388bb7123ade167250d50f1c0 upstream.

Have the specific functions for kernel probes that read strings to inject the "(fault)" name directly. trace_probes.c does this too (for uprobes) but as the code to read strings are going to be used by synthetic events (and perhaps other utilities), it simplifies the code by making sure those other uses do not need to implement the "(fault)" name injection as well.

Link: https://lkml.kernel.org/r/20221012104534.644803645@goodmis.org

Cc: stable@vger.kernel.org Cc: Andrew Morton akpm@linux-foundation.org Cc: Tom Zanussi zanussi@kernel.org Acked-by: Masami Hiramatsu (Google) mhiramat@kernel.org Reviewed-by: Tom Zanussi zanussi@kernel.org Fixes: bd82631d7ccdc ("tracing: Add support for dynamic strings to synthetic events") Signed-off-by: Steven Rostedt (Google) rostedt@goodmis.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/trace/trace_probe_kernel.h | 31 +++++++++++++++++++++++++------ 1 file changed, 25 insertions(+), 6 deletions(-)

--- a/kernel/trace/trace_probe_kernel.h +++ b/kernel/trace/trace_probe_kernel.h @@ -2,6 +2,8 @@ #ifndef __TRACE_PROBE_KERNEL_H_ #define __TRACE_PROBE_KERNEL_H_

+#define FAULT_STRING "(fault)" + /* * This depends on trace_probe.h, but can not include it due to * the way trace_probe_tmpl.h is used by trace_kprobe.c and trace_eprobe.c. @@ -13,8 +15,16 @@ static nokprobe_inline int kern_fetch_store_strlen_user(unsigned long addr) { const void __user *uaddr = (__force const void __user *)addr; + int ret;

- return strnlen_user_nofault(uaddr, MAX_STRING_SIZE); + ret = strnlen_user_nofault(uaddr, MAX_STRING_SIZE); + /* + * strnlen_user_nofault returns zero on fault, insert the + * FAULT_STRING when that occurs. + */ + if (ret <= 0) + return strlen(FAULT_STRING) + 1; + return ret; }

/* Return the length of string -- including null terminal byte */ @@ -34,7 +44,18 @@ kern_fetch_store_strlen(unsigned long ad len++; } while (c && ret == 0 && len < MAX_STRING_SIZE);

- return (ret < 0) ? ret : len; + /* For faults, return enough to hold the FAULT_STRING */ + return (ret < 0) ? strlen(FAULT_STRING) + 1 : len; +} + +static nokprobe_inline void set_data_loc(int ret, void *dest, void *__dest, void *base, int len) +{ + if (ret >= 0) { + *(u32 *)dest = make_data_loc(ret, __dest - base); + } else { + strscpy(__dest, FAULT_STRING, len); + ret = strlen(__dest) + 1; + } }

/* @@ -55,8 +76,7 @@ kern_fetch_store_string_user(unsigned lo __dest = get_loc_data(dest, base);

ret = strncpy_from_user_nofault(__dest, uaddr, maxlen); - if (ret >= 0) - *(u32 *)dest = make_data_loc(ret, __dest - base); + set_data_loc(ret, dest, __dest, base, maxlen);

return ret; } @@ -87,8 +107,7 @@ kern_fetch_store_string(unsigned long ad * probing. */ ret = strncpy_from_kernel_nofault(__dest, (void *)addr, maxlen); - if (ret >= 0) - *(u32 *)dest = make_data_loc(ret, __dest - base); + set_data_loc(ret, dest, __dest, base, maxlen);

return ret; }

From: Mario Limonciello mario.limonciello@amd.com

commit 5d2569cb4a65c373896ec0217febdf88739ed295 upstream.

Software that has run before the USB4 CM in Linux runs may have disabled hotplug events for a given lane adapter.

Other CMs such as that one distributed with Windows 11 will enable hotplug events. Do the same thing in the Linux CM which fixes hotplug events on "AMD Pink Sardine".

Cc: stable@vger.kernel.org Signed-off-by: Mario Limonciello mario.limonciello@amd.com Signed-off-by: Mika Westerberg mika.westerberg@linux.intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/thunderbolt/switch.c | 24 ++++++++++++++++++++++++ drivers/thunderbolt/tb.h | 1 + drivers/thunderbolt/tb_regs.h | 1 + drivers/thunderbolt/usb4.c | 20 ++++++++++++++++++++ 4 files changed, 46 insertions(+)

--- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -2690,6 +2690,26 @@ static void tb_switch_credits_init(struc tb_sw_info(sw, "failed to determine preferred buffer allocation, using defaults\n"); }

+static int tb_switch_port_hotplug_enable(struct tb_switch *sw) +{ + struct tb_port *port; + + if (tb_switch_is_icm(sw)) + return 0; + + tb_switch_for_each_port(sw, port) { + int res; + + if (!port->cap_usb4) + continue; + + res = usb4_port_hotplug_enable(port); + if (res) + return res; + } + return 0; +} + /** * tb_switch_add() - Add a switch to the domain * @sw: Switch to add @@ -2761,6 +2781,10 @@ int tb_switch_add(struct tb_switch *sw) return ret; }

+ ret = tb_switch_port_hotplug_enable(sw); + if (ret) + return ret; + ret = device_add(&sw->dev); if (ret) { dev_err(&sw->dev, "failed to add device: %d\n", ret); --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -1067,6 +1067,7 @@ int usb4_switch_add_ports(struct tb_swit void usb4_switch_remove_ports(struct tb_switch *sw);

int usb4_port_unlock(struct tb_port *port); +int usb4_port_hotplug_enable(struct tb_port *port); int usb4_port_configure(struct tb_port *port); void usb4_port_unconfigure(struct tb_port *port); int usb4_port_configure_xdomain(struct tb_port *port); --- a/drivers/thunderbolt/tb_regs.h +++ b/drivers/thunderbolt/tb_regs.h @@ -301,6 +301,7 @@ struct tb_regs_port_header { #define ADP_CS_5 0x05 #define ADP_CS_5_LCA_MASK GENMASK(28, 22) #define ADP_CS_5_LCA_SHIFT 22 +#define ADP_CS_5_DHP BIT(31)

/* TMU adapter registers */ #define TMU_ADP_CS_3 0x03 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -1068,6 +1068,26 @@ int usb4_port_unlock(struct tb_port *por return tb_port_write(port, &val, TB_CFG_PORT, ADP_CS_4, 1); }

+/** + * usb4_port_hotplug_enable() - Enables hotplug for a port + * @port: USB4 port to operate on + * + * Enables hot plug events on a given port. This is only intended + * to be used on lane, DP-IN, and DP-OUT adapters. + */ +int usb4_port_hotplug_enable(struct tb_port *port) +{ + int ret; + u32 val; + + ret = tb_port_read(port, &val, TB_CFG_PORT, ADP_CS_5, 1); + if (ret) + return ret; + + val &= ~ADP_CS_5_DHP; + return tb_port_write(port, &val, TB_CFG_PORT, ADP_CS_5, 1); +} + static int usb4_port_set_configured(struct tb_port *port, bool configured) { int ret;

From: Dmitry Osipenko dmitry.osipenko@collabora.com

commit 708938f8495147fe2e77a9a3e1015d8e6899323e upstream.

The cedrus_hw_resume() crashes with NULL deference on driver probe if runtime PM is disabled because it uses platform data that hasn't been set up yet. Fix this by setting the platform data earlier during probe.

Cc: stable@vger.kernel.org Fixes: 50e761516f2b (media: platform: Add Cedrus VPU decoder driver) Signed-off-by: Dmitry Osipenko dmitry.osipenko@collabora.com Signed-off-by: Nicolas Dufresne nicolas.dufresne@collabora.com Reviewed-by: Samuel Holland samuel@sholland.org Acked-by: Paul Kocialkowski paul.kocialkowski@bootlin.com Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/staging/media/sunxi/cedrus/cedrus.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/staging/media/sunxi/cedrus/cedrus.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus.c @@ -369,6 +369,8 @@ static int cedrus_probe(struct platform_ if (!dev) return -ENOMEM;

+ platform_set_drvdata(pdev, dev); + dev->vfd = cedrus_video_device; dev->dev = &pdev->dev; dev->pdev = pdev; @@ -440,8 +442,6 @@ static int cedrus_probe(struct platform_ goto err_m2m_mc; }

- platform_set_drvdata(pdev, dev); - return 0;

err_m2m_mc:

From: Yu Kuai yukuai3@huawei.com

commit 8c5035dfbb9475b67c82b3fdb7351236525bf52b upstream.

Our test found a problem that wbt inflight counter is negative, which will cause io hang(noted that this problem doesn't exist in mainline):

t1: device create t2: issue io add_disk blk_register_queue wbt_enable_default wbt_init rq_qos_add // wb_normal is still 0 /* * in mainline, disk can't be opened before * bdev_add(), however, in old kernels, disk * can be opened before blk_register_queue(). */ blkdev_issue_flush // disk size is 0, however, it's not checked submit_bio_wait submit_bio blk_mq_submit_bio rq_qos_throttle wbt_wait bio_to_wbt_flags rwb_enabled // wb_normal is 0, inflight is not increased

wbt_queue_depth_changed(&rwb->rqos); wbt_update_limits // wb_normal is initialized rq_qos_track wbt_track rq->wbt_flags |= bio_to_wbt_flags(rwb, bio); // wb_normal is not 0，wbt_flags will be set t3: io completion blk_mq_free_request rq_qos_done wbt_done wbt_is_tracked // return true __wbt_done wbt_rqw_done atomic_dec_return(&rqw->inflight); // inflight is decreased

commit 8235b5c1e8c1 ("block: call bdev_add later in device_add_disk") can avoid this problem, however it's better to fix this problem in wbt:

1) Lower kernel can't backport this patch due to lots of refactor. 2) Root cause is that wbt call rq_qos_add() before wb_normal is initialized.

Fixes: e34cbd307477 ("blk-wbt: add general throttling mechanism") Cc: stable@vger.kernel.org Signed-off-by: Yu Kuai yukuai3@huawei.com Link: https://lore.kernel.org/r/20220913105749.3086243-1-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- block/blk-wbt.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-)

--- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -843,6 +843,10 @@ int wbt_init(struct request_queue *q) rwb->enable_state = WBT_STATE_ON_DEFAULT; rwb->wc = 1; rwb->rq_depth.default_depth = RWB_DEF_DEPTH; + rwb->min_lat_nsec = wbt_default_latency_nsec(q); + + wbt_queue_depth_changed(&rwb->rqos); + wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));

/* * Assign rwb and add the stats callback. @@ -853,11 +857,6 @@ int wbt_init(struct request_queue *q)

blk_stat_add_callback(q, rwb->cb);

- rwb->min_lat_nsec = wbt_default_latency_nsec(q); - - wbt_queue_depth_changed(&rwb->rqos); - wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); - return 0;

err_free:

From: Sean Christopherson seanjc@google.com

commit d953540430c5af57f5de97ea9e36253908204027 upstream.

Drop pending exceptions and events queued for re-injection when leaving nested guest mode, even if the "exit" is due to VM-Fail, SMI, or forced by host userspace. Failure to purge events could result in an event belonging to L2 being injected into L1.

This _should_ never happen for VM-Fail as all events should be blocked by nested_run_pending, but it's possible if KVM, not the L1 hypervisor, is the source of VM-Fail when running vmcs02.

SMI is a nop (barring unknown bugs) as recognition of SMI and thus entry to SMM is blocked by pending exceptions and re-injected events.

Forced exit is definitely buggy, but has likely gone unnoticed because userspace probably follows the forced exit with KVM_SET_VCPU_EVENTS (or some other ioctl() that purges the queue).

Fixes: 4f350c6dbcb9 ("kvm: nVMX: Handle deferred early VMLAUNCH/VMRESUME failure properly") Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson seanjc@google.com Reviewed-by: Jim Mattson jmattson@google.com Reviewed-by: Maxim Levitsky mlevitsk@redhat.com Link: https://lore.kernel.org/r/20220830231614.3580124-2-seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/vmx/nested.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-)

--- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4251,14 +4251,6 @@ static void prepare_vmcs12(struct kvm_vc nested_vmx_abort(vcpu, VMX_ABORT_SAVE_GUEST_MSR_FAIL); } - - /* - * Drop what we picked up for L2 via vmx_complete_interrupts. It is - * preserved above and would only end up incorrectly in L1. - */ - vcpu->arch.nmi_injected = false; - kvm_clear_exception_queue(vcpu); - kvm_clear_interrupt_queue(vcpu); }

/* @@ -4598,6 +4590,17 @@ void nested_vmx_vmexit(struct kvm_vcpu * WARN_ON_ONCE(nested_early_check); }

+ /* + * Drop events/exceptions that were queued for re-injection to L2 + * (picked up via vmx_complete_interrupts()), as well as exceptions + * that were pending for L2. Note, this must NOT be hoisted above + * prepare_vmcs12(), events/exceptions queued for re-injection need to + * be captured in vmcs12 (see vmcs12_save_pending_event()). + */ + vcpu->arch.nmi_injected = false; + kvm_clear_exception_queue(vcpu); + kvm_clear_interrupt_queue(vcpu); + vmx_switch_vmcs(vcpu, &vmx->vmcs01);

/* Update any VMCS fields that might have changed while L2 ran */

From: Sean Christopherson seanjc@google.com

commit eba9799b5a6efe2993cf92529608e4aa8163d73b upstream.

Deliberately truncate the exception error code when shoving it into the VMCS (VM-Entry field for vmcs01 and vmcs02, VM-Exit field for vmcs12). Intel CPUs are incapable of handling 32-bit error codes and will never generate an error code with bits 31:16, but userspace can provide an arbitrary error code via KVM_SET_VCPU_EVENTS. Failure to drop the bits on exception injection results in failed VM-Entry, as VMX disallows setting bits 31:16. Setting the bits on VM-Exit would at best confuse L1, and at worse induce a nested VM-Entry failure, e.g. if L1 decided to reinject the exception back into L2.

Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson seanjc@google.com Reviewed-by: Jim Mattson jmattson@google.com Reviewed-by: Maxim Levitsky mlevitsk@redhat.com Link: https://lore.kernel.org/r/20220830231614.3580124-3-seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/vmx/nested.c | 11 ++++++++++- arch/x86/kvm/vmx/vmx.c | 12 +++++++++++- 2 files changed, 21 insertions(+), 2 deletions(-)

--- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3826,7 +3826,16 @@ static void nested_vmx_inject_exception_ u32 intr_info = nr | INTR_INFO_VALID_MASK;

if (vcpu->arch.exception.has_error_code) { - vmcs12->vm_exit_intr_error_code = vcpu->arch.exception.error_code; + /* + * Intel CPUs do not generate error codes with bits 31:16 set, + * and more importantly VMX disallows setting bits 31:16 in the + * injected error code for VM-Entry. Drop the bits to mimic + * hardware and avoid inducing failure on nested VM-Entry if L1 + * chooses to inject the exception back to L2. AMD CPUs _do_ + * generate "full" 32-bit error codes, so KVM allows userspace + * to inject exception error codes with bits 31:16 set. + */ + vmcs12->vm_exit_intr_error_code = (u16)vcpu->arch.exception.error_code; intr_info |= INTR_INFO_DELIVER_CODE_MASK; }

--- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1676,7 +1676,17 @@ static void vmx_queue_exception(struct k kvm_deliver_exception_payload(vcpu);

if (has_error_code) { - vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code); + /* + * Despite the error code being architecturally defined as 32 + * bits, and the VMCS field being 32 bits, Intel CPUs and thus + * VMX don't actually supporting setting bits 31:16. Hardware + * will (should) never provide a bogus error code, but AMD CPUs + * do generate error codes with bits 31:16 set, and so KVM's + * ABI lets userspace shove in arbitrary 32-bit values. Drop + * the upper bits to avoid VM-Fail, losing information that + * does't really exist is preferable to killing the VM. + */ + vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, (u16)error_code); intr_info |= INTR_INFO_DELIVER_CODE_MASK; }

From: Lyude Paul lyude@redhat.com

commit 8ba9249396bef37cb68be9e8dee7847f1737db9d upstream.

As it turns out: while Nvidia does actually have interlacing knobs on their GPU still pretty much no current GPUs since Volta actually support it. Trying interlacing on these GPUs will result in NVDisplay being quite unhappy like so:

nouveau 0000:1f:00.0: disp: chid 0 stat 00004802 reason 4 [INVALID_ARG] mthd 2008 data 00000001 code 00080000 nouveau 0000:1f:00.0: disp: chid 0 stat 10005080 reason 5 [INVALID_STATE] mthd 0200 data 00000001 code 00000001

So let's fix this by following the same behavior Nvidia's driver does and disable interlacing entirely.

Signed-off-by: Lyude Paul lyude@redhat.com Cc: stable@vger.kernel.org Reviewed-by: Karol Herbst kherbst@redhat.com Link: https://patchwork.freedesktop.org/patch/msgid/20220816180436.156310-1-lyude@... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/nouveau/nouveau_connector.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -503,7 +503,8 @@ nouveau_connector_set_encoder(struct drm connector->interlace_allowed = nv_encoder->caps.dp_interlace; else - connector->interlace_allowed = true; + connector->interlace_allowed = + drm->client.device.info.family < NV_DEVICE_INFO_V0_VOLTA; connector->doublescan_allowed = true; } else if (nv_encoder->dcb->type == DCB_OUTPUT_LVDS ||

From: Ville Syrjälä ville.syrjala@linux.intel.com

commit c56453a00f19ccddee302f5f9fe96b80e0b47fd3 upstream.

Take the gen12+ RC CCS modifier into account when calculating the watermarks. Othwerwise we'll calculate the watermarks thinking this Y-tiled modifier is linear.

The rc_surface part is actually a nop since that is not used for any glk+ platform.

v2: Split RC CCS vs. MC CCS to separate patches

Cc: stable@vger.kernel.org Fixes: b3e57bccd68a ("drm/i915/tgl: Gen-12 render decompression") Reviewed-by: Juha-Pekka Heikkila juhapekka.heikkila@gmail.com Signed-off-by: Ville Syrjälä ville.syrjala@linux.intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20221003111544.8007-2-ville.sy... (cherry picked from commit a89a96a586114f67598c6391c75678b4dba5c2da) Signed-off-by: Tvrtko Ursulin tvrtko.ursulin@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/intel_pm.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -5402,10 +5402,12 @@ skl_compute_wm_params(const struct intel wp->y_tiled = modifier == I915_FORMAT_MOD_Y_TILED || modifier == I915_FORMAT_MOD_Yf_TILED || modifier == I915_FORMAT_MOD_Y_TILED_CCS || - modifier == I915_FORMAT_MOD_Yf_TILED_CCS; + modifier == I915_FORMAT_MOD_Yf_TILED_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS; wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED; wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS || - modifier == I915_FORMAT_MOD_Yf_TILED_CCS; + modifier == I915_FORMAT_MOD_Yf_TILED_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS; wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier);

wp->width = width;

From: Ville Syrjälä ville.syrjala@linux.intel.com

commit 070a2855900de17b1e11a0dc35af9794e80f1a28 upstream.

Take the gen12+ CCS+CC modifier into account when calculating the watermarks. Othwerwise we'll calculate the watermarks thinking this Y-tiled modifier is linear.

The rc_surface part is actually a nop since that is not used for any glk+ platform.

Cc: stable@vger.kernel.org Fixes: d1e2775e9b96 ("drm/i915/tgl: Add Clear Color support for TGL Render Decompression") Reviewed-by: Juha-Pekka Heikkila juhapekka.heikkila@gmail.com Signed-off-by: Ville Syrjälä ville.syrjala@linux.intel.com Link: https://patchwork.freedesktop.org/patch/msgid/20221003111544.8007-4-ville.sy... (cherry picked from commit a627455bbe50a111475d7a42beb58fa64bd96c83) Signed-off-by: Tvrtko Ursulin tvrtko.ursulin@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/i915/intel_pm.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -5404,12 +5404,14 @@ skl_compute_wm_params(const struct intel modifier == I915_FORMAT_MOD_Y_TILED_CCS || modifier == I915_FORMAT_MOD_Yf_TILED_CCS || modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS; + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC; wp->x_tiled = modifier == I915_FORMAT_MOD_X_TILED; wp->rc_surface = modifier == I915_FORMAT_MOD_Y_TILED_CCS || modifier == I915_FORMAT_MOD_Yf_TILED_CCS || modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS || - modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS; + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS || + modifier == I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC; wp->is_planar = intel_format_info_is_yuv_semiplanar(format, modifier);

wp->width = width;

From: Steve French stfrench@microsoft.com

commit f09bd695af3b8ab46fc24e5d6954a24104c38387 upstream.

Coverity spotted that we were not initalizing Stbz1 and Stbz2 to zero in create_sd_buf.

Addresses-Coverity: 1513848 ("Uninitialized scalar variable") Cc: stable@vger.kernel.org Reviewed-by: Paulo Alcantara (SUSE) pc@cjr.nz Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/cifs/smb2pdu.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2354,7 +2354,7 @@ create_sd_buf(umode_t mode, bool set_own unsigned int acelen, acl_size, ace_count; unsigned int owner_offset = 0; unsigned int group_offset = 0; - struct smb3_acl acl; + struct smb3_acl acl = {};

*len = roundup(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 4), 8);

@@ -2427,6 +2427,7 @@ create_sd_buf(umode_t mode, bool set_own acl.AclRevision = ACL_REVISION; /* See 2.4.4.1 of MS-DTYP */ acl.AclSize = cpu_to_le16(acl_size); acl.AceCount = cpu_to_le16(ace_count); + /* acl.Sbz1 and Sbz2 MBZ so are not set here, but initialized above */ memcpy(aclptr, &acl, sizeof(struct smb3_acl));

buf->ccontext.DataLength = cpu_to_le32(ptr - (__u8 *)&buf->sd);

From: Mimi Zohar zohar@linux.ibm.com

[ Upstream commit 5926586f291b53cb8a0c9631fc19489be1186e2d ]

Limit validating the hash algorithm to just security.ima xattr, not the security.evm xattr or any of the protected EVM security xattrs, nor posix acls.

Fixes: 50f742dd9147 ("IMA: block writes of the security.ima xattr with unsupported algorithms") Reported-by: Christian Brauner brauner@kernel.org Acked-by: Christian Brauner (Microsoft) brauner@kernel.org Signed-off-by: Mimi Zohar zohar@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- security/integrity/ima/ima_appraise.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c index ed04bb7c7512..08b49bd1e8ca 100644 --- a/security/integrity/ima/ima_appraise.c +++ b/security/integrity/ima/ima_appraise.c @@ -644,22 +644,26 @@ int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name, const struct evm_ima_xattr_data *xvalue = xattr_value; int digsig = 0; int result; + int err;

result = ima_protect_xattr(dentry, xattr_name, xattr_value, xattr_value_len); if (result == 1) { if (!xattr_value_len || (xvalue->type >= IMA_XATTR_LAST)) return -EINVAL; + + err = validate_hash_algo(dentry, xvalue, xattr_value_len); + if (err) + return err; + digsig = (xvalue->type == EVM_IMA_XATTR_DIGSIG); } else if (!strcmp(xattr_name, XATTR_NAME_EVM) && xattr_value_len > 0) { digsig = (xvalue->type == EVM_XATTR_PORTABLE_DIGSIG); } if (result == 1 || evm_revalidate_status(xattr_name)) { - result = validate_hash_algo(dentry, xvalue, xattr_value_len); - if (result) - return result; - ima_reset_appraise_flags(d_backing_inode(dentry), digsig); + if (result == 1) + result = 0; } return result; }

From: Christian Brauner brauner@kernel.org

[ Upstream commit a26aa12384158116c0d80d50e0bdc7b3323551e2 ]

The xattr code in ntfs3 is currently a bit confused. For example, it defines a POSIX ACL i_op->set_acl() method but instead of relying on the generic POSIX ACL VFS helpers it defines its own set of xattr helpers with the consequence that i_op->set_acl() is currently dead code.

Switch ntfs3 to rely on the VFS POSIX ACL xattr handlers. Also remove i_op->{g,s}et_acl() methods from symlink inode operations. Symlinks don't support xattrs.

This is a preliminary change for the following patches which move handling idmapped mounts directly in posix_acl_xattr_set().

This survives POSIX ACL xfstests.

Fixes: be71b5cba2e6 ("fs/ntfs3: Add attrib operations") Signed-off-by: Christian Brauner (Microsoft) brauner@kernel.org Reviewed-by: Seth Forshee (DigitalOcean) sforshee@kernel.org> Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ntfs3/inode.c | 2 - fs/ntfs3/xattr.c | 102 +++-------------------------------------------- 2 files changed, 6 insertions(+), 98 deletions(-)

diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index b2cc1191be69..64b4a3c29878 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -1942,8 +1942,6 @@ const struct inode_operations ntfs_link_inode_operations = { .setattr = ntfs3_setattr, .listxattr = ntfs_listxattr, .permission = ntfs_permission, - .get_acl = ntfs_get_acl, - .set_acl = ntfs_set_acl, };

const struct address_space_operations ntfs_aops = { diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 4652b9796995..eb799a5cdfad 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -623,67 +623,6 @@ int ntfs_set_acl(struct user_namespace *mnt_userns, struct inode *inode, return ntfs_set_acl_ex(mnt_userns, inode, acl, type, false); }

-static int ntfs_xattr_get_acl(struct user_namespace *mnt_userns, - struct inode *inode, int type, void *buffer, - size_t size) -{ - struct posix_acl *acl; - int err; - - if (!(inode->i_sb->s_flags & SB_POSIXACL)) { - ntfs_inode_warn(inode, "add mount option "acl" to use acl"); - return -EOPNOTSUPP; - } - - acl = ntfs_get_acl(inode, type, false); - if (IS_ERR(acl)) - return PTR_ERR(acl); - - if (!acl) - return -ENODATA; - - err = posix_acl_to_xattr(&init_user_ns, acl, buffer, size); - posix_acl_release(acl); - - return err; -} - -static int ntfs_xattr_set_acl(struct user_namespace *mnt_userns, - struct inode *inode, int type, const void *value, - size_t size) -{ - struct posix_acl *acl; - int err; - - if (!(inode->i_sb->s_flags & SB_POSIXACL)) { - ntfs_inode_warn(inode, "add mount option "acl" to use acl"); - return -EOPNOTSUPP; - } - - if (!inode_owner_or_capable(mnt_userns, inode)) - return -EPERM; - - if (!value) { - acl = NULL; - } else { - acl = posix_acl_from_xattr(&init_user_ns, value, size); - if (IS_ERR(acl)) - return PTR_ERR(acl); - - if (acl) { - err = posix_acl_valid(&init_user_ns, acl); - if (err) - goto release_and_out; - } - } - - err = ntfs_set_acl(mnt_userns, inode, acl, type); - -release_and_out: - posix_acl_release(acl); - return err; -} - /* * ntfs_init_acl - Initialize the ACLs of a new inode. * @@ -850,23 +789,6 @@ static int ntfs_getxattr(const struct xattr_handler *handler, struct dentry *de, goto out; }

-#ifdef CONFIG_NTFS3_FS_POSIX_ACL - if ((name_len == sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1 && - !memcmp(name, XATTR_NAME_POSIX_ACL_ACCESS, - sizeof(XATTR_NAME_POSIX_ACL_ACCESS))) || - (name_len == sizeof(XATTR_NAME_POSIX_ACL_DEFAULT) - 1 && - !memcmp(name, XATTR_NAME_POSIX_ACL_DEFAULT, - sizeof(XATTR_NAME_POSIX_ACL_DEFAULT)))) { - /* TODO: init_user_ns? */ - err = ntfs_xattr_get_acl( - &init_user_ns, inode, - name_len == sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1 - ? ACL_TYPE_ACCESS - : ACL_TYPE_DEFAULT, - buffer, size); - goto out; - } -#endif /* Deal with NTFS extended attribute. */ err = ntfs_get_ea(inode, name, name_len, buffer, size, NULL);

@@ -979,22 +901,6 @@ static noinline int ntfs_setxattr(const struct xattr_handler *handler, goto out; }

-#ifdef CONFIG_NTFS3_FS_POSIX_ACL - if ((name_len == sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1 && - !memcmp(name, XATTR_NAME_POSIX_ACL_ACCESS, - sizeof(XATTR_NAME_POSIX_ACL_ACCESS))) || - (name_len == sizeof(XATTR_NAME_POSIX_ACL_DEFAULT) - 1 && - !memcmp(name, XATTR_NAME_POSIX_ACL_DEFAULT, - sizeof(XATTR_NAME_POSIX_ACL_DEFAULT)))) { - err = ntfs_xattr_set_acl( - mnt_userns, inode, - name_len == sizeof(XATTR_NAME_POSIX_ACL_ACCESS) - 1 - ? ACL_TYPE_ACCESS - : ACL_TYPE_DEFAULT, - value, size); - goto out; - } -#endif /* Deal with NTFS extended attribute. */ err = ntfs_set_ea(inode, name, name_len, value, size, flags);

@@ -1082,7 +988,7 @@ static bool ntfs_xattr_user_list(struct dentry *dentry) }

// clang-format off -static const struct xattr_handler ntfs_xattr_handler = { +static const struct xattr_handler ntfs_other_xattr_handler = { .prefix = "", .get = ntfs_getxattr, .set = ntfs_setxattr, @@ -1090,7 +996,11 @@ static const struct xattr_handler ntfs_xattr_handler = { };

const struct xattr_handler *ntfs_xattr_handlers[] = { - &ntfs_xattr_handler, +#ifdef CONFIG_NTFS3_FS_POSIX_ACL + &posix_acl_access_xattr_handler, + &posix_acl_default_xattr_handler, +#endif + &ntfs_other_xattr_handler, NULL, }; // clang-format on

From: Kees Cook keescook@chromium.org

[ Upstream commit c5783af354688b24abd359f7086c282ec74de993 ]

As done for other sections, define the extern as a character array, which relaxes many of the compiler-time object size checks, which would otherwise assume it's a single long. Solves the following build error:

arch/sh/kernel/machvec.c: error: array subscript 'struct sh_machine_vector[0]' is partly outside array bounds of 'long int[1]' [-Werror=array-bounds]: => 105:33

Cc: Yoshinori Sato ysato@users.sourceforge.jp Cc: Rich Felker dalias@libc.org Cc: linux-sh@vger.kernel.org Reported-by: Geert Uytterhoeven geert@linux-m68k.org Link: https://lore.kernel.org/lkml/alpine.DEB.2.22.394.2209050944290.964530@ramsan... Fixes: 9655ad03af2d ("sh: Fixup machvec support.") Reviewed-by: Geert Uytterhoeven geert+renesas@glider.be Reviewed-by: Gustavo A. R. Silva gustavoars@kernel.org Acked-by: Rich Felker dalias@libc.org Signed-off-by: Kees Cook keescook@chromium.org Signed-off-by: Sasha Levin sashal@kernel.org --- arch/sh/include/asm/sections.h | 2 +- arch/sh/kernel/machvec.c | 10 +++++----- 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/sh/include/asm/sections.h b/arch/sh/include/asm/sections.h index 8edb824049b9..0cb0ca149ac3 100644 --- a/arch/sh/include/asm/sections.h +++ b/arch/sh/include/asm/sections.h @@ -4,7 +4,7 @@

#include <asm-generic/sections.h>

-extern long __machvec_start, __machvec_end; +extern char __machvec_start[], __machvec_end[]; extern char __uncached_start, __uncached_end; extern char __start_eh_frame[], __stop_eh_frame[];

diff --git a/arch/sh/kernel/machvec.c b/arch/sh/kernel/machvec.c index d606679a211e..57efaf5b82ae 100644 --- a/arch/sh/kernel/machvec.c +++ b/arch/sh/kernel/machvec.c @@ -20,8 +20,8 @@ #define MV_NAME_SIZE 32

#define for_each_mv(mv) \ - for ((mv) = (struct sh_machine_vector *)&__machvec_start; \ - (mv) && (unsigned long)(mv) < (unsigned long)&__machvec_end; \ + for ((mv) = (struct sh_machine_vector *)__machvec_start; \ + (mv) && (unsigned long)(mv) < (unsigned long)__machvec_end; \ (mv)++)

static struct sh_machine_vector * __init get_mv_byname(const char *name) @@ -87,8 +87,8 @@ void __init sh_mv_setup(void) if (!machvec_selected) { unsigned long machvec_size;

- machvec_size = ((unsigned long)&__machvec_end - - (unsigned long)&__machvec_start); + machvec_size = ((unsigned long)__machvec_end - + (unsigned long)__machvec_start);

/* * Sanity check for machvec section alignment. Ensure @@ -102,7 +102,7 @@ void __init sh_mv_setup(void) * vector (usually the only one) from .machvec.init. */ if (machvec_size >= sizeof(struct sh_machine_vector)) - sh_mv = *(struct sh_machine_vector *)&__machvec_start; + sh_mv = *(struct sh_machine_vector *)__machvec_start; }

pr_notice("Booting machvec: %s\n", get_system_type());

From: Lin Yujun linyujun809@huawei.com

[ Upstream commit 11bec9cba4de06b3c0e9e4041453c2caaa1cbec1 ]

In error case in bridge_platform_create after calling platform_device_add()/platform_device_add_data()/ platform_device_add_resources(), release the failed 'pdev' or it will be leak, call platform_device_put() to fix this problem.

Besides, 'pdev' is divided into 'pdev_wd' and 'pdev_bd', use platform_device_unregister() to release sgi_w1 resources when xtalk-bridge registration fails.

Fixes: 5dc76a96e95a ("MIPS: PCI: use information from 1-wire PROM for IOC3 detection") Signed-off-by: Lin Yujun linyujun809@huawei.com Signed-off-by: Thomas Bogendoerfer tsbogend@alpha.franken.de Signed-off-by: Sasha Levin sashal@kernel.org --- arch/mips/sgi-ip27/ip27-xtalk.c | 70 +++++++++++++++++++++++---------- 1 file changed, 50 insertions(+), 20 deletions(-)

diff --git a/arch/mips/sgi-ip27/ip27-xtalk.c b/arch/mips/sgi-ip27/ip27-xtalk.c index e762886d1dda..5143d1cf8984 100644 --- a/arch/mips/sgi-ip27/ip27-xtalk.c +++ b/arch/mips/sgi-ip27/ip27-xtalk.c @@ -27,15 +27,18 @@ static void bridge_platform_create(nasid_t nasid, int widget, int masterwid) { struct xtalk_bridge_platform_data *bd; struct sgi_w1_platform_data *wd; - struct platform_device *pdev; + struct platform_device *pdev_wd; + struct platform_device *pdev_bd; struct resource w1_res; unsigned long offset;

offset = NODE_OFFSET(nasid);

wd = kzalloc(sizeof(*wd), GFP_KERNEL); - if (!wd) - goto no_mem; + if (!wd) { + pr_warn("xtalk:n%d/%x bridge create out of memory\n", nasid, widget); + return; + }

snprintf(wd->dev_id, sizeof(wd->dev_id), "bridge-%012lx", offset + (widget << SWIN_SIZE_BITS)); @@ -46,24 +49,35 @@ static void bridge_platform_create(nasid_t nasid, int widget, int masterwid) w1_res.end = w1_res.start + 3; w1_res.flags = IORESOURCE_MEM;

- pdev = platform_device_alloc("sgi_w1", PLATFORM_DEVID_AUTO); - if (!pdev) { - kfree(wd); - goto no_mem; + pdev_wd = platform_device_alloc("sgi_w1", PLATFORM_DEVID_AUTO); + if (!pdev_wd) { + pr_warn("xtalk:n%d/%x bridge create out of memory\n", nasid, widget); + goto err_kfree_wd; + } + if (platform_device_add_resources(pdev_wd, &w1_res, 1)) { + pr_warn("xtalk:n%d/%x bridge failed to add platform resources.\n", nasid, widget); + goto err_put_pdev_wd; + } + if (platform_device_add_data(pdev_wd, wd, sizeof(*wd))) { + pr_warn("xtalk:n%d/%x bridge failed to add platform data.\n", nasid, widget); + goto err_put_pdev_wd; + } + if (platform_device_add(pdev_wd)) { + pr_warn("xtalk:n%d/%x bridge failed to add platform device.\n", nasid, widget); + goto err_put_pdev_wd; } - platform_device_add_resources(pdev, &w1_res, 1); - platform_device_add_data(pdev, wd, sizeof(*wd)); /* platform_device_add_data() duplicates the data */ kfree(wd); - platform_device_add(pdev);

bd = kzalloc(sizeof(*bd), GFP_KERNEL); - if (!bd) - goto no_mem; - pdev = platform_device_alloc("xtalk-bridge", PLATFORM_DEVID_AUTO); - if (!pdev) { - kfree(bd); - goto no_mem; + if (!bd) { + pr_warn("xtalk:n%d/%x bridge create out of memory\n", nasid, widget); + goto err_unregister_pdev_wd; + } + pdev_bd = platform_device_alloc("xtalk-bridge", PLATFORM_DEVID_AUTO); + if (!pdev_bd) { + pr_warn("xtalk:n%d/%x bridge create out of memory\n", nasid, widget); + goto err_kfree_bd; }

@@ -84,15 +98,31 @@ static void bridge_platform_create(nasid_t nasid, int widget, int masterwid) bd->io.flags = IORESOURCE_IO; bd->io_offset = offset;

- platform_device_add_data(pdev, bd, sizeof(*bd)); + if (platform_device_add_data(pdev_bd, bd, sizeof(*bd))) { + pr_warn("xtalk:n%d/%x bridge failed to add platform data.\n", nasid, widget); + goto err_put_pdev_bd; + } + if (platform_device_add(pdev_bd)) { + pr_warn("xtalk:n%d/%x bridge failed to add platform device.\n", nasid, widget); + goto err_put_pdev_bd; + } /* platform_device_add_data() duplicates the data */ kfree(bd); - platform_device_add(pdev); pr_info("xtalk:n%d/%x bridge widget\n", nasid, widget); return;

-no_mem: - pr_warn("xtalk:n%d/%x bridge create out of memory\n", nasid, widget); +err_put_pdev_bd: + platform_device_put(pdev_bd); +err_kfree_bd: + kfree(bd); +err_unregister_pdev_wd: + platform_device_unregister(pdev_wd); + return; +err_put_pdev_wd: + platform_device_put(pdev_wd); +err_kfree_wd: + kfree(wd); + return; }

static int probe_one_port(nasid_t nasid, int widget, int masterwid)

From: Wang Kefeng wangkefeng.wang@huawei.com

[ Upstream commit 14ca1a4690750bb54e1049e49f3140ef48958a6e ]

MT_MEMORY_RO is introduced by commit 598f0a99fa8a ("ARM: 9210/1: Mark the FDT_FIXED sections as shareable"), which is a readonly memory type for FDT area, but there are some different between ARM_LPAE and non-ARM_LPAE, we need to setup PMD_SECT_AP2 and L_PMD_SECT_RDONLY for MT_MEMORY_RO when ARM_LAPE enabled.

non-ARM_LPAE 0xff800000-0xffa00000 2M PGD KERNEL ro NX SHD ARM_LPAE 0xff800000-0xffc00000 4M PMD RW NX SHD ARM_LPAE+fix 0xff800000-0xffc00000 4M PMD ro NX SHD

Fixes: 598f0a99fa8a ("ARM: 9210/1: Mark the FDT_FIXED sections as shareable") Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com Signed-off-by: Russell King (Oracle) rmk+kernel@armlinux.org.uk Signed-off-by: Sasha Levin sashal@kernel.org --- arch/arm/mm/mmu.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index cd17e324aa51..83a91e0ab848 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -300,7 +300,11 @@ static struct mem_type mem_types[] __ro_after_init = { .prot_pte = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY | L_PTE_XN | L_PTE_RDONLY, .prot_l1 = PMD_TYPE_TABLE, +#ifdef CONFIG_ARM_LPAE + .prot_sect = PMD_TYPE_SECT | L_PMD_SECT_RDONLY | PMD_SECT_AP2, +#else .prot_sect = PMD_TYPE_SECT, +#endif .domain = DOMAIN_KERNEL, }, [MT_ROM] = {

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit fd1ef88049de09bc70d60b549992524cfc0e66ff ]

If this memdup_user() call fails, the memory allocated in a previous call a few lines above should be freed. Otherwise it leaks.

Fixes: 6ee95d1c8991 ("nfsd: add support for upcall version 2") Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Reviewed-by: Jeff Layton jlayton@kernel.org Signed-off-by: Chuck Lever chuck.lever@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfsd/nfs4recover.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index c634483d85d2..8f24485e0f04 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -815,8 +815,10 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg, princhash.data = memdup_user( &ci->cc_princhash.cp_data, princhashlen); - if (IS_ERR_OR_NULL(princhash.data)) + if (IS_ERR_OR_NULL(princhash.data)) { + kfree(name.data); return -EFAULT; + } princhash.len = princhashlen; } else princhash.len = 0;

From: Chuck Lever chuck.lever@oracle.com

[ Upstream commit 1242a87da0d8cd2a428e96ca68e7ea899b0f4624 ]

Commit 2825a7f90753 ("nfsd4: allow encoding across page boundaries") added an explicit computation of the remaining length in the rq_res XDR buffer.

The computation appears to suffer from an "off-by-one" bug. Because buflen is too large by one page, XDR encoding can run off the end of the send buffer by eventually trying to use the struct page address in rq_page_end, which always contains NULL.

Fixes: bddfdbcddbe2 ("NFSD: Extract the svcxdr_init_encode() helper") Reviewed-by: Jeff Layton jlayton@kernel.org Signed-off-by: Chuck Lever chuck.lever@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/sunrpc/svc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h index 6be55d0e73fd..045f34add206 100644 --- a/include/linux/sunrpc/svc.h +++ b/include/linux/sunrpc/svc.h @@ -609,7 +609,7 @@ static inline void svcxdr_init_encode(struct svc_rqst *rqstp) xdr->end = resv->iov_base + PAGE_SIZE - rqstp->rq_auth_slack; buf->len = resv->iov_len; xdr->page_ptr = buf->pages - 1; - buf->buflen = PAGE_SIZE * (1 + rqstp->rq_page_end - buf->pages); + buf->buflen = PAGE_SIZE * (rqstp->rq_page_end - buf->pages); buf->buflen -= rqstp->rq_auth_slack; xdr->rqst = NULL; }

From: Chuck Lever chuck.lever@oracle.com

[ Upstream commit 7518a3dc5ea249d4112156ce71b8b184eb786151 ]

If an NFS server returns NFS4ERR_RESOURCE on the first operation in an NFSv4 COMPOUND, there's no way for a client to know where the problem is and then simplify the compound to make forward progress.

So instead, make NFSD process as many operations in an oversized COMPOUND as it can and then return NFS4ERR_RESOURCE on the first operation it did not process.

pynfs NFSv4.0 COMP6 exercises this case, but checks only for the COMPOUND status code, not whether the server has processed any of the operations.

pynfs NFSv4.1 SEQ6 and SEQ7 exercise the NFSv4.1 case, which detects too many operations per COMPOUND by checking against the limits negotiated when the session was created.

Suggested-by: Bruce Fields bfields@fieldses.org Fixes: 0078117c6d91 ("nfsd: return RESOURCE not GARBAGE_ARGS on too many ops") Signed-off-by: Chuck Lever chuck.lever@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/nfsd/nfs4proc.c | 19 +++++++++++++------ fs/nfsd/nfs4xdr.c | 11 +++-------- fs/nfsd/xdr4.h | 3 ++- 3 files changed, 18 insertions(+), 15 deletions(-)

--- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -2493,9 +2493,6 @@ nfsd4_proc_compound(struct svc_rqst *rqs status = nfserr_minor_vers_mismatch; if (nfsd_minorversion(nn, args->minorversion, NFSD_TEST) <= 0) goto out; - status = nfserr_resource; - if (args->opcnt > NFSD_MAX_OPS_PER_COMPOUND) - goto out;

status = nfs41_check_op_ordering(args); if (status) { @@ -2508,10 +2505,20 @@ nfsd4_proc_compound(struct svc_rqst *rqs

rqstp->rq_lease_breaker = (void **)&cstate->clp;

- trace_nfsd_compound(rqstp, args->opcnt); + trace_nfsd_compound(rqstp, args->client_opcnt); while (!status && resp->opcnt < args->opcnt) { op = &args->ops[resp->opcnt++];

+ if (unlikely(resp->opcnt == NFSD_MAX_OPS_PER_COMPOUND)) { + /* If there are still more operations to process, + * stop here and report NFS4ERR_RESOURCE. */ + if (cstate->minorversion == 0 && + args->client_opcnt > resp->opcnt) { + op->status = nfserr_resource; + goto encode_op; + } + } + /* * The XDR decode routines may have pre-set op->status; * for example, if there is a miscellaneous XDR error @@ -2587,8 +2594,8 @@ encode_op: status = op->status; }

- trace_nfsd_compound_status(args->opcnt, resp->opcnt, status, - nfsd4_op_name(op->opnum)); + trace_nfsd_compound_status(args->client_opcnt, resp->opcnt, + status, nfsd4_op_name(op->opnum));

nfsd4_cstate_clear_replay(cstate); nfsd4_increment_op_stats(op->opnum); --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2349,16 +2349,11 @@ nfsd4_decode_compound(struct nfsd4_compo

if (xdr_stream_decode_u32(argp->xdr, &argp->minorversion) < 0) return 0; - if (xdr_stream_decode_u32(argp->xdr, &argp->opcnt) < 0) + if (xdr_stream_decode_u32(argp->xdr, &argp->client_opcnt) < 0) return 0;

- /* - * NFS4ERR_RESOURCE is a more helpful error than GARBAGE_ARGS - * here, so we return success at the xdr level so that - * nfsd4_proc can handle this is an NFS-level error. - */ - if (argp->opcnt > NFSD_MAX_OPS_PER_COMPOUND) - return 1; + argp->opcnt = min_t(u32, argp->client_opcnt, + NFSD_MAX_OPS_PER_COMPOUND);

if (argp->opcnt > ARRAY_SIZE(argp->iops)) { argp->ops = kzalloc(argp->opcnt * sizeof(*argp->ops), GFP_KERNEL); --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -688,9 +688,10 @@ struct nfsd4_compoundargs { struct svcxdr_tmpbuf *to_free; struct svc_rqst *rqstp;

- u32 taglen; char * tag; + u32 taglen; u32 minorversion; + u32 client_opcnt; u32 opcnt; struct nfsd4_op *ops; struct nfsd4_op iops[8];

From: Wen Gong quic_wgong@quicinc.com