5.5.7-stable review

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/iommu/qcom_iommu.c |   28 ++++++++++++----------------
 1 file changed, 12 insertions(+), 16 deletions(-)

drivers/iommu/qcom_iommu.c +12 ~~-16~~

@@ -345,21 +345,19 @@ static void qcom_iommu_domain_free(struc
 {
 	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
 
-	if (WARN_ON(qcom_domain->iommu))    /* forgot to detach? */
-		return;
-
 	iommu_put_dma_cookie(domain);
 
-	/* NOTE: unmap can be called after client device is powered off,
-	 * for example, with GPUs or anything involving dma-buf.  So we
-	 * cannot rely on the device_link.  Make sure the IOMMU is on to
-	 * avoid unclocked accesses in the TLB inv path:
-	 */
-	pm_runtime_get_sync(qcom_domain->iommu->dev);
-
-	free_io_pgtable_ops(qcom_domain->pgtbl_ops);
-
-	pm_runtime_put_sync(qcom_domain->iommu->dev);
+	if (qcom_domain->iommu) {
+		/*
+		 * NOTE: unmap can be called after client device is powered
+		 * off, for example, with GPUs or anything involving dma-buf.
+		 * So we cannot rely on the device_link.  Make sure the IOMMU
+		 * is on to avoid unclocked accesses in the TLB inv path:
+		 */
+		pm_runtime_get_sync(qcom_domain->iommu->dev);
+		free_io_pgtable_ops(qcom_domain->pgtbl_ops);
+		pm_runtime_put_sync(qcom_domain->iommu->dev);
+	}
 
 	kfree(qcom_domain);
 }

@@ -405,7 +403,7 @@ static void qcom_iommu_detach_dev(struct
 	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
 	unsigned i;
 
-	if (!qcom_domain->iommu)
+	if (WARN_ON(!qcom_domain->iommu))
 		return;
 
 	pm_runtime_get_sync(qcom_iommu->dev);

@@ -418,8 +416,6 @@ static void qcom_iommu_detach_dev(struct
 		ctx->domain = NULL;
 	}
 	pm_runtime_put_sync(qcom_iommu->dev);
-
-	qcom_domain->iommu = NULL;
 }
 
 static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova,

Greg Kroah-Hartman

author maintainer

2020-02-27 14:13 UTC #2 lore raw

PATCH 2/150 iommu/vt-d: Add attach_deferred() helper

From: Joerg Roedel <[email protected]>

commit 1d4615978f525b769990a4a4ef22fb1b9a04cdf1 upstream.

Implement a helper function to check whether a device's attach process is deferred.

Fixes 1ee0186b9a12 ("iommu/vt-d: Refactor find_domain() helper")

Cc [email protected] # v5.5

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/iommu/intel-iommu.c |   12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

drivers/iommu/intel-iommu.c +8 -4

@@ -732,6 +732,11 @@ static int iommu_dummy(struct device *de
 	return dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO;
 }
 
+static bool attach_deferred(struct device *dev)
+{
+	return dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO;
+}
+
 /**
  * is_downstream_to_pci_bridge - test if a device belongs to the PCI
  *				 sub-hierarchy of a candidate PCI-PCI bridge

@@ -2424,8 +2429,7 @@ static struct dmar_domain *find_domain(s
 {
 	struct device_domain_info *info;
 
-	if (unlikely(dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO ||
-		     dev->archdata.iommu == DUMMY_DEVICE_DOMAIN_INFO))
+	if (unlikely(attach_deferred(dev) || iommu_dummy(dev)))
 		return NULL;
 
 	/* No lock here, assumes no domain exit in normal case */

@@ -2438,7 +2442,7 @@ static struct dmar_domain *find_domain(s
 
 static struct dmar_domain *deferred_attach_domain(struct device *dev)
 {
-	if (unlikely(dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO)) {
+	if (unlikely(attach_deferred(dev))) {
 		struct iommu_domain *domain;
 
 		dev->archdata.iommu = NULL;

@@ -5989,7 +5993,7 @@ intel_iommu_aux_get_pasid(struct iommu_d
 static bool intel_iommu_is_attach_deferred(struct iommu_domain *domain,
 					   struct device *dev)
 {
-	return dev->archdata.iommu == DEFER_DEVICE_DOMAIN_INFO;
+	return attach_deferred(dev);
 }
 
 const struct iommu_ops intel_iommu_ops = {

Greg Kroah-Hartman

author maintainer

2020-02-27 14:13 UTC #3 lore raw

PATCH 3/150 iommu/vt-d: Move deferred device attachment into helper function

From: Joerg Roedel <[email protected]>

commit 034d98cc0cdcde2415c6f598fa9125e3eaa02569 upstream.

Move the code that does the deferred device attachment into a separate helper function.

Fixes 1ee0186b9a12 ("iommu/vt-d: Refactor find_domain() helper")

Cc [email protected] # v5.5

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/iommu/intel-iommu.c |   20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

drivers/iommu/intel-iommu.c +12 -8

@@ -2440,16 +2440,20 @@ static struct dmar_domain *find_domain(s
 	return NULL;
 }
 
-static struct dmar_domain *deferred_attach_domain(struct device *dev)
+static void do_deferred_attach(struct device *dev)
 {
-	if (unlikely(attach_deferred(dev))) {
-		struct iommu_domain *domain;
+	struct iommu_domain *domain;
+
+	dev->archdata.iommu = NULL;
+	domain = iommu_get_domain_for_dev(dev);
+	if (domain)
+		intel_iommu_attach_device(domain, dev);
+}
 
-		dev->archdata.iommu = NULL;
-		domain = iommu_get_domain_for_dev(dev);
-		if (domain)
-			intel_iommu_attach_device(domain, dev);
-	}
+static struct dmar_domain *deferred_attach_domain(struct device *dev)
+{
+	if (unlikely(attach_deferred(dev)))
+		do_deferred_attach(dev);
 
 	return find_domain(dev);
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:13 UTC #4 lore raw

PATCH 4/150 iommu/vt-d: Do deferred attachment in iommu_need_mapping()

From: Joerg Roedel <[email protected]>

commit a11bfde9c77df1fd350ea27169ab921f511bf5d0 upstream.

The attachment of deferred devices needs to happen before the check whether the device is identity mapped or not. Otherwise the check will return wrong results, cause warnings boot failures in kdump kernels, like

	WARNING: CPU: 0 PID: 318 at ../drivers/iommu/intel-iommu.c:592 domain_get_iommu+0x61/0x70

	[...]

	 Call Trace:
	  __intel_map_single+0x55/0x190
	  intel_alloc_coherent+0xac/0x110
	  dmam_alloc_attrs+0x50/0xa0
	  ahci_port_start+0xfb/0x1f0 [libahci]
	  ata_host_start.part.39+0x104/0x1e0 [libata]

With the earlier check the kdump boot succeeds and a crashdump is written.

Fixes 1ee0186b9a12 ("iommu/vt-d: Refactor find_domain() helper")

Cc [email protected] # v5.5

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/iommu/intel-iommu.c |   10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

drivers/iommu/intel-iommu.c +7 -3

@@ -2452,9 +2452,6 @@ static void do_deferred_attach(struct de
 
 static struct dmar_domain *deferred_attach_domain(struct device *dev)
 {
-	if (unlikely(attach_deferred(dev)))
-		do_deferred_attach(dev);
-
 	return find_domain(dev);
 }

@@ -3478,6 +3475,9 @@ static bool iommu_need_mapping(struct de
 	if (iommu_dummy(dev))
 		return false;
 
+	if (unlikely(attach_deferred(dev)))
+		do_deferred_attach(dev);
+
 	ret = identity_mapping(dev);
 	if (ret) {
 		u64 dma_mask = *dev->dma_mask;

@@ -3841,7 +3841,11 @@ bounce_map_single(struct device *dev, ph
 	int prot = 0;
 	int ret;
 
+	if (unlikely(attach_deferred(dev)))
+		do_deferred_attach(dev);
+
 	domain = deferred_attach_domain(dev);
+
 	if (WARN_ON(dir == DMA_NONE || !domain))
 		return DMA_MAPPING_ERROR;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:24 UTC #5 lore raw

PATCH 5/150 iommu/vt-d: Remove deferred_attach_domain()

From: Joerg Roedel <[email protected]>

commit 96d170f3b1a607612caf3618c534d5c64fc2d61b upstream.

The function is now only a wrapper around find_domain(). Remove the function and call find_domain() directly at the call-sites.

Fixes 1ee0186b9a12 ("iommu/vt-d: Refactor find_domain() helper")

Cc [email protected] # v5.5

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/iommu/intel-iommu.c |   11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

drivers/iommu/intel-iommu.c +3 -8

@@ -2450,11 +2450,6 @@ static void do_deferred_attach(struct de
 		intel_iommu_attach_device(domain, dev);
 }
 
-static struct dmar_domain *deferred_attach_domain(struct device *dev)
-{
-	return find_domain(dev);
-}
-
 static inline struct device_domain_info *
 dmar_search_domain_by_dev_info(int segment, int bus, int devfn)
 {

@@ -3526,7 +3521,7 @@ static dma_addr_t __intel_map_single(str
 
 	BUG_ON(dir == DMA_NONE);
 
-	domain = deferred_attach_domain(dev);
+	domain = find_domain(dev);
 	if (!domain)
 		return DMA_MAPPING_ERROR;

@@ -3746,7 +3741,7 @@ static int intel_map_sg(struct device *d
 	if (!iommu_need_mapping(dev))
 		return dma_direct_map_sg(dev, sglist, nelems, dir, attrs);
 
-	domain = deferred_attach_domain(dev);
+	domain = find_domain(dev);
 	if (!domain)
 		return 0;

@@ -3844,7 +3839,7 @@ bounce_map_single(struct device *dev, ph
 	if (unlikely(attach_deferred(dev)))
 		do_deferred_attach(dev);
 
-	domain = deferred_attach_domain(dev);
+	domain = find_domain(dev);
 
 	if (WARN_ON(dir == DMA_NONE || !domain))
 		return DMA_MAPPING_ERROR;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:13 UTC #6 lore raw

PATCH 6/150 iommu/vt-d: Simplify check in identity_mapping()

From: Joerg Roedel <[email protected]>

commit 1ddb32da4a629fa7f87873d0b6836c2e1feb7518 upstream.

The function only has one call-site and there it is never called with dummy or deferred devices. Simplify the check in the function to account for that.

Fixes 1ee0186b9a12 ("iommu/vt-d: Refactor find_domain() helper")

Cc [email protected] # v5.5

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/iommu/intel-iommu.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/iommu/intel-iommu.c +1 -1

@@ -2799,7 +2799,7 @@ static int identity_mapping(struct devic
 	struct device_domain_info *info;
 
 	info = dev->archdata.iommu;
-	if (info && info != DUMMY_DEVICE_DOMAIN_INFO && info != DEFER_DEVICE_DOMAIN_INFO)
+	if (info)
 		return (info->domain == si_domain);
 
 	return 0;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:13 UTC #7 lore raw

PATCH 7/150 ALSA: hda: Use scnprintf() for printing texts for sysfs/procfs

From: Takashi Iwai <[email protected]>

commit 44eeb081b8630bb3ad3cd381d1ae1831463e48bb upstream.

Some code in HD-audio driver calls snprintf() in a loop and still expects that the return value were actually written size, while snprintf() returns the expected would-be length instead. When the given buffer limit were small, this leads to a buffer overflow.

Use scnprintf() for addressing those issues. It returns the actually written size unlike snprintf().

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 sound/hda/hdmi_chmap.c    |    2 +-
 sound/pci/hda/hda_codec.c |    2 +-
 sound/pci/hda/hda_eld.c   |    2 +-
 sound/pci/hda/hda_sysfs.c |    4 ++--
 4 files changed, 5 insertions(+), 5 deletions(-)

sound/hda/hdmi_chmap.c +1 -1

@@ -250,7 +250,7 @@ void snd_hdac_print_channel_allocation(i
 
 	for (i = 0, j = 0; i < ARRAY_SIZE(cea_speaker_allocation_names); i++) {
 		if (spk_alloc & (1 << i))
-			j += snprintf(buf + j, buflen - j,  " %s",
+			j += scnprintf(buf + j, buflen - j,  " %s",
 					cea_speaker_allocation_names[i]);
 	}
 	buf[j] = '\0';	/* necessary when j == 0 */

sound/pci/hda/hda_codec.c +1 -1

@@ -4019,7 +4019,7 @@ void snd_print_pcm_bits(int pcm, char *b
 
 	for (i = 0, j = 0; i < ARRAY_SIZE(bits); i++)
 		if (pcm & (AC_SUPPCM_BITS_8 << i))
-			j += snprintf(buf + j, buflen - j,  " %d", bits[i]);
+			j += scnprintf(buf + j, buflen - j,  " %d", bits[i]);
 
 	buf[j] = '\0'; /* necessary when j == 0 */
 }

sound/pci/hda/hda_eld.c +1 -1

@@ -360,7 +360,7 @@ static void hdmi_print_pcm_rates(int pcm
 
 	for (i = 0, j = 0; i < ARRAY_SIZE(alsa_rates); i++)
 		if (pcm & (1 << i))
-			j += snprintf(buf + j, buflen - j,  " %d",
+			j += scnprintf(buf + j, buflen - j,  " %d",
 				alsa_rates[i]);
 
 	buf[j] = '\0'; /* necessary when j == 0 */

sound/pci/hda/hda_sysfs.c +2 -2

@@ -222,7 +222,7 @@ static ssize_t init_verbs_show(struct de
 	int i, len = 0;
 	mutex_lock(&codec->user_mutex);
 	snd_array_for_each(&codec->init_verbs, i, v) {
-		len += snprintf(buf + len, PAGE_SIZE - len,
+		len += scnprintf(buf + len, PAGE_SIZE - len,
 				"0x%02x 0x%03x 0x%04x\n",
 				v->nid, v->verb, v->param);
 	}

@@ -272,7 +272,7 @@ static ssize_t hints_show(struct device
 	int i, len = 0;
 	mutex_lock(&codec->user_mutex);
 	snd_array_for_each(&codec->hints, i, hint) {
-		len += snprintf(buf + len, PAGE_SIZE - len,
+		len += scnprintf(buf + len, PAGE_SIZE - len,
 				"%s = %s\n", hint->key, hint->val);
 	}
 	mutex_unlock(&codec->user_mutex);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:23 UTC #8 lore raw

PATCH 8/150 ALSA: hda/realtek - Apply quirk for MSI GP63, too

From: Takashi Iwai <[email protected]>

commit a655e2b107d463ce2745188ce050d07daed09a71 upstream.

The same quirk that was applied to MSI GL73 is needed for MSI GP63, too. Adding the entry with the SSID 1462:1228.

BugLink https://bugzilla.kernel.org/show_bug.cgi?id=206503

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 sound/pci/hda/patch_realtek.c |    1 +
 1 file changed, 1 insertion(+)

sound/pci/hda/patch_realtek.c +1 -0

@@ -2447,6 +2447,7 @@ static const struct snd_pci_quirk alc882
 	SND_PCI_QUIRK(0x1071, 0x8258, "Evesham Voyaeger", ALC882_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x1458, 0xa002, "Gigabyte EP45-DS3/Z87X-UD3H", ALC889_FIXUP_FRONT_HP_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1458, 0xa0b8, "Gigabyte AZ370-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS),
+	SND_PCI_QUIRK(0x1462, 0x1228, "MSI-GP63", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1462, 0x1276, "MSI-GL73", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD),
 	SND_PCI_QUIRK(0x1462, 0xda57, "MSI Z270-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS),

Greg Kroah-Hartman

author maintainer

2020-02-27 14:13 UTC #9 lore raw

PATCH 9/150 ALSA: hda/realtek - Apply quirk for yet another MSI laptop

From: Takashi Iwai <[email protected]>

commit cc5049ae4d457194796f854eb2e38b9727ad8c2d upstream.

MSI GP65 laptop with SSID 1462:1293 requires the same quirk as other MSI models.

BugLink https://bugzilla.kernel.org/show_bug.cgi?id=204159

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 sound/pci/hda/patch_realtek.c |    1 +
 1 file changed, 1 insertion(+)

sound/pci/hda/patch_realtek.c +1 -0

@@ -2449,6 +2449,7 @@ static const struct snd_pci_quirk alc882
 	SND_PCI_QUIRK(0x1458, 0xa0b8, "Gigabyte AZ370-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS),
 	SND_PCI_QUIRK(0x1462, 0x1228, "MSI-GP63", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1462, 0x1276, "MSI-GL73", ALC1220_FIXUP_CLEVO_P950),
+	SND_PCI_QUIRK(0x1462, 0x1293, "MSI-GP65", ALC1220_FIXUP_CLEVO_P950),
 	SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD),
 	SND_PCI_QUIRK(0x1462, 0xda57, "MSI Z270-Gaming", ALC1220_FIXUP_GB_DUAL_CODECS),
 	SND_PCI_QUIRK_VENDOR(0x1462, "MSI", ALC882_FIXUP_GPIO3),

Greg Kroah-Hartman

author maintainer

2020-02-27 14:12 UTC #10 lore raw

PATCH 10/150 ASoC: codec2codec: avoid invalid/double-free of pcm runtime

From: Samuel Holland <[email protected]>

commit b6570fdb96edf45bcf71884bd2644bd73d348d1a upstream.

The PCM runtime was freed during PMU in the case that the event hook encountered an error. However, it is also unconditionally freed during PMD. Avoid a double-free by dropping the call to kfree in the PMU hook.

Fixes a72706ed8208 ("ASoC: codec2codec: remove ephemeral variables")

Signed-off-by Samuel Holland <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Mark Brown <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 sound/soc/soc-dapm.c |    3 ---
 1 file changed, 3 deletions(-)

sound/soc/soc-dapm.c +0 -3

@@ -3888,9 +3888,6 @@ snd_soc_dai_link_event_pre_pmu(struct sn
 	runtime->rate = params_rate(params);
 
 out:
-	if (ret < 0)
-		kfree(runtime);
-
 	kfree(params);
 	return ret;
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:24 UTC #11 lore raw

PATCH 11/150 ASoC: sun8i-codec: Fix setting DAI data format

From: Samuel Holland <[email protected]>

commit 96781fd941b39e1f78098009344ebcd7af861c67 upstream.

Use the correct mask for this two-bit field. This fixes setting the DAI data format to RIGHT_J or DSP_A.

Fixes 36c684936fae ("ASoC: Add sun8i digital audio codec")

Signed-off-by Samuel Holland <[email protected]>

Acked-by Chen-Yu Tsai <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Mark Brown <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 sound/soc/sunxi/sun8i-codec.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

sound/soc/sunxi/sun8i-codec.c +2 -1

@@ -80,6 +80,7 @@
 
 #define SUN8I_SYS_SR_CTRL_AIF1_FS_MASK		GENMASK(15, 12)
 #define SUN8I_SYS_SR_CTRL_AIF2_FS_MASK		GENMASK(11, 8)
+#define SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT_MASK	GENMASK(3, 2)
 #define SUN8I_AIF1CLK_CTRL_AIF1_WORD_SIZ_MASK	GENMASK(5, 4)
 #define SUN8I_AIF1CLK_CTRL_AIF1_LRCK_DIV_MASK	GENMASK(8, 6)
 #define SUN8I_AIF1CLK_CTRL_AIF1_BCLK_DIV_MASK	GENMASK(12, 9)

@@ -241,7 +242,7 @@ static int sun8i_set_fmt(struct snd_soc_
 		return -EINVAL;
 	}
 	regmap_update_bits(scodec->regmap, SUN8I_AIF1CLK_CTRL,
-			   BIT(SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT),
+			   SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT_MASK,
 			   value << SUN8I_AIF1CLK_CTRL_AIF1_DATA_FMT);
 
 	return 0;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:13 UTC #12 lore raw

PATCH 12/150 tpm: Revert tpm_tis_spi_mod.ko to tpm_tis_spi.ko.

From: Jarkko Sakkinen <[email protected]>

commit faaca0a0d48e7b122f6e7e2521f4f6fc487d0451 upstream.

Revert tpm_tis_spi_mod.ko back to tpm_tis_spi.ko as the rename could break user space scripts. This can be achieved by renaming tpm_tis_spi.c as tpm_tis_spi_main.c. Then tpm_tis_spi-y can be used inside the makefile.

Cc Andrey Pronin <[email protected]>

Cc Stephen Boyd <[email protected]>

Cc [email protected] # 5.5.x

Fixes 797c0113c9a4 ("tpm: tpm_tis_spi: Support cr50 devices")

Reported-by Alexander Steffen <[email protected]>

Tested-by Alexander Steffen <[email protected]>

Reviewed-by Stephen Boyd <[email protected]>

Signed-off-by Jarkko Sakkinen <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/char/tpm/Makefile           |    8 
 drivers/char/tpm/tpm_tis_spi.c      |  298 ------------------------------------
 drivers/char/tpm/tpm_tis_spi_main.c |  298 ++++++++++++++++++++++++++++++++++++
 3 files changed, 303 insertions(+), 301 deletions(-)

drivers/char/tpm/Makefile +5 -3

@@ -21,9 +21,11 @@ tpm-$(CONFIG_EFI) += eventlog/efi.o
 tpm-$(CONFIG_OF) += eventlog/of.o
 obj-$(CONFIG_TCG_TIS_CORE) += tpm_tis_core.o
 obj-$(CONFIG_TCG_TIS) += tpm_tis.o
-obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi_mod.o
-tpm_tis_spi_mod-y := tpm_tis_spi.o
-tpm_tis_spi_mod-$(CONFIG_TCG_TIS_SPI_CR50) += tpm_tis_spi_cr50.o
+
+obj-$(CONFIG_TCG_TIS_SPI) += tpm_tis_spi.o
+tpm_tis_spi-y := tpm_tis_spi_main.o
+tpm_tis_spi-$(CONFIG_TCG_TIS_SPI_CR50) += tpm_tis_spi_cr50.o
+
 obj-$(CONFIG_TCG_TIS_I2C_ATMEL) += tpm_i2c_atmel.o
 obj-$(CONFIG_TCG_TIS_I2C_INFINEON) += tpm_i2c_infineon.o
 obj-$(CONFIG_TCG_TIS_I2C_NUVOTON) += tpm_i2c_nuvoton.o

drivers/char/tpm/tpm_tis_spi.c deleted +0 ~~-298~~

298 lines not on this page · raw message

drivers/char/tpm/tpm_tis_spi_main.c new file +298 -0

298 lines not on this page · raw message

Greg Kroah-Hartman

author maintainer

2020-02-27 14:13 UTC #13 lore raw

PATCH 13/150 tpm: Initialize crypto_id of allocated_banks to HASH_ALGO__LAST

From: Roberto Sassu <[email protected]>

commit dc10e4181c05a2315ddc375e963b7c763b5ee0df upstream.

chip->allocated_banks, an array of tpm_bank_info structures, contains the list of TPM algorithm IDs of allocated PCR banks. It also contains the corresponding ID of the crypto subsystem, so that users of the TPM driver can calculate a digest for a PCR extend operation.

However, if there is no mapping between TPM algorithm ID and crypto ID, the crypto_id field of tpm_bank_info remains set to zero (the array is allocated and initialized with kcalloc() in tpm2_get_pcr_allocation()). Zero should not be used as value for unknown mappings, as it is a valid crypto ID (HASH_ALGO_MD4).

Thus, initialize crypto_id to HASH_ALGO__LAST.

Cc [email protected] # 5.1.x

Fixes 879b589210a9 ("tpm: retrieve digest size of unknown algorithms with PCR read")

Signed-off-by Roberto Sassu <[email protected]>

Reviewed-by Petr Vorel <[email protected]>

Reviewed-by Jarkko Sakkinen <[email protected]>

Signed-off-by Jarkko Sakkinen <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/char/tpm/tpm2-cmd.c |    2 ++
 1 file changed, 2 insertions(+)

drivers/char/tpm/tpm2-cmd.c +2 -0

@@ -525,6 +525,8 @@ static int tpm2_init_bank_info(struct tp
 		return 0;
 	}
 
+	bank->crypto_id = HASH_ALGO__LAST;
+
 	return tpm2_pcr_read(chip, 0, &digest, &bank->digest_size);
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:13 UTC #14 lore raw

PATCH 14/150 ecryptfs: fix a memory leak bug in parse_tag_1_packet()

From: Wenwen Wang <[email protected]>

commit fe2e082f5da5b4a0a92ae32978f81507ef37ec66 upstream.

In parse_tag_1_packet(), if tag 1 packet contains a key larger than ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES, no cleanup is executed, leading to a memory leak on the allocated 'auth_tok_list_item'. To fix this issue, go to the label 'out_free' to perform the cleanup work.

Fixes dddfa461fc89 ("[PATCH] eCryptfs: Public key; packet management")

Signed-off-by Wenwen Wang <[email protected]>

Signed-off-by Tyler Hicks <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/ecryptfs/keystore.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

fs/ecryptfs/keystore.c +1 -1

@@ -1304,7 +1304,7 @@ parse_tag_1_packet(struct ecryptfs_crypt
 		printk(KERN_WARNING "Tag 1 packet contains key larger "
 		       "than ECRYPTFS_MAX_ENCRYPTED_KEY_BYTES\n");
 		rc = -EINVAL;
-		goto out;
+		goto out_free;
 	}
 	memcpy((*new_auth_tok)->session_key.encrypted_key,
 	       &data[(*packet_size)], (body_size - (ECRYPTFS_SIG_SIZE + 2)));

Greg Kroah-Hartman

author maintainer

2020-02-27 14:24 UTC #15 lore raw

PATCH 15/150 ecryptfs: fix a memory leak bug in ecryptfs_init_messaging()

From: Wenwen Wang <[email protected]>

commit b4a81b87a4cfe2bb26a4a943b748d96a43ef20e8 upstream.

In ecryptfs_init_messaging(), if the allocation for 'ecryptfs_msg_ctx_arr' fails, the previously allocated 'ecryptfs_daemon_hash' is not deallocated, leading to a memory leak bug. To fix this issue, free 'ecryptfs_daemon_hash' before returning the error.

Fixes 88b4a07e6610 ("[PATCH] eCryptfs: Public key transport mechanism")

Signed-off-by Wenwen Wang <[email protected]>

Signed-off-by Tyler Hicks <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/ecryptfs/messaging.c |    1 +
 1 file changed, 1 insertion(+)

fs/ecryptfs/messaging.c +1 -0

@@ -379,6 +379,7 @@ int __init ecryptfs_init_messaging(void)
 					* ecryptfs_message_buf_len),
 				       GFP_KERNEL);
 	if (!ecryptfs_msg_ctx_arr) {
+		kfree(ecryptfs_daemon_hash);
 		rc = -ENOMEM;
 		goto out;
 	}

Greg Kroah-Hartman

author maintainer

2020-02-27 14:13 UTC #16 lore raw

PATCH 16/150 Btrfs: fix race between shrinking truncate and fiemap

From: Filipe Manana <[email protected]>

commit 28553fa992cb28be6a65566681aac6cafabb4f2d upstream.

When there is a fiemap executing in parallel with a shrinking truncate we can end up in a situation where we have extent maps for which we no longer have corresponding file extent items. This is generally harmless and at the moment the only consequences are missing file extent items representing holes after we expand the file size again after the truncate operation removed the prealloc extent items, and stale information for future fiemap calls (reporting extents that no longer exist or may have been reallocated to other files for example).

Consider the following example:

1) Our inode has a size of 128KiB, one 128KiB extent at file offset 0 and a 1MiB prealloc extent at file offset 128KiB;

2) Task A starts doing a shrinking truncate of our inode to reduce it to a size of 64KiB. Before it searches the subvolume tree for file extent items to delete, it drops all the extent maps in the range from 64KiB to (u64)-1 by calling btrfs_drop_extent_cache();

3) Task B starts doing a fiemap against our inode. When looking up for the inode's extent maps in the range from 128KiB to (u64)-1, it doesn't find any in the inode's extent map tree, since they were removed by task A. Because it didn't find any in the extent map tree, it scans the inode's subvolume tree for file extent items, and it finds the 1MiB prealloc extent at file offset 128KiB, then it creates an extent map based on that file extent item and adds it to inode's extent map tree (this ends up being done by btrfs_get_extent() <- btrfs_get_extent_fiemap() <- get_extent_skip_holes());

4) Task A then drops the prealloc extent at file offset 128KiB and shrinks the 128KiB extent file offset 0 to a length of 64KiB. The truncation operation finishes and we end up with an extent map representing a 1MiB prealloc extent at file offset 128KiB, despite we don't have any more that extent;

After this the two types of problems we have are:

1) Future calls to fiemap always report that a 1MiB prealloc extent exists at file offset 128KiB. This is stale information, no longer correct;

2) If the size of the file is increased, by a truncate operation that increases the file size or by a write into a file offset > 64KiB for example, we end up not inserting file extent items to represent holes for any range between 128KiB and 128KiB + 1MiB, since the hole expansion function, btrfs_cont_expand() will skip hole insertion for any range for which an extent map exists that represents a prealloc extent. This causes fsck to complain about missing file extent items when not using the NO_HOLES feature.

The second issue could be often triggered by test case generic/561 from fstests, which runs fsstress and duperemove in parallel, and duperemove does frequent fiemap calls.

Essentially the problems happens because fiemap does not acquire the inode's lock while truncate does, and fiemap locks the file range in the inode's iotree while truncate does not. So fix the issue by making btrfs_truncate_inode_items() lock the file range from the new file size to (u64)-1, so that it serializes with fiemap.

CC [email protected] # 4.4+

Signed-off-by Filipe Manana <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/btrfs/inode.c |    8 ++++++++
 1 file changed, 8 insertions(+)

fs/btrfs/inode.c +8 -0

@@ -4757,6 +4757,8 @@ int btrfs_truncate_inode_items(struct bt
 	u64 bytes_deleted = 0;
 	bool be_nice = false;
 	bool should_throttle = false;
+	const u64 lock_start = ALIGN_DOWN(new_size, fs_info->sectorsize);
+	struct extent_state *cached_state = NULL;
 
 	BUG_ON(new_size > 0 && min_type != BTRFS_EXTENT_DATA_KEY);

@@ -4773,6 +4775,9 @@ int btrfs_truncate_inode_items(struct bt
 		return -ENOMEM;
 	path->reada = READA_BACK;
 
+	lock_extent_bits(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1,
+			 &cached_state);
+
 	/*
 	 * We want to drop from the next block forward in case this new size is
 	 * not block aligned since we will be keeping the last block of the

@@ -5039,6 +5044,9 @@ out:
 		btrfs_ordered_update_i_size(inode, last_size, NULL);
 	}
 
+	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1,
+			     &cached_state);
+
 	btrfs_free_path(path);
 	return ret;
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:24 UTC #17 lore raw

PATCH 17/150 btrfs: dont set path->leave_spinning for truncate

From: Josef Bacik <[email protected]>

commit 52e29e331070cd7d52a64cbf1b0958212a340e28 upstream.

The only time we actually leave the path spinning is if we're truncating a small amount and don't actually free an extent, which is not a common occurrence. We have to set the path blocking in order to add the delayed ref anyway, so the first extent we find we set the path to blocking and stay blocking for the duration of the operation. With the upcoming file extent map stuff there will be another case that we have to have the path blocking, so just swap to blocking always.

Note: this patch also fixes a warning after 28553fa992cb ("Btrfs: fix race between shrinking truncate and fiemap") got merged that inserts extent locks around truncation so the path must not leave spinning locks after btrfs_search_slot.

  [70.794783] BUG: sleeping function called from invalid context at mm/slab.h:565
  [70.794834] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 1141, name: rsync
  [70.794863] 5 locks held by rsync/1141:
  [70.794876]  #0: ffff888417b9c408 (sb_writers#17){.+.+}, at: mnt_want_write+0x20/0x50
  [70.795030]  #1: ffff888428de28e8 (&type->i_mutex_dir_key#13/1){+.+.}, at: lock_rename+0xf1/0x100
  [70.795051]  #2: ffff888417b9c608 (sb_internal#2){.+.+}, at: start_transaction+0x394/0x560
  [70.795124]  #3: ffff888403081768 (btrfs-fs-01){++++}, at: btrfs_try_tree_write_lock+0x2f/0x160
  [70.795203]  #4: ffff888403086568 (btrfs-fs-00){++++}, at: btrfs_try_tree_write_lock+0x2f/0x160
  [70.795222] CPU: 5 PID: 1141 Comm: rsync Not tainted 5.6.0-rc2-backup+ #2
  [70.795362] Call Trace:
  [70.795374]  dump_stack+0x71/0xa0
  [70.795445]  ___might_sleep.part.96.cold.106+0xa6/0xb6
  [70.795459]  kmem_cache_alloc+0x1d3/0x290
  [70.795471]  alloc_extent_state+0x22/0x1c0
  [70.795544]  __clear_extent_bit+0x3ba/0x580
  [70.795557]  ? _raw_spin_unlock_irq+0x24/0x30
  [70.795569]  btrfs_truncate_inode_items+0x339/0xe50
  [70.795647]  btrfs_evict_inode+0x269/0x540
  [70.795659]  ? dput.part.38+0x29/0x460
  [70.795671]  evict+0xcd/0x190
  [70.795682]  __dentry_kill+0xd6/0x180
  [70.795754]  dput.part.38+0x2ad/0x460
  [70.795765]  do_renameat2+0x3cb/0x540
  [70.795777]  __x64_sys_rename+0x1c/0x20

Reported-by Dave Jones <[email protected]>

Fixes 28553fa992cb ("Btrfs: fix race between shrinking truncate and fiemap")

CC [email protected] # 4.4+

Reviewed-by Filipe Manana <[email protected]>

Signed-off-by Josef Bacik <[email protected]>

[ add note ]

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/btrfs/inode.c |    2 --
 1 file changed, 2 deletions(-)

fs/btrfs/inode.c +0 -2

@@ -4814,7 +4814,6 @@ search_again:
 		goto out;
 	}
 
-	path->leave_spinning = 1;
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 	if (ret < 0)
 		goto out;

@@ -4966,7 +4965,6 @@ delete:
 		     root == fs_info->tree_root)) {
 			struct btrfs_ref ref = { 0 };
 
-			btrfs_set_path_blocking(path);
 			bytes_deleted += extent_num_bytes;
 
 			btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF,

Greg Kroah-Hartman

author maintainer

2020-02-27 14:13 UTC #18 lore raw

PATCH 18/150 btrfs: handle logged extent failure properly

From: Josef Bacik <[email protected]>

commit bd727173e4432fe6cb70ba108dc1f3602c5409d7 upstream.

If we're allocating a logged extent we attempt to insert an extent record for the file extent directly. We increase space_info->bytes_reserved, because the extent entry addition will call btrfs_update_block_group(), which will convert the ->bytes_reserved to ->bytes_used. However if we fail at any point while inserting the extent entry we will bail and leave space on ->bytes_reserved, which will trigger a WARN_ON() on umount. Fix this by pinning the space if we fail to insert, which is what happens in every other failure case that involves adding the extent entry.

CC [email protected] # 5.4+

Reviewed-by Johannes Thumshirn <[email protected]>

Reviewed-by Nikolay Borisov <[email protected]>

Signed-off-by Josef Bacik <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/btrfs/extent-tree.c |    2 ++
 1 file changed, 2 insertions(+)

fs/btrfs/extent-tree.c +2 -0

@@ -4430,6 +4430,8 @@ int btrfs_alloc_logged_file_extent(struc
 
 	ret = alloc_reserved_file_extent(trans, 0, root_objectid, 0, owner,
 					 offset, ins, 1);
+	if (ret)
+		btrfs_pin_extent(fs_info, ins->objectid, ins->offset, 1);
 	btrfs_put_block_group(block_group);
 	return ret;
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:24 UTC #19 lore raw

PATCH 19/150 thunderbolt: Prevent crash if non-active NVMem file is read

From: Mika Westerberg <[email protected]>

commit 03cd45d2e219301880cabc357e3cf478a500080f upstream.

The driver does not populate .reg_read callback for the non-active NVMem because the file is supposed to be write-only. However, it turns out NVMem subsystem does not yet support this and expects that the .reg_read callback is provided. If user reads the binary attribute it triggers NULL pointer dereference like this one:

  BUG: kernel NULL pointer dereference, address: 0000000000000000
  ...
  Call Trace:
   bin_attr_nvmem_read+0x64/0x80
   kernfs_fop_read+0xa7/0x180
   vfs_read+0xbd/0x170
   ksys_read+0x5a/0xd0
   do_syscall_64+0x43/0x150
   entry_SYSCALL_64_after_hwframe+0x44/0xa9

Fix this in the driver by providing .reg_read callback that always returns an error.

Reported-by Nicholas Johnson <[email protected]>

Fixes e6b245ccd524 ("thunderbolt: Add support for host and device NVM firmware upgrade")

Signed-off-by Mika Westerberg <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/thunderbolt/switch.c |    7 +++++++
 1 file changed, 7 insertions(+)

drivers/thunderbolt/switch.c +7 -0

@@ -274,6 +274,12 @@ out:
 	return ret;
 }
 
+static int tb_switch_nvm_no_read(void *priv, unsigned int offset, void *val,
+				 size_t bytes)
+{
+	return -EPERM;
+}
+
 static int tb_switch_nvm_write(void *priv, unsigned int offset, void *val,
 			       size_t bytes)
 {

@@ -319,6 +325,7 @@ static struct nvmem_device *register_nvm
 		config.read_only = true;
 	} else {
 		config.name = "nvm_non_active";
+		config.reg_read = tb_switch_nvm_no_read;
 		config.reg_write = tb_switch_nvm_write;
 		config.root_only = true;
 	}

Greg Kroah-Hartman

author maintainer

2020-02-27 14:13 UTC #20 lore raw

PATCH 20/150 USB: misc: iowarrior: add support for 2 OEMed devices

From: Greg Kroah-Hartman <[email protected]>

commit 461d8deb26a7d70254bc0391feb4fd8a95e674e8 upstream.

Add support for two OEM devices that are identical to existing IO-Warrior devices, except for the USB device id.

Cc Christoph Jung <[email protected]>

Cc stable <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/misc/iowarrior.c |   15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

drivers/usb/misc/iowarrior.c +13 -2

@@ -34,6 +34,10 @@
 /* full speed iowarrior */
 #define USB_DEVICE_ID_CODEMERCS_IOW56	0x1503
 
+/* OEMed devices */
+#define USB_DEVICE_ID_CODEMERCS_IOW24SAG	0x158a
+#define USB_DEVICE_ID_CODEMERCS_IOW56AM		0x158b
+
 /* Get a minor range for your devices from the usb maintainer */
 #ifdef CONFIG_USB_DYNAMIC_MINORS
 #define IOWARRIOR_MINOR_BASE	0

@@ -133,6 +137,8 @@ static const struct usb_device_id iowarr
 	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOWPV1)},
 	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOWPV2)},
 	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW56)},
+	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW24SAG)},
+	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW56AM)},
 	{}			/* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, iowarrior_ids);

@@ -357,6 +363,7 @@ static ssize_t iowarrior_write(struct fi
 	}
 	switch (dev->product_id) {
 	case USB_DEVICE_ID_CODEMERCS_IOW24:
+	case USB_DEVICE_ID_CODEMERCS_IOW24SAG:
 	case USB_DEVICE_ID_CODEMERCS_IOWPV1:
 	case USB_DEVICE_ID_CODEMERCS_IOWPV2:
 	case USB_DEVICE_ID_CODEMERCS_IOW40:

@@ -371,6 +378,7 @@ static ssize_t iowarrior_write(struct fi
 		goto exit;
 		break;
 	case USB_DEVICE_ID_CODEMERCS_IOW56:
+	case USB_DEVICE_ID_CODEMERCS_IOW56AM:
 		/* The IOW56 uses asynchronous IO and more urbs */
 		if (atomic_read(&dev->write_busy) == MAX_WRITES_IN_FLIGHT) {
 			/* Wait until we are below the limit for submitted urbs */

@@ -493,6 +501,7 @@ static long iowarrior_ioctl(struct file
 	switch (cmd) {
 	case IOW_WRITE:
 		if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW24 ||
+		    dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW24SAG ||
 		    dev->product_id == USB_DEVICE_ID_CODEMERCS_IOWPV1 ||
 		    dev->product_id == USB_DEVICE_ID_CODEMERCS_IOWPV2 ||
 		    dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW40) {

@@ -767,7 +776,8 @@ static int iowarrior_probe(struct usb_in
 		goto error;
 	}
 
-	if (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) {
+	if ((dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) ||
+	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM)) {
 		res = usb_find_last_int_out_endpoint(iface_desc,
 				&dev->int_out_endpoint);
 		if (res) {

@@ -780,7 +790,8 @@ static int iowarrior_probe(struct usb_in
 	/* we have to check the report_size often, so remember it in the endianness suitable for our machine */
 	dev->report_size = usb_endpoint_maxp(dev->int_in_endpoint);
 	if ((dev->interface->cur_altsetting->desc.bInterfaceNumber == 0) &&
-	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56))
+	    ((dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) ||
+	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM)))
 		/* IOWarrior56 has wMaxPacketSize different from report size */
 		dev->report_size = 7;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:22 UTC #21 lore raw

PATCH 21/150 USB: misc: iowarrior: add support for the 28 and 28L devices

From: Greg Kroah-Hartman <[email protected]>

commit 5f6f8da2d7b5a431d3f391d0d73ace8edfb42af7 upstream.

Add new device ids for the 28 and 28L devices. These have 4 interfaces instead of 2, but the driver binds the same, so the driver changes are minimal.

Cc Christoph Jung <[email protected]>

Cc stable <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/misc/iowarrior.c |   15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

drivers/usb/misc/iowarrior.c +13 -2

@@ -33,6 +33,9 @@
 #define USB_DEVICE_ID_CODEMERCS_IOWPV2	0x1512
 /* full speed iowarrior */
 #define USB_DEVICE_ID_CODEMERCS_IOW56	0x1503
+/* fuller speed iowarrior */
+#define USB_DEVICE_ID_CODEMERCS_IOW28	0x1504
+#define USB_DEVICE_ID_CODEMERCS_IOW28L	0x1505
 
 /* OEMed devices */
 #define USB_DEVICE_ID_CODEMERCS_IOW24SAG	0x158a

@@ -139,6 +142,8 @@ static const struct usb_device_id iowarr
 	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW56)},
 	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW24SAG)},
 	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW56AM)},
+	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW28)},
+	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW28L)},
 	{}			/* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, iowarrior_ids);

@@ -379,6 +384,8 @@ static ssize_t iowarrior_write(struct fi
 		break;
 	case USB_DEVICE_ID_CODEMERCS_IOW56:
 	case USB_DEVICE_ID_CODEMERCS_IOW56AM:
+	case USB_DEVICE_ID_CODEMERCS_IOW28:
+	case USB_DEVICE_ID_CODEMERCS_IOW28L:
 		/* The IOW56 uses asynchronous IO and more urbs */
 		if (atomic_read(&dev->write_busy) == MAX_WRITES_IN_FLIGHT) {
 			/* Wait until we are below the limit for submitted urbs */

@@ -777,7 +784,9 @@ static int iowarrior_probe(struct usb_in
 	}
 
 	if ((dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) ||
-	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM)) {
+	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM) ||
+	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28) ||
+	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28L)) {
 		res = usb_find_last_int_out_endpoint(iface_desc,
 				&dev->int_out_endpoint);
 		if (res) {

@@ -791,7 +800,9 @@ static int iowarrior_probe(struct usb_in
 	dev->report_size = usb_endpoint_maxp(dev->int_in_endpoint);
 	if ((dev->interface->cur_altsetting->desc.bInterfaceNumber == 0) &&
 	    ((dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) ||
-	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM)))
+	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM) ||
+	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28) ||
+	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28L)))
 		/* IOWarrior56 has wMaxPacketSize different from report size */
 		dev->report_size = 7;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:13 UTC #22 lore raw

PATCH 22/150 USB: misc: iowarrior: add support for the 100 device

From: Greg Kroah-Hartman <[email protected]>

commit bab5417f5f0118ce914bc5b2f8381e959e891155 upstream.

Add a new device id for the 100 devie. It has 4 interfaces like the 28 and 28L devices but a larger endpoint so more I/O pins.

Cc Christoph Jung <[email protected]>

Cc stable <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/misc/iowarrior.c |    9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

drivers/usb/misc/iowarrior.c +7 -2

@@ -36,6 +36,7 @@
 /* fuller speed iowarrior */
 #define USB_DEVICE_ID_CODEMERCS_IOW28	0x1504
 #define USB_DEVICE_ID_CODEMERCS_IOW28L	0x1505
+#define USB_DEVICE_ID_CODEMERCS_IOW100	0x1506
 
 /* OEMed devices */
 #define USB_DEVICE_ID_CODEMERCS_IOW24SAG	0x158a

@@ -144,6 +145,7 @@ static const struct usb_device_id iowarr
 	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW56AM)},
 	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW28)},
 	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW28L)},
+	{USB_DEVICE(USB_VENDOR_ID_CODEMERCS, USB_DEVICE_ID_CODEMERCS_IOW100)},
 	{}			/* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, iowarrior_ids);

@@ -386,6 +388,7 @@ static ssize_t iowarrior_write(struct fi
 	case USB_DEVICE_ID_CODEMERCS_IOW56AM:
 	case USB_DEVICE_ID_CODEMERCS_IOW28:
 	case USB_DEVICE_ID_CODEMERCS_IOW28L:
+	case USB_DEVICE_ID_CODEMERCS_IOW100:
 		/* The IOW56 uses asynchronous IO and more urbs */
 		if (atomic_read(&dev->write_busy) == MAX_WRITES_IN_FLIGHT) {
 			/* Wait until we are below the limit for submitted urbs */

@@ -786,7 +789,8 @@ static int iowarrior_probe(struct usb_in
 	if ((dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) ||
 	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM) ||
 	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28) ||
-	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28L)) {
+	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28L) ||
+	    (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW100)) {
 		res = usb_find_last_int_out_endpoint(iface_desc,
 				&dev->int_out_endpoint);
 		if (res) {

@@ -802,7 +806,8 @@ static int iowarrior_probe(struct usb_in
 	    ((dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56) ||
 	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW56AM) ||
 	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28) ||
-	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28L)))
+	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW28L) ||
+	     (dev->product_id == USB_DEVICE_ID_CODEMERCS_IOW100)))
 		/* IOWarrior56 has wMaxPacketSize different from report size */
 		dev->report_size = 7;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #23 lore raw

PATCH 23/150 floppy: check FDC index for errors before assigning it

From: Linus Torvalds <[email protected]>

commit 2e90ca68b0d2f5548804f22f0dd61145516171e3 upstream.

Jordy Zomer reported a KASAN out-of-bounds read in the floppy driver in wait_til_ready().

Which on the face of it can't happen, since as Willy Tarreau points out, the function does no particular memory access. Except through the FDCS macro, which just indexes a static allocation through teh current fdc, which is always checked against N_FDC.

Except the checking happens after we've already assigned the value.

The floppy driver is a disgrace (a lot of it going back to my original horrd "design"), and has no real maintainer. Nobody has the hardware, and nobody really cares. But it still gets used in virtual environment because it's one of those things that everybody supports.

The whole thing should be re-written, or at least parts of it should be seriously cleaned up. The 'current fdc' index, which is used by the FDCS macro, and which is often shadowed by a local 'fdc' variable, is a prime example of how not to write code.

But because nobody has the hardware or the motivation, let's just fix up the immediate problem with a nasty band-aid: test the fdc index before actually assigning it to the static 'fdc' variable.

Reported-by Jordy Zomer <[email protected]>

Cc Willy Tarreau <[email protected]>

Cc Dan Carpenter <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/block/floppy.c |    7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

drivers/block/floppy.c +5 -2

@@ -853,14 +853,17 @@ static void reset_fdc_info(int mode)
 /* selects the fdc and drive, and enables the fdc's input/dma. */
 static void set_fdc(int drive)
 {
+	unsigned int new_fdc = fdc;
+
 	if (drive >= 0 && drive < N_DRIVE) {
-		fdc = FDC(drive);
+		new_fdc = FDC(drive);
 		current_drive = drive;
 	}
-	if (fdc != 1 && fdc != 0) {
+	if (new_fdc >= N_FDC) {
 		pr_info("bad fdc value\n");
 		return;
 	}
+	fdc = new_fdc;
 	set_dor(fdc, ~0, 8);
 #if N_FDC > 1
 	set_dor(1 - fdc, ~8, 0);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:23 UTC #24 lore raw

PATCH 24/150 USB: serial: ch341: fix receiver regression

From: Johan Hovold <[email protected]>

commit 7c3d02285ad558691f27fde760bcd841baa27eab upstream.

While assumed not to make a difference, not using the factor-2 prescaler makes the receiver more susceptible to errors.

Specifically, there have been reports of problems with devices that cannot generate a 115200 rate with a smaller error than 2.1% (e.g. 117647 bps). But this can also be reproduced with a low-speed RS232 tranceiver at 115200 when the input rate matches the nominal rate.

So whenever possible, enable the factor-2 prescaler and halve the divisor in order to use settings closer to that of the previous algorithm.

Fixes 35714565089e ("USB: serial: ch341: reimplement line-speed handling")

Cc stable <[email protected]> # 5.5

Reported-by Jakub Nantl <[email protected]>

Tested-by Jakub Nantl <[email protected]>

Reviewed-by Greg Kroah-Hartman <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/serial/ch341.c |   10 ++++++++++
 1 file changed, 10 insertions(+)

drivers/usb/serial/ch341.c +10 -0

@@ -205,6 +205,16 @@ static int ch341_get_divisor(speed_t spe
 			16 * speed - 16 * CH341_CLKRATE / (clk_div * (div + 1)))
 		div++;
 
+	/*
+	 * Prefer lower base clock (fact = 0) if even divisor.
+	 *
+	 * Note that this makes the receiver more tolerant to errors.
+	 */
+	if (fact == 1 && div % 2 == 0) {
+		div /= 2;
+		fact = 0;
+	}
+
 	return (0x100 - div) << 8 | fact << 2 | ps;
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:15 UTC #25 lore raw

PATCH 25/150 vt: fix scrollback flushing on background consoles

From: Nicolas Pitre <[email protected]>

commit 3f4ef485be9d54040b695f32ec76d0f1ea50bbf3 upstream.

Commit a6dbe4427559 ("vt: perform safe console erase in the right order") provided fixes to an earlier commit by gathering all console scrollback flushing operations in a function of its own. This includes the invocation of vc_sw->con_switch() as previously done through a update_screen() call. That commit failed to carry over the con_is_visible() conditional though, as well as cursor handling, which caused problems when "\e[3J" was written to a background console.

One could argue for preserving the call to update_screen(). However this does far more than we need, and it is best to remove scrollback assumptions from it. Instead let's gather the minimum needed to actually perform scrollback flushing properly in that one place.

While at it, let's document the vc_sw->con_switch() side effect being relied upon.

Signed-off-by Nicolas Pitre <[email protected]>

Reported-and-tested-by Lukas Wunner <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/tty/vt/vt.c |   15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

drivers/tty/vt/vt.c +13 -2

@@ -936,10 +936,21 @@ static void flush_scrollback(struct vc_d
 	WARN_CONSOLE_UNLOCKED();
 
 	set_origin(vc);
-	if (vc->vc_sw->con_flush_scrollback)
+	if (vc->vc_sw->con_flush_scrollback) {
 		vc->vc_sw->con_flush_scrollback(vc);
-	else
+	} else if (con_is_visible(vc)) {
+		/*
+		 * When no con_flush_scrollback method is provided then the
+		 * legacy way for flushing the scrollback buffer is to use
+		 * a side effect of the con_switch method. We do it only on
+		 * the foreground console as background consoles have no
+		 * scrollback buffers in that case and we obviously don't
+		 * want to switch to them.
+		 */
+		hide_cursor(vc);
 		vc->vc_sw->con_switch(vc);
+		set_cursor(vc);
+	}
 }
 
 /*

Greg Kroah-Hartman

author maintainer

2020-02-27 14:15 UTC #26 lore raw

PATCH 26/150 vt: selection, handle pending signals in paste_selection

From: Jiri Slaby <[email protected]>

commit 687bff0cd08f790d540cfb7b2349f0d876cdddec upstream.

When pasting a selection to a vt, the task is set as INTERRUPTIBLE while waiting for a tty to unthrottle. But signals are not handled at all. Normally, this is not a problem as tty_ldisc_receive_buf receives all the goods and a user has no reason to interrupt the task.

There are two scenarios where this matters:
1) when the tty is throttled and a signal is sent to the process, it spins on a CPU until the tty is unthrottled. schedule() does not really echedule, but returns immediately, of course.
2) when the sel_buffer becomes invalid, KASAN prevents any reads from it and the loop simply does not proceed and spins forever (causing the tty to throttle, but the code never sleeps, the same as above). This sometimes happens as there is a race in the sel_buffer handling code.

So add signal handling to this ioctl (TIOCL_PASTESEL) and return -EINTR in case a signal is pending.

Signed-off-by Jiri Slaby <[email protected]>

Cc stable <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/tty/vt/selection.c |    9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

drivers/tty/vt/selection.c +8 -1

@@ -29,6 +29,8 @@
 #include <linux/console.h>
 #include <linux/tty_flip.h>
 
+#include <linux/sched/signal.h>
+
 /* Don't take this from <ctype.h>: 011-015 on the screen aren't spaces */
 #define isspace(c)	((c) == ' ')

@@ -350,6 +352,7 @@ int paste_selection(struct tty_struct *t
 	unsigned int count;
 	struct  tty_ldisc *ld;
 	DECLARE_WAITQUEUE(wait, current);
+	int ret = 0;
 
 	console_lock();
 	poke_blanked_console();

@@ -363,6 +366,10 @@ int paste_selection(struct tty_struct *t
 	add_wait_queue(&vc->paste_wait, &wait);
 	while (sel_buffer && sel_buffer_lth > pasted) {
 		set_current_state(TASK_INTERRUPTIBLE);
+		if (signal_pending(current)) {
+			ret = -EINTR;
+			break;
+		}
 		if (tty_throttled(tty)) {
 			schedule();
 			continue;

@@ -378,6 +385,6 @@ int paste_selection(struct tty_struct *t
 
 	tty_buffer_unlock_exclusive(&vc->port);
 	tty_ldisc_deref(ld);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(paste_selection);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:15 UTC #27 lore raw

PATCH 27/150 vt: selection, close sel_buffer race

From: Jiri Slaby <[email protected]>

commit 07e6124a1a46b4b5a9b3cacc0c306b50da87abf5 upstream.

syzkaller reported this UAF:

BUG: KASAN: use-after-free in n_tty_receive_buf_common+0x2481/0x2940 drivers/tty/n_tty.c:1741
Read of size 1 at addr ffff8880089e40e9 by task syz-executor.1/13184

CPU: 0 PID: 13184 Comm: syz-executor.1 Not tainted 5.4.7 #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
Call Trace:
...
 kasan_report+0xe/0x20 mm/kasan/common.c:634
 n_tty_receive_buf_common+0x2481/0x2940 drivers/tty/n_tty.c:1741
 tty_ldisc_receive_buf+0xac/0x190 drivers/tty/tty_buffer.c:461
 paste_selection+0x297/0x400 drivers/tty/vt/selection.c:372
 tioclinux+0x20d/0x4e0 drivers/tty/vt/vt.c:3044
 vt_ioctl+0x1bcf/0x28d0 drivers/tty/vt/vt_ioctl.c:364
 tty_ioctl+0x525/0x15a0 drivers/tty/tty_io.c:2657
 vfs_ioctl fs/ioctl.c:47 [inline]

It is due to a race between parallel paste_selection (TIOCL_PASTESEL) and set_selection_user (TIOCL_SETSEL) invocations. One uses sel_buffer, while the other frees it and reallocates a new one for another selection. Add a mutex to close this race.

The mutex takes care properly of sel_buffer and sel_buffer_lth only. The other selection global variables (like sel_start, sel_end, and sel_cons) are protected only in set_selection_user. The other functions need quite some more work to close the races of the variables there. This is going to happen later.

This likely fixes (I am unsure as there is no reproducer provided) bug 206361 too. It was marked as CVE-2020-8648.

Signed-off-by Jiri Slaby <[email protected]>

Reported-by [email protected]

Cc stable <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/tty/vt/selection.c |   23 +++++++++++++++++------
 1 file changed, 17 insertions(+), 6 deletions(-)

drivers/tty/vt/selection.c +17 -6

@@ -16,6 +16,7 @@
 #include <linux/tty.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/types.h>

@@ -45,6 +46,7 @@ static volatile int sel_start = -1; 	/*
 static int sel_end;
 static int sel_buffer_lth;
 static char *sel_buffer;
+static DEFINE_MUTEX(sel_lock);
 
 /* clear_selection, highlight and highlight_pointer can be called
    from interrupt (via scrollback/front) */

@@ -186,7 +188,7 @@ int set_selection_kernel(struct tiocl_se
 	char *bp, *obp;
 	int i, ps, pe, multiplier;
 	u32 c;
-	int mode;
+	int mode, ret = 0;
 
 	poke_blanked_console();

@@ -212,6 +214,7 @@ int set_selection_kernel(struct tiocl_se
 	if (ps > pe)	/* make sel_start <= sel_end */
 		swap(ps, pe);
 
+	mutex_lock(&sel_lock);
 	if (sel_cons != vc_cons[fg_console].d) {
 		clear_selection();
 		sel_cons = vc_cons[fg_console].d;

@@ -257,9 +260,10 @@ int set_selection_kernel(struct tiocl_se
 			break;
 		case TIOCL_SELPOINTER:
 			highlight_pointer(pe);
-			return 0;
+			goto unlock;
 		default:
-			return -EINVAL;
+			ret = -EINVAL;
+			goto unlock;
 	}
 
 	/* remove the pointer */

@@ -281,7 +285,7 @@ int set_selection_kernel(struct tiocl_se
 	else if (new_sel_start == sel_start)
 	{
 		if (new_sel_end == sel_end)	/* no action required */
-			return 0;
+			goto unlock;
 		else if (new_sel_end > sel_end)	/* extend to right */
 			highlight(sel_end + 2, new_sel_end);
 		else				/* contract from right */

@@ -309,7 +313,8 @@ int set_selection_kernel(struct tiocl_se
 	if (!bp) {
 		printk(KERN_WARNING "selection: kmalloc() failed\n");
 		clear_selection();
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto unlock;
 	}
 	kfree(sel_buffer);
 	sel_buffer = bp;

@@ -334,7 +339,9 @@ int set_selection_kernel(struct tiocl_se
 		}
 	}
 	sel_buffer_lth = bp - sel_buffer;
-	return 0;
+unlock:
+	mutex_unlock(&sel_lock);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(set_selection_kernel);

@@ -364,6 +371,7 @@ int paste_selection(struct tty_struct *t
 	tty_buffer_lock_exclusive(&vc->port);
 
 	add_wait_queue(&vc->paste_wait, &wait);
+	mutex_lock(&sel_lock);
 	while (sel_buffer && sel_buffer_lth > pasted) {
 		set_current_state(TASK_INTERRUPTIBLE);
 		if (signal_pending(current)) {

@@ -371,7 +379,9 @@ int paste_selection(struct tty_struct *t
 			break;
 		}
 		if (tty_throttled(tty)) {
+			mutex_unlock(&sel_lock);
 			schedule();
+			mutex_lock(&sel_lock);
 			continue;
 		}
 		__set_current_state(TASK_RUNNING);

@@ -380,6 +390,7 @@ int paste_selection(struct tty_struct *t
 					      count);
 		pasted += count;
 	}
+	mutex_unlock(&sel_lock);
 	remove_wait_queue(&vc->paste_wait, &wait);
 	__set_current_state(TASK_RUNNING);

Jiri Slaby

2020-02-28 06:54 UTC #28 lore raw

Re: [PATCH 5.5 027/150] vt: selection, close sel_buffer race

Quoted 5 lines · Greg Kroah-Hartman

From: Jiri Slaby <[email protected]>
commit 07e6124a1a46b4b5a9b3cacc0c306b50da87abf5 upstream.
syzkaller reported this UAF:

With this patch, syzkaller reports possible circular locking dependency:
https://lore.kernel.org/lkml/[email protected]/

Could you drop the patch from stable until this is resolved?

Quoted 146 lines

BUG: KASAN: use-after-free in n_tty_receive_buf_common+0x2481/0x2940 drivers/tty/n_tty.c:1741
Read of size 1 at addr ffff8880089e40e9 by task syz-executor.1/13184

CPU: 0 PID: 13184 Comm: syz-executor.1 Not tainted 5.4.7 #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
Call Trace:
...
 kasan_report+0xe/0x20 mm/kasan/common.c:634
 n_tty_receive_buf_common+0x2481/0x2940 drivers/tty/n_tty.c:1741
 tty_ldisc_receive_buf+0xac/0x190 drivers/tty/tty_buffer.c:461
 paste_selection+0x297/0x400 drivers/tty/vt/selection.c:372
 tioclinux+0x20d/0x4e0 drivers/tty/vt/vt.c:3044
 vt_ioctl+0x1bcf/0x28d0 drivers/tty/vt/vt_ioctl.c:364
 tty_ioctl+0x525/0x15a0 drivers/tty/tty_io.c:2657
 vfs_ioctl fs/ioctl.c:47 [inline]

This likely fixes (I am unsure as there is no reproducer provided) bug 206361 too. It was marked as CVE-2020-8648.

Signed-off-by Jiri Slaby <[email protected]>

Reported-by [email protected]

Cc stable <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/tty/vt/selection.c |   23 +++++++++++++++++------
 1 file changed, 17 insertions(+), 6 deletions(-)

drivers/tty/vt/selection.c +17 -6

@@ -16,6 +16,7 @@
 #include <linux/tty.h>
 #include <linux/sched.h>
 #include <linux/mm.h>
+#include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/types.h>

@@ -45,6 +46,7 @@ static volatile int sel_start = -1; 	/*
 static int sel_end;
 static int sel_buffer_lth;
 static char *sel_buffer;
+static DEFINE_MUTEX(sel_lock);
 
 /* clear_selection, highlight and highlight_pointer can be called
    from interrupt (via scrollback/front) */

@@ -186,7 +188,7 @@ int set_selection_kernel(struct tiocl_se
 	char *bp, *obp;
 	int i, ps, pe, multiplier;
 	u32 c;
-	int mode;
+	int mode, ret = 0;
 
 	poke_blanked_console();

@@ -212,6 +214,7 @@ int set_selection_kernel(struct tiocl_se
 	if (ps > pe)	/* make sel_start <= sel_end */
 		swap(ps, pe);
 
+	mutex_lock(&sel_lock);
 	if (sel_cons != vc_cons[fg_console].d) {
 		clear_selection();
 		sel_cons = vc_cons[fg_console].d;

@@ -257,9 +260,10 @@ int set_selection_kernel(struct tiocl_se
 			break;
 		case TIOCL_SELPOINTER:
 			highlight_pointer(pe);
-			return 0;
+			goto unlock;
 		default:
-			return -EINVAL;
+			ret = -EINVAL;
+			goto unlock;
 	}
 
 	/* remove the pointer */

@@ -281,7 +285,7 @@ int set_selection_kernel(struct tiocl_se
 	else if (new_sel_start == sel_start)
 	{
 		if (new_sel_end == sel_end)	/* no action required */
-			return 0;
+			goto unlock;
 		else if (new_sel_end > sel_end)	/* extend to right */
 			highlight(sel_end + 2, new_sel_end);
 		else				/* contract from right */

@@ -309,7 +313,8 @@ int set_selection_kernel(struct tiocl_se
 	if (!bp) {
 		printk(KERN_WARNING "selection: kmalloc() failed\n");
 		clear_selection();
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto unlock;
 	}
 	kfree(sel_buffer);
 	sel_buffer = bp;

@@ -334,7 +339,9 @@ int set_selection_kernel(struct tiocl_se
 		}
 	}
 	sel_buffer_lth = bp - sel_buffer;
-	return 0;
+unlock:
+	mutex_unlock(&sel_lock);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(set_selection_kernel);

@@ -364,6 +371,7 @@ int paste_selection(struct tty_struct *t
 	tty_buffer_lock_exclusive(&vc->port);
 
 	add_wait_queue(&vc->paste_wait, &wait);
+	mutex_lock(&sel_lock);
 	while (sel_buffer && sel_buffer_lth > pasted) {
 		set_current_state(TASK_INTERRUPTIBLE);
 		if (signal_pending(current)) {

@@ -371,7 +379,9 @@ int paste_selection(struct tty_struct *t
 			break;
 		}
 		if (tty_throttled(tty)) {
+			mutex_unlock(&sel_lock);
 			schedule();
+			mutex_lock(&sel_lock);
 			continue;
 		}
 		__set_current_state(TASK_RUNNING);

@@ -380,6 +390,7 @@ int paste_selection(struct tty_struct *t
 					      count);
 		pasted += count;
 	}
+	mutex_unlock(&sel_lock);
 	remove_wait_queue(&vc->paste_wait, &wait);
 	__set_current_state(TASK_RUNNING);

Signature · 2 lines

js
suse labs

Greg Kroah-Hartman

author maintainer

2020-02-28 11:46 UTC #29 lore raw

Re: [PATCH 5.5 027/150] vt: selection, close sel_buffer race

Quoted 11 lines · Jiri Slaby

Quoted 5 lines · Greg Kroah-Hartman
From: Jiri Slaby <[email protected]>
commit 07e6124a1a46b4b5a9b3cacc0c306b50da87abf5 upstream.
syzkaller reported this UAF:
With this patch, syzkaller reports possible circular locking dependency:
https://lore.kernel.org/lkml/[email protected]/
Could you drop the patch from stable until this is resolved?

Good idea, now dropped from 4.19.y, 5.4.y, and 5.5.y, thanks.

greg k-h

Greg Kroah-Hartman

author maintainer

2020-02-27 14:15 UTC #30 lore raw

PATCH 28/150 vt: vt_ioctl: fix race in VT_RESIZEX

From: Eric Dumazet <[email protected]>

commit 6cd1ed50efd88261298577cd92a14f2768eddeeb upstream.

We need to make sure vc_cons[i].d is not NULL after grabbing console_lock(), or risk a crash.

general protection fault, probably for non-canonical address 0xdffffc0000000068: 0000 [#1] PREEMPT SMP KASAN
KASAN: null-ptr-deref in range [0x0000000000000340-0x0000000000000347]
CPU: 1 PID: 19462 Comm: syz-executor.5 Not tainted 5.5.0-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
RIP: 0010:vt_ioctl+0x1f96/0x26d0 drivers/tty/vt/vt_ioctl.c:883
Code: 74 41 e8 bd a6 84 fd 48 89 d8 48 c1 e8 03 42 80 3c 28 00 0f 85 e4 04 00 00 48 8b 03 48 8d b8 40 03 00 00 48 89 fa 48 c1 ea 03 <42> 0f b6 14 2a 84 d2 74 09 80 fa 03 0f 8e b1 05 00 00 44 89 b8 40
RSP: 0018:ffffc900086d7bb0 EFLAGS: 00010202
RAX: 0000000000000000 RBX: ffffffff8c34ee88 RCX: ffffc9001415c000
RDX: 0000000000000068 RSI: ffffffff83f0e6e3 RDI: 0000000000000340
RBP: ffffc900086d7cd0 R08: ffff888054ce0100 R09: fffffbfff16a2f6d
R10: ffff888054ce0998 R11: ffff888054ce0100 R12: 000000000000001d
R13: dffffc0000000000 R14: 1ffff920010daf79 R15: 000000000000ff7f
FS:  00007f7d13c12700(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007ffd477e3c38 CR3: 0000000095d0a000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 tty_ioctl+0xa37/0x14f0 drivers/tty/tty_io.c:2660
 vfs_ioctl fs/ioctl.c:47 [inline]
 ksys_ioctl+0x123/0x180 fs/ioctl.c:763
 __do_sys_ioctl fs/ioctl.c:772 [inline]
 __se_sys_ioctl fs/ioctl.c:770 [inline]
 __x64_sys_ioctl+0x73/0xb0 fs/ioctl.c:770
 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x45b399
Code: ad b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 7b b6 fb ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f7d13c11c78 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007f7d13c126d4 RCX: 000000000045b399
RDX: 0000000020000080 RSI: 000000000000560a RDI: 0000000000000003
RBP: 000000000075bf20 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 0000000000000666 R14: 00000000004c7f04 R15: 000000000075bf2c
Modules linked in:
---[ end trace 80970faf7a67eb77 ]---
RIP: 0010:vt_ioctl+0x1f96/0x26d0 drivers/tty/vt/vt_ioctl.c:883
Code: 74 41 e8 bd a6 84 fd 48 89 d8 48 c1 e8 03 42 80 3c 28 00 0f 85 e4 04 00 00 48 8b 03 48 8d b8 40 03 00 00 48 89 fa 48 c1 ea 03 <42> 0f b6 14 2a 84 d2 74 09 80 fa 03 0f 8e b1 05 00 00 44 89 b8 40
RSP: 0018:ffffc900086d7bb0 EFLAGS: 00010202
RAX: 0000000000000000 RBX: ffffffff8c34ee88 RCX: ffffc9001415c000
RDX: 0000000000000068 RSI: ffffffff83f0e6e3 RDI: 0000000000000340
RBP: ffffc900086d7cd0 R08: ffff888054ce0100 R09: fffffbfff16a2f6d
R10: ffff888054ce0998 R11: ffff888054ce0100 R12: 000000000000001d
R13: dffffc0000000000 R14: 1ffff920010daf79 R15: 000000000000ff7f
FS:  00007f7d13c12700(0000) GS:ffff8880ae900000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007ffd477e3c38 CR3: 0000000095d0a000 CR4: 00000000001406e0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400

Fixes 1da177e4c3f4 ("Linux-2.6.12-rc2")

Signed-off-by Eric Dumazet <[email protected]>

Cc stable <[email protected]>

Reported-by syzbot <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/tty/vt/vt_ioctl.c |   17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

drivers/tty/vt/vt_ioctl.c +11 -6

@@ -876,15 +876,20 @@ int vt_ioctl(struct tty_struct *tty,
 			return -EINVAL;
 
 		for (i = 0; i < MAX_NR_CONSOLES; i++) {
+			struct vc_data *vcp;
+
 			if (!vc_cons[i].d)
 				continue;
 			console_lock();
-			if (v.v_vlin)
-				vc_cons[i].d->vc_scan_lines = v.v_vlin;
-			if (v.v_clin)
-				vc_cons[i].d->vc_font.height = v.v_clin;
-			vc_cons[i].d->vc_resize_user = 1;
-			vc_resize(vc_cons[i].d, v.v_cols, v.v_rows);
+			vcp = vc_cons[i].d;
+			if (vcp) {
+				if (v.v_vlin)
+					vcp->vc_scan_lines = v.v_vlin;
+				if (v.v_clin)
+					vcp->vc_font.height = v.v_clin;
+				vcp->vc_resize_user = 1;
+				vc_resize(vcp, v.v_cols, v.v_rows);
+			}
 			console_unlock();
 		}
 		break;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:23 UTC #31 lore raw

PATCH 29/150 staging: android: ashmem: Disallow ashmem memory from being remapped

From: Suren Baghdasaryan <[email protected]>

commit 6d67b0290b4b84c477e6a2fc6e005e174d3c7786 upstream.

When ashmem file is mmapped, the resulting vma->vm_file points to the backing shmem file with the generic fops that do not check ashmem permissions like fops of ashmem do. If an mremap is done on the ashmem region, then the permission checks will be skipped. Fix that by disallowing mapping operation on the backing shmem file.

Reported-by Jann Horn <[email protected]>

Signed-off-by Suren Baghdasaryan <[email protected]>

Cc stable <[email protected]> # 4.4,4.9,4.14,4.18,5.4

Signed-off-by Todd Kjos <[email protected]>

Reviewed-by Joel Fernandes (Google) <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/staging/android/ashmem.c |   28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

drivers/staging/android/ashmem.c +28 -0

@@ -351,8 +351,23 @@ static inline vm_flags_t calc_vm_may_fla
 	       _calc_vm_trans(prot, PROT_EXEC,  VM_MAYEXEC);
 }
 
+static int ashmem_vmfile_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	/* do not allow to mmap ashmem backing shmem file directly */
+	return -EPERM;
+}
+
+static unsigned long
+ashmem_vmfile_get_unmapped_area(struct file *file, unsigned long addr,
+				unsigned long len, unsigned long pgoff,
+				unsigned long flags)
+{
+	return current->mm->get_unmapped_area(file, addr, len, pgoff, flags);
+}
+
 static int ashmem_mmap(struct file *file, struct vm_area_struct *vma)
 {
+	static struct file_operations vmfile_fops;
 	struct ashmem_area *asma = file->private_data;
 	int ret = 0;

@@ -393,6 +408,19 @@ static int ashmem_mmap(struct file *file
 		}
 		vmfile->f_mode |= FMODE_LSEEK;
 		asma->file = vmfile;
+		/*
+		 * override mmap operation of the vmfile so that it can't be
+		 * remapped which would lead to creation of a new vma with no
+		 * asma permission checks. Have to override get_unmapped_area
+		 * as well to prevent VM_BUG_ON check for f_ops modification.
+		 */
+		if (!vmfile_fops.mmap) {
+			vmfile_fops = *vmfile->f_op;
+			vmfile_fops.mmap = ashmem_vmfile_mmap;
+			vmfile_fops.get_unmapped_area =
+					ashmem_vmfile_get_unmapped_area;
+		}
+		vmfile->f_op = &vmfile_fops;
 	}
 	get_file(asma->file);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:22 UTC #32 lore raw

PATCH 30/150 staging: vt6656: fix sign of rx_dbm to bb_pre_ed_rssi.

From: Malcolm Priestley <[email protected]>

commit 93134df520f23f4e9998c425b8987edca7016817 upstream.

bb_pre_ed_rssi is an u8 rx_dm always returns negative signed values add minus operator to always yield positive.

fixes issue where rx sensitivity is always set to maximum because the unsigned numbers were always greater then 100.

Fixes 63b9907f58f1 ("staging: vt6656: mac80211 conversion: create rx function.")

Cc stable <[email protected]>

Signed-off-by Malcolm Priestley <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/staging/vt6656/dpc.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/staging/vt6656/dpc.c +1 -1

@@ -130,7 +130,7 @@ int vnt_rx_data(struct vnt_private *priv
 
 	vnt_rf_rssi_to_dbm(priv, *rssi, &rx_dbm);
 
-	priv->bb_pre_ed_rssi = (u8)rx_dbm + 1;
+	priv->bb_pre_ed_rssi = (u8)-rx_dbm + 1;
 	priv->current_rssi = priv->bb_pre_ed_rssi;
 
 	skb_pull(skb, 8);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:13 UTC #33 lore raw

PATCH 31/150 xhci: Force Maximum Packet size for Full-speed bulk devices to valid range.

From: Mathias Nyman <[email protected]>

commit f148b9f402ef002b57bcff3964d45abc8ffb6c3f upstream.

A Full-speed bulk USB audio device (DJ-Tech CTRL) with a invalid Maximum Packet Size of 4 causes a xHC "Parameter Error" at enumeration.

This is because valid Maximum packet sizes for Full-speed bulk endpoints are 8, 16, 32 and 64 bytes. Hosts are not required to support other values than these. See usb 2 specs section 5.8.3 for details.

The device starts working after forcing the maximum packet size to 8. This is most likely the case with other devices as well, so force the maximum packet size to a valid range.

Reported-by Rene D Obermueller <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/host/xhci-mem.c |   12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

drivers/usb/host/xhci-mem.c +9 -3

@@ -1475,9 +1475,15 @@ int xhci_endpoint_init(struct xhci_hcd *
 	/* Allow 3 retries for everything but isoc, set CErr = 3 */
 	if (!usb_endpoint_xfer_isoc(&ep->desc))
 		err_count = 3;
-	/* Some devices get this wrong */
-	if (usb_endpoint_xfer_bulk(&ep->desc) && udev->speed == USB_SPEED_HIGH)
-		max_packet = 512;
+	/* HS bulk max packet should be 512, FS bulk supports 8, 16, 32 or 64 */
+	if (usb_endpoint_xfer_bulk(&ep->desc)) {
+		if (udev->speed == USB_SPEED_HIGH)
+			max_packet = 512;
+		if (udev->speed == USB_SPEED_FULL) {
+			max_packet = rounddown_pow_of_two(max_packet);
+			max_packet = clamp_val(max_packet, 8, 64);
+		}
+	}
 	/* xHCI 1.0 and 1.1 indicates that ctrl ep avg TRB Length should be 8 */
 	if (usb_endpoint_xfer_control(&ep->desc) && xhci->hci_version >= 0x100)
 		avg_trb_len = 8;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:23 UTC #34 lore raw

PATCH 32/150 xhci: fix runtime pm enabling for quirky Intel hosts

From: Mathias Nyman <[email protected]>

commit 024d411e9c5d49eb96c825af52a3ce2682895676 upstream.

Intel hosts that need the XHCI_PME_STUCK_QUIRK flag should enable runtime pm by calling xhci_pme_acpi_rtd3_enable() before usb_hcd_pci_probe() calls pci_dev_run_wake().
Otherwise usage count for the device won't be decreased, and runtime suspend is prevented.

usb_hcd_pci_probe() only decreases the usage count if device can generate run-time wake-up events, i.e. when pci_dev_run_wake() returns true.

This issue was exposed by pci_dev_run_wake() change in commit 8feaec33b986 ("PCI / PM: Always check PME wakeup capability for runtime wakeup support")
and should be backported to kernels with that change

Cc <[email protected]> # 4.13+

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/host/xhci-pci.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

drivers/usb/host/xhci-pci.c +3 -3

@@ -302,6 +302,9 @@ static int xhci_pci_setup(struct usb_hcd
 	if (!usb_hcd_is_primary_hcd(hcd))
 		return 0;
 
+	if (xhci->quirks & XHCI_PME_STUCK_QUIRK)
+		xhci_pme_acpi_rtd3_enable(pdev);
+
 	xhci_dbg(xhci, "Got SBRN %u\n", (unsigned int) xhci->sbrn);
 
 	/* Find any debug ports */

@@ -359,9 +362,6 @@ static int xhci_pci_probe(struct pci_dev
 			HCC_MAX_PSA(xhci->hcc_params) >= 4)
 		xhci->shared_hcd->can_do_streams = 1;
 
-	if (xhci->quirks & XHCI_PME_STUCK_QUIRK)
-		xhci_pme_acpi_rtd3_enable(dev);
-
 	/* USB-2 and USB-3 roothubs initialized, allow runtime pm suspend */
 	pm_runtime_put_noidle(&dev->dev);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:13 UTC #35 lore raw

PATCH 33/150 xhci: apply XHCI_PME_STUCK_QUIRK to Intel Comet Lake platforms

From: Mathias Nyman <[email protected]>

commit a3ae87dce3a5abe0b57c811bab02b2564b574106 upstream.

Intel Comet Lake based platform require the XHCI_PME_STUCK_QUIRK quirk as well. Without this xHC can not enter D3 in runtime suspend.

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/host/xhci-pci.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

drivers/usb/host/xhci-pci.c +3 -1

@@ -49,6 +49,7 @@
 #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_4C_XHCI		0x15ec
 #define PCI_DEVICE_ID_INTEL_TITAN_RIDGE_DD_XHCI		0x15f0
 #define PCI_DEVICE_ID_INTEL_ICE_LAKE_XHCI		0x8a13
+#define PCI_DEVICE_ID_INTEL_CML_XHCI			0xa3af
 
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_4			0x43b9
 #define PCI_DEVICE_ID_AMD_PROMONTORYA_3			0x43ba

@@ -187,7 +188,8 @@ static void xhci_pci_quirks(struct devic
 		 pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_M_XHCI ||
 		 pdev->device == PCI_DEVICE_ID_INTEL_BROXTON_B_XHCI ||
 		 pdev->device == PCI_DEVICE_ID_INTEL_APL_XHCI ||
-		 pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI)) {
+		 pdev->device == PCI_DEVICE_ID_INTEL_DNV_XHCI ||
+		 pdev->device == PCI_DEVICE_ID_INTEL_CML_XHCI)) {
 		xhci->quirks |= XHCI_PME_STUCK_QUIRK;
 	}
 	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&

Greg Kroah-Hartman

author maintainer

2020-02-27 14:13 UTC #36 lore raw

PATCH 34/150 xhci: Fix memory leak when caching protocol extended capability PSI tables - take 2

From: Mathias Nyman <[email protected]>

commit cf0ee7c60c89641f6e4d1d3c7867fe32b9e30300 upstream.

xhci driver assumed that xHC controllers have at most one custom supported speed table (PSI) for all usb 3.x ports.
Memory was allocated for one PSI table under the xhci hub structure.

Turns out this is not the case, some controllers have a separate "supported protocol capability" entry with a PSI table for each port. This means each usb3 roothub port can in theory support different custom speeds.

To solve this, cache all supported protocol capabilities with their PSI tables in an array, and add pointers to the xhci port structure so that every port points to its capability entry in the array.

When creating the SuperSpeedPlus USB Device Capability BOS descriptor for the xhci USB 3.1 roothub we for now will use only data from the first USB 3.1 capable protocol capability entry in the array. This could be improved later, this patch focuses resolving the memory leak.

Reported-by Paul Menzel <[email protected]>

Reported-by Sajja Venkateswara Rao <[email protected]>

Fixes 47189098f8be ("xhci: parse xhci protocol speed ID list for usb 3.1 usage")

Cc stable <[email protected]> # v4.4+

Tested-by Marek Szyprowski <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/host/xhci-hub.c |   25 ++++++++++++------
 drivers/usb/host/xhci-mem.c |   61 +++++++++++++++++++++++++++-----------------
 drivers/usb/host/xhci.h     |   14 +++++++---
 3 files changed, 66 insertions(+), 34 deletions(-)

drivers/usb/host/xhci-hub.c +17 -8

@@ -55,6 +55,7 @@ static u8 usb_bos_descriptor [] = {
 static int xhci_create_usb3_bos_desc(struct xhci_hcd *xhci, char *buf,
 				     u16 wLength)
 {
+	struct xhci_port_cap *port_cap = NULL;
 	int i, ssa_count;
 	u32 temp;
 	u16 desc_size, ssp_cap_size, ssa_size = 0;

@@ -64,16 +65,24 @@ static int xhci_create_usb3_bos_desc(str
 	ssp_cap_size = sizeof(usb_bos_descriptor) - desc_size;
 
 	/* does xhci support USB 3.1 Enhanced SuperSpeed */
-	if (xhci->usb3_rhub.min_rev >= 0x01) {
+	for (i = 0; i < xhci->num_port_caps; i++) {
+		if (xhci->port_caps[i].maj_rev == 0x03 &&
+		    xhci->port_caps[i].min_rev >= 0x01) {
+			usb3_1 = true;
+			port_cap = &xhci->port_caps[i];
+			break;
+		}
+	}
+
+	if (usb3_1) {
 		/* does xhci provide a PSI table for SSA speed attributes? */
-		if (xhci->usb3_rhub.psi_count) {
+		if (port_cap->psi_count) {
 			/* two SSA entries for each unique PSI ID, RX and TX */
-			ssa_count = xhci->usb3_rhub.psi_uid_count * 2;
+			ssa_count = port_cap->psi_uid_count * 2;
 			ssa_size = ssa_count * sizeof(u32);
 			ssp_cap_size -= 16; /* skip copying the default SSA */
 		}
 		desc_size += ssp_cap_size;
-		usb3_1 = true;
 	}
 	memcpy(buf, &usb_bos_descriptor, min(desc_size, wLength));

@@ -99,7 +108,7 @@ static int xhci_create_usb3_bos_desc(str
 	}
 
 	/* If PSI table exists, add the custom speed attributes from it */
-	if (usb3_1 && xhci->usb3_rhub.psi_count) {
+	if (usb3_1 && port_cap->psi_count) {
 		u32 ssp_cap_base, bm_attrib, psi, psi_mant, psi_exp;
 		int offset;

@@ -111,7 +120,7 @@ static int xhci_create_usb3_bos_desc(str
 
 		/* attribute count SSAC bits 4:0 and ID count SSIC bits 8:5 */
 		bm_attrib = (ssa_count - 1) & 0x1f;
-		bm_attrib |= (xhci->usb3_rhub.psi_uid_count - 1) << 5;
+		bm_attrib |= (port_cap->psi_uid_count - 1) << 5;
 		put_unaligned_le32(bm_attrib, &buf[ssp_cap_base + 4]);
 
 		if (wLength < desc_size + ssa_size)

@@ -124,8 +133,8 @@ static int xhci_create_usb3_bos_desc(str
 		 * USB 3.1 requires two SSA entries (RX and TX) for every link
 		 */
 		offset = desc_size;
-		for (i = 0; i < xhci->usb3_rhub.psi_count; i++) {
-			psi = xhci->usb3_rhub.psi[i];
+		for (i = 0; i < port_cap->psi_count; i++) {
+			psi = port_cap->psi[i];
 			psi &= ~USB_SSP_SUBLINK_SPEED_RSVD;
 			psi_exp = XHCI_EXT_PORT_PSIE(psi);
 			psi_mant = XHCI_EXT_PORT_PSIM(psi);

drivers/usb/host/xhci-mem.c +38 ~~-23~~

104 lines not on this page · raw message

drivers/usb/host/xhci.h +11 -3

@@ -1702,12 +1702,20 @@ struct xhci_bus_state {
  * Intel Lynx Point LP xHCI host.
  */
 #define	XHCI_MAX_REXIT_TIMEOUT_MS	20
+struct xhci_port_cap {
+	u32			*psi;	/* array of protocol speed ID entries */
+	u8			psi_count;
+	u8			psi_uid_count;
+	u8			maj_rev;
+	u8			min_rev;
+};
 
 struct xhci_port {
 	__le32 __iomem		*addr;
 	int			hw_portnum;
 	int			hcd_portnum;
 	struct xhci_hub		*rhub;
+	struct xhci_port_cap	*port_cap;
 };
 
 struct xhci_hub {

@@ -1719,9 +1727,6 @@ struct xhci_hub {
 	/* supported prococol extended capabiliy values */
 	u8			maj_rev;
 	u8			min_rev;
-	u32			*psi;	/* array of protocol speed ID entries */
-	u8			psi_count;
-	u8			psi_uid_count;
 };
 
 /* There is one xhci_hcd structure per controller */

@@ -1880,6 +1885,9 @@ struct xhci_hcd {
 	/* cached usb2 extened protocol capabilites */
 	u32                     *ext_caps;
 	unsigned int            num_ext_caps;
+	/* cached extended protocol port capabilities */
+	struct xhci_port_cap	*port_caps;
+	unsigned int		num_port_caps;
 	/* Compliance Mode Recovery Data */
 	struct timer_list	comp_mode_recovery_timer;
 	u32			port_status_u0;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #37 lore raw

PATCH 35/150 USB: core: add endpoint-blacklist quirk

From: Johan Hovold <[email protected]>

commit 73f8bda9b5dc1c69df2bc55c0cbb24461a6391a9 upstream.

Add a new device quirk that can be used to blacklist endpoints.

Since commit 3e4f8e21c4f2 ("USB: core: fix check for duplicate endpoints") USB core ignores any duplicate endpoints found during descriptor parsing.

In order to handle devices where the first interfaces with duplicate endpoints are the ones that should have their endpoints ignored, we need to add a blacklist.

Tested-by edes <[email protected]>

Cc stable <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/core/config.c  |   11 +++++++++++
 drivers/usb/core/quirks.c  |   32 ++++++++++++++++++++++++++++++++
 drivers/usb/core/usb.h     |    3 +++
 include/linux/usb/quirks.h |    3 +++
 4 files changed, 49 insertions(+)

drivers/usb/core/config.c +11 -0

@@ -256,6 +256,7 @@ static int usb_parse_endpoint(struct dev
 		struct usb_host_interface *ifp, int num_ep,
 		unsigned char *buffer, int size)
 {
+	struct usb_device *udev = to_usb_device(ddev);
 	unsigned char *buffer0 = buffer;
 	struct usb_endpoint_descriptor *d;
 	struct usb_host_endpoint *endpoint;

@@ -297,6 +298,16 @@ static int usb_parse_endpoint(struct dev
 		goto skip_to_next_endpoint_or_interface_descriptor;
 	}
 
+	/* Ignore blacklisted endpoints */
+	if (udev->quirks & USB_QUIRK_ENDPOINT_BLACKLIST) {
+		if (usb_endpoint_is_blacklisted(udev, ifp, d)) {
+			dev_warn(ddev, "config %d interface %d altsetting %d has a blacklisted endpoint with address 0x%X, skipping\n",
+					cfgno, inum, asnum,
+					d->bEndpointAddress);
+			goto skip_to_next_endpoint_or_interface_descriptor;
+		}
+	}
+
 	endpoint = &ifp->endpoint[ifp->desc.bNumEndpoints];
 	++ifp->desc.bNumEndpoints;

drivers/usb/core/quirks.c +32 -0

@@ -472,6 +472,38 @@ static const struct usb_device_id usb_am
 	{ }  /* terminating entry must be last */
 };
 
+/*
+ * Entries for blacklisted endpoints that should be ignored when parsing
+ * configuration descriptors.
+ *
+ * Matched for devices with USB_QUIRK_ENDPOINT_BLACKLIST.
+ */
+static const struct usb_device_id usb_endpoint_blacklist[] = {
+	{ }
+};
+
+bool usb_endpoint_is_blacklisted(struct usb_device *udev,
+		struct usb_host_interface *intf,
+		struct usb_endpoint_descriptor *epd)
+{
+	const struct usb_device_id *id;
+	unsigned int address;
+
+	for (id = usb_endpoint_blacklist; id->match_flags; ++id) {
+		if (!usb_match_device(udev, id))
+			continue;
+
+		if (!usb_match_one_id_intf(udev, intf, id))
+			continue;
+
+		address = id->driver_info;
+		if (address == epd->bEndpointAddress)
+			return true;
+	}
+
+	return false;
+}
+
 static bool usb_match_any_interface(struct usb_device *udev,
 				    const struct usb_device_id *id)
 {

drivers/usb/core/usb.h +3 -0

@@ -37,6 +37,9 @@ extern void usb_authorize_interface(stru
 extern void usb_detect_quirks(struct usb_device *udev);
 extern void usb_detect_interface_quirks(struct usb_device *udev);
 extern void usb_release_quirk_list(void);
+extern bool usb_endpoint_is_blacklisted(struct usb_device *udev,
+		struct usb_host_interface *intf,
+		struct usb_endpoint_descriptor *epd);
 extern int usb_remove_device(struct usb_device *udev);
 
 extern int usb_get_device_descriptor(struct usb_device *dev,

include/linux/usb/quirks.h +3 -0

@@ -69,4 +69,7 @@
 /* Hub needs extra delay after resetting its port. */
 #define USB_QUIRK_HUB_SLOW_RESET		BIT(14)
 
+/* device has blacklisted endpoints */
+#define USB_QUIRK_ENDPOINT_BLACKLIST		BIT(15)
+
 #endif /* __LINUX_USB_QUIRKS_H */

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #38 lore raw

PATCH 36/150 USB: quirks: blacklist duplicate ep on Sound Devices USBPre2

From: Johan Hovold <[email protected]>

commit bdd1b147b8026df0e4260b387026b251d888ed01 upstream.

This device has a broken vendor-specific altsetting for interface 1, where endpoint 0x85 is declared as an isochronous endpoint despite being used by interface 2 for audio capture.

Device Descriptor:
bLength 18
bDescriptorType 1
bcdUSB 2.00
bDeviceClass 239 Miscellaneous Device
bDeviceSubClass 2
bDeviceProtocol 1 Interface Association
bMaxPacketSize0 64
idVendor 0x0926
idProduct 0x0202
bcdDevice 1.00

  iManufacturer           1 Sound Devices
  iProduct                2 USBPre2
  iSerial                 3 [...]
  bNumConfigurations      1

[...]

Interface Descriptor:
bLength 9
bDescriptorType 4
bInterfaceNumber 1
bAlternateSetting 3
bNumEndpoints 2
bInterfaceClass 255 Vendor Specific Class
bInterfaceSubClass 0
bInterfaceProtocol 0
iInterface 0
Endpoint Descriptor:
bLength 7
bDescriptorType 5
bEndpointAddress 0x85 EP 5 IN
bmAttributes 5
Transfer Type Isochronous
Synch Type Asynchronous
Usage Type Data
wMaxPacketSize 0x0126 1x 294 bytes
bInterval 1

[...]

Interface Descriptor:
bLength 9
bDescriptorType 4
bInterfaceNumber 2
bAlternateSetting 1
bNumEndpoints 1
bInterfaceClass 1 Audio
bInterfaceSubClass 2 Streaming
bInterfaceProtocol 0
iInterface 0
AudioStreaming Interface Descriptor:
bLength 7
bDescriptorType 36
bDescriptorSubtype 1 (AS_GENERAL)
bTerminalLink 4
bDelay 1 frames
wFormatTag 0x0001 PCM
AudioStreaming Interface Descriptor:
bLength 26
bDescriptorType 36
bDescriptorSubtype 2 (FORMAT_TYPE)
bFormatType 1 (FORMAT_TYPE_I)
bNrChannels 2
bSubframeSize 2
bBitResolution 16
bSamFreqType 6 Discrete
tSamFreq[ 0] 8000
tSamFreq[ 1] 16000
tSamFreq[ 2] 24000
tSamFreq[ 3] 32000
tSamFreq[ 4] 44100
tSamFreq[ 5] 48000
Endpoint Descriptor:
bLength 9
bDescriptorType 5
bEndpointAddress 0x85 EP 5 IN
bmAttributes 5
Transfer Type Isochronous
Synch Type Asynchronous
Usage Type Data
wMaxPacketSize 0x0126 1x 294 bytes
bInterval 4
bRefresh 0
bSynchAddress 0
AudioStreaming Endpoint Descriptor:
bLength 7
bDescriptorType 37
bDescriptorSubtype 1 (EP_GENERAL)
bmAttributes 0x01
Sampling Frequency
bLockDelayUnits 2 Decoded PCM samples
wLockDelay 0x0000

Since commit 3e4f8e21c4f2 ("USB: core: fix check for duplicate endpoints") USB core ignores any duplicate endpoints found during descriptor parsing, but in this case we need to ignore the first instance in order to avoid breaking the audio capture interface.

Fixes 3e4f8e21c4f2 ("USB: core: fix check for duplicate endpoints")

Cc stable <[email protected]>

Reported-by edes <[email protected]>

Tested-by edes <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/core/quirks.c |    5 +++++
 1 file changed, 5 insertions(+)

drivers/usb/core/quirks.c +5 -0

@@ -354,6 +354,10 @@ static const struct usb_device_id usb_qu
 	{ USB_DEVICE(0x0904, 0x6103), .driver_info =
 			USB_QUIRK_LINEAR_FRAME_INTR_BINTERVAL },
 
+	/* Sound Devices USBPre2 */
+	{ USB_DEVICE(0x0926, 0x0202), .driver_info =
+			USB_QUIRK_ENDPOINT_BLACKLIST },
+
 	/* Keytouch QWERTY Panel keyboard */
 	{ USB_DEVICE(0x0926, 0x3333), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },

@@ -479,6 +483,7 @@ static const struct usb_device_id usb_am
  * Matched for devices with USB_QUIRK_ENDPOINT_BLACKLIST.
  */
 static const struct usb_device_id usb_endpoint_blacklist[] = {
+	{ USB_DEVICE_INTERFACE_NUMBER(0x0926, 0x0202, 1), .driver_info = 0x85 },
 	{ }
 };

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #39 lore raw

PATCH 37/150 usb: uas: fix a plug & unplug racing

From: EJ Hsu <[email protected]>

commit 3e99862c05a9caa5a27969f41566b428696f5a9a upstream.

When a uas disk is plugged into an external hub, uas_probe() will be called by the hub thread to do the probe. It will first create a SCSI host and then do the scan for this host. During the scan, it will probe the LUN using SCSI INQUERY command which will be packed in the URB and submitted to uas disk.

There might be a chance that this external hub with uas disk attached is unplugged during the scan. In this case, uas driver will fail to submit the URB (due to the NOTATTACHED state of uas device) and try to put this SCSI command back to request queue waiting for next chance to run.

In normal case, this cycle will terminate when hub thread gets disconnection event and calls into uas_disconnect() accordingly. But in this case, uas_disconnect() will not be called because hub thread of external hub gets stuck waiting for the completion of this SCSI command. A deadlock happened.

In this fix, uas will call scsi_scan_host() asynchronously to avoid the blocking of hub thread.

Signed-off-by EJ Hsu <[email protected]>

Acked-by Oliver Neukum <[email protected]>

Cc stable <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/storage/uas.c |   23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

drivers/usb/storage/uas.c +22 -1

@@ -45,6 +45,7 @@ struct uas_dev_info {
 	struct scsi_cmnd *cmnd[MAX_CMNDS];
 	spinlock_t lock;
 	struct work_struct work;
+	struct work_struct scan_work;      /* for async scanning */
 };
 
 enum {

@@ -114,6 +115,17 @@ out:
 	spin_unlock_irqrestore(&devinfo->lock, flags);
 }
 
+static void uas_scan_work(struct work_struct *work)
+{
+	struct uas_dev_info *devinfo =
+		container_of(work, struct uas_dev_info, scan_work);
+	struct Scsi_Host *shost = usb_get_intfdata(devinfo->intf);
+
+	dev_dbg(&devinfo->intf->dev, "starting scan\n");
+	scsi_scan_host(shost);
+	dev_dbg(&devinfo->intf->dev, "scan complete\n");
+}
+
 static void uas_add_work(struct uas_cmd_info *cmdinfo)
 {
 	struct scsi_pointer *scp = (void *)cmdinfo;

@@ -982,6 +994,7 @@ static int uas_probe(struct usb_interfac
 	init_usb_anchor(&devinfo->data_urbs);
 	spin_lock_init(&devinfo->lock);
 	INIT_WORK(&devinfo->work, uas_do_work);
+	INIT_WORK(&devinfo->scan_work, uas_scan_work);
 
 	result = uas_configure_endpoints(devinfo);
 	if (result)

@@ -998,7 +1011,9 @@ static int uas_probe(struct usb_interfac
 	if (result)
 		goto free_streams;
 
-	scsi_scan_host(shost);
+	/* Submit the delayed_work for SCSI-device scanning */
+	schedule_work(&devinfo->scan_work);
+
 	return result;
 
 free_streams:

@@ -1166,6 +1181,12 @@ static void uas_disconnect(struct usb_in
 	usb_kill_anchored_urbs(&devinfo->data_urbs);
 	uas_zap_pending(devinfo, DID_NO_CONNECT);
 
+	/*
+	 * Prevent SCSI scanning (if it hasn't started yet)
+	 * or wait for the SCSI-scanning routine to stop.
+	 */
+	cancel_work_sync(&devinfo->scan_work);
+
 	scsi_remove_host(shost);
 	uas_free_streams(devinfo);
 	scsi_host_put(shost);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #40 lore raw

PATCH 38/150 USB: Fix novation SourceControl XL after suspend

From: Richard Dodd <[email protected]>

commit b692056db8ecc7f452b934f016c17348282b7699 upstream.

Currently, the SourceControl will stay in power-down mode after resuming from suspend. This patch resets the device after suspend to power it up.

Signed-off-by Richard Dodd <[email protected]>

Cc stable <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/core/quirks.c |    3 +++
 1 file changed, 3 insertions(+)

drivers/usb/core/quirks.c +3 -0

@@ -449,6 +449,9 @@ static const struct usb_device_id usb_qu
 	/* INTEL VALUE SSD */
 	{ USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* novation SoundControl XL */
+	{ USB_DEVICE(0x1235, 0x0061), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	{ }  /* terminating entry must be last */
 };

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #41 lore raw

PATCH 39/150 USB: hub: Dont record a connect-change event during reset-resume

From: Alan Stern <[email protected]>

commit 8099f58f1ecddf4f374f4828a3dff8397c7cbd74 upstream.

Paul Zimmerman reports that his USB Bluetooth adapter sometimes crashes following system resume, when it receives a Get-Device-Descriptor request while it is busy doing something else.

Such a request was added by commit a4f55d8b8c14 ("usb: hub: Check device descriptor before resusciation"). It gets sent when the hub driver's work thread checks whether a connect-change event on an enabled port really indicates a new device has been connected, as opposed to an old device momentarily disconnecting and then reconnecting (which can happen with xHCI host controllers, since they automatically enable connected ports).

The same kind of thing occurs when a port's power session is lost during system suspend. When the system wakes up it sees a connect-change event on the port, and if the child device's persist_enabled flag was set then hub_activate() sets the device's reset_resume flag as well as the port's bit in hub->change_bits. The reset-resume code then takes responsibility for checking that the same device is still attached to the port, and it does this as part of the device's resume pathway. By the time the hub driver's work thread starts up again, the device has already been fully reinitialized and is busy doing its own thing. There's no need for the work thread to do the same check a second time, and in fact this unnecessary check is what caused the problem that Paul observed.

Note that performing the unnecessary check is not actually a bug. Devices are supposed to be able to send descriptors back to the host even when they are busy doing something else. The underlying cause of Paul's problem lies in his Bluetooth adapter. Nevertheless, we shouldn't perform the same check twice in a row -- and as a nice side benefit, removing the extra check allows the Bluetooth adapter to work more reliably.

The work thread performs its check when it sees that the port's bit is set in hub->change_bits. In this situation that bit is interpreted as though a connect-change event had occurred on the port _after_ the reset-resume, which is not what actually happened.

One possible fix would be to make the reset-resume code clear the port's bit in hub->change_bits. But it seems simpler to just avoid setting the bit during hub_activate() in the first place. That's what this patch does.

(Proving that the patch is correct when CONFIG_PM is disabled requires a little thought. In that setting hub_activate() will be called only for initialization and resets, since there won't be any resumes or reset-resumes. During initialization and hub resets the hub doesn't have any child devices, and so this code path never gets executed.)

Reported-and-tested-by Paul Zimmerman <[email protected]>

Signed-off-by Alan Stern <[email protected]>

Link https://marc.info/?t=157949360700001&r=1&w=2

CC David Heinzelmann <[email protected]>

CC <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/core/hub.c |    5 -----
 1 file changed, 5 deletions(-)

drivers/usb/core/hub.c +0 -5

@@ -1217,11 +1217,6 @@ static void hub_activate(struct usb_hub
 #ifdef CONFIG_PM
 			udev->reset_resume = 1;
 #endif
-			/* Don't set the change_bits when the device
-			 * was powered off.
-			 */
-			if (test_bit(port1, hub->power_bits))
-				set_bit(port1, hub->change_bits);
 
 		} else {
 			/* The power session is gone; tell hub_wq */

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #42 lore raw

PATCH 40/150 USB: hub: Fix the broken detection of USB3 device in SMSC hub

From: Hardik Gajjar <[email protected]>

commit 1208f9e1d758c991b0a46a1bd60c616b906bbe27 upstream.

Renesas R-Car H3ULCB + Kingfisher Infotainment Board is either not able to detect the USB3.0 mass storage devices or is detecting those as USB2.0 high speed devices.

The explanation given by Renesas is that, due to a HW issue, the XHCI driver does not wake up after going to sleep on connecting a USB3.0 device.

In order to mitigate that, disable the auto-suspend feature specifically for SMSC hubs from hub_probe() function, as a quirk.

Renesas Kingfisher Infotainment Board has two USB3.0 ports (CN2) which are connected via USB5534B 4-port SuperSpeed/Hi-Speed, low-power, configurable hub controller.

[1] SanDisk USB 3.0 device detected as USB-2.0 before the patch

 [   74.036390] usb 5-1.1: new high-speed USB device number 4 using xhci-hcd
 [   74.061598] usb 5-1.1: New USB device found, idVendor=0781, idProduct=5581, bcdDevice= 1.00
 [   74.069976] usb 5-1.1: New USB device strings: Mfr=1, Product=2, SerialNumber=3
 [   74.077303] usb 5-1.1: Product: Ultra
 [   74.080980] usb 5-1.1: Manufacturer: SanDisk
 [   74.085263] usb 5-1.1: SerialNumber: 4C530001110208116550

[2] SanDisk USB 3.0 device detected as USB-3.0 after the patch

 [   34.565078] usb 6-1.1: new SuperSpeed Gen 1 USB device number 3 using xhci-hcd
 [   34.588719] usb 6-1.1: New USB device found, idVendor=0781, idProduct=5581, bcdDevice= 1.00
 [   34.597098] usb 6-1.1: New USB device strings: Mfr=1, Product=2, SerialNumber=3
 [   34.604430] usb 6-1.1: Product: Ultra
 [   34.608110] usb 6-1.1: Manufacturer: SanDisk
 [   34.612397] usb 6-1.1: SerialNumber: 4C530001110208116550

Signed-off-by Hardik Gajjar <[email protected]>

Acked-by Alan Stern <[email protected]>

Tested-by Eugeniu Rosca <[email protected]>

Cc stable <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/core/hub.c |   15 +++++++++++++++
 drivers/usb/core/hub.h |    1 +
 2 files changed, 16 insertions(+)

drivers/usb/core/hub.c +15 -0

@@ -38,7 +38,9 @@
 #include "otg_whitelist.h"
 
 #define USB_VENDOR_GENESYS_LOGIC		0x05e3
+#define USB_VENDOR_SMSC				0x0424
 #define HUB_QUIRK_CHECK_PORT_AUTOSUSPEND	0x01
+#define HUB_QUIRK_DISABLE_AUTOSUSPEND		0x02
 
 #define USB_TP_TRANSMISSION_DELAY	40	/* ns */
 #define USB_TP_TRANSMISSION_DELAY_MAX	65535	/* ns */

@@ -1726,6 +1728,10 @@ static void hub_disconnect(struct usb_in
 	kfree(hub->buffer);
 
 	pm_suspend_ignore_children(&intf->dev, false);
+
+	if (hub->quirk_disable_autosuspend)
+		usb_autopm_put_interface(intf);
+
 	kref_put(&hub->kref, hub_release);
 }

@@ -1858,6 +1864,11 @@ static int hub_probe(struct usb_interfac
 	if (id->driver_info & HUB_QUIRK_CHECK_PORT_AUTOSUSPEND)
 		hub->quirk_check_port_auto_suspend = 1;
 
+	if (id->driver_info & HUB_QUIRK_DISABLE_AUTOSUSPEND) {
+		hub->quirk_disable_autosuspend = 1;
+		usb_autopm_get_interface(intf);
+	}
+
 	if (hub_configure(hub, &desc->endpoint[0].desc) >= 0)
 		return 0;

@@ -5594,6 +5605,10 @@ out_hdev_lock:
 }
 
 static const struct usb_device_id hub_id_table[] = {
+    { .match_flags = USB_DEVICE_ID_MATCH_VENDOR | USB_DEVICE_ID_MATCH_INT_CLASS,
+      .idVendor = USB_VENDOR_SMSC,
+      .bInterfaceClass = USB_CLASS_HUB,
+      .driver_info = HUB_QUIRK_DISABLE_AUTOSUSPEND},
     { .match_flags = USB_DEVICE_ID_MATCH_VENDOR
 			| USB_DEVICE_ID_MATCH_INT_CLASS,
       .idVendor = USB_VENDOR_GENESYS_LOGIC,

drivers/usb/core/hub.h +1 -0

@@ -61,6 +61,7 @@ struct usb_hub {
 	unsigned		quiescing:1;
 	unsigned		disconnected:1;
 	unsigned		in_reset:1;
+	unsigned		quirk_disable_autosuspend:1;
 
 	unsigned		quirk_check_port_auto_suspend:1;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #43 lore raw

PATCH 41/150 usb: dwc2: Fix SET/CLEAR_FEATURE and GET_STATUS flows

From: Minas Harutyunyan <[email protected]>

commit 9a0d6f7c0a83844baae1d6d85482863d2bf3b7a7 upstream.

SET/CLEAR_FEATURE for Remote Wakeup allowance not handled correctly. GET_STATUS handling provided not correct data on DATA Stage. Issue seen when gadget's dr_mode set to "otg" mode and connected to MacOS.
Both are fixed and tested using USBCV Ch.9 tests.

Signed-off-by Minas Harutyunyan <[email protected]>

Fixes fa389a6d7726 ("usb: dwc2: gadget: Add remote_wakeup_allowed flag")

Tested-by Jack Mitchell <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/dwc2/gadget.c |   28 ++++++++++++++++------------
 1 file changed, 16 insertions(+), 12 deletions(-)

drivers/usb/dwc2/gadget.c +16 ~~-12~~

@@ -1632,6 +1632,7 @@ static int dwc2_hsotg_process_req_status
 	struct dwc2_hsotg_ep *ep0 = hsotg->eps_out[0];
 	struct dwc2_hsotg_ep *ep;
 	__le16 reply;
+	u16 status;
 	int ret;
 
 	dev_dbg(hsotg->dev, "%s: USB_REQ_GET_STATUS\n", __func__);

@@ -1643,11 +1644,10 @@ static int dwc2_hsotg_process_req_status
 
 	switch (ctrl->bRequestType & USB_RECIP_MASK) {
 	case USB_RECIP_DEVICE:
-		/*
-		 * bit 0 => self powered
-		 * bit 1 => remote wakeup
-		 */
-		reply = cpu_to_le16(0);
+		status = 1 << USB_DEVICE_SELF_POWERED;
+		status |= hsotg->remote_wakeup_allowed <<
+			  USB_DEVICE_REMOTE_WAKEUP;
+		reply = cpu_to_le16(status);
 		break;
 
 	case USB_RECIP_INTERFACE:

@@ -1758,7 +1758,10 @@ static int dwc2_hsotg_process_req_featur
 	case USB_RECIP_DEVICE:
 		switch (wValue) {
 		case USB_DEVICE_REMOTE_WAKEUP:
-			hsotg->remote_wakeup_allowed = 1;
+			if (set)
+				hsotg->remote_wakeup_allowed = 1;
+			else
+				hsotg->remote_wakeup_allowed = 0;
 			break;
 
 		case USB_DEVICE_TEST_MODE:

@@ -1768,16 +1771,17 @@ static int dwc2_hsotg_process_req_featur
 				return -EINVAL;
 
 			hsotg->test_mode = wIndex >> 8;
-			ret = dwc2_hsotg_send_reply(hsotg, ep0, NULL, 0);
-			if (ret) {
-				dev_err(hsotg->dev,
-					"%s: failed to send reply\n", __func__);
-				return ret;
-			}
 			break;
 		default:
 			return -ENOENT;
 		}
+
+		ret = dwc2_hsotg_send_reply(hsotg, ep0, NULL, 0);
+		if (ret) {
+			dev_err(hsotg->dev,
+				"%s: failed to send reply\n", __func__);
+			return ret;
+		}
 		break;
 
 	case USB_RECIP_ENDPOINT:

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #44 lore raw

PATCH 42/150 usb: dwc3: gadget: Check for IOC/LST bit in TRB->ctrl fields

From: Anurag Kumar Vulisha <[email protected]>

commit 5ee858975b13a9b40db00f456989a689fdbb296c upstream.

The current code in dwc3_gadget_ep_reclaim_completed_trb() will check for IOC/LST bit in the event->status and returns if IOC/LST bit is set. This logic doesn't work if multiple TRBs are queued per request and the IOC/LST bit is set on the last TRB of that request.

Consider an example where a queued request has multiple queued TRBs and IOC/LST bit is set only for the last TRB. In this case, the core generates XferComplete/XferInProgress events only for the last TRB (since IOC/LST are set only for the last TRB). As per the logic in dwc3_gadget_ep_reclaim_completed_trb() event->status is checked for IOC/LST bit and returns on the first TRB. This leaves the remaining TRBs left unhandled.

Similarly, if the gadget function enqueues an unaligned request with sglist already in it, it should fail the same way, since we will append another TRB to something that already uses more than one TRB.

To aviod this, this patch changes the code to check for IOC/LST bits in TRB->ctrl instead.

At a practical level, this patch resolves USB transfer stalls seen with adb on dwc3 based HiKey960 after functionfs gadget added scatter-gather support around v4.20.

Cc Felipe Balbi <[email protected]>

Cc Yang Fei <[email protected]>

Cc Thinh Nguyen <[email protected]>

Cc Tejas Joglekar <[email protected]>

Cc Andrzej Pietrasiewicz <[email protected]>

Cc Jack Pham <[email protected]>

Cc Todd Kjos <[email protected]>

Cc Greg KH <[email protected]>

Cc Linux USB List <[email protected]>

Cc stable <[email protected]>

Tested-by Tejas Joglekar <[email protected]>

Reviewed-by Thinh Nguyen <[email protected]>

Signed-off-by Anurag Kumar Vulisha <[email protected]>

[jstultz: forward ported to mainline, reworded commit log, reworked
to only check trb->ctrl as suggested by Felipe]

Signed-off-by John Stultz <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/dwc3/gadget.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

drivers/usb/dwc3/gadget.c +2 -1

@@ -2426,7 +2426,8 @@ static int dwc3_gadget_ep_reclaim_comple
 	if (event->status & DEPEVT_STATUS_SHORT && !chain)
 		return 1;
 
-	if (event->status & DEPEVT_STATUS_IOC)
+	if ((trb->ctrl & DWC3_TRB_CTRL_IOC) ||
+	    (trb->ctrl & DWC3_TRB_CTRL_LST))
 		return 1;
 
 	return 0;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #45 lore raw

PATCH 43/150 usb: dwc3: debug: fix string position formatting mixup with ret and len

From: Colin Ian King <[email protected]>

commit b32196e35bd7bbc8038db1aba1fbf022dc469b6a upstream.

Currently the string formatting is mixing up the offset of ret and len. Re-work the code to use just len, remove ret and use scnprintf instead of snprintf and len position accumulation where required. Remove the -ve return check since scnprintf never returns a failure -ve size. Also break overly long lines to clean up checkpatch warnings.

Addresses-Coverity: ("Unused value")

Fixes 1381a5113caf ("usb: dwc3: debug: purge usage of strcat")

Signed-off-by Colin Ian King <[email protected]>

Reviewed-by Dan Carpenter <[email protected]>

Cc stable <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/dwc3/debug.h |   39 +++++++++++++++------------------------
 1 file changed, 15 insertions(+), 24 deletions(-)

drivers/usb/dwc3/debug.h +15 ~~-24~~

@@ -256,86 +256,77 @@ static inline const char *dwc3_ep_event_
 	u8 epnum = event->endpoint_number;
 	size_t len;
 	int status;
-	int ret;
 
-	ret = snprintf(str, size, "ep%d%s: ", epnum >> 1,
+	len = scnprintf(str, size, "ep%d%s: ", epnum >> 1,
 			(epnum & 1) ? "in" : "out");
-	if (ret < 0)
-		return "UNKNOWN";
 
 	status = event->status;
 
 	switch (event->endpoint_event) {
 	case DWC3_DEPEVT_XFERCOMPLETE:
-		len = strlen(str);
-		snprintf(str + len, size - len, "Transfer Complete (%c%c%c)",
+		len += scnprintf(str + len, size - len,
+				"Transfer Complete (%c%c%c)",
 				status & DEPEVT_STATUS_SHORT ? 'S' : 's',
 				status & DEPEVT_STATUS_IOC ? 'I' : 'i',
 				status & DEPEVT_STATUS_LST ? 'L' : 'l');
 
-		len = strlen(str);
-
 		if (epnum <= 1)
-			snprintf(str + len, size - len, " [%s]",
+			scnprintf(str + len, size - len, " [%s]",
 					dwc3_ep0_state_string(ep0state));
 		break;
 	case DWC3_DEPEVT_XFERINPROGRESS:
-		len = strlen(str);
-
-		snprintf(str + len, size - len, "Transfer In Progress [%d] (%c%c%c)",
+		scnprintf(str + len, size - len,
+				"Transfer In Progress [%d] (%c%c%c)",
 				event->parameters,
 				status & DEPEVT_STATUS_SHORT ? 'S' : 's',
 				status & DEPEVT_STATUS_IOC ? 'I' : 'i',
 				status & DEPEVT_STATUS_LST ? 'M' : 'm');
 		break;
 	case DWC3_DEPEVT_XFERNOTREADY:
-		len = strlen(str);
-
-		snprintf(str + len, size - len, "Transfer Not Ready [%d]%s",
+		len += scnprintf(str + len, size - len,
+				"Transfer Not Ready [%d]%s",
 				event->parameters,
 				status & DEPEVT_STATUS_TRANSFER_ACTIVE ?
 				" (Active)" : " (Not Active)");
 
-		len = strlen(str);
-
 		/* Control Endpoints */
 		if (epnum <= 1) {
 			int phase = DEPEVT_STATUS_CONTROL_PHASE(event->status);
 
 			switch (phase) {
 			case DEPEVT_STATUS_CONTROL_DATA:
-				snprintf(str + ret, size - ret,
+				scnprintf(str + len, size - len,
 						" [Data Phase]");
 				break;
 			case DEPEVT_STATUS_CONTROL_STATUS:
-				snprintf(str + ret, size - ret,
+				scnprintf(str + len, size - len,
 						" [Status Phase]");
 			}
 		}
 		break;
 	case DWC3_DEPEVT_RXTXFIFOEVT:
-		snprintf(str + ret, size - ret, "FIFO");
+		scnprintf(str + len, size - len, "FIFO");
 		break;
 	case DWC3_DEPEVT_STREAMEVT:
 		status = event->status;
 
 		switch (status) {
 		case DEPEVT_STREAMEVT_FOUND:
-			snprintf(str + ret, size - ret, " Stream %d Found",
+			scnprintf(str + len, size - len, " Stream %d Found",
 					event->parameters);
 			break;
 		case DEPEVT_STREAMEVT_NOTFOUND:
 		default:
-			snprintf(str + ret, size - ret, " Stream Not Found");
+			scnprintf(str + len, size - len, " Stream Not Found");
 			break;
 		}
 
 		break;
 	case DWC3_DEPEVT_EPCMDCMPLT:
-		snprintf(str + ret, size - ret, "Endpoint Command Complete");
+		scnprintf(str + len, size - len, "Endpoint Command Complete");
 		break;
 	default:
-		snprintf(str, size, "UNKNOWN");
+		scnprintf(str + len, size - len, "UNKNOWN");
 	}
 
 	return str;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:23 UTC #46 lore raw

PATCH 44/150 scsi: Revert "target/core: Inline transport_lun_remove_cmd()"

From: Bart Van Assche <[email protected]>

commit c14335ebb92a98646ddbf447e6cacc66de5269ad upstream.

Commit 83f85b8ec305 postponed the percpu_ref_put(&se_cmd->se_lun->lun_ref) call from command completion to the time when the final command reference is dropped. That approach is not compatible with the iSCSI target driver because the iSCSI target driver keeps the command with the highest stat_sn after it has completed until the next command is received (see also iscsit_ack_from_expstatsn()). Fix this regression by reverting commit 83f85b8ec305.

Fixes 83f85b8ec305 ("scsi: target/core: Inline transport_lun_remove_cmd()")

Cc Pavel Zakharov <[email protected]>

Cc Mike Christie <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Reported-by Pavel Zakharov <[email protected]>

Signed-off-by Bart Van Assche <[email protected]>

Signed-off-by Martin K. Petersen <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/target/target_core_transport.c |   31 ++++++++++++++++++++++++++++---
 1 file changed, 28 insertions(+), 3 deletions(-)

drivers/target/target_core_transport.c +28 -3

@@ -666,6 +666,11 @@ static int transport_cmd_check_stop_to_f
 
 	target_remove_from_state_list(cmd);
 
+	/*
+	 * Clear struct se_cmd->se_lun before the handoff to FE.
+	 */
+	cmd->se_lun = NULL;
+
 	spin_lock_irqsave(&cmd->t_state_lock, flags);
 	/*
 	 * Determine if frontend context caller is requesting the stopping of

@@ -693,6 +698,17 @@ static int transport_cmd_check_stop_to_f
 	return cmd->se_tfo->check_stop_free(cmd);
 }
 
+static void transport_lun_remove_cmd(struct se_cmd *cmd)
+{
+	struct se_lun *lun = cmd->se_lun;
+
+	if (!lun)
+		return;
+
+	if (cmpxchg(&cmd->lun_ref_active, true, false))
+		percpu_ref_put(&lun->lun_ref);
+}
+
 static void target_complete_failure_work(struct work_struct *work)
 {
 	struct se_cmd *cmd = container_of(work, struct se_cmd, work);

@@ -783,6 +799,8 @@ static void target_handle_abort(struct s
 
 	WARN_ON_ONCE(kref_read(&cmd->cmd_kref) == 0);
 
+	transport_lun_remove_cmd(cmd);
+
 	transport_cmd_check_stop_to_fabric(cmd);
 }

@@ -1708,6 +1726,7 @@ static void target_complete_tmr_failure(
 	se_cmd->se_tmr_req->response = TMR_LUN_DOES_NOT_EXIST;
 	se_cmd->se_tfo->queue_tm_rsp(se_cmd);
 
+	transport_lun_remove_cmd(se_cmd);
 	transport_cmd_check_stop_to_fabric(se_cmd);
 }

@@ -1898,6 +1917,7 @@ void transport_generic_request_failure(s
 		goto queue_full;
 
 check_stop:
+	transport_lun_remove_cmd(cmd);
 	transport_cmd_check_stop_to_fabric(cmd);
 	return;

@@ -2195,6 +2215,7 @@ queue_status:
 		transport_handle_queue_full(cmd, cmd->se_dev, ret, false);
 		return;
 	}
+	transport_lun_remove_cmd(cmd);
 	transport_cmd_check_stop_to_fabric(cmd);
 }

@@ -2289,6 +2310,7 @@ static void target_complete_ok_work(stru
 		if (ret)
 			goto queue_full;
 
+		transport_lun_remove_cmd(cmd);
 		transport_cmd_check_stop_to_fabric(cmd);
 		return;
 	}

@@ -2314,6 +2336,7 @@ static void target_complete_ok_work(stru
 			if (ret)
 				goto queue_full;
 
+			transport_lun_remove_cmd(cmd);
 			transport_cmd_check_stop_to_fabric(cmd);
 			return;
 		}

@@ -2349,6 +2372,7 @@ queue_rsp:
 			if (ret)
 				goto queue_full;
 
+			transport_lun_remove_cmd(cmd);
 			transport_cmd_check_stop_to_fabric(cmd);
 			return;
 		}

@@ -2384,6 +2408,7 @@ queue_status:
 		break;
 	}
 
+	transport_lun_remove_cmd(cmd);
 	transport_cmd_check_stop_to_fabric(cmd);
 	return;

@@ -2710,6 +2735,9 @@ int transport_generic_free_cmd(struct se
 		 */
 		if (cmd->state_active)
 			target_remove_from_state_list(cmd);
+
+		if (cmd->se_lun)
+			transport_lun_remove_cmd(cmd);
 	}
 	if (aborted)
 		cmd->free_compl = &compl;

@@ -2781,9 +2809,6 @@ static void target_release_cmd_kref(stru
 	struct completion *abrt_compl = se_cmd->abrt_compl;
 	unsigned long flags;
 
-	if (se_cmd->lun_ref_active)
-		percpu_ref_put(&se_cmd->se_lun->lun_ref);
-
 	if (se_sess) {
 		spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
 		list_del_init(&se_cmd->se_cmd_list);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #47 lore raw

PATCH 45/150 staging: rtl8188eu: Fix potential security hole

From: Larry Finger <[email protected]>

commit 499c405b2b80bb3a04425ba3541d20305e014d3e upstream.

In routine rtw_hostapd_ioctl(), the user-controlled p->length is assumed to be at least the size of struct ieee_param size, but this assumption is never checked. This could result in out-of-bounds read/write on kernel heap in case a p->length less than the size of struct ieee_param is specified by the user. If p->length is allowed to be greater than the size of the struct, then a malicious user could be wasting kernel memory. Fixes commit a2c60d42d97c ("Add files for new driver - part 16").

Reported by: Pietro Oliva <[email protected]>

Cc Pietro Oliva <[email protected]>

Cc Stable <[email protected]>

Fixes a2c60d42d97c ("staging: r8188eu: Add files for new driver - part 16")

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/staging/rtl8188eu/os_dep/ioctl_linux.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/staging/rtl8188eu/os_dep/ioctl_linux.c +1 -1

@@ -2798,7 +2798,7 @@ static int rtw_hostapd_ioctl(struct net_
 		goto out;
 	}
 
-	if (!p->pointer) {
+	if (!p->pointer || p->length != sizeof(struct ieee_param)) {
 		ret = -EINVAL;
 		goto out;
 	}

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #48 lore raw

PATCH 46/150 staging: rtl8188eu: Fix potential overuse of kernel memory

From: Larry Finger <[email protected]>

commit 4ddf8ab8d15ddbc52eefb44eb64e38466ce1f70f upstream.

In routine wpa_supplicant_ioctl(), the user-controlled p->length is checked to be at least the size of struct ieee_param size, but the code does not detect the case where p->length is greater than the size of the struct, thus a malicious user could be wasting kernel memory. Fixes commit a2c60d42d97c ("Add files for new driver - part 16").

Reported by: Pietro Oliva <[email protected]>
Cc: Pietro Oliva <[email protected]>
Cc: Stable <[email protected]>
Fixes commit a2c60d42d97c ("Add files for new driver - part 16").

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/staging/rtl8188eu/os_dep/ioctl_linux.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/staging/rtl8188eu/os_dep/ioctl_linux.c +1 -1

@@ -2011,7 +2011,7 @@ static int wpa_supplicant_ioctl(struct n
 	struct ieee_param *param;
 	uint ret = 0;
 
-	if (p->length < sizeof(struct ieee_param) || !p->pointer) {
+	if (!p->pointer || p->length != sizeof(struct ieee_param)) {
 		ret = -EINVAL;
 		goto out;
 	}

Greg Kroah-Hartman

author maintainer

2020-02-27 14:23 UTC #49 lore raw

PATCH 47/150 staging: rtl8723bs: Fix potential security hole

From: Larry Finger <[email protected]>

commit ac33597c0c0d1d819dccfe001bcd0acef7107e7c upstream.

In routine rtw_hostapd_ioctl(), the user-controlled p->length is assumed to be at least the size of struct ieee_param size, but this assumption is never checked. This could result in out-of-bounds read/write on kernel heap in case a p->length less than the size of struct ieee_param is specified by the user. If p->length is allowed to be greater than the size of the struct, then a malicious user could be wasting kernel memory. Fixes commit 554c0a3abf216 ("0taging: Add rtl8723bs sdio wifi driver").

Reported by: Pietro Oliva <[email protected]>
Cc: Pietro Oliva <[email protected]>
Cc: Stable <[email protected]>
Fixes 554c0a3abf216 ("0taging: Add rtl8723bs sdio wifi driver").

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/staging/rtl8723bs/os_dep/ioctl_linux.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/staging/rtl8723bs/os_dep/ioctl_linux.c +1 -1

@@ -4207,7 +4207,7 @@ static int rtw_hostapd_ioctl(struct net_
 
 
 	/* if (p->length < sizeof(struct ieee_param) || !p->pointer) { */
-	if (!p->pointer) {
+	if (!p->pointer || p->length != sizeof(*param)) {
 		ret = -EINVAL;
 		goto out;
 	}

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #50 lore raw

PATCH 48/150 staging: rtl8723bs: Fix potential overuse of kernel memory

From: Larry Finger <[email protected]>

commit 23954cb078febfc63a755301fe77e06bccdb4d2a upstream.

In routine wpa_supplicant_ioctl(), the user-controlled p->length is checked to be at least the size of struct ieee_param size, but the code does not detect the case where p->length is greater than the size of the struct, thus a malicious user could be wasting kernel memory. Fixes commit 554c0a3abf216 ("staging: Add rtl8723bs sdio wifi driver").

Reported by: Pietro Oliva <[email protected]>

Cc Pietro Oliva <[email protected]>

Cc Stable <[email protected]>

Fixes 554c0a3abf216 ("staging: Add rtl8723bs sdio wifi driver").

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/staging/rtl8723bs/os_dep/ioctl_linux.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/staging/rtl8723bs/os_dep/ioctl_linux.c +1 -1

@@ -3373,7 +3373,7 @@ static int wpa_supplicant_ioctl(struct n
 
 	/* down(&ieee->wx_sem); */
 
-	if (p->length < sizeof(struct ieee_param) || !p->pointer) {
+	if (!p->pointer || p->length != sizeof(struct ieee_param)) {
 		ret = -EINVAL;
 		goto out;
 	}

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #51 lore raw

PATCH 49/150 hwmon: (acpi_power_meter) Fix lockdep splat

From: Guenter Roeck <[email protected]>

commit badcd4546d52ae4318f2bcfda0e47a1394b60e38 upstream.

Damien Le Moal reports a lockdep splat with the acpi_power_meter, observed with Linux v5.5 and later.

======================================================
WARNING: possible circular locking dependency detected
5.6.0-rc2+ #629 Not tainted
------------------------------------------------------
python/1397 is trying to acquire lock:
ffff888619080070 (&resource->lock){+.+.}, at: show_power+0x3c/0xa0 [acpi_power_meter]

but task is already holding lock:
ffff88881643f188 (kn->count#119){++++}, at: kernfs_seq_start+0x6a/0x160

               which lock already depends on the new lock.

               the existing dependency chain (in reverse order) is:

               -> #1 (kn->count#119){++++}:
       __kernfs_remove+0x626/0x7e0
       kernfs_remove_by_name_ns+0x41/0x80
       remove_attrs+0xcb/0x3c0 [acpi_power_meter]
       acpi_power_meter_notify+0x1f7/0x310 [acpi_power_meter]
       acpi_ev_notify_dispatch+0x198/0x1f3
       acpi_os_execute_deferred+0x4d/0x70
       process_one_work+0x7c8/0x1340
       worker_thread+0x94/0xc70
       kthread+0x2ed/0x3f0
       ret_from_fork+0x24/0x30

               -> #0 (&resource->lock){+.+.}:
       __lock_acquire+0x20be/0x49b0
       lock_acquire+0x127/0x340
       __mutex_lock+0x15b/0x1350
       show_power+0x3c/0xa0 [acpi_power_meter]
       dev_attr_show+0x3f/0x80
       sysfs_kf_seq_show+0x216/0x410
       seq_read+0x407/0xf90
       vfs_read+0x152/0x2c0
       ksys_read+0xf3/0x1d0
       do_syscall_64+0x95/0x1010
       entry_SYSCALL_64_after_hwframe+0x49/0xbe

               other info that might help us debug this:

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(kn->count#119);
                               lock(&resource->lock);
                               lock(kn->count#119);

lock(&resource->lock);

                *** DEADLOCK ***

4 locks held by python/1397:
#0: ffff8890242d64e0 (&f->f_pos_lock){+.+.}, at: __fdget_pos+0x9b/0xb0 #1: ffff889040be74e0 (&p->lock){+.+.}, at: seq_read+0x6b/0xf90 #2: ffff8890448eb880 (&of->mutex){+.+.}, at: kernfs_seq_start+0x47/0x160 #3: ffff88881643f188 (kn->count#119){++++}, at: kernfs_seq_start+0x6a/0x160

               stack backtrace:
CPU: 10 PID: 1397 Comm: python Not tainted 5.6.0-rc2+ #629
Hardware name: Supermicro Super Server/X11DPL-i, BIOS 3.1 05/21/2019
Call Trace:
 dump_stack+0x97/0xe0
 check_noncircular+0x32e/0x3e0
 ? print_circular_bug.isra.0+0x1e0/0x1e0
 ? unwind_next_frame+0xb9a/0x1890
 ? entry_SYSCALL_64_after_hwframe+0x49/0xbe
 ? graph_lock+0x79/0x170
 ? __lockdep_reset_lock+0x3c0/0x3c0
 ? mark_lock+0xbc/0x1150
 __lock_acquire+0x20be/0x49b0
 ? mark_held_locks+0xe0/0xe0
 ? stack_trace_save+0x91/0xc0
 lock_acquire+0x127/0x340
 ? show_power+0x3c/0xa0 [acpi_power_meter]
 ? device_remove_bin_file+0x10/0x10
 ? device_remove_bin_file+0x10/0x10
 __mutex_lock+0x15b/0x1350
 ? show_power+0x3c/0xa0 [acpi_power_meter]
 ? show_power+0x3c/0xa0 [acpi_power_meter]
 ? mutex_lock_io_nested+0x11f0/0x11f0
 ? lock_downgrade+0x6a0/0x6a0
 ? kernfs_seq_start+0x47/0x160
 ? lock_acquire+0x127/0x340
 ? kernfs_seq_start+0x6a/0x160
 ? device_remove_bin_file+0x10/0x10
 ? show_power+0x3c/0xa0 [acpi_power_meter]
 show_power+0x3c/0xa0 [acpi_power_meter]
 dev_attr_show+0x3f/0x80
 ? memset+0x20/0x40
 sysfs_kf_seq_show+0x216/0x410
 seq_read+0x407/0xf90
 ? security_file_permission+0x16f/0x2c0
 vfs_read+0x152/0x2c0

Problem is that reading an attribute takes the kernfs lock in the kernfs code, then resource->lock in the driver. During an ACPI notification, the opposite happens: The resource lock is taken first, followed by the kernfs lock when sysfs attributes are removed and re-created. Presumably this is now seen due to some locking related changes in kernfs after v5.4, but it was likely always a problem.

Fix the problem by not blindly acquiring the lock in the notification function. It is only needed to protect the various update functions. However, those update functions are called anyway when sysfs attributes are read. This means that we can just stop calling those functions from the notifier, and the resource lock in the notifier function is no longer needed.

That leaves two situations:

First, METER_NOTIFY_CONFIG removes and re-allocates capability strings. While it did so under the resource lock, _displaying_ those strings was not protected, creating a race condition. To solve this problem, selectively protect both removal/creation and reporting of capability attributes with the resource lock.

Second, removing and re-creating the attribute files is no longer protected by the resource lock. That doesn't matter since access to each individual attribute is protected by the kernfs lock. Userspace may get messed up if attributes disappear and reappear under its nose, but that is not different than today, and there is nothing we can do about it without major driver restructuring.

Last but not least, when removing the driver, remove attribute functions first, then release capability strings. This avoids yet another race condition.

Reported-by Damien Le Moal <[email protected]>

Cc Damien Le Moal <[email protected]>

Cc [email protected] # v5.5+

Tested-by Damien Le Moal <[email protected]>

Signed-off-by Guenter Roeck <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/hwmon/acpi_power_meter.c |   16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

drivers/hwmon/acpi_power_meter.c +8 -8

@@ -355,7 +355,9 @@ static ssize_t show_str(struct device *d
 	struct acpi_device *acpi_dev = to_acpi_device(dev);
 	struct acpi_power_meter_resource *resource = acpi_dev->driver_data;
 	acpi_string val;
+	int ret;
 
+	mutex_lock(&resource->lock);
 	switch (attr->index) {
 	case 0:
 		val = resource->model_number;

@@ -372,8 +374,9 @@ static ssize_t show_str(struct device *d
 		val = "";
 		break;
 	}
-
-	return sprintf(buf, "%s\n", val);
+	ret = sprintf(buf, "%s\n", val);
+	mutex_unlock(&resource->lock);
+	return ret;
 }
 
 static ssize_t show_val(struct device *dev,

@@ -817,11 +820,12 @@ static void acpi_power_meter_notify(stru
 
 	resource = acpi_driver_data(device);
 
-	mutex_lock(&resource->lock);
 	switch (event) {
 	case METER_NOTIFY_CONFIG:
+		mutex_lock(&resource->lock);
 		free_capabilities(resource);
 		res = read_capabilities(resource);
+		mutex_unlock(&resource->lock);
 		if (res)
 			break;

@@ -830,15 +834,12 @@ static void acpi_power_meter_notify(stru
 		break;
 	case METER_NOTIFY_TRIP:
 		sysfs_notify(&device->dev.kobj, NULL, POWER_AVERAGE_NAME);
-		update_meter(resource);
 		break;
 	case METER_NOTIFY_CAP:
 		sysfs_notify(&device->dev.kobj, NULL, POWER_CAP_NAME);
-		update_cap(resource);
 		break;
 	case METER_NOTIFY_INTERVAL:
 		sysfs_notify(&device->dev.kobj, NULL, POWER_AVG_INTERVAL_NAME);
-		update_avg_interval(resource);
 		break;
 	case METER_NOTIFY_CAPPING:
 		sysfs_notify(&device->dev.kobj, NULL, POWER_ALARM_NAME);

@@ -848,7 +849,6 @@ static void acpi_power_meter_notify(stru
 		WARN(1, "Unexpected event %d\n", event);
 		break;
 	}
-	mutex_unlock(&resource->lock);
 
 	acpi_bus_generate_netlink_event(ACPI_POWER_METER_CLASS,
 					dev_name(&device->dev), event, 0);

@@ -912,8 +912,8 @@ static int acpi_power_meter_remove(struc
 	resource = acpi_driver_data(device);
 	hwmon_device_unregister(resource->hwmon_dev);
 
-	free_capabilities(resource);
 	remove_attrs(resource);
+	free_capabilities(resource);
 
 	kfree(resource);
 	return 0;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:23 UTC #52 lore raw

PATCH 50/150 drm/panfrost: perfcnt: Reserve/use the AS attached to the perfcnt MMU context

From: Boris Brezillon <[email protected]>

commit dde2bb2da01e96c17f0a44b4a3cf72a30e66e3ef upstream.

We need to use the AS attached to the opened FD when dumping counters.

Reported-by Antonio Caggiano <[email protected]>

Fixes 7282f7645d06 ("drm/panfrost: Implement per FD address spaces")

Link https://patchwork.freedesktop.org/patch/msgid/[email protected]

Signed-off-by Boris Brezillon <[email protected]>

Reviewed-by Steven Price <[email protected]>

Tested-by Antonio Caggiano <[email protected]>

Signed-off-by Rob Herring <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/panfrost/panfrost_mmu.c     |    7 ++++++-
 drivers/gpu/drm/panfrost/panfrost_perfcnt.c |   11 ++++-------
 2 files changed, 10 insertions(+), 8 deletions(-)

drivers/gpu/drm/panfrost/panfrost_mmu.c +6 -1

@@ -151,7 +151,12 @@ u32 panfrost_mmu_as_get(struct panfrost_
 	as = mmu->as;
 	if (as >= 0) {
 		int en = atomic_inc_return(&mmu->as_count);
-		WARN_ON(en >= NUM_JOB_SLOTS);
+
+		/*
+		 * AS can be retained by active jobs or a perfcnt context,
+		 * hence the '+ 1' here.
+		 */
+		WARN_ON(en >= (NUM_JOB_SLOTS + 1));
 
 		list_move(&mmu->list, &pfdev->as_lru_list);
 		goto out;

drivers/gpu/drm/panfrost/panfrost_perfcnt.c +4 -7

@@ -73,7 +73,7 @@ static int panfrost_perfcnt_enable_locke
 	struct panfrost_file_priv *user = file_priv->driver_priv;
 	struct panfrost_perfcnt *perfcnt = pfdev->perfcnt;
 	struct drm_gem_shmem_object *bo;
-	u32 cfg;
+	u32 cfg, as;
 	int ret;
 
 	if (user == perfcnt->user)

@@ -126,12 +126,8 @@ static int panfrost_perfcnt_enable_locke
 
 	perfcnt->user = user;
 
-	/*
-	 * Always use address space 0 for now.
-	 * FIXME: this needs to be updated when we start using different
-	 * address space.
-	 */
-	cfg = GPU_PERFCNT_CFG_AS(0) |
+	as = panfrost_mmu_as_get(pfdev, perfcnt->mapping->mmu);
+	cfg = GPU_PERFCNT_CFG_AS(as) |
 	      GPU_PERFCNT_CFG_MODE(GPU_PERFCNT_CFG_MODE_MANUAL);
 
 	/*

@@ -195,6 +191,7 @@ static int panfrost_perfcnt_disable_lock
 	drm_gem_shmem_vunmap(&perfcnt->mapping->obj->base.base, perfcnt->buf);
 	perfcnt->buf = NULL;
 	panfrost_gem_close(&perfcnt->mapping->obj->base.base, file_priv);
+	panfrost_mmu_as_put(pfdev, perfcnt->mapping->mmu);
 	panfrost_gem_mapping_put(perfcnt->mapping);
 	perfcnt->mapping = NULL;
 	pm_runtime_mark_last_busy(pfdev->dev);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #53 lore raw

PATCH 51/150 powerpc/8xx: Fix clearing of bits 20-23 in ITLB miss

From: Christophe Leroy <[email protected]>

commit a4031afb9d10d97f4d0285844abbc0ab04245304 upstream.

In ITLB miss handled the line supposed to clear bits 20-23 on the L2 ITLB entry is buggy and does indeed nothing, leading to undefined value which could allow execution when it shouldn't.

Properly do the clearing with the relevant instruction.

Fixes 74fabcadfd43 ("powerpc/8xx: don't use r12/SPRN_SPRG_SCRATCH2 in TLB Miss handlers")

Cc [email protected] # v5.0+

Reviewed-by Leonardo Bras <[email protected]>

Link https://lore.kernel.org/r/4f70c2778163affce8508a210f65d140e84524b4.1581272050.git.christophe.leroy@c-s.fr open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/powerpc/kernel/head_8xx.S |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

arch/powerpc/kernel/head_8xx.S +1 -1

@@ -289,7 +289,7 @@ InstructionTLBMiss:
 	 * set.  All other Linux PTE bits control the behavior
 	 * of the MMU.
 	 */
-	rlwimi	r10, r10, 0, 0x0f00	/* Clear bits 20-23 */
+	rlwinm	r10, r10, 0, ~0x0f00	/* Clear bits 20-23 */
 	rlwimi	r10, r10, 4, 0x0400	/* Copy _PAGE_EXEC into bit 21 */
 	ori	r10, r10, RPN_PATTERN | 0x200 /* Set 22 and 24-27 */
 	mtspr	SPRN_MI_RPN, r10	/* Update TLB entry */

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #54 lore raw

PATCH 52/150 powerpc/eeh: Fix deadlock handling dead PHB

From: Sam Bobroff <[email protected]>

commit d4f194ed9eb9841a8f978710e4d24296f791a85b upstream.

Recovering a dead PHB can currently cause a deadlock as the PCI rescan/remove lock is taken twice.

This is caused as part of an existing bug in eeh_handle_special_event(). The pe is processed while traversing the PHBs even though the pe is unrelated to the loop. This causes the pe to be, incorrectly, processed more than once.

Untangling this section can move the pe processing out of the loop and also outside the locked section, correcting both problems.

Fixes 2e25505147b8 ("powerpc/eeh: Fix crash when edev->pdev changes")

Cc [email protected] # 5.4+

Signed-off-by Sam Bobroff <[email protected]>

Reviewed-by Frederic Barrat <[email protected]>

Tested-by Frederic Barrat <[email protected]>

Link https://lore.kernel.org/r/0547e82dbf90ee0729a2979a8cac5c91665c621f.1581051445.git.sbobroff@linux.ibm.com open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/powerpc/kernel/eeh_driver.c |   21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

arch/powerpc/kernel/eeh_driver.c +11 ~~-10~~

@@ -1184,6 +1184,17 @@ void eeh_handle_special_event(void)
 			eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
 			eeh_handle_normal_event(pe);
 		} else {
+			eeh_for_each_pe(pe, tmp_pe)
+				eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev)
+					edev->mode &= ~EEH_DEV_NO_HANDLER;
+
+			/* Notify all devices to be down */
+			eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true);
+			eeh_set_channel_state(pe, pci_channel_io_perm_failure);
+			eeh_pe_report(
+				"error_detected(permanent failure)", pe,
+				eeh_report_failure, NULL);
+
 			pci_lock_rescan_remove();
 			list_for_each_entry(hose, &hose_list, list_node) {
 				phb_pe = eeh_phb_pe_get(hose);

@@ -1192,16 +1203,6 @@ void eeh_handle_special_event(void)
 				    (phb_pe->state & EEH_PE_RECOVERING))
 					continue;
 
-				eeh_for_each_pe(pe, tmp_pe)
-					eeh_pe_for_each_dev(tmp_pe, edev, tmp_edev)
-						edev->mode &= ~EEH_DEV_NO_HANDLER;
-
-				/* Notify all devices to be down */
-				eeh_pe_state_clear(pe, EEH_PE_PRI_BUS, true);
-				eeh_set_channel_state(pe, pci_channel_io_perm_failure);
-				eeh_pe_report(
-					"error_detected(permanent failure)", pe,
-					eeh_report_failure, NULL);
 				bus = eeh_pe_bus_get(phb_pe);
 				if (!bus) {
 					pr_err("%s: Cannot find PCI bus for "

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #55 lore raw

PATCH 53/150 powerpc/tm: Fix clearing MSR[TS] in current when reclaiming on signal delivery

From: Gustavo Luiz Duarte <[email protected]>

commit 2464cc4c345699adea52c7aef75707207cb8a2f6 upstream.

After a treclaim, we expect to be in non-transactional state. If we don't clear the current thread's MSR[TS] before we get preempted, then tm_recheckpoint_new_task() will recheckpoint and we get rescheduled in suspended transaction state.

When handling a signal caught in transactional state, handle_rt_signal64() calls get_tm_stackpointer() that treclaims the transaction using tm_reclaim_current() but without clearing the thread's MSR[TS]. This can cause the TM Bad Thing exception below if later we pagefault and get preempted trying to access the user's sigframe, using __put_user(). Afterwards, when we are rescheduled back into do_page_fault() (but now in suspended state since the thread's MSR[TS] was not cleared), upon executing 'rfid' after completion of the page fault handling, the exception is raised because a transition from suspended to non-transactional state is invalid.

Unexpected TM Bad Thing exception at c00000000000de44 (msr 0x8000000302a03031) tm_scratch=800000010280b033

  Oops: Unrecoverable exception, sig: 6 [#1]
  LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
  CPU: 25 PID: 15547 Comm: a.out Not tainted 5.4.0-rc2 #32
  NIP:  c00000000000de44 LR: c000000000034728 CTR: 0000000000000000
  REGS: c00000003fe7bd70 TRAP: 0700   Not tainted  (5.4.0-rc2)
  MSR:  8000000302a03031 <SF,VEC,VSX,FP,ME,IR,DR,LE,TM[SE]>  CR: 44000884  XER: 00000000
  CFAR: c00000000000dda4 IRQMASK: 0
  PACATMSCRATCH: 800000010280b033
  GPR00: c000000000034728 c000000f65a17c80 c000000001662800 00007fffacf3fd78
  GPR04: 0000000000001000 0000000000001000 0000000000000000 c000000f611f8af0
  GPR08: 0000000000000000 0000000078006001 0000000000000000 000c000000000000
  GPR12: c000000f611f84b0 c00000003ffcb200 0000000000000000 0000000000000000
  GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
  GPR20: 0000000000000000 0000000000000000 0000000000000000 c000000f611f8140
  GPR24: 0000000000000000 00007fffacf3fd68 c000000f65a17d90 c000000f611f7800
  GPR28: c000000f65a17e90 c000000f65a17e90 c000000001685e18 00007fffacf3f000
  NIP [c00000000000de44] fast_exception_return+0xf4/0x1b0
  LR [c000000000034728] handle_rt_signal64+0x78/0xc50
  Call Trace:
  [c000000f65a17c80] [c000000000034710] handle_rt_signal64+0x60/0xc50 (unreliable)
  [c000000f65a17d30] [c000000000023640] do_notify_resume+0x330/0x460
  [c000000f65a17e20] [c00000000000dcc4] ret_from_except_lite+0x70/0x74
  Instruction dump:
  7c4ff120 e8410170 7c5a03a6 38400000 f8410060 e8010070 e8410080 e8610088
  60000000 60000000 e8810090 e8210078 <4c000024> 48000000 e8610178 88ed0989
  ---[ end trace 93094aa44b442f87 ]---

The simplified sequence of events that triggers the above exception is:

... # userspace in NON-TRANSACTIONAL state
tbegin # userspace in TRANSACTIONAL state
signal delivery # kernelspace in SUSPENDED state
handle_rt_signal64()
get_tm_stackpointer()
treclaim # kernelspace in NON-TRANSACTIONAL state
__put_user()
page fault happens. We will never get back here because of the TM Bad Thing exception.

page fault handling kicks in and we voluntarily preempt ourselves do_page_fault()

    __schedule()
      __switch_to(other_task)

our task is rescheduled and we recheckpoint because the thread's MSR[TS] was not cleared __switch_to(our_task)
switch_to_tm()
tm_recheckpoint_new_task()
trechkpt # kernelspace in SUSPENDED state

The page fault handling resumes, but now we are in suspended transaction state
do_page_fault() completes
rfid <----- trying to get back where the page fault happened (we were non-transactional back then)
TM Bad Thing # illegal transition from suspended to non-transactional

This patch fixes that issue by clearing the current thread's MSR[TS] just after treclaim in get_tm_stackpointer() so that we stay in non-transactional state in case we are preempted. In order to make treclaim and clearing the thread's MSR[TS] atomic from a preemption perspective when CONFIG_PREEMPT is set, preempt_disable/enable() is used. It's also necessary to save the previous value of the thread's MSR before get_tm_stackpointer() is called so that it can be exposed to the signal handler later in setup_tm_sigcontexts() to inform the userspace MSR at the moment of the signal delivery.

Found with tm-signal-context-force-tm kernel selftest.

Fixes 2b0a576d15e0 ("powerpc: Add new transactional memory state to the signal context")

Cc [email protected] # v3.9

Signed-off-by Gustavo Luiz Duarte <[email protected]>

Acked-by Michael Neuling <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/powerpc/kernel/signal.c    |   17 +++++++++++++++--
 arch/powerpc/kernel/signal_32.c |   28 ++++++++++++++--------------
 arch/powerpc/kernel/signal_64.c |   22 ++++++++++------------
 3 files changed, 39 insertions(+), 28 deletions(-)

arch/powerpc/kernel/signal.c +15 -2

@@ -200,14 +200,27 @@ unsigned long get_tm_stackpointer(struct
 	 * normal/non-checkpointed stack pointer.
 	 */
 
+	unsigned long ret = tsk->thread.regs->gpr[1];
+
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	BUG_ON(tsk != current);
 
 	if (MSR_TM_ACTIVE(tsk->thread.regs->msr)) {
+		preempt_disable();
 		tm_reclaim_current(TM_CAUSE_SIGNAL);
 		if (MSR_TM_TRANSACTIONAL(tsk->thread.regs->msr))
-			return tsk->thread.ckpt_regs.gpr[1];
+			ret = tsk->thread.ckpt_regs.gpr[1];
+
+		/*
+		 * If we treclaim, we must clear the current thread's TM bits
+		 * before re-enabling preemption. Otherwise we might be
+		 * preempted and have the live MSR[TS] changed behind our back
+		 * (tm_recheckpoint_new_task() would recheckpoint). Besides, we
+		 * enter the signal handler in non-transactional state.
+		 */
+		tsk->thread.regs->msr &= ~MSR_TS_MASK;
+		preempt_enable();
 	}
 #endif
-	return tsk->thread.regs->gpr[1];
+	return ret;
 }

arch/powerpc/kernel/signal_32.c +14 ~~-14~~

@@ -489,19 +489,11 @@ static int save_user_regs(struct pt_regs
  */
 static int save_tm_user_regs(struct pt_regs *regs,
 			     struct mcontext __user *frame,
-			     struct mcontext __user *tm_frame, int sigret)
+			     struct mcontext __user *tm_frame, int sigret,
+			     unsigned long msr)
 {
-	unsigned long msr = regs->msr;
-
 	WARN_ON(tm_suspend_disabled);
 
-	/* Remove TM bits from thread's MSR.  The MSR in the sigcontext
-	 * just indicates to userland that we were doing a transaction, but we
-	 * don't want to return in transactional state.  This also ensures
-	 * that flush_fp_to_thread won't set TIF_RESTORE_TM again.
-	 */
-	regs->msr &= ~MSR_TS_MASK;
-
 	/* Save both sets of general registers */
 	if (save_general_regs(&current->thread.ckpt_regs, frame)
 	    || save_general_regs(regs, tm_frame))

@@ -912,6 +904,10 @@ int handle_rt_signal32(struct ksignal *k
 	int sigret;
 	unsigned long tramp;
 	struct pt_regs *regs = tsk->thread.regs;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/* Save the thread's msr before get_tm_stackpointer() changes it */
+	unsigned long msr = regs->msr;
+#endif
 
 	BUG_ON(tsk != current);

@@ -944,13 +940,13 @@ int handle_rt_signal32(struct ksignal *k
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	tm_frame = &rt_sf->uc_transact.uc_mcontext;
-	if (MSR_TM_ACTIVE(regs->msr)) {
+	if (MSR_TM_ACTIVE(msr)) {
 		if (__put_user((unsigned long)&rt_sf->uc_transact,
 			       &rt_sf->uc.uc_link) ||
 		    __put_user((unsigned long)tm_frame,
 			       &rt_sf->uc_transact.uc_regs))
 			goto badframe;
-		if (save_tm_user_regs(regs, frame, tm_frame, sigret))
+		if (save_tm_user_regs(regs, frame, tm_frame, sigret, msr))
 			goto badframe;
 	}
 	else

@@ -1369,6 +1365,10 @@ int handle_signal32(struct ksignal *ksig
 	int sigret;
 	unsigned long tramp;
 	struct pt_regs *regs = tsk->thread.regs;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/* Save the thread's msr before get_tm_stackpointer() changes it */
+	unsigned long msr = regs->msr;
+#endif
 
 	BUG_ON(tsk != current);

@@ -1402,9 +1402,9 @@ int handle_signal32(struct ksignal *ksig
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	tm_mctx = &frame->mctx_transact;
-	if (MSR_TM_ACTIVE(regs->msr)) {
+	if (MSR_TM_ACTIVE(msr)) {
 		if (save_tm_user_regs(regs, &frame->mctx, &frame->mctx_transact,
-				      sigret))
+				      sigret, msr))
 			goto badframe;
 	}
 	else

arch/powerpc/kernel/signal_64.c +10 ~~-12~~

@@ -192,7 +192,8 @@ static long setup_sigcontext(struct sigc
 static long setup_tm_sigcontexts(struct sigcontext __user *sc,
 				 struct sigcontext __user *tm_sc,
 				 struct task_struct *tsk,
-				 int signr, sigset_t *set, unsigned long handler)
+				 int signr, sigset_t *set, unsigned long handler,
+				 unsigned long msr)
 {
 	/* When CONFIG_ALTIVEC is set, we _always_ setup v_regs even if the
 	 * process never used altivec yet (MSR_VEC is zero in pt_regs of

@@ -207,12 +208,11 @@ static long setup_tm_sigcontexts(struct
 	elf_vrreg_t __user *tm_v_regs = sigcontext_vmx_regs(tm_sc);
 #endif
 	struct pt_regs *regs = tsk->thread.regs;
-	unsigned long msr = tsk->thread.regs->msr;
 	long err = 0;
 
 	BUG_ON(tsk != current);
 
-	BUG_ON(!MSR_TM_ACTIVE(regs->msr));
+	BUG_ON(!MSR_TM_ACTIVE(msr));
 
 	WARN_ON(tm_suspend_disabled);

@@ -222,13 +222,6 @@ static long setup_tm_sigcontexts(struct
 	 */
 	msr |= tsk->thread.ckpt_regs.msr & (MSR_FP | MSR_VEC | MSR_VSX);
 
-	/* Remove TM bits from thread's MSR.  The MSR in the sigcontext
-	 * just indicates to userland that we were doing a transaction, but we
-	 * don't want to return in transactional state.  This also ensures
-	 * that flush_fp_to_thread won't set TIF_RESTORE_TM again.
-	 */
-	regs->msr &= ~MSR_TS_MASK;
-
 #ifdef CONFIG_ALTIVEC
 	err |= __put_user(v_regs, &sc->v_regs);
 	err |= __put_user(tm_v_regs, &tm_sc->v_regs);

@@ -824,6 +817,10 @@ int handle_rt_signal64(struct ksignal *k
 	unsigned long newsp = 0;
 	long err = 0;
 	struct pt_regs *regs = tsk->thread.regs;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/* Save the thread's msr before get_tm_stackpointer() changes it */
+	unsigned long msr = regs->msr;
+#endif
 
 	BUG_ON(tsk != current);

@@ -841,7 +838,7 @@ int handle_rt_signal64(struct ksignal *k
 	err |= __put_user(0, &frame->uc.uc_flags);
 	err |= __save_altstack(&frame->uc.uc_stack, regs->gpr[1]);
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	if (MSR_TM_ACTIVE(regs->msr)) {
+	if (MSR_TM_ACTIVE(msr)) {
 		/* The ucontext_t passed to userland points to the second
 		 * ucontext_t (for transactional state) with its uc_link ptr.
 		 */

@@ -849,7 +846,8 @@ int handle_rt_signal64(struct ksignal *k
 		err |= setup_tm_sigcontexts(&frame->uc.uc_mcontext,
 					    &frame->uc_transact.uc_mcontext,
 					    tsk, ksig->sig, NULL,
-					    (unsigned long)ksig->ka.sa.sa_handler);
+					    (unsigned long)ksig->ka.sa.sa_handler,
+					    msr);
 	} else
 #endif
 	{

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #56 lore raw

PATCH 54/150 powerpc/entry: Fix an #if which should be an #ifdef in entry_32.S

From: Christophe Leroy <[email protected]>

commit 9eb425b2e04e0e3006adffea5bf5f227a896f128 upstream.

Fixes 12c3f1fd87bf ("powerpc/32s: get rid of CPU_FTR_601 feature")

Cc [email protected] # v5.4+

Link https://lore.kernel.org/r/a99fc0ad65b87a1ba51cfa3e0e9034ee294c3e07.1582034961.git.christophe.leroy@c-s.fr open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/powerpc/kernel/entry_32.S |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

arch/powerpc/kernel/entry_32.S +2 -2

@@ -778,7 +778,7 @@ fast_exception_return:
 1:	lis	r3,exc_exit_restart_end@ha
 	addi	r3,r3,exc_exit_restart_end@l
 	cmplw	r12,r3
-#if CONFIG_PPC_BOOK3S_601
+#ifdef CONFIG_PPC_BOOK3S_601
 	bge	2b
 #else
 	bge	3f

@@ -786,7 +786,7 @@ fast_exception_return:
 	lis	r4,exc_exit_restart@ha
 	addi	r4,r4,exc_exit_restart@l
 	cmplw	r12,r4
-#if CONFIG_PPC_BOOK3S_601
+#ifdef CONFIG_PPC_BOOK3S_601
 	blt	2b
 #else
 	blt	3f

Greg Kroah-Hartman

author maintainer

2020-02-27 14:14 UTC #57 lore raw

PATCH 55/150 powerpc/hugetlb: Fix 512k hugepages on 8xx with 16k page size

From: Christophe Leroy <[email protected]>

commit f2b67ef90b0d5eca0f2255e02cf2f620bc0ddcdb upstream.

Commit 55c8fc3f4930 ("powerpc/8xx: reintroduce 16K pages with HW assistance") redefined pte_t as a struct of 4 pte_basic_t, because in 16K pages mode there are four identical entries in the page table. But the size of hugepage tables is calculated based of the size of (void *). Therefore, we end up with page tables of size 1k instead of 4k for 512k pages.

As 512k hugepage tables are the same size as standard page tables, ie 4k, use the standard page tables instead of PGT_CACHE tables.

Fixes 3fb69c6a1a13 ("powerpc/8xx: Enable 512k hugepage support with HW assistance")

Cc [email protected] # v5.0+

Link https://lore.kernel.org/r/90ec56a2315be602494619ed0223bba3b0b8d619.1580997007.git.christophe.leroy@c-s.fr open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/powerpc/mm/hugetlbpage.c |   29 ++++++++++++++++++-----------
 1 file changed, 18 insertions(+), 11 deletions(-)

arch/powerpc/mm/hugetlbpage.c +18 ~~-11~~

@@ -53,20 +53,24 @@ static int __hugepte_alloc(struct mm_str
 	if (pshift >= pdshift) {
 		cachep = PGT_CACHE(PTE_T_ORDER);
 		num_hugepd = 1 << (pshift - pdshift);
+		new = NULL;
 	} else if (IS_ENABLED(CONFIG_PPC_8xx)) {
-		cachep = PGT_CACHE(PTE_INDEX_SIZE);
+		cachep = NULL;
 		num_hugepd = 1;
+		new = pte_alloc_one(mm);
 	} else {
 		cachep = PGT_CACHE(pdshift - pshift);
 		num_hugepd = 1;
+		new = NULL;
 	}
 
-	if (!cachep) {
+	if (!cachep && !new) {
 		WARN_ONCE(1, "No page table cache created for hugetlb tables");
 		return -ENOMEM;
 	}
 
-	new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL));
+	if (cachep)
+		new = kmem_cache_alloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL));
 
 	BUG_ON(pshift > HUGEPD_SHIFT_MASK);
 	BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);

@@ -97,7 +101,10 @@ static int __hugepte_alloc(struct mm_str
 	if (i < num_hugepd) {
 		for (i = i - 1 ; i >= 0; i--, hpdp--)
 			*hpdp = __hugepd(0);
-		kmem_cache_free(cachep, new);
+		if (cachep)
+			kmem_cache_free(cachep, new);
+		else
+			pte_free(mm, new);
 	} else {
 		kmemleak_ignore(new);
 	}

@@ -324,8 +331,7 @@ static void free_hugepd_range(struct mmu
 	if (shift >= pdshift)
 		hugepd_free(tlb, hugepte);
 	else if (IS_ENABLED(CONFIG_PPC_8xx))
-		pgtable_free_tlb(tlb, hugepte,
-				 get_hugepd_cache_index(PTE_INDEX_SIZE));
+		pgtable_free_tlb(tlb, hugepte, 0);
 	else
 		pgtable_free_tlb(tlb, hugepte,
 				 get_hugepd_cache_index(pdshift - shift));

@@ -639,12 +645,13 @@ static int __init hugetlbpage_init(void)
 		 * if we have pdshift and shift value same, we don't
 		 * use pgt cache for hugepd.
 		 */
-		if (pdshift > shift && IS_ENABLED(CONFIG_PPC_8xx))
-			pgtable_cache_add(PTE_INDEX_SIZE);
-		else if (pdshift > shift)
-			pgtable_cache_add(pdshift - shift);
-		else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) || IS_ENABLED(CONFIG_PPC_8xx))
+		if (pdshift > shift) {
+			if (!IS_ENABLED(CONFIG_PPC_8xx))
+				pgtable_cache_add(pdshift - shift);
+		} else if (IS_ENABLED(CONFIG_PPC_FSL_BOOK3E) ||
+			   IS_ENABLED(CONFIG_PPC_8xx)) {
 			pgtable_cache_add(PTE_T_ORDER);
+		}
 
 		configured = true;
 	}

Greg Kroah-Hartman

author maintainer

2020-02-27 14:23 UTC #58 lore raw

PATCH 56/150 powerpc/hugetlb: Fix 8M hugepages on 8xx

From: Christophe Leroy <[email protected]>

commit 50a175dd18de7a647e72aca7daf4744e3a5a81e3 upstream.

With HW assistance all page tables must be 4k aligned, the 8xx drops the last 12 bits during the walk.

Redefine HUGEPD_SHIFT_MASK to mask last 12 bits out. HUGEPD_SHIFT_MASK is used to for alignment of page table cache.

Fixes 22569b881d37 ("powerpc/8xx: Enable 8M hugepage support with HW assistance")

Cc [email protected] # v5.0+

Link https://lore.kernel.org/r/778b1a248c4c7ca79640eeff7740044da6a220a0.1581264115.git.christophe.leroy@c-s.fr open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/powerpc/include/asm/page.h |    5 +++++
 1 file changed, 5 insertions(+)

arch/powerpc/include/asm/page.h +5 -0

@@ -295,8 +295,13 @@ static inline bool pfn_valid(unsigned lo
 /*
  * Some number of bits at the level of the page table that points to
  * a hugepte are used to encode the size.  This masks those bits.
+ * On 8xx, HW assistance requires 4k alignment for the hugepte.
  */
+#ifdef CONFIG_PPC_8xx
+#define HUGEPD_SHIFT_MASK     0xfff
+#else
 #define HUGEPD_SHIFT_MASK     0x3f
+#endif
 
 #ifndef __ASSEMBLY__

Greg Kroah-Hartman

author maintainer

2020-02-27 14:15 UTC #59 lore raw

PATCH 57/150 arm64: memory: Add missing brackets to untagged_addr() macro

From: Will Deacon <[email protected]>

commit d0022c0ef29b78bcbe8a5c5894bd2307143afce1 upstream.

Add brackets around the evaluation of the 'addr' parameter to the untagged_addr() macro so that the cast to 'u64' applies to the result of the expression.

Fixes 597399d0cb91 ("arm64: tags: Preserve tags for addresses translated via TTBR1")

Reported-by Linus Torvalds <[email protected]>

Signed-off-by Will Deacon <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/arm64/include/asm/memory.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

arch/arm64/include/asm/memory.h +1 -1

@@ -213,7 +213,7 @@ static inline unsigned long kaslr_offset
 	((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55))
 
 #define untagged_addr(addr)	({					\
-	u64 __addr = (__force u64)addr;					\
+	u64 __addr = (__force u64)(addr);					\
 	__addr &= __untagged_addr(__addr);				\
 	(__force __typeof__(addr))__addr;				\
 })

Greg Kroah-Hartman

author maintainer

2020-02-27 14:15 UTC #60 lore raw

PATCH 58/150 jbd2: fix ocfs2 corrupt when clearing block group bits

From: wangyan <[email protected]>

commit 8eedabfd66b68a4623beec0789eac54b8c9d0fb6 upstream.

I found a NULL pointer dereference in ocfs2_block_group_clear_bits(). The running environment:
kernel version: 4.19
A cluster with two nodes, 5 luns mounted on two nodes, and do some file operations like dd/fallocate/truncate/rm on every lun with storage network disconnection.

The fallocate operation on dm-23-45 caused an null pointer dereference.

The information of NULL pointer dereference as follows:

	[577992.878282] JBD2: Error -5 detected when updating journal superblock for dm-23-45.
	[577992.878290] Aborting journal on device dm-23-45.
	...
	[577992.890778] JBD2: Error -5 detected when updating journal superblock for dm-24-46.
	[577992.890908] __journal_remove_journal_head: freeing b_committed_data
	[577992.890916] (fallocate,88392,52):ocfs2_extend_trans:474 ERROR: status = -30
	[577992.890918] __journal_remove_journal_head: freeing b_committed_data
	[577992.890920] (fallocate,88392,52):ocfs2_rotate_tree_right:2500 ERROR: status = -30
	[577992.890922] __journal_remove_journal_head: freeing b_committed_data
	[577992.890924] (fallocate,88392,52):ocfs2_do_insert_extent:4382 ERROR: status = -30
	[577992.890928] (fallocate,88392,52):ocfs2_insert_extent:4842 ERROR: status = -30
	[577992.890928] __journal_remove_journal_head: freeing b_committed_data
	[577992.890930] (fallocate,88392,52):ocfs2_add_clusters_in_btree:4947 ERROR: status = -30
	[577992.890933] __journal_remove_journal_head: freeing b_committed_data
	[577992.890939] __journal_remove_journal_head: freeing b_committed_data
	[577992.890949] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000020
	[577992.890950] Mem abort info:
	[577992.890951]   ESR = 0x96000004
	[577992.890952]   Exception class = DABT (current EL), IL = 32 bits
	[577992.890952]   SET = 0, FnV = 0
	[577992.890953]   EA = 0, S1PTW = 0
	[577992.890954] Data abort info:
	[577992.890955]   ISV = 0, ISS = 0x00000004
	[577992.890956]   CM = 0, WnR = 0
	[577992.890958] user pgtable: 4k pages, 48-bit VAs, pgdp = 00000000f8da07a9
	[577992.890960] [0000000000000020] pgd=0000000000000000
	[577992.890964] Internal error: Oops: 96000004 [#1] SMP
	[577992.890965] Process fallocate (pid: 88392, stack limit = 0x00000000013db2fd)
	[577992.890968] CPU: 52 PID: 88392 Comm: fallocate Kdump: loaded Tainted: G        W  OE     4.19.36 #1
	[577992.890969] Hardware name: Huawei TaiShan 2280 V2/BC82AMDD, BIOS 0.98 08/25/2019
	[577992.890971] pstate: 60400009 (nZCv daif +PAN -UAO)
	[577992.891054] pc : _ocfs2_free_suballoc_bits+0x63c/0x968 [ocfs2]
	[577992.891082] lr : _ocfs2_free_suballoc_bits+0x618/0x968 [ocfs2]
	[577992.891084] sp : ffff0000c8e2b810
	[577992.891085] x29: ffff0000c8e2b820 x28: 0000000000000000
	[577992.891087] x27: 00000000000006f3 x26: ffffa07957b02e70
	[577992.891089] x25: ffff807c59d50000 x24: 00000000000006f2
	[577992.891091] x23: 0000000000000001 x22: ffff807bd39abc30
	[577992.891093] x21: ffff0000811d9000 x20: ffffa07535d6a000
	[577992.891097] x19: ffff000001681638 x18: ffffffffffffffff
	[577992.891098] x17: 0000000000000000 x16: ffff000080a03df0
	[577992.891100] x15: ffff0000811d9708 x14: 203d207375746174
	[577992.891101] x13: 73203a524f525245 x12: 20373439343a6565
	[577992.891103] x11: 0000000000000038 x10: 0101010101010101
	[577992.891106] x9 : ffffa07c68a85d70 x8 : 7f7f7f7f7f7f7f7f
	[577992.891109] x7 : 0000000000000000 x6 : 0000000000000080
	[577992.891110] x5 : 0000000000000000 x4 : 0000000000000002
	[577992.891112] x3 : ffff000001713390 x2 : 2ff90f88b1c22f00
	[577992.891114] x1 : ffff807bd39abc30 x0 : 0000000000000000
	[577992.891116] Call trace:
	[577992.891139]  _ocfs2_free_suballoc_bits+0x63c/0x968 [ocfs2]
	[577992.891162]  _ocfs2_free_clusters+0x100/0x290 [ocfs2]
	[577992.891185]  ocfs2_free_clusters+0x50/0x68 [ocfs2]
	[577992.891206]  ocfs2_add_clusters_in_btree+0x198/0x5e0 [ocfs2]
	[577992.891227]  ocfs2_add_inode_data+0x94/0xc8 [ocfs2]
	[577992.891248]  ocfs2_extend_allocation+0x1bc/0x7a8 [ocfs2]
	[577992.891269]  ocfs2_allocate_extents+0x14c/0x338 [ocfs2]
	[577992.891290]  __ocfs2_change_file_space+0x3f8/0x610 [ocfs2]
	[577992.891309]  ocfs2_fallocate+0xe4/0x128 [ocfs2]
	[577992.891316]  vfs_fallocate+0x11c/0x250
	[577992.891317]  ksys_fallocate+0x54/0x88
	[577992.891319]  __arm64_sys_fallocate+0x28/0x38
	[577992.891323]  el0_svc_common+0x78/0x130
	[577992.891325]  el0_svc_handler+0x38/0x78
	[577992.891327]  el0_svc+0x8/0xc

My analysis process as follows:
ocfs2_fallocate
__ocfs2_change_file_space

    ocfs2_allocate_extents
      ocfs2_extend_allocation
        ocfs2_add_inode_data
          ocfs2_add_clusters_in_btree
            ocfs2_insert_extent
              ocfs2_do_insert_extent
                ocfs2_rotate_tree_right
                  ocfs2_extend_rotate_transaction
                    ocfs2_extend_trans
                      jbd2_journal_restart
                        jbd2__journal_restart
                          /* handle->h_transaction is NULL,
                           * is_handle_aborted(handle) is true
                           */
                          handle->h_transaction = NULL;
                          start_this_handle
                            return -EROFS;
            ocfs2_free_clusters
              _ocfs2_free_clusters
                _ocfs2_free_suballoc_bits
                  ocfs2_block_group_clear_bits
                    ocfs2_journal_access_gd
                      __ocfs2_journal_access
                        jbd2_journal_get_undo_access
                          /* I think jbd2_write_access_granted() will
                           * return true, because do_get_write_access()
                           * will return -EROFS.
                           */
                          if (jbd2_write_access_granted(...)) return 0;
                          do_get_write_access
                            /* handle->h_transaction is NULL, it will
                             * return -EROFS here, so do_get_write_access()
                             * was not called.
                             */
                            if (is_handle_aborted(handle)) return -EROFS;
                    /* bh2jh(group_bh) is NULL, caused NULL
                       pointer dereference */
                    undo_bg = (struct ocfs2_group_desc *)
                                bh2jh(group_bh)->b_committed_data;

If handle->h_transaction == NULL, then jbd2_write_access_granted() does not really guarantee that journal_head will stay around, not even speaking of its b_committed_data. The bh2jh(group_bh) can be removed after ocfs2_journal_access_gd() and before call "bh2jh(group_bh)->b_committed_data". So, we should move is_handle_aborted() check from do_get_write_access() into jbd2_journal_get_undo_access() and jbd2_journal_get_write_access() before the call to jbd2_write_access_granted().

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Yan Wang <[email protected]>

Reviewed-by Jun Piao <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/jbd2/transaction.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

fs/jbd2/transaction.c +6 -2

@@ -936,8 +936,6 @@ do_get_write_access(handle_t *handle, st
 	char *frozen_buffer = NULL;
 	unsigned long start_lock, time_lock;
 
-	if (is_handle_aborted(handle))
-		return -EROFS;
 	journal = transaction->t_journal;
 
 	jbd_debug(5, "journal_head %p, force_copy %d\n", jh, force_copy);

@@ -1189,6 +1187,9 @@ int jbd2_journal_get_write_access(handle
 	struct journal_head *jh;
 	int rc;
 
+	if (is_handle_aborted(handle))
+		return -EROFS;
+
 	if (jbd2_write_access_granted(handle, bh, false))
 		return 0;

@@ -1326,6 +1327,9 @@ int jbd2_journal_get_undo_access(handle_
 	struct journal_head *jh;
 	char *committed_data = NULL;
 
+	if (is_handle_aborted(handle))
+		return -EROFS;
+
 	if (jbd2_write_access_granted(handle, bh, true))
 		return 0;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:15 UTC #61 lore raw

PATCH 59/150 x86/ima: use correct identifier for SetupMode variable

From: Ard Biesheuvel <[email protected]>

commit ff5ac61ee83c13f516544d29847d28be093a40ee upstream.

The IMA arch code attempts to inspect the "SetupMode" EFI variable by populating a variable called efi_SetupMode_name with the string "SecureBoot" and passing that to the EFI GetVariable service, which obviously does not yield the expected result.

Given that the string is only referenced a single time, let's get rid of the intermediate variable, and pass the correct string as an immediate argument. While at it, do the same for "SecureBoot".

Fixes 399574c64eaf ("x86/ima: retry detecting secure boot mode")

Fixes 980ef4d22a95 ("x86/ima: check EFI SetupMode too")

Cc Matthew Garrett <[email protected]>

Signed-off-by Ard Biesheuvel <[email protected]>

Cc [email protected] # v5.3

Signed-off-by Mimi Zohar <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/x86/kernel/ima_arch.c |    6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

arch/x86/kernel/ima_arch.c +2 -4

@@ -10,8 +10,6 @@ extern struct boot_params boot_params;
 
 static enum efi_secureboot_mode get_sb_mode(void)
 {
-	efi_char16_t efi_SecureBoot_name[] = L"SecureBoot";
-	efi_char16_t efi_SetupMode_name[] = L"SecureBoot";
 	efi_guid_t efi_variable_guid = EFI_GLOBAL_VARIABLE_GUID;
 	efi_status_t status;
 	unsigned long size;

@@ -25,7 +23,7 @@ static enum efi_secureboot_mode get_sb_m
 	}
 
 	/* Get variable contents into buffer */
-	status = efi.get_variable(efi_SecureBoot_name, &efi_variable_guid,
+	status = efi.get_variable(L"SecureBoot", &efi_variable_guid,
 				  NULL, &size, &secboot);
 	if (status == EFI_NOT_FOUND) {
 		pr_info("ima: secureboot mode disabled\n");

@@ -38,7 +36,7 @@ static enum efi_secureboot_mode get_sb_m
 	}
 
 	size = sizeof(setupmode);
-	status = efi.get_variable(efi_SetupMode_name, &efi_variable_guid,
+	status = efi.get_variable(L"SetupMode", &efi_variable_guid,
 				  NULL, &size, &setupmode);
 
 	if (status != EFI_SUCCESS)	/* ignore unknown SetupMode */

Greg Kroah-Hartman

author maintainer

2020-02-27 14:17 UTC #62 lore raw

PATCH 60/150 x86/mce/amd: Publish the bank pointer only after setup has succeeded

From: Borislav Petkov <[email protected]>

commit 6e5cf31fbe651bed7ba1df768f2e123531132417 upstream.

threshold_create_bank() creates a bank descriptor per MCA error thresholding counter which can be controlled over sysfs. It publishes the pointer to that bank in a per-CPU variable and then goes on to create additional thresholding blocks if the bank has such.

However, that creation of additional blocks in allocate_threshold_blocks() can fail, leading to a use-after-free through the per-CPU pointer.

Therefore, publish that pointer only after all blocks have been setup successfully.

Fixes 019f34fccfd5 ("x86, MCE, AMD: Move shared bank to node descriptor")

Reported-by Saar Amar <[email protected]>

Reported-by Dan Carpenter <[email protected]>

Signed-off-by Borislav Petkov <[email protected]>

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/x86/kernel/cpu/mce/amd.c |   33 ++++++++++++++++-----------------
 1 file changed, 16 insertions(+), 17 deletions(-)

arch/x86/kernel/cpu/mce/amd.c +16 ~~-17~~

@@ -1196,8 +1196,9 @@ static const char *get_name(unsigned int
 	return buf_mcatype;
 }
 
-static int allocate_threshold_blocks(unsigned int cpu, unsigned int bank,
-				     unsigned int block, u32 address)
+static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb,
+				     unsigned int bank, unsigned int block,
+				     u32 address)
 {
 	struct threshold_block *b = NULL;
 	u32 low, high;

@@ -1241,16 +1242,12 @@ static int allocate_threshold_blocks(uns
 
 	INIT_LIST_HEAD(&b->miscj);
 
-	if (per_cpu(threshold_banks, cpu)[bank]->blocks) {
-		list_add(&b->miscj,
-			 &per_cpu(threshold_banks, cpu)[bank]->blocks->miscj);
-	} else {
-		per_cpu(threshold_banks, cpu)[bank]->blocks = b;
-	}
+	if (tb->blocks)
+		list_add(&b->miscj, &tb->blocks->miscj);
+	else
+		tb->blocks = b;
 
-	err = kobject_init_and_add(&b->kobj, &threshold_ktype,
-				   per_cpu(threshold_banks, cpu)[bank]->kobj,
-				   get_name(bank, b));
+	err = kobject_init_and_add(&b->kobj, &threshold_ktype, tb->kobj, get_name(bank, b));
 	if (err)
 		goto out_free;
 recurse:

@@ -1258,7 +1255,7 @@ recurse:
 	if (!address)
 		return 0;
 
-	err = allocate_threshold_blocks(cpu, bank, block, address);
+	err = allocate_threshold_blocks(cpu, tb, bank, block, address);
 	if (err)
 		goto out_free;

@@ -1343,8 +1340,6 @@ static int threshold_create_bank(unsigne
 		goto out_free;
 	}
 
-	per_cpu(threshold_banks, cpu)[bank] = b;
-
 	if (is_shared_bank(bank)) {
 		refcount_set(&b->cpus, 1);

@@ -1355,9 +1350,13 @@ static int threshold_create_bank(unsigne
 		}
 	}
 
-	err = allocate_threshold_blocks(cpu, bank, 0, msr_ops.misc(bank));
-	if (!err)
-		goto out;
+	err = allocate_threshold_blocks(cpu, b, bank, 0, msr_ops.misc(bank));
+	if (err)
+		goto out_free;
+
+	per_cpu(threshold_banks, cpu)[bank] = b;
+
+	return 0;
 
  out_free:
 	kfree(b);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:15 UTC #63 lore raw

PATCH 61/150 x86/mce/amd: Fix kobject lifetime

From: Thomas Gleixner <[email protected]>

commit 51dede9c05df2b78acd6dcf6a17d21f0877d2d7b upstream.

Accessing the MCA thresholding controls in sysfs concurrently with CPU hotplug can lead to a couple of KASAN-reported issues:

  BUG: KASAN: use-after-free in sysfs_file_ops+0x155/0x180
  Read of size 8 at addr ffff888367578940 by task grep/4019

and

  BUG: KASAN: use-after-free in show_error_count+0x15c/0x180
  Read of size 2 at addr ffff888368a05514 by task grep/4454

for example. Both result from the fact that the threshold block creation/teardown code frees the descriptor memory itself instead of defining proper ->release function and leaving it to the driver core to take care of that, after all sysfs accesses have completed.

Do that and get rid of the custom freeing code, fixing the above UAFs in the process.

[ bp: write commit message. ]

Fixes 95268664390b ("[PATCH] x86_64: mce_amd support for family 0x10 processors")

Signed-off-by Borislav Petkov <[email protected]>

Link https://lkml.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/x86/kernel/cpu/mce/amd.c |   17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

arch/x86/kernel/cpu/mce/amd.c +11 -6

@@ -1161,9 +1161,12 @@ static const struct sysfs_ops threshold_
 	.store			= store,
 };
 
+static void threshold_block_release(struct kobject *kobj);
+
 static struct kobj_type threshold_ktype = {
 	.sysfs_ops		= &threshold_ops,
 	.default_attrs		= default_attrs,
+	.release		= threshold_block_release,
 };
 
 static const char *get_name(unsigned int bank, struct threshold_block *b)

@@ -1365,8 +1368,12 @@ static int threshold_create_bank(unsigne
 	return err;
 }
 
-static void deallocate_threshold_block(unsigned int cpu,
-						 unsigned int bank)
+static void threshold_block_release(struct kobject *kobj)
+{
+	kfree(to_block(kobj));
+}
+
+static void deallocate_threshold_block(unsigned int cpu, unsigned int bank)
 {
 	struct threshold_block *pos = NULL;
 	struct threshold_block *tmp = NULL;

@@ -1376,13 +1383,11 @@ static void deallocate_threshold_block(u
 		return;
 
 	list_for_each_entry_safe(pos, tmp, &head->blocks->miscj, miscj) {
-		kobject_put(&pos->kobj);
 		list_del(&pos->miscj);
-		kfree(pos);
+		kobject_put(&pos->kobj);
 	}
 
-	kfree(per_cpu(threshold_banks, cpu)[bank]->blocks);
-	per_cpu(threshold_banks, cpu)[bank]->blocks = NULL;
+	kobject_put(&head->blocks->kobj);
 }
 
 static void __threshold_remove_blocks(struct threshold_bank *b)

Greg Kroah-Hartman

author maintainer

2020-02-27 14:15 UTC #64 lore raw

PATCH 62/150 x86/cpu/amd: Enable the fixed Instructions Retired counter IRPERF

From: Kim Phillips <[email protected]>

commit 21b5ee59ef18e27d85810584caf1f7ddc705ea83 upstream.

Commit

aaf248848db50 ("perf/x86/msr: Add AMD IRPERF (Instructions Retired)
performance counter")

added support for access to the free-running counter via 'perf -e msr/irperf/', but when exercised, it always returns a 0 count:

BEFORE:

  $ perf stat -e instructions,msr/irperf/ true

Performance counter stats for 'true':

             624,833      instructions
                   0      msr/irperf/

Simply set its enable bit - HWCR bit 30 - to make it start counting.

Enablement is restricted to all machines advertising IRPERF capability, except those susceptible to an erratum that makes the IRPERF return bad values.

That erratum occurs in Family 17h models 00-1fh [1], but not in F17h models 20h and above [2].

AFTER (on a family 17h model 31h machine):

  $ perf stat -e instructions,msr/irperf/ true

Performance counter stats for 'true':

             621,690      instructions
             622,490      msr/irperf/

[1] Revision Guide for AMD Family 17h Models 00h-0Fh Processors
[2] Revision Guide for AMD Family 17h Models 30h-3Fh Processors

The revision guides are available from the bugzilla Link below.

[ bp: Massage commit message. ]

Fixes aaf248848db50 ("perf/x86/msr: Add AMD IRPERF (Instructions Retired) performance counter")

Signed-off-by Kim Phillips <[email protected]>

Signed-off-by Borislav Petkov <[email protected]>

Cc Peter Zijlstra <[email protected]>

Link https://bugzilla.kernel.org/show_bug.cgi?id=206537

Link http://lkml.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/x86/include/asm/msr-index.h |    2 ++
 arch/x86/kernel/cpu/amd.c        |   14 ++++++++++++++
 2 files changed, 16 insertions(+)

arch/x86/include/asm/msr-index.h +2 -0

@@ -512,6 +512,8 @@
 #define MSR_K7_HWCR			0xc0010015
 #define MSR_K7_HWCR_SMMLOCK_BIT		0
 #define MSR_K7_HWCR_SMMLOCK		BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
+#define MSR_K7_HWCR_IRPERF_EN_BIT	30
+#define MSR_K7_HWCR_IRPERF_EN		BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT)
 #define MSR_K7_FID_VID_CTL		0xc0010041
 #define MSR_K7_FID_VID_STATUS		0xc0010042

arch/x86/kernel/cpu/amd.c +14 -0

@@ -28,6 +28,7 @@
 
 static const int amd_erratum_383[];
 static const int amd_erratum_400[];
+static const int amd_erratum_1054[];
 static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum);
 
 /*

@@ -978,6 +979,15 @@ static void init_amd(struct cpuinfo_x86
 	/* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */
 	if (!cpu_has(c, X86_FEATURE_XENPV))
 		set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS);
+
+	/*
+	 * Turn on the Instructions Retired free counter on machines not
+	 * susceptible to erratum #1054 "Instructions Retired Performance
+	 * Counter May Be Inaccurate".
+	 */
+	if (cpu_has(c, X86_FEATURE_IRPERF) &&
+	    !cpu_has_amd_erratum(c, amd_erratum_1054))
+		msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT);
 }
 
 #ifdef CONFIG_X86_32

@@ -1105,6 +1115,10 @@ static const int amd_erratum_400[] =
 static const int amd_erratum_383[] =
 	AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf));
 
+/* #1054: Instructions Retired Performance Counter May Be Inaccurate */
+static const int amd_erratum_1054[] =
+	AMD_OSVW_ERRATUM(0, AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf));
+
 
 static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
 {

Greg Kroah-Hartman

author maintainer

2020-02-27 14:21 UTC #65 lore raw

PATCH 63/150 MIPS: ingenic: DTS: Fix watchdog nodes

From: Paul Cercueil <[email protected]>

commit 11479e8e3cd896673a15af21cd0f145a4752f01a upstream.

The devicetree ABI was broken on purpose by commit 6d532143c915 ("watchdog: jz4740: Use regmap provided by TCU driver"), and commit 1d9c30745455 ("watchdog: jz4740: Use WDT clock provided by TCU driver"). The commit message of the latter explains why the ABI was broken.

However, the current devicetree files were not updated to the new ABI described in Documentation/devicetree/bindings/timer/ingenic,tcu.txt, so the watchdog driver would not probe.

Fix this problem by updating the watchdog nodes to comply with the new ABI.

Fixes 6d532143c915 ("watchdog: jz4740: Use regmap provided by TCU driver")

Signed-off-by Paul Cercueil <[email protected]>

Reviewed-by Philippe Mathieu-Daudé <[email protected]>

Signed-off-by Paul Burton <[email protected]>

Cc Ralf Baechle <[email protected]>

Cc Rob Herring <[email protected]>

Cc Mark Rutland <[email protected]>

Cc Zhou Yanjie <[email protected]>

Cc <[email protected]> # v5.5+

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/mips/boot/dts/ingenic/jz4740.dtsi |   17 +++++++++--------
 arch/mips/boot/dts/ingenic/jz4780.dtsi |   17 +++++++++--------
 2 files changed, 18 insertions(+), 16 deletions(-)

arch/mips/boot/dts/ingenic/jz4740.dtsi +9 -8

@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <dt-bindings/clock/jz4740-cgu.h>
+#include <dt-bindings/clock/ingenic,tcu.h>
 
 / {
 	#address-cells = <1>;

@@ -45,14 +46,6 @@
 		#clock-cells = <1>;
 	};
 
-	watchdog: watchdog@10002000 {
-		compatible = "ingenic,jz4740-watchdog";
-		reg = <0x10002000 0x10>;
-
-		clocks = <&cgu JZ4740_CLK_RTC>;
-		clock-names = "rtc";
-	};
-
 	tcu: timer@10002000 {
 		compatible = "ingenic,jz4740-tcu", "simple-mfd";
 		reg = <0x10002000 0x1000>;

@@ -73,6 +66,14 @@
 
 		interrupt-parent = <&intc>;
 		interrupts = <23 22 21>;
+
+		watchdog: watchdog@0 {
+			compatible = "ingenic,jz4740-watchdog";
+			reg = <0x0 0xc>;
+
+			clocks = <&tcu TCU_CLK_WDT>;
+			clock-names = "wdt";
+		};
 	};
 
 	rtc_dev: rtc@10003000 {

arch/mips/boot/dts/ingenic/jz4780.dtsi +9 -8

@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <dt-bindings/clock/jz4780-cgu.h>
+#include <dt-bindings/clock/ingenic,tcu.h>
 #include <dt-bindings/dma/jz4780-dma.h>
 
 / {

@@ -67,6 +68,14 @@
 
 		interrupt-parent = <&intc>;
 		interrupts = <27 26 25>;
+
+		watchdog: watchdog@0 {
+			compatible = "ingenic,jz4780-watchdog";
+			reg = <0x0 0xc>;
+
+			clocks = <&tcu TCU_CLK_WDT>;
+			clock-names = "wdt";
+		};
 	};
 
 	rtc_dev: rtc@10003000 {

@@ -348,14 +357,6 @@
 		status = "disabled";
 	};
 
-	watchdog: watchdog@10002000 {
-		compatible = "ingenic,jz4780-watchdog";
-		reg = <0x10002000 0x10>;
-
-		clocks = <&cgu JZ4780_CLK_RTCLK>;
-		clock-names = "rtc";
-	};
-
 	nemc: nemc@13410000 {
 		compatible = "ingenic,jz4780-nemc";
 		reg = <0x13410000 0x10000>;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:16 UTC #66 lore raw

PATCH 64/150 serial: 8250: Check UPF_IRQ_SHARED in advance

From: Andy Shevchenko <[email protected]>

commit 7febbcbc48fc92e3f33863b32ed715ba4aff18c4 upstream.

The commit 54e53b2e8081
("tty: serial: 8250: pass IRQ shared flag to UART ports")
nicely explained the problem:

---8<---8<---

On some systems IRQ lines between multiple UARTs might be shared. If so, the irqflags have to be configured accordingly. The reason is: The 8250 port startup code performs IRQ tests *before* the IRQ handler for that particular port is registered. This is performed in serial8250_do_startup(). This function checks whether IRQF_SHARED is configured and only then disables the IRQ line while testing.

This test is performed upon each open() of the UART device. Imagine two UARTs share the same IRQ line: On is already opened and the IRQ is active. When the second UART is opened, the IRQ line has to be disabled while performing IRQ tests. Otherwise an IRQ might handler might be invoked, but the IRQ itself cannot be handled, because the corresponding handler isn't registered, yet. That's because the 8250 code uses a chain-handler and invokes the corresponding port's IRQ handling routines himself.

Unfortunately this IRQF_SHARED flag isn't configured for UARTs probed via device tree even if the IRQs are shared. This way, the actual and shared IRQ line isn't disabled while performing tests and the kernel correctly detects a spurious IRQ. So, adding this flag to the DT probe solves the issue.

Note: The UPF_SHARE_IRQ flag is configured unconditionally. Therefore, the IRQF_SHARED flag can be set unconditionally as well.

Example stack trace by performing echo 1 > /dev/ttyS2 on a non-patched system:

|irq 85: nobody cared (try booting with the "irqpoll" option)
| [...]
|handlers:
|[<ffff0000080fc628>] irq_default_primary_handler threaded [<ffff00000855fbb8>] serial8250_interrupt
|Disabling IRQ #85

---8<---8<---

But unfortunately didn't fix the root cause. Let's try again here by moving IRQ flag assignment from serial_link_irq_chain() to serial8250_do_startup().

This should fix the similar issue reported for 8250_pnp case.

Since this change we don't need to have custom solutions in 8250_aspeed_vuart and 8250_of drivers, thus, drop them.

Fixes 1c2f04937b3e ("serial: 8250: add IRQ trigger support")

Reported-by Li RongQing <[email protected]>

Cc Kurt Kanzenbach <[email protected]>

Cc Vikram Pandita <[email protected]>

Signed-off-by Andy Shevchenko <[email protected]>

Cc stable <[email protected]>

Acked-by Kurt Kanzenbach <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/tty/serial/8250/8250_aspeed_vuart.c |    1 -
 drivers/tty/serial/8250/8250_core.c         |    5 ++---
 drivers/tty/serial/8250/8250_of.c           |    1 -
 drivers/tty/serial/8250/8250_port.c         |    4 ++++
 4 files changed, 6 insertions(+), 5 deletions(-)

drivers/tty/serial/8250/8250_aspeed_vuart.c +0 -1

@@ -449,7 +449,6 @@ static int aspeed_vuart_probe(struct pla
 		port.port.line = rc;
 
 	port.port.irq = irq_of_parse_and_map(np, 0);
-	port.port.irqflags = IRQF_SHARED;
 	port.port.handle_irq = aspeed_vuart_handle_irq;
 	port.port.iotype = UPIO_MEM;
 	port.port.type = PORT_16550A;

drivers/tty/serial/8250/8250_core.c +2 -3

@@ -174,7 +174,7 @@ static int serial_link_irq_chain(struct
 	struct hlist_head *h;
 	struct hlist_node *n;
 	struct irq_info *i;
-	int ret, irq_flags = up->port.flags & UPF_SHARE_IRQ ? IRQF_SHARED : 0;
+	int ret;
 
 	mutex_lock(&hash_mutex);

@@ -209,9 +209,8 @@ static int serial_link_irq_chain(struct
 		INIT_LIST_HEAD(&up->list);
 		i->head = &up->list;
 		spin_unlock_irq(&i->lock);
-		irq_flags |= up->port.irqflags;
 		ret = request_irq(up->port.irq, serial8250_interrupt,
-				  irq_flags, up->port.name, i);
+				  up->port.irqflags, up->port.name, i);
 		if (ret < 0)
 			serial_do_unlink(i, up);
 	}

drivers/tty/serial/8250/8250_of.c +0 -1

@@ -202,7 +202,6 @@ static int of_platform_serial_setup(stru
 
 	port->type = type;
 	port->uartclk = clk;
-	port->irqflags |= IRQF_SHARED;
 
 	if (of_property_read_bool(np, "no-loopback-test"))
 		port->flags |= UPF_SKIP_TEST;

drivers/tty/serial/8250/8250_port.c +4 -0

@@ -2178,6 +2178,10 @@ int serial8250_do_startup(struct uart_po
 		}
 	}
 
+	/* Check if we need to have shared IRQs */
+	if (port->irq && (up->port.flags & UPF_SHARE_IRQ))
+		up->port.irqflags |= IRQF_SHARED;
+
 	if (port->irq && !(up->port.flags & UPF_NO_THRE_TEST)) {
 		unsigned char iir1;
 		/*

Greg Kroah-Hartman

author maintainer

2020-02-27 14:16 UTC #67 lore raw

PATCH 65/150 tty/serial: atmel: manage shutdown in case of RS485 or ISO7816 mode

From: Nicolas Ferre <[email protected]>

commit 04b5bfe3dc94e64d0590c54045815cb5183fb095 upstream.

In atmel_shutdown() we call atmel_stop_rx() and atmel_stop_tx() functions. Prevent the rx restart that is implemented in RS485 or ISO7816 modes when calling atmel_stop_tx() by using the atomic information tasklet_shutdown that is already in place for this purpose.

Fixes 98f2082c3ac4 ("tty/serial: atmel: enforce tasklet init and termination sequences")

Signed-off-by Nicolas Ferre <[email protected]>

Cc stable <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/tty/serial/atmel_serial.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

drivers/tty/serial/atmel_serial.c +2 -1

@@ -574,7 +574,8 @@ static void atmel_stop_tx(struct uart_po
 	atmel_uart_writel(port, ATMEL_US_IDR, atmel_port->tx_done_mask);
 
 	if (atmel_uart_is_half_duplex(port))
-		atmel_start_rx(port);
+		if (!atomic_read(&atmel_port->tasklet_shutdown))
+			atmel_start_rx(port);
 
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:17 UTC #68 lore raw

PATCH 66/150 tty: serial: imx: setup the correct sg entry for tx dma

From: Fugang Duan <[email protected]>

commit f76707831829530ffdd3888bebc108aecefccaa0 upstream.

There has oops as below happen on i.MX8MP EVK platform that has 6G bytes DDR memory.

when (xmit->tail < xmit->head) && (xmit->head == 0), it setups one sg entry with sg->length is zero:

	sg_set_buf(sgl + 1, xmit->buf, xmit->head);

if xmit->buf is allocated from >4G address space, and SDMA only support <4G address space, then dma_map_sg() will call swiotlb_map() to do bounce buffer copying and mapping.

But swiotlb_map() don't allow sg entry's length is zero, otherwise report BUG_ON().

So the patch is to correct the tx DMA scatter list.

Oops:

[  287.675715] kernel BUG at kernel/dma/swiotlb.c:497!
[  287.680592] Internal error: Oops - BUG: 0 [#1] PREEMPT SMP
[  287.686075] Modules linked in:
[  287.689133] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.4.3-00016-g3fdc4e0-dirty #10
[  287.696872] Hardware name: FSL i.MX8MP EVK (DT)
[  287.701402] pstate: 80000085 (Nzcv daIf -PAN -UAO)
[  287.706199] pc : swiotlb_tbl_map_single+0x1fc/0x310
[  287.711076] lr : swiotlb_map+0x60/0x148
[  287.714909] sp : ffff800010003c00
[  287.718221] x29: ffff800010003c00 x28: 0000000000000000
[  287.723533] x27: 0000000000000040 x26: ffff800011ae0000
[  287.728844] x25: ffff800011ae09f8 x24: 0000000000000000
[  287.734155] x23: 00000001b7af9000 x22: 0000000000000000
[  287.739465] x21: ffff000176409c10 x20: 00000000001f7ffe
[  287.744776] x19: ffff000176409c10 x18: 000000000000002e
[  287.750087] x17: 0000000000000000 x16: 0000000000000000
[  287.755397] x15: 0000000000000000 x14: 0000000000000000
[  287.760707] x13: ffff00017f334000 x12: 0000000000000001
[  287.766018] x11: 00000000001fffff x10: 0000000000000000
[  287.771328] x9 : 0000000000000003 x8 : 0000000000000000
[  287.776638] x7 : 0000000000000000 x6 : 0000000000000000
[  287.781949] x5 : 0000000000200000 x4 : 0000000000000000
[  287.787259] x3 : 0000000000000001 x2 : 00000001b7af9000
[  287.792570] x1 : 00000000fbfff000 x0 : 0000000000000000
[  287.797881] Call trace:
[  287.800328]  swiotlb_tbl_map_single+0x1fc/0x310
[  287.804859]  swiotlb_map+0x60/0x148
[  287.808347]  dma_direct_map_page+0xf0/0x130
[  287.812530]  dma_direct_map_sg+0x78/0xe0
[  287.816453]  imx_uart_dma_tx+0x134/0x2f8
[  287.820374]  imx_uart_dma_tx_callback+0xd8/0x168
[  287.824992]  vchan_complete+0x194/0x200
[  287.828828]  tasklet_action_common.isra.0+0x154/0x1a0
[  287.833879]  tasklet_action+0x24/0x30
[  287.837540]  __do_softirq+0x120/0x23c
[  287.841202]  irq_exit+0xb8/0xd8
[  287.844343]  __handle_domain_irq+0x64/0xb8
[  287.848438]  gic_handle_irq+0x5c/0x148
[  287.852185]  el1_irq+0xb8/0x180
[  287.855327]  cpuidle_enter_state+0x84/0x360
[  287.859508]  cpuidle_enter+0x34/0x48
[  287.863083]  call_cpuidle+0x18/0x38
[  287.866571]  do_idle+0x1e0/0x280
[  287.869798]  cpu_startup_entry+0x20/0x40
[  287.873721]  rest_init+0xd4/0xe0
[  287.876949]  arch_call_rest_init+0xc/0x14
[  287.880958]  start_kernel+0x420/0x44c
[  287.884622] Code: 9124c021 9417aff8 a94363f7 17ffffd5 (d4210000)
[  287.890718] ---[ end trace 5bc44c4ab6b009ce ]---
[  287.895334] Kernel panic - not syncing: Fatal exception in interrupt
[  287.901686] SMP: stopping secondary CPUs
[  288.905607] SMP: failed to stop secondary CPUs 0-1
[  288.910395] Kernel Offset: disabled
[  288.913882] CPU features: 0x0002,2000200c
[  288.917888] Memory Limit: none
[  288.920944] ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]---

Reported-by Eagle Zhou <[email protected]>

Tested-by Eagle Zhou <[email protected]>

Signed-off-by Fugang Duan <[email protected]>

Cc stable <[email protected]>

Fixes 7942f8577f2a ("serial: imx: TX DMA: clean up sg initialization")

Reviewed-by Uwe Kleine-König <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/tty/serial/imx.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/tty/serial/imx.c +1 -1

@@ -603,7 +603,7 @@ static void imx_uart_dma_tx(struct imx_p
 
 	sport->tx_bytes = uart_circ_chars_pending(xmit);
 
-	if (xmit->tail < xmit->head) {
+	if (xmit->tail < xmit->head || xmit->head == 0) {
 		sport->dma_tx_nents = 1;
 		sg_init_one(sgl, xmit->buf + xmit->tail, sport->tx_bytes);
 	} else {

Greg Kroah-Hartman

author maintainer

2020-02-27 14:21 UTC #69 lore raw

PATCH 67/150 tty: serial: qcom_geni_serial: Fix RX cancel command failure

From: satya priya <[email protected]>

commit 679aac5ead2f18d223554a52b543e1195e181811 upstream.

RX cancel command fails when BT is switched on and off multiple times.

To handle this, poll for the cancel bit in SE_GENI_S_IRQ_STATUS register instead of SE_GENI_S_CMD_CTRL_REG.

As per the HPG update, handle the RX last bit after cancel command and flush out the RX FIFO buffer.

Signed-off-by satya priya <[email protected]>

Cc stable <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/tty/serial/qcom_geni_serial.c |   18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

drivers/tty/serial/qcom_geni_serial.c +14 -4

@@ -128,6 +128,7 @@ static int handle_rx_console(struct uart
 static int handle_rx_uart(struct uart_port *uport, u32 bytes, bool drop);
 static unsigned int qcom_geni_serial_tx_empty(struct uart_port *port);
 static void qcom_geni_serial_stop_rx(struct uart_port *uport);
+static void qcom_geni_serial_handle_rx(struct uart_port *uport, bool drop);
 
 static const unsigned long root_freq[] = {7372800, 14745600, 19200000, 29491200,
 					32000000, 48000000, 64000000, 80000000,

@@ -618,7 +619,7 @@ static void qcom_geni_serial_stop_rx(str
 	u32 irq_en;
 	u32 status;
 	struct qcom_geni_serial_port *port = to_dev_port(uport, uport);
-	u32 irq_clear = S_CMD_DONE_EN;
+	u32 s_irq_status;
 
 	irq_en = readl(uport->membase + SE_GENI_S_IRQ_EN);
 	irq_en &= ~(S_RX_FIFO_WATERMARK_EN | S_RX_FIFO_LAST_EN);

@@ -634,10 +635,19 @@ static void qcom_geni_serial_stop_rx(str
 		return;
 
 	geni_se_cancel_s_cmd(&port->se);
-	qcom_geni_serial_poll_bit(uport, SE_GENI_S_CMD_CTRL_REG,
-					S_GENI_CMD_CANCEL, false);
+	qcom_geni_serial_poll_bit(uport, SE_GENI_S_IRQ_STATUS,
+					S_CMD_CANCEL_EN, true);
+	/*
+	 * If timeout occurs secondary engine remains active
+	 * and Abort sequence is executed.
+	 */
+	s_irq_status = readl(uport->membase + SE_GENI_S_IRQ_STATUS);
+	/* Flush the Rx buffer */
+	if (s_irq_status & S_RX_FIFO_LAST_EN)
+		qcom_geni_serial_handle_rx(uport, true);
+	writel(s_irq_status, uport->membase + SE_GENI_S_IRQ_CLEAR);
+
 	status = readl(uport->membase + SE_GENI_STATUS);
-	writel(irq_clear, uport->membase + SE_GENI_S_IRQ_CLEAR);
 	if (status & S_GENI_CMD_ACTIVE)
 		qcom_geni_serial_abort_rx(uport);
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:21 UTC #70 lore raw

PATCH 68/150 serdev: ttyport: restore client ops on deregistration

From: Johan Hovold <[email protected]>

commit 0c5aae59270fb1f827acce182786094c9ccf598e upstream.

The serdev tty-port controller driver should reset the tty-port client operations also on deregistration to avoid a NULL-pointer dereference in case the port is later re-registered as a normal tty device.

Note that this can only happen with tty drivers such as 8250 which have statically allocated port structures that can end up being reused and where a later registration would not register a serdev controller (e.g. due to registration errors or if the devicetree has been changed in between).

Specifically, this can be an issue for any statically defined ports that would be registered by 8250 core when an 8250 driver is being unbound.

Fixes bed35c6dfa6a ("serdev: add a tty port controller driver")

Cc stable <[email protected]> # 4.11

Reported-by Loic Poulain <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/tty/serdev/serdev-ttyport.c |    6 ++----
 drivers/tty/tty_port.c              |    5 +++--
 include/linux/tty.h                 |    2 ++
 3 files changed, 7 insertions(+), 6 deletions(-)

drivers/tty/serdev/serdev-ttyport.c +2 -4

@@ -265,7 +265,6 @@ struct device *serdev_tty_port_register(
 					struct device *parent,
 					struct tty_driver *drv, int idx)
 {
-	const struct tty_port_client_operations *old_ops;
 	struct serdev_controller *ctrl;
 	struct serport *serport;
 	int ret;

@@ -284,7 +283,6 @@ struct device *serdev_tty_port_register(
 
 	ctrl->ops = &ctrl_ops;
 
-	old_ops = port->client_ops;
 	port->client_ops = &client_ops;
 	port->client_data = ctrl;

@@ -297,7 +295,7 @@ struct device *serdev_tty_port_register(
 
 err_reset_data:
 	port->client_data = NULL;
-	port->client_ops = old_ops;
+	port->client_ops = &tty_port_default_client_ops;
 	serdev_controller_put(ctrl);
 
 	return ERR_PTR(ret);

@@ -312,8 +310,8 @@ int serdev_tty_port_unregister(struct tt
 		return -ENODEV;
 
 	serdev_controller_remove(ctrl);
-	port->client_ops = NULL;
 	port->client_data = NULL;
+	port->client_ops = &tty_port_default_client_ops;
 	serdev_controller_put(ctrl);
 
 	return 0;

drivers/tty/tty_port.c +3 -2

@@ -52,10 +52,11 @@ static void tty_port_default_wakeup(stru
 	}
 }
 
-static const struct tty_port_client_operations default_client_ops = {
+const struct tty_port_client_operations tty_port_default_client_ops = {
 	.receive_buf = tty_port_default_receive_buf,
 	.write_wakeup = tty_port_default_wakeup,
 };
+EXPORT_SYMBOL_GPL(tty_port_default_client_ops);
 
 void tty_port_init(struct tty_port *port)
 {

@@ -68,7 +69,7 @@ void tty_port_init(struct tty_port *port
 	spin_lock_init(&port->lock);
 	port->close_delay = (50 * HZ) / 100;
 	port->closing_wait = (3000 * HZ) / 100;
-	port->client_ops = &default_client_ops;
+	port->client_ops = &tty_port_default_client_ops;
 	kref_init(&port->kref);
 }
 EXPORT_SYMBOL(tty_port_init);

include/linux/tty.h +2 -0

@@ -225,6 +225,8 @@ struct tty_port_client_operations {
 	void (*write_wakeup)(struct tty_port *port);
 };
 
+extern const struct tty_port_client_operations tty_port_default_client_ops;
+
 struct tty_port {
 	struct tty_bufhead	buf;		/* Locked internally */
 	struct tty_struct	*tty;		/* Back pointer */

Greg Kroah-Hartman

author maintainer

2020-02-27 14:17 UTC #71 lore raw

PATCH 69/150 MAINTAINERS: Update drm/i915 bug filing URL

From: Jani Nikula <[email protected]>

commit 96228b7df33f8eb9006f8ae96949400aed9bd303 upstream.

We've moved from bugzilla to gitlab.

Link https://patchwork.freedesktop.org/patch/msgid/[email protected]

Reviewed-by Chris Wilson <[email protected]>

Signed-off-by Jani Nikula <[email protected]>

(cherry picked from commit 3a6a4f0810c8ade6f1ff63c34aa9834176b9d88b)

Signed-off-by Jani Nikula <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 MAINTAINERS |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

MAINTAINERS +1 -1

@@ -8302,7 +8302,7 @@ M:	Joonas Lahtinen <joonas.lahtinen@linu
 M:	Rodrigo Vivi <[email protected]>
 L:	[email protected]
 W:	https://01.org/linuxgraphics/
-B:	https://01.org/linuxgraphics/documentation/how-report-bugs
+B:	https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs
 C:	irc://chat.freenode.net/intel-gfx
 Q:	http://patchwork.freedesktop.org/project/intel-gfx/
 T:	git git://anongit.freedesktop.org/drm-intel

Greg Kroah-Hartman

author maintainer

2020-02-27 14:15 UTC #72 lore raw

PATCH 70/150 fsi: aspeed: add unspecified HAS_IOMEM dependency

From: Brendan Higgins <[email protected]>

commit ea3d147a474cb522bfdfe68f1f2557750dcf41dd upstream.

Currently CONFIG_FSI_MASTER_ASPEED=y implicitly depends on CONFIG_HAS_IOMEM=y; consequently, on architectures without IOMEM we get the following build error:

ld: drivers/fsi/fsi-master-aspeed.o: in function `fsi_master_aspeed_probe':
drivers/fsi/fsi-master-aspeed.c:436: undefined reference to `devm_ioremap_resource'

Fix the build error by adding the unspecified dependency.

Fixes 606397d67f41 ("fsi: Add ast2600 master driver")

Reported-by Brendan Higgins <[email protected]>

Signed-off-by Brendan Higgins <[email protected]>

Reviewed-by Joel Stanley <[email protected]>

Signed-off-by Joel Stanley <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/fsi/Kconfig |    1 +
 1 file changed, 1 insertion(+)

drivers/fsi/Kconfig +1 -0

@@ -55,6 +55,7 @@ config FSI_MASTER_AST_CF
 
 config FSI_MASTER_ASPEED
 	tristate "FSI ASPEED master"
+	depends on HAS_IOMEM
 	help
 	 This option enables a FSI master that is present behind an OPB bridge
 	 in the AST2600.

Greg Kroah-Hartman

author maintainer

2020-02-27 14:15 UTC #73 lore raw

PATCH 71/150 ACPI: PM: s2idle: Check fixed wakeup events in acpi_s2idle_wake()

From: Rafael J. Wysocki <[email protected]>

commit 63fb9623427fbb44e3782233b6e4714057b76ff2 upstream.

Commit fdde0ff8590b ("ACPI: PM: s2idle: Prevent spurious SCIs from waking up the system") overlooked the fact that fixed events can wake up the system too and broke RTC wakeup from suspend-to-idle as a result.

Fix this issue by checking the fixed events in acpi_s2idle_wake() in addition to checking wakeup GPEs and break out of the suspend-to-idle loop if the status bits of any enabled fixed events are set then.

Fixes fdde0ff8590b ("ACPI: PM: s2idle: Prevent spurious SCIs from waking up the system")

Reported-and-tested-by Chris Wilson <[email protected]>

Cc 5.4+ <[email protected]> # 5.4+

Signed-off-by Rafael J. Wysocki <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/acpi/acpica/evevent.c |   45 ++++++++++++++++++++++++++++++++++++++++++
 drivers/acpi/sleep.c          |    7 ++++++
 include/acpi/acpixf.h         |    1 
 3 files changed, 53 insertions(+)

drivers/acpi/acpica/evevent.c +45 -0

@@ -265,4 +265,49 @@ static u32 acpi_ev_fixed_event_dispatch(
 		 handler) (acpi_gbl_fixed_event_handlers[event].context));
 }
 
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_any_fixed_event_status_set
+ *
+ * PARAMETERS:  None
+ *
+ * RETURN:      TRUE or FALSE
+ *
+ * DESCRIPTION: Checks the PM status register for active fixed events
+ *
+ ******************************************************************************/
+
+u32 acpi_any_fixed_event_status_set(void)
+{
+	acpi_status status;
+	u32 in_status;
+	u32 in_enable;
+	u32 i;
+
+	status = acpi_hw_register_read(ACPI_REGISTER_PM1_ENABLE, &in_enable);
+	if (ACPI_FAILURE(status)) {
+		return (FALSE);
+	}
+
+	status = acpi_hw_register_read(ACPI_REGISTER_PM1_STATUS, &in_status);
+	if (ACPI_FAILURE(status)) {
+		return (FALSE);
+	}
+
+	/*
+	 * Check for all possible Fixed Events and dispatch those that are active
+	 */
+	for (i = 0; i < ACPI_NUM_FIXED_EVENTS; i++) {
+
+		/* Both the status and enable bits must be on for this event */
+
+		if ((in_status & acpi_gbl_fixed_event_info[i].status_bit_mask) &&
+		    (in_enable & acpi_gbl_fixed_event_info[i].enable_bit_mask)) {
+			return (TRUE);
+		}
+	}
+
+	return (FALSE);
+}
+
 #endif				/* !ACPI_REDUCED_HARDWARE */

drivers/acpi/sleep.c +7 -0

@@ -1003,6 +1003,13 @@ static bool acpi_s2idle_wake(void)
 			return true;
 
 		/*
+		 * If the status bit of any enabled fixed event is set, the
+		 * wakeup is regarded as valid.
+		 */
+		if (acpi_any_fixed_event_status_set())
+			return true;
+
+		/*
 		 * If there are no EC events to process and at least one of the
 		 * other enabled GPEs is active, the wakeup is regarded as a
 		 * genuine one.

include/acpi/acpixf.h +1 -0

@@ -753,6 +753,7 @@ ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_sta
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_runtime_gpes(void))
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status acpi_enable_all_wakeup_gpes(void))
 ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_any_gpe_status_set(void))
+ACPI_HW_DEPENDENT_RETURN_UINT32(u32 acpi_any_fixed_event_status_set(void))
 
 ACPI_HW_DEPENDENT_RETURN_STATUS(acpi_status
 				acpi_get_gpe_device(u32 gpe_index,

Greg Kroah-Hartman

author maintainer

2020-02-27 14:15 UTC #74 lore raw

PATCH 72/150 Revert "ipc,sem: remove uneeded sem_undo_list lock usage in exit_sem()"

[1] https://bugzilla.redhat.com/show_bug.cgi?id=1694779

From: Ioanna Alifieraki <[email protected]>

commit edf28f4061afe4c2d9eb1c3323d90e882c1d6800 upstream.

This reverts commit a97955844807e327df11aa33869009d14d6b7de0.

Commit a97955844807 ("ipc,sem: remove uneeded sem_undo_list lock usage in exit_sem()") removes a lock that is needed. This leads to a process looping infinitely in exit_sem() and can also lead to a crash. There is a reproducer available in [1] and with the commit reverted the issue does not reproduce anymore.

Using the reproducer found in [1] is fairly easy to reach a point where one of the child processes is looping infinitely in exit_sem between for(;;) and if (semid == -1) block, while it's trying to free its last sem_undo structure which has already been freed by freeary().

Each sem_undo struct is on two lists: one per semaphore set (list_id) and one per process (list_proc). The list_id list tracks undos by semaphore set, and the list_proc by process.

Undo structures are removed either by freeary() or by exit_sem(). The freeary function is invoked when the user invokes a syscall to remove a semaphore set. During this operation freeary() traverses the list_id associated with the semaphore set and removes the undo structures from both the list_id and list_proc lists.

For this case, exit_sem() is called at process exit. Each process contains a struct sem_undo_list (referred to as "ulp") which contains the head for the list_proc list. When the process exits, exit_sem() traverses this list to remove each sem_undo struct. As in freeary(), whenever a sem_undo struct is removed from list_proc, it is also removed from the list_id list.

Removing elements from list_id is safe for both exit_sem() and freeary() due to sem_lock(). Removing elements from list_proc is not safe; freeary() locks &un->ulp->lock when it performs list_del_rcu(&un->list_proc) but exit_sem() does not (locking was removed by commit a97955844807 ("ipc,sem: remove uneeded sem_undo_list lock usage in exit_sem()").

This can result in the following situation while executing the reproducer [1] : Consider a child process in exit_sem() and the parent in freeary() (because of semctl(sid[i], NSEM, IPC_RMID)).

- The list_proc for the child contains the last two undo structs A and B (the rest have been removed either by exit_sem() or freeary()).

- The semid for A is 1 and semid for B is 2.

- exit_sem() removes A and at the same time freeary() removes B.

- Since A and B have different semid sem_lock() will acquire different locks for each process and both can proceed.

The bug is that they remove A and B from the same list_proc at the same time because only freeary() acquires the ulp lock. When exit_sem() removes A it makes ulp->list_proc.next to point at B and at the same time freeary() removes B setting B->semid=-1.

At the next iteration of for(;;) loop exit_sem() will try to remove B.

The only way to break from for(;;) is for (&un->list_proc == &ulp->list_proc) to be true which is not. Then exit_sem() will check if B->semid=-1 which is and will continue looping in for(;;) until the memory for B is reallocated and the value at B->semid is changed.

At that point, exit_sem() will crash attempting to unlink B from the lists (this can be easily triggered by running the reproducer [1] a second time).

To prove this scenario instrumentation was added to keep information about each sem_undo (un) struct that is removed per process and per semaphore set (sma).

CPU0 CPU1

  [caller holds sem_lock(sma for A)]      ...
  freeary()                               exit_sem()
  ...                                     ...
  ...                                     sem_lock(sma for B)
  spin_lock(A->ulp->lock)                 ...
  list_del_rcu(un_A->list_proc)           list_del_rcu(un_B->list_proc)

Undo structures A and B have different semid and sem_lock() operations proceed. However they belong to the same list_proc list and they are removed at the same time. This results into ulp->list_proc.next pointing to the address of B which is already removed.

After reverting commit a97955844807 ("ipc,sem: remove uneeded sem_undo_list lock usage in exit_sem()") the issue was no longer reproducible.

Link http://lkml.kernel.org/r/[email protected] open here

Fixes a97955844807 ("ipc,sem: remove uneeded sem_undo_list lock usage in exit_sem()")

Signed-off-by Ioanna Alifieraki <[email protected]>

Acked-by Manfred Spraul <[email protected]>

Acked-by Herton R. Krzesinski <[email protected]>

Cc Arnd Bergmann <[email protected]>

Cc Catalin Marinas <[email protected]>

Cc Joel Fernandes (Google) <[email protected]>

Cc Davidlohr Bueso <[email protected]>

Cc Jay Vosburgh <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 ipc/sem.c |    6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

ipc/sem.c +2 -4

@@ -2368,11 +2368,9 @@ void exit_sem(struct task_struct *tsk)
 		ipc_assert_locked_object(&sma->sem_perm);
 		list_del(&un->list_id);
 
-		/* we are the last process using this ulp, acquiring ulp->lock
-		 * isn't required. Besides that, we are also protected against
-		 * IPC_RMID as we hold sma->sem_perm lock now
-		 */
+		spin_lock(&ulp->lock);
 		list_del_rcu(&un->list_proc);
+		spin_unlock(&ulp->lock);
 
 		/* perform adjustments registered in un */
 		for (i = 0; i < sma->sem_nsems; i++) {

Greg Kroah-Hartman

author maintainer

2020-02-27 14:15 UTC #75 lore raw

PATCH 73/150 mm/memcontrol.c: lost css_put in memcg_expand_shrinker_maps()

From: Vasily Averin <[email protected]>

commit 75866af62b439859d5146b7093ceb6b482852683 upstream.

for_each_mem_cgroup() increases css reference counter for memory cgroup and requires to use mem_cgroup_iter_break() if the walk is cancelled.

Link http://lkml.kernel.org/r/[email protected] open here

Fixes 0a4465d34028 ("mm, memcg: assign memcg-aware shrinkers bitmap to memcg")

Signed-off-by Vasily Averin <[email protected]>

Acked-by Kirill Tkhai <[email protected]>

Acked-by Michal Hocko <[email protected]>

Reviewed-by Roman Gushchin <[email protected]>

Cc Johannes Weiner <[email protected]>

Cc Vladimir Davydov <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 mm/memcontrol.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

mm/memcontrol.c +3 -1

@@ -409,8 +409,10 @@ int memcg_expand_shrinker_maps(int new_i
 		if (mem_cgroup_is_root(memcg))
 			continue;
 		ret = memcg_expand_one_shrinker_map(memcg, size, old_size);
-		if (ret)
+		if (ret) {
+			mem_cgroup_iter_break(NULL, memcg);
 			goto unlock;
+		}
 	}
 unlock:
 	if (!ret)

Greg Kroah-Hartman

author maintainer

2020-02-27 14:15 UTC #76 lore raw

PATCH 74/150 nvme-multipath: Fix memory leak with ana_log_buf

From: Logan Gunthorpe <[email protected]>

commit 3b7830904e17202524bad1974505a9bfc718d31f upstream.

kmemleak reports a memory leak with the ana_log_buf allocated by nvme_mpath_init():

unreferenced object 0xffff888120e94000 (size 8208):
comm "nvme", pid 6884, jiffies 4295020435 (age 78786.312s)

    hex dump (first 32 bytes):
      00 00 00 00 00 00 00 00 01 00 00 00 00 00 00 00  ................
      01 00 00 00 01 00 00 00 00 00 00 00 00 00 00 00  ................
    backtrace:
      [<00000000e2360188>] kmalloc_order+0x97/0xc0
      [<0000000079b18dd4>] kmalloc_order_trace+0x24/0x100
      [<00000000f50c0406>] __kmalloc+0x24c/0x2d0
      [<00000000f31a10b9>] nvme_mpath_init+0x23c/0x2b0
      [<000000005802589e>] nvme_init_identify+0x75f/0x1600
      [<0000000058ef911b>] nvme_loop_configure_admin_queue+0x26d/0x280
      [<00000000673774b9>] nvme_loop_create_ctrl+0x2a7/0x710
      [<00000000f1c7a233>] nvmf_dev_write+0xc66/0x10b9
      [<000000004199f8d0>] __vfs_write+0x50/0xa0
      [<0000000065466fef>] vfs_write+0xf3/0x280
      [<00000000b0db9a8b>] ksys_write+0xc6/0x160
      [<0000000082156b91>] __x64_sys_write+0x43/0x50
      [<00000000c34fbb6d>] do_syscall_64+0x77/0x2f0
      [<00000000bbc574c9>] entry_SYSCALL_64_after_hwframe+0x49/0xbe

nvme_mpath_init() is called by nvme_init_identify() which is called in multiple places (nvme_reset_work(), nvme_passthru_end(), etc). This means nvme_mpath_init() may be called multiple times before nvme_mpath_uninit() (which is only called on nvme_free_ctrl()).

When nvme_mpath_init() is called multiple times, it overwrites the ana_log_buf pointer with a new allocation, thus leaking the previous allocation.

To fix this, free ana_log_buf before allocating a new one.

Fixes 0d0b660f214dc490 ("nvme: add ANA support")

Reviewed-by Sagi Grimberg <[email protected]>

Reviewed-by Christoph Hellwig <[email protected]>

Signed-off-by Logan Gunthorpe <[email protected]>

Signed-off-by Keith Busch <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/nvme/host/multipath.c |    1 +
 1 file changed, 1 insertion(+)

drivers/nvme/host/multipath.c +1 -0

@@ -715,6 +715,7 @@ int nvme_mpath_init(struct nvme_ctrl *ct
 	}
 
 	INIT_WORK(&ctrl->ana_work, nvme_ana_work);
+	kfree(ctrl->ana_log_buf);
 	ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL);
 	if (!ctrl->ana_log_buf) {
 		error = -ENOMEM;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:15 UTC #77 lore raw

PATCH 75/150 genirq/irqdomain: Make sure all irq domain flags are distinct

From: Zenghui Yu <[email protected]>

commit 2546287c5fb363a0165933ae2181c92f03e701d0 upstream.

This was noticed when printing debugfs for MSIs on my ARM64 server. The new dstate IRQD_MSI_NOMASK_QUIRK came out surprisingly while it should only be the x86 stuff for the time being...

The new MSI quirk flag uses the same bit as IRQ_DOMAIN_NAME_ALLOCATED which is oddly defined as bit 6 for no good reason.

Switch it to the non used bit 1.

Fixes 6f1a4891a592 ("x86/apic/msi: Plug non-maskable MSI affinity race")

Signed-off-by Zenghui Yu <[email protected]>

Link https://lkml.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 include/linux/irqdomain.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

include/linux/irqdomain.h +1 -1

@@ -192,7 +192,7 @@ enum {
 	IRQ_DOMAIN_FLAG_HIERARCHY	= (1 << 0),
 
 	/* Irq domain name was allocated in __irq_domain_add() */
-	IRQ_DOMAIN_NAME_ALLOCATED	= (1 << 6),
+	IRQ_DOMAIN_NAME_ALLOCATED	= (1 << 1),
 
 	/* Irq domain is an IPI domain with virq per cpu */
 	IRQ_DOMAIN_FLAG_IPI_PER_CPU	= (1 << 2),

Greg Kroah-Hartman

author maintainer

2020-02-27 14:22 UTC #78 lore raw

PATCH 76/150 mm/vmscan.c: dont round up scan size for online memory cgroup

From: Gavin Shan <[email protected]>

commit 76073c646f5f4999d763f471df9e38a5a912d70d upstream.

Commit 68600f623d69 ("mm: don't miss the last page because of round-off error") makes the scan size round up to @denominator regardless of the memory cgroup's state, online or offline. This affects the overall reclaiming behavior: the corresponding LRU list is eligible for reclaiming only when its size logically right shifted by @sc->priority is bigger than zero in the former formula.

For example, the inactive anonymous LRU list should have at least 0x4000 pages to be eligible for reclaiming when we have 60/12 for swappiness/priority and without taking scan/rotation ratio into account.

After the roundup is applied, the inactive anonymous LRU list becomes eligible for reclaiming when its size is bigger than or equal to 0x1000 in the same condition.

    (0x4000 >> 12) * 60 / (60 + 140 + 1) = 1
    ((0x1000 >> 12) * 60) + 200) / (60 + 140 + 1) = 1

aarch64 has 512MB huge page size when the base page size is 64KB. The memory cgroup that has a huge page is always eligible for reclaiming in that case.

The reclaiming is likely to stop after the huge page is reclaimed, meaing the further iteration on @sc->priority and the silbing and child memory cgroups will be skipped. The overall behaviour has been changed. This fixes the issue by applying the roundup to offlined memory cgroups only, to give more preference to reclaim memory from offlined memory cgroup. It sounds reasonable as those memory is unlikedly to be used by anyone.

The issue was found by starting up 8 VMs on a Ampere Mustang machine, which has 8 CPUs and 16 GB memory. Each VM is given with 2 vCPUs and 2GB memory. It took 264 seconds for all VMs to be completely up and 784MB swap is consumed after that. With this patch applied, it took 236 seconds and 60MB swap to do same thing. So there is 10% performance improvement for my case. Note that KSM is disable while THP is enabled in the testing.

         total     used    free   shared  buff/cache   available
   Mem:  16196    10065    2049       16        4081        3749
   Swap:  8175      784    7391
         total     used    free   shared  buff/cache   available
   Mem:  16196    11324    3656       24        1215        2936
   Swap:  8175       60    8115

Link http://lkml.kernel.org/r/[email protected] open here

Fixes 68600f623d69 ("mm: don't miss the last page because of round-off error")

Signed-off-by Gavin Shan <[email protected]>

Acked-by Roman Gushchin <[email protected]>

Cc <[email protected]> [4.20+]

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 mm/vmscan.c |    9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

mm/vmscan.c +6 -3

@@ -2429,10 +2429,13 @@ out:
 			/*
 			 * Scan types proportional to swappiness and
 			 * their relative recent reclaim efficiency.
-			 * Make sure we don't miss the last page
-			 * because of a round-off error.
+			 * Make sure we don't miss the last page on
+			 * the offlined memory cgroups because of a
+			 * round-off error.
 			 */
-			scan = DIV64_U64_ROUND_UP(scan * fraction[file],
+			scan = mem_cgroup_online(memcg) ?
+			       div64_u64(scan * fraction[file], denominator) :
+			       DIV64_U64_ROUND_UP(scan * fraction[file],
 						  denominator);
 			break;
 		case SCAN_FILE:

Greg Kroah-Hartman

author maintainer

2020-02-27 14:15 UTC #79 lore raw

PATCH 77/150 mm/sparsemem: pfn_to_page is not valid yet on SPARSEMEM

From: Wei Yang <[email protected]>

commit 18e19f195cd888f65643a77a0c6aee8f5be6439a upstream.

When we use SPARSEMEM instead of SPARSEMEM_VMEMMAP, pfn_to_page() doesn't work before sparse_init_one_section() is called.

This leads to a crash when hotplug memory:

    BUG: unable to handle page fault for address: 0000000006400000
    #PF: supervisor write access in kernel mode
    #PF: error_code(0x0002) - not-present page
    PGD 0 P4D 0
    Oops: 0002 [#1] SMP PTI
    CPU: 3 PID: 221 Comm: kworker/u16:1 Tainted: G        W         5.5.0-next-20200205+ #343
    Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 0.0.0 02/06/2015
    Workqueue: kacpi_hotplug acpi_hotplug_work_fn
    RIP: 0010:__memset+0x24/0x30
    Code: cc cc cc cc cc cc 0f 1f 44 00 00 49 89 f9 48 89 d1 83 e2 07 48 c1 e9 03 40 0f b6 f6 48 b8 01 01 01 01 01 01 01 01 48 0f af c6 <f3> 48 ab 89 d1 f3 aa 4c 89 c8 c3 90 49 89 f9 40 88 f0 48 89 d1 f3
    RSP: 0018:ffffb43ac0373c80 EFLAGS: 00010a87
    RAX: ffffffffffffffff RBX: ffff8a1518800000 RCX: 0000000000050000
    RDX: 0000000000000000 RSI: 00000000000000ff RDI: 0000000006400000
    RBP: 0000000000140000 R08: 0000000000100000 R09: 0000000006400000
    R10: 0000000000000000 R11: 0000000000000002 R12: 0000000000000000
    R13: 0000000000000028 R14: 0000000000000000 R15: ffff8a153ffd9280
    FS:  0000000000000000(0000) GS:ffff8a153ab00000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: 0000000006400000 CR3: 0000000136fca000 CR4: 00000000000006e0
    DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
    DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
    Call Trace:
     sparse_add_section+0x1c9/0x26a
     __add_pages+0xbf/0x150
     add_pages+0x12/0x60
     add_memory_resource+0xc8/0x210
     __add_memory+0x62/0xb0
     acpi_memory_device_add+0x13f/0x300
     acpi_bus_attach+0xf6/0x200
     acpi_bus_scan+0x43/0x90
     acpi_device_hotplug+0x275/0x3d0
     acpi_hotplug_work_fn+0x1a/0x30
     process_one_work+0x1a7/0x370
     worker_thread+0x30/0x380
     kthread+0x112/0x130
     ret_from_fork+0x35/0x40

We should use memmap as it did.

On x86 the impact is limited to x86_32 builds, or x86_64 configurations that override the default setting for SPARSEMEM_VMEMMAP.

Other memory hotplug archs (arm64, ia64, and ppc) also default to SPARSEMEM_VMEMMAP=y.

[[email protected]: changelog update]
{[email protected]: changelog update]

Link http://lkml.kernel.org/r/[email protected] open here

Fixes ba72b4c8cf60 ("mm/sparsemem: support sub-section hotplug")

Signed-off-by Wei Yang <[email protected]>

Signed-off-by Baoquan He <[email protected]>

Acked-by David Hildenbrand <[email protected]>

Reviewed-by Baoquan He <[email protected]>

Reviewed-by Dan Williams <[email protected]>

Acked-by Michal Hocko <[email protected]>

Cc Mike Rapoport <[email protected]>

Cc Oscar Salvador <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 mm/sparse.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

mm/sparse.c +1 -1

@@ -886,7 +886,7 @@ int __meminit sparse_add_section(int nid
 	 * Poison uninitialized struct pages in order to catch invalid flags
 	 * combinations.
 	 */
-	page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages);
+	page_init_poison(memmap, sizeof(struct page) * nr_pages);
 
 	ms = __nr_to_section(section_nr);
 	set_section_nid(section_nr, nid);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:22 UTC #80 lore raw

PATCH 78/150 lib/stackdepot.c: fix global out-of-bounds in stack_slabs

From: Alexander Potapenko <[email protected]>

commit 305e519ce48e935702c32241f07d393c3c8fed3e upstream.

Walter Wu has reported a potential case in which init_stack_slab() is called after stack_slabs[STACK_ALLOC_MAX_SLABS - 1] has already been initialized. In that case init_stack_slab() will overwrite stack_slabs[STACK_ALLOC_MAX_SLABS], which may result in a memory corruption.

Link http://lkml.kernel.org/r/[email protected] open here

Fixes cd11016e5f521 ("mm, kasan: stackdepot implementation. Enable stackdepot for SLAB")

Signed-off-by Alexander Potapenko <[email protected]>

Reported-by Walter Wu <[email protected]>

Cc Dmitry Vyukov <[email protected]>

Cc Matthias Brugger <[email protected]>

Cc Thomas Gleixner <[email protected]>

Cc Josh Poimboeuf <[email protected]>

Cc Kate Stewart <[email protected]>

Cc Greg Kroah-Hartman <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 lib/stackdepot.c |    8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

lib/stackdepot.c +6 -2

@@ -83,15 +83,19 @@ static bool init_stack_slab(void **preal
 		return true;
 	if (stack_slabs[depot_index] == NULL) {
 		stack_slabs[depot_index] = *prealloc;
+		*prealloc = NULL;
 	} else {
-		stack_slabs[depot_index + 1] = *prealloc;
+		/* If this is the last depot slab, do not touch the next one. */
+		if (depot_index + 1 < STACK_ALLOC_MAX_SLABS) {
+			stack_slabs[depot_index + 1] = *prealloc;
+			*prealloc = NULL;
+		}
 		/*
 		 * This smp_store_release pairs with smp_load_acquire() from
 		 * |next_slab_inited| above and in stack_depot_save().
 		 */
 		smp_store_release(&next_slab_inited, 1);
 	}
-	*prealloc = NULL;
 	return true;
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:15 UTC #81 lore raw

PATCH 79/150 mm: Avoid creating virtual address aliases in brk()/mmap()/mremap()

From: Catalin Marinas <[email protected]>

commit dcde237319e626d1ec3c9d8b7613032f0fd4663a upstream.

Currently the arm64 kernel ignores the top address byte passed to brk(), mmap() and mremap(). When the user is not aware of the 56-bit address limit or relies on the kernel to return an error, untagging such pointers has the potential to create address aliases in user-space. Passing a tagged address to munmap(), madvise() is permitted since the tagged pointer is expected to be inside an existing mapping.

The current behaviour breaks the existing glibc malloc() implementation which relies on brk() with an address beyond 56-bit to be rejected by the kernel.

Remove untagging in the above functions by partially reverting commit ce18d171cb73 ("mm: untag user pointers in mmap/munmap/mremap/brk"). In addition, update the arm64 tagged-address-abi.rst document accordingly.

Link https://bugzilla.redhat.com/1797052

Fixes ce18d171cb73 ("mm: untag user pointers in mmap/munmap/mremap/brk")

Cc <[email protected]> # 5.4.x-

Cc Florian Weimer <[email protected]>

Reviewed-by Andrew Morton <[email protected]>

Reported-by Victor Stinner <[email protected]>

Acked-by Will Deacon <[email protected]>

Acked-by Andrey Konovalov <[email protected]>

Signed-off-by Catalin Marinas <[email protected]>

Signed-off-by Will Deacon <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 Documentation/arm64/tagged-address-abi.rst |   11 +++++++++--
 mm/mmap.c                                  |    4 ----
 mm/mremap.c                                |    1 -
 3 files changed, 9 insertions(+), 7 deletions(-)

Documentation/arm64/tagged-address-abi.rst +9 -2

@@ -44,8 +44,15 @@ The AArch64 Tagged Address ABI has two s
 how the user addresses are used by the kernel:
 
 1. User addresses not accessed by the kernel but used for address space
-   management (e.g. ``mmap()``, ``mprotect()``, ``madvise()``). The use
-   of valid tagged pointers in this context is always allowed.
+   management (e.g. ``mprotect()``, ``madvise()``). The use of valid
+   tagged pointers in this context is allowed with the exception of
+   ``brk()``, ``mmap()`` and the ``new_address`` argument to
+   ``mremap()`` as these have the potential to alias with existing
+   user addresses.
+
+   NOTE: This behaviour changed in v5.6 and so some earlier kernels may
+   incorrectly accept valid tagged pointers for the ``brk()``,
+   ``mmap()`` and ``mremap()`` system calls.
 
 2. User addresses accessed by the kernel (e.g. ``write()``). This ABI
    relaxation is disabled by default and the application thread needs to

mm/mmap.c +0 -4

@@ -195,8 +195,6 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	bool downgraded = false;
 	LIST_HEAD(uf);
 
-	brk = untagged_addr(brk);
-
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;

@@ -1561,8 +1559,6 @@ unsigned long ksys_mmap_pgoff(unsigned l
 	struct file *file = NULL;
 	unsigned long retval;
 
-	addr = untagged_addr(addr);
-
 	if (!(flags & MAP_ANONYMOUS)) {
 		audit_mmap_fd(fd, flags);
 		file = fget(fd);

mm/mremap.c +0 -1

@@ -607,7 +607,6 @@ SYSCALL_DEFINE5(mremap, unsigned long, a
 	LIST_HEAD(uf_unmap);
 
 	addr = untagged_addr(addr);
-	new_addr = untagged_addr(new_addr);
 
 	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
 		return ret;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:16 UTC #82 lore raw

PATCH 80/150 drm/amdgpu/soc15: fix xclk for raven

From: Alex Deucher <[email protected]>

commit c657b936ea98630ef5ba4f130ab1ad5c534d0165 upstream.

It's 25 Mhz (refclk / 4). This fixes the interpretation of the rlc clock counter.

Acked-by Evan Quan <[email protected]>

Signed-off-by Alex Deucher <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/amd/amdgpu/soc15.c |    7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

drivers/gpu/drm/amd/amdgpu/soc15.c +6 -1

@@ -270,7 +270,12 @@ static u32 soc15_get_config_memsize(stru
 
 static u32 soc15_get_xclk(struct amdgpu_device *adev)
 {
-	return adev->clock.spll.reference_freq;
+	u32 reference_clock = adev->clock.spll.reference_freq;
+
+	if (adev->asic_type == CHIP_RAVEN)
+		return reference_clock / 4;
+
+	return reference_clock;
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:16 UTC #83 lore raw

PATCH 81/150 drm/amdgpu/gfx9: disable gfxoff when reading rlc clock

From: Alex Deucher <[email protected]>

commit 120cf959308e1bda984e40a9edd25ee2d6262efd upstream.

Otherwise we readback all ones. Fixes rlc counter readback while gfxoff is active.

Reviewed-by Xiaojie Yuan <[email protected]>

Signed-off-by Alex Deucher <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c |    2 ++
 1 file changed, 2 insertions(+)

drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +2 -0

@@ -3852,6 +3852,7 @@ static uint64_t gfx_v9_0_get_gpu_clock_c
 {
 	uint64_t clock;
 
+	amdgpu_gfx_off_ctrl(adev, false);
 	mutex_lock(&adev->gfx.gpu_clock_mutex);
 	if (adev->asic_type == CHIP_VEGA10 && amdgpu_sriov_runtime(adev)) {
 		uint32_t tmp, lsb, msb, i = 0;

@@ -3870,6 +3871,7 @@ static uint64_t gfx_v9_0_get_gpu_clock_c
 			((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
 	}
 	mutex_unlock(&adev->gfx.gpu_clock_mutex);
+	amdgpu_gfx_off_ctrl(adev, true);
 	return clock;
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:16 UTC #84 lore raw

PATCH 82/150 drm/amdgpu/gfx10: disable gfxoff when reading rlc clock

From: Alex Deucher <[email protected]>

commit b08c3ed609aabc4e76e74edc4404f0c26279d7ed upstream.

Otherwise we readback all ones. Fixes rlc counter readback while gfxoff is active.

Reviewed-by Xiaojie Yuan <[email protected]>

Signed-off-by Alex Deucher <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c |    2 ++
 1 file changed, 2 insertions(+)

drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +2 -0

@@ -3909,11 +3909,13 @@ static uint64_t gfx_v10_0_get_gpu_clock_
 {
 	uint64_t clock;
 
+	amdgpu_gfx_off_ctrl(adev, false);
 	mutex_lock(&adev->gfx.gpu_clock_mutex);
 	WREG32_SOC15(GC, 0, mmRLC_CAPTURE_GPU_CLOCK_COUNT, 1);
 	clock = (uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_LSB) |
 		((uint64_t)RREG32_SOC15(GC, 0, mmRLC_GPU_CLOCK_COUNT_MSB) << 32ULL);
 	mutex_unlock(&adev->gfx.gpu_clock_mutex);
+	amdgpu_gfx_off_ctrl(adev, true);
 	return clock;
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:22 UTC #85 lore raw

PATCH 83/150 drm/nouveau/kms/gv100-: Re-set LUT after clearing for modesets

From: Lyude Paul <[email protected]>

commit f287d3d19769b1d22cba4e51fa0487f2697713c9 upstream.

While certain modeset operations on gv100+ need us to temporarily disable the LUT, we make the mistake of sometimes neglecting to reprogram the LUT after such modesets. In particular, moving a head from one encoder to another seems to trigger this quite often. GV100+ is very picky about having a LUT in most scenarios, so this causes the display engine to hang with the following error code:

disp: chid 1 stat 00005080 reason 5 [INVALID_STATE] mthd 0200 data 00000001 code 0000002d)

So, fix this by always re-programming the LUT if we're clearing it in a state where the wndw is still visible, and has a XLUT handle programmed.

Signed-off-by Lyude Paul <[email protected]>

Fixes facaed62b4cb ("drm/nouveau/kms/gv100: initial support")

Cc <[email protected]> # v4.18+

Signed-off-by Ben Skeggs <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/nouveau/dispnv50/wndw.c |    2 ++
 1 file changed, 2 insertions(+)

drivers/gpu/drm/nouveau/dispnv50/wndw.c +2 -0

@@ -451,6 +451,8 @@ nv50_wndw_atomic_check(struct drm_plane
 		asyw->clr.ntfy = armw->ntfy.handle != 0;
 		asyw->clr.sema = armw->sema.handle != 0;
 		asyw->clr.xlut = armw->xlut.handle != 0;
+		if (asyw->clr.xlut && asyw->visible)
+			asyw->set.xlut = asyw->xlut.handle != 0;
 		asyw->clr.csc  = armw->csc.valid;
 		if (wndw->func->image_clr)
 			asyw->clr.image = armw->image.handle[0] != 0;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:22 UTC #86 lore raw

PATCH 84/150 drm/i915: Wean off drm_pci_alloc/drm_pci_free

From: Chris Wilson <[email protected]>

commit aa3146193ae25d0fe4b96d815169a135db2e8f01 upstream.

drm_pci_alloc and drm_pci_free are just very thin wrappers around dma_alloc_coherent, with a note that we should be removing them. Furthermore since

commit de09d31dd38a50fdce106c15abd68432eebbd014

Author: Kirill A. Shutemov <[email protected]>
Date:   Fri Jan 15 16:51:42 2016 -0800

page-flags: define PG_reserved behavior on compound pages

As far as I can see there's no users of PG_reserved on compound pages. Let's use PF_NO_COMPOUND here.

drm_pci_alloc has been declared broken since it mixes GFP_COMP and SetPageReserved. Avoid this conflict by weaning ourselves off using the abstraction and using the dma functions directly.

Reported-by Taketo Kabe

Closes https://gitlab.freedesktop.org/drm/intel/issues/1027

Fixes de09d31dd38a ("page-flags: define PG_reserved behavior on compound pages")

Link https://patchwork.freedesktop.org/patch/msgid/[email protected]

Cc <[email protected]> # v4.5+

Reviewed-by Daniel Vetter <[email protected]>

(cherry picked from commit c6790dc22312f592c1434577258b31c48c72d52a)

Signed-off-by Jani Nikula <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/i915/display/intel_display.c     |    2 
 drivers/gpu/drm/i915/gem/i915_gem_object_types.h |    3 
 drivers/gpu/drm/i915/gem/i915_gem_phys.c         |   98 +++++++++++------------
 drivers/gpu/drm/i915/i915_gem.c                  |    8 -
 4 files changed, 55 insertions(+), 56 deletions(-)

drivers/gpu/drm/i915/display/intel_display.c +1 -1

@@ -10731,7 +10731,7 @@ static u32 intel_cursor_base(const struc
 	u32 base;
 
 	if (INTEL_INFO(dev_priv)->display.cursor_needs_physical)
-		base = obj->phys_handle->busaddr;
+		base = sg_dma_address(obj->mm.pages->sgl);
 	else
 		base = intel_plane_ggtt_offset(plane_state);

drivers/gpu/drm/i915/gem/i915_gem_object_types.h +0 -3

@@ -260,9 +260,6 @@ struct drm_i915_gem_object {
 
 		void *gvt_info;
 	};
-
-	/** for phys allocated objects */
-	struct drm_dma_handle *phys_handle;
 };
 
 static inline struct drm_i915_gem_object *

drivers/gpu/drm/i915/gem/i915_gem_phys.c +50 ~~-48~~

160 lines not on this page · raw message

drivers/gpu/drm/i915/i915_gem.c +4 -4

@@ -154,7 +154,7 @@ i915_gem_phys_pwrite(struct drm_i915_gem
 		     struct drm_i915_gem_pwrite *args,
 		     struct drm_file *file)
 {
-	void *vaddr = obj->phys_handle->vaddr + args->offset;
+	void *vaddr = sg_page(obj->mm.pages->sgl) + args->offset;
 	char __user *user_data = u64_to_user_ptr(args->data_ptr);
 
 	/*

@@ -800,10 +800,10 @@ i915_gem_pwrite_ioctl(struct drm_device
 		ret = i915_gem_gtt_pwrite_fast(obj, args);
 
 	if (ret == -EFAULT || ret == -ENOSPC) {
-		if (obj->phys_handle)
-			ret = i915_gem_phys_pwrite(obj, args, file);
-		else
+		if (i915_gem_object_has_struct_page(obj))
 			ret = i915_gem_shmem_pwrite(obj, args);
+		else
+			ret = i915_gem_phys_pwrite(obj, args, file);
 	}
 
 	i915_gem_object_unpin_pages(obj);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:16 UTC #87 lore raw

PATCH 85/150 drm/i915: Update drm/i915 bug filing URL

From: Jani Nikula <[email protected]>

commit 7ddc7005a0aa2f43a826b71f5d6bd7d4b90f8f2a upstream.

We've moved from bugzilla to gitlab.

Link https://patchwork.freedesktop.org/patch/msgid/[email protected]

Reviewed-by Chris Wilson <[email protected]>

Signed-off-by Jani Nikula <[email protected]>

(cherry picked from commit ddae4d7af0bbe3b2051f1603459a8b24e9a19324)

Signed-off-by Jani Nikula <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/i915/Kconfig          |    5 ++---
 drivers/gpu/drm/i915/i915_gpu_error.c |    3 ++-
 drivers/gpu/drm/i915/i915_utils.c     |    5 ++---
 3 files changed, 6 insertions(+), 7 deletions(-)

drivers/gpu/drm/i915/Kconfig +2 -3

@@ -75,9 +75,8 @@ config DRM_I915_CAPTURE_ERROR
 	help
 	  This option enables capturing the GPU state when a hang is detected.
 	  This information is vital for triaging hangs and assists in debugging.
-	  Please report any hang to
-	    https://bugs.freedesktop.org/enter_bug.cgi?product=DRI
-	  for triaging.
+	  Please report any hang for triaging according to:
+	    https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs
 
 	  If in doubt, say "Y".

drivers/gpu/drm/i915/i915_gpu_error.c +2 -1

@@ -1820,7 +1820,8 @@ void i915_capture_error_state(struct drm
 	if (!xchg(&warned, true) &&
 	    ktime_get_real_seconds() - DRIVER_TIMESTAMP < DAY_AS_SECONDS(180)) {
 		pr_info("GPU hangs can indicate a bug anywhere in the entire gfx stack, including userspace.\n");
-		pr_info("Please file a _new_ bug report on bugs.freedesktop.org against DRI -> DRM/Intel\n");
+		pr_info("Please file a _new_ bug report at https://gitlab.freedesktop.org/drm/intel/issues/new.\n");
+		pr_info("Please see https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs for details.\n");
 		pr_info("drm/i915 developers can then reassign to the right component if it's not a kernel issue.\n");
 		pr_info("The GPU crash dump is required to analyze GPU hangs, so please always attach it.\n");
 		pr_info("GPU crash dump saved to /sys/class/drm/card%d/error\n",

drivers/gpu/drm/i915/i915_utils.c +2 -3

@@ -8,9 +8,8 @@
 #include "i915_drv.h"
 #include "i915_utils.h"
 
-#define FDO_BUG_URL "https://bugs.freedesktop.org/enter_bug.cgi?product=DRI"
-#define FDO_BUG_MSG "Please file a bug at " FDO_BUG_URL " against DRM/Intel " \
-		    "providing the dmesg log by booting with drm.debug=0xf"
+#define FDO_BUG_URL "https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs"
+#define FDO_BUG_MSG "Please file a bug on drm/i915; see " FDO_BUG_URL " for details."
 
 void
 __i915_printk(struct drm_i915_private *dev_priv, const char *level,

Greg Kroah-Hartman

author maintainer

2020-02-27 14:21 UTC #88 lore raw

PATCH 86/150 sched/psi: Fix OOB write when writing 0 bytes to PSI files

From: Suren Baghdasaryan <[email protected]>

commit 6fcca0fa48118e6d63733eb4644c6cd880c15b8f upstream.

Issuing write() with count parameter set to 0 on any file under /proc/pressure/ will cause an OOB write because of the access to buf[buf_size-1] when NUL-termination is performed. Fix this by checking for buf_size to be non-zero.

Signed-off-by Suren Baghdasaryan <[email protected]>

Signed-off-by Peter Zijlstra (Intel) <[email protected]>

Signed-off-by Ingo Molnar <[email protected]>

Acked-by Johannes Weiner <[email protected]>

Link https://lkml.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 kernel/sched/psi.c |    3 +++
 1 file changed, 3 insertions(+)

kernel/sched/psi.c +3 -0

@@ -1199,6 +1199,9 @@ static ssize_t psi_write(struct file *fi
 	if (static_branch_likely(&psi_disabled))
 		return -EOPNOTSUPP;
 
+	if (!nbytes)
+		return -EINVAL;
+
 	buf_size = min(nbytes, sizeof(buf));
 	if (copy_from_user(buf, user_buf, buf_size))
 		return -EFAULT;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:22 UTC #89 lore raw

PATCH 87/150 KVM: nVMX: Dont emulate instructions in guest mode

From: Paolo Bonzini <[email protected]>

commit 07721feee46b4b248402133228235318199b05ec upstream.

vmx_check_intercept is not yet fully implemented. To avoid emulating instructions disallowed by the L1 hypervisor, refuse to emulate instructions by default.

[Made commit, added commit msg - Oliver]

Signed-off-by Oliver Upton <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/x86/kvm/vmx/vmx.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

arch/x86/kvm/vmx/vmx.c +1 -1

@@ -7165,7 +7165,7 @@ static int vmx_check_intercept(struct kv
 	}
 
 	/* TODO: check more intercepts... */
-	return X86EMUL_CONTINUE;
+	return X86EMUL_UNHANDLEABLE;
 }
 
 #ifdef CONFIG_X86_64

Greg Kroah-Hartman

author maintainer

2020-02-27 14:16 UTC #90 lore raw

PATCH 88/150 KVM: x86: dont notify userspace IOAPIC on edge-triggered interrupt EOI

From: Miaohe Lin <[email protected]>

commit 7455a8327674e1a7c9a1f5dd1b0743ab6713f6d1 upstream.

Commit 13db77347db1 ("KVM: x86: don't notify userspace IOAPIC on edge EOI") said, edge-triggered interrupts don't set a bit in TMR, which means that IOAPIC isn't notified on EOI. And var level indicates level-triggered interrupt.
But commit 3159d36ad799 ("KVM: x86: use generic function for MSI parsing") replace var level with irq.level by mistake. Fix it by changing irq.level to irq.trig_mode.

Fixes 3159d36ad799 ("KVM: x86: use generic function for MSI parsing")

Signed-off-by Miaohe Lin <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/x86/kvm/irq_comm.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

arch/x86/kvm/irq_comm.c +1 -1

@@ -416,7 +416,7 @@ void kvm_scan_ioapic_routes(struct kvm_v
 
 			kvm_set_msi_irq(vcpu->kvm, entry, &irq);
 
-			if (irq.level && kvm_apic_match_dest(vcpu, NULL, 0,
+			if (irq.trig_mode && kvm_apic_match_dest(vcpu, NULL, 0,
 						irq.dest_id, irq.dest_mode))
 				__set_bit(irq.vector, ioapic_handled_vectors);
 		}

Greg Kroah-Hartman

author maintainer

2020-02-27 14:16 UTC #91 lore raw

PATCH 89/150 ext4: fix a data race in EXT4_I(inode)->i_disksize

From: Qian Cai <[email protected]>

commit 35df4299a6487f323b0aca120ea3f485dfee2ae3 upstream.

EXT4_I(inode)->i_disksize could be accessed concurrently as noticed by KCSAN,

 BUG: KCSAN: data-race in ext4_write_end [ext4] / ext4_writepages [ext4]

write to 0xffff91c6713b00f8 of 8 bytes by task 49268 on cpu 127:

  ext4_write_end+0x4e3/0x750 [ext4]
  ext4_update_i_disksize at fs/ext4/ext4.h:3032
  (inlined by) ext4_update_inode_size at fs/ext4/ext4.h:3046
  (inlined by) ext4_write_end at fs/ext4/inode.c:1287
  generic_perform_write+0x208/0x2a0
  ext4_buffered_write_iter+0x11f/0x210 [ext4]
  ext4_file_write_iter+0xce/0x9e0 [ext4]
  new_sync_write+0x29c/0x3b0
  __vfs_write+0x92/0xa0
  vfs_write+0x103/0x260
  ksys_write+0x9d/0x130
  __x64_sys_write+0x4c/0x60
  do_syscall_64+0x91/0xb47
  entry_SYSCALL_64_after_hwframe+0x49/0xbe

read to 0xffff91c6713b00f8 of 8 bytes by task 24872 on cpu 37:

  ext4_writepages+0x10ac/0x1d00 [ext4]
  mpage_map_and_submit_extent at fs/ext4/inode.c:2468
  (inlined by) ext4_writepages at fs/ext4/inode.c:2772
  do_writepages+0x5e/0x130
  __writeback_single_inode+0xeb/0xb20
  writeback_sb_inodes+0x429/0x900
  __writeback_inodes_wb+0xc4/0x150
  wb_writeback+0x4bd/0x870
  wb_workfn+0x6b4/0x960
  process_one_work+0x54c/0xbe0
  worker_thread+0x80/0x650
  kthread+0x1e0/0x200
  ret_from_fork+0x27/0x50

Reported by Kernel Concurrency Sanitizer on:

 CPU: 37 PID: 24872 Comm: kworker/u261:2 Tainted: G        W  O L 5.5.0-next-20200204+ #5
 Hardware name: HPE ProLiant DL385 Gen10/ProLiant DL385 Gen10, BIOS A40 07/10/2019
 Workqueue: writeback wb_workfn (flush-7:0)

Since only the read is operating as lockless (outside of the "i_data_sem"), load tearing could introduce a logic bug. Fix it by adding READ_ONCE() for the read and WRITE_ONCE() for the write.

Signed-off-by Qian Cai <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/ext4/ext4.h  |    2 +-
 fs/ext4/inode.c |    2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

fs/ext4/ext4.h +1 -1

@@ -2972,7 +2972,7 @@ static inline void ext4_update_i_disksiz
 		     !inode_is_locked(inode));
 	down_write(&EXT4_I(inode)->i_data_sem);
 	if (newsize > EXT4_I(inode)->i_disksize)
-		EXT4_I(inode)->i_disksize = newsize;
+		WRITE_ONCE(EXT4_I(inode)->i_disksize, newsize);
 	up_write(&EXT4_I(inode)->i_data_sem);
 }

fs/ext4/inode.c +1 -1

@@ -2466,7 +2466,7 @@ update_disksize:
 	 * truncate are avoided by checking i_size under i_data_sem.
 	 */
 	disksize = ((loff_t)mpd->first_page) << PAGE_SHIFT;
-	if (disksize > EXT4_I(inode)->i_disksize) {
+	if (disksize > READ_ONCE(EXT4_I(inode)->i_disksize)) {
 		int err2;
 		loff_t i_size;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:16 UTC #92 lore raw

PATCH 90/150 ext4: add cond_resched() to __ext4_find_entry()

From: Shijie Luo <[email protected]>

commit 9424ef56e13a1f14c57ea161eed3ecfdc7b2770e upstream.

We tested a soft lockup problem in linux 4.19 which could also be found in linux 5.x.

When dir inode takes up a large number of blocks, and if the directory is growing when we are searching, it's possible the restart branch could be called many times, and the do while loop could hold cpu a long time.

Here is the call trace in linux 4.19.

[  473.756186] Call trace:
[  473.756196]  dump_backtrace+0x0/0x198
[  473.756199]  show_stack+0x24/0x30
[  473.756205]  dump_stack+0xa4/0xcc
[  473.756210]  watchdog_timer_fn+0x300/0x3e8
[  473.756215]  __hrtimer_run_queues+0x114/0x358
[  473.756217]  hrtimer_interrupt+0x104/0x2d8
[  473.756222]  arch_timer_handler_virt+0x38/0x58
[  473.756226]  handle_percpu_devid_irq+0x90/0x248
[  473.756231]  generic_handle_irq+0x34/0x50
[  473.756234]  __handle_domain_irq+0x68/0xc0
[  473.756236]  gic_handle_irq+0x6c/0x150
[  473.756238]  el1_irq+0xb8/0x140
[  473.756286]  ext4_es_lookup_extent+0xdc/0x258 [ext4]
[  473.756310]  ext4_map_blocks+0x64/0x5c0 [ext4]
[  473.756333]  ext4_getblk+0x6c/0x1d0 [ext4]
[  473.756356]  ext4_bread_batch+0x7c/0x1f8 [ext4]
[  473.756379]  ext4_find_entry+0x124/0x3f8 [ext4]
[  473.756402]  ext4_lookup+0x8c/0x258 [ext4]
[  473.756407]  __lookup_hash+0x8c/0xe8
[  473.756411]  filename_create+0xa0/0x170
[  473.756413]  do_mkdirat+0x6c/0x140
[  473.756415]  __arm64_sys_mkdirat+0x28/0x38
[  473.756419]  el0_svc_common+0x78/0x130
[  473.756421]  el0_svc_handler+0x38/0x78
[  473.756423]  el0_svc+0x8/0xc
[  485.755156] watchdog: BUG: soft lockup - CPU#2 stuck for 22s! [tmp:5149]

Add cond_resched() to avoid soft lockup and to provide a better system responding.

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Shijie Luo <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/ext4/namei.c |    1 +
 1 file changed, 1 insertion(+)

fs/ext4/namei.c +1 -0

@@ -1507,6 +1507,7 @@ restart:
 		/*
 		 * We deal with the read-ahead logic here.
 		 */
+		cond_resched();
 		if (ra_ptr >= ra_max) {
 			/* Refill the readahead buffer */
 			ra_ptr = 0;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:16 UTC #93 lore raw

PATCH 91/150 ext4: fix potential race between online resizing and write operations

Link https://bugzilla.kernel.org/show_bug.cgi?id=206443

From: Theodore Ts'o <[email protected]>

commit 1d0c3924a92e69bfa91163bda83c12a994b4d106 upstream.

During an online resize an array of pointers to buffer heads gets replaced so it can get enlarged. If there is a racing block allocation or deallocation which uses the old array, and the old array has gotten reused this can lead to a GPF or some other random kernel memory getting modified.

Link https://lore.kernel.org/r/[email protected] open here

Reported-by Suraj Jitindar Singh <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/ext4/balloc.c |   14 +++++++++++---
 fs/ext4/ext4.h   |   20 +++++++++++++++++++-
 fs/ext4/resize.c |   55 ++++++++++++++++++++++++++++++++++++++++++++-----------
 fs/ext4/super.c  |   33 +++++++++++++++++++++++----------
 4 files changed, 97 insertions(+), 25 deletions(-)

fs/ext4/balloc.c +11 -3

@@ -270,6 +270,7 @@ struct ext4_group_desc * ext4_get_group_
 	ext4_group_t ngroups = ext4_get_groups_count(sb);
 	struct ext4_group_desc *desc;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct buffer_head *bh_p;
 
 	if (block_group >= ngroups) {
 		ext4_error(sb, "block_group >= groups_count - block_group = %u,"

@@ -280,7 +281,14 @@ struct ext4_group_desc * ext4_get_group_
 
 	group_desc = block_group >> EXT4_DESC_PER_BLOCK_BITS(sb);
 	offset = block_group & (EXT4_DESC_PER_BLOCK(sb) - 1);
-	if (!sbi->s_group_desc[group_desc]) {
+	bh_p = sbi_array_rcu_deref(sbi, s_group_desc, group_desc);
+	/*
+	 * sbi_array_rcu_deref returns with rcu unlocked, this is ok since
+	 * the pointer being dereferenced won't be dereferenced again. By
+	 * looking at the usage in add_new_gdb() the value isn't modified,
+	 * just the pointer, and so it remains valid.
+	 */
+	if (!bh_p) {
 		ext4_error(sb, "Group descriptor not loaded - "
 			   "block_group = %u, group_desc = %u, desc = %u",
 			   block_group, group_desc, offset);

@@ -288,10 +296,10 @@ struct ext4_group_desc * ext4_get_group_
 	}
 
 	desc = (struct ext4_group_desc *)(
-		(__u8 *)sbi->s_group_desc[group_desc]->b_data +
+		(__u8 *)bh_p->b_data +
 		offset * EXT4_DESC_SIZE(sb));
 	if (bh)
-		*bh = sbi->s_group_desc[group_desc];
+		*bh = bh_p;
 	return desc;
 }

fs/ext4/ext4.h +19 -1

@@ -1401,7 +1401,7 @@ struct ext4_sb_info {
 	loff_t s_bitmap_maxbytes;	/* max bytes for bitmap files */
 	struct buffer_head * s_sbh;	/* Buffer containing the super block */
 	struct ext4_super_block *s_es;	/* Pointer to the super block in the buffer */
-	struct buffer_head **s_group_desc;
+	struct buffer_head * __rcu *s_group_desc;
 	unsigned int s_mount_opt;
 	unsigned int s_mount_opt2;
 	unsigned int s_mount_flags;

@@ -1575,6 +1575,23 @@ static inline int ext4_valid_inum(struct
 }
 
 /*
+ * Returns: sbi->field[index]
+ * Used to access an array element from the following sbi fields which require
+ * rcu protection to avoid dereferencing an invalid pointer due to reassignment
+ * - s_group_desc
+ * - s_group_info
+ * - s_flex_group
+ */
+#define sbi_array_rcu_deref(sbi, field, index)				   \
+({									   \
+	typeof(*((sbi)->field)) _v;					   \
+	rcu_read_lock();						   \
+	_v = ((typeof(_v)*)rcu_dereference((sbi)->field))[index];	   \
+	rcu_read_unlock();						   \
+	_v;								   \
+})
+
+/*
  * Inode dynamic state flags
  */
 enum {

@@ -2669,6 +2686,7 @@ extern int ext4_generic_delete_entry(han
 extern bool ext4_empty_dir(struct inode *inode);
 
 /* resize.c */
+extern void ext4_kvfree_array_rcu(void *to_free);
 extern int ext4_group_add(struct super_block *sb,
 				struct ext4_new_group_data *input);
 extern int ext4_group_extend(struct super_block *sb,

fs/ext4/resize.c +44 ~~-11~~

110 lines not on this page · raw message

fs/ext4/super.c +23 ~~-10~~

@@ -970,6 +970,7 @@ static void ext4_put_super(struct super_
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
+	struct buffer_head **group_desc;
 	int aborted = 0;
 	int i, err;

@@ -1000,9 +1001,12 @@ static void ext4_put_super(struct super_
 	if (!sb_rdonly(sb))
 		ext4_commit_super(sb, 1);
 
+	rcu_read_lock();
+	group_desc = rcu_dereference(sbi->s_group_desc);
 	for (i = 0; i < sbi->s_gdb_count; i++)
-		brelse(sbi->s_group_desc[i]);
-	kvfree(sbi->s_group_desc);
+		brelse(group_desc[i]);
+	kvfree(group_desc);
+	rcu_read_unlock();
 	kvfree(sbi->s_flex_groups);
 	percpu_counter_destroy(&sbi->s_freeclusters_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);

@@ -3589,7 +3593,7 @@ static int ext4_fill_super(struct super_
 {
 	struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
 	char *orig_data = kstrdup(data, GFP_KERNEL);
-	struct buffer_head *bh;
+	struct buffer_head *bh, **group_desc;
 	struct ext4_super_block *es = NULL;
 	struct ext4_sb_info *sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
 	ext4_fsblk_t block;

@@ -4245,9 +4249,10 @@ static int ext4_fill_super(struct super_
 			goto failed_mount;
 		}
 	}
-	sbi->s_group_desc = kvmalloc_array(db_count,
-					   sizeof(struct buffer_head *),
-					   GFP_KERNEL);
+	rcu_assign_pointer(sbi->s_group_desc,
+			   kvmalloc_array(db_count,
+					  sizeof(struct buffer_head *),
+					  GFP_KERNEL));
 	if (sbi->s_group_desc == NULL) {
 		ext4_msg(sb, KERN_ERR, "not enough memory");
 		ret = -ENOMEM;

@@ -4263,14 +4268,19 @@ static int ext4_fill_super(struct super_
 	}
 
 	for (i = 0; i < db_count; i++) {
+		struct buffer_head *bh;
+
 		block = descriptor_loc(sb, logical_sb_block, i);
-		sbi->s_group_desc[i] = sb_bread_unmovable(sb, block);
-		if (!sbi->s_group_desc[i]) {
+		bh = sb_bread_unmovable(sb, block);
+		if (!bh) {
 			ext4_msg(sb, KERN_ERR,
 			       "can't read group descriptor %d", i);
 			db_count = i;
 			goto failed_mount2;
 		}
+		rcu_read_lock();
+		rcu_dereference(sbi->s_group_desc)[i] = bh;
+		rcu_read_unlock();
 	}
 	sbi->s_gdb_count = db_count;
 	if (!ext4_check_descriptors(sb, logical_sb_block, &first_not_zeroed)) {

@@ -4672,9 +4682,12 @@ failed_mount3:
 	if (sbi->s_mmp_tsk)
 		kthread_stop(sbi->s_mmp_tsk);
 failed_mount2:
+	rcu_read_lock();
+	group_desc = rcu_dereference(sbi->s_group_desc);
 	for (i = 0; i < db_count; i++)
-		brelse(sbi->s_group_desc[i]);
-	kvfree(sbi->s_group_desc);
+		brelse(group_desc[i]);
+	kvfree(group_desc);
+	rcu_read_unlock();
 failed_mount:
 	if (sbi->s_chksum_driver)
 		crypto_free_shash(sbi->s_chksum_driver);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:21 UTC #94 lore raw

PATCH 92/150 ext4: fix potential race between s_group_info online resizing and access

Link https://bugzilla.kernel.org/show_bug.cgi?id=206443

From: Suraj Jitindar Singh <[email protected]>

commit df3da4ea5a0fc5d115c90d5aa6caa4dd433750a7 upstream.

During an online resize an array of pointers to s_group_info gets replaced so it can get enlarged. If there is a concurrent access to the array in ext4_get_group_info() and this memory has been reused then this can lead to an invalid memory access.

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Suraj Jitindar Singh <[email protected]>

Reviewed-by Balbir Singh <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/ext4/ext4.h    |    8 ++++----
 fs/ext4/mballoc.c |   52 +++++++++++++++++++++++++++++++++++-----------------
 2 files changed, 39 insertions(+), 21 deletions(-)

fs/ext4/ext4.h +4 -4

@@ -1463,7 +1463,7 @@ struct ext4_sb_info {
 #endif
 
 	/* for buddy allocator */
-	struct ext4_group_info ***s_group_info;
+	struct ext4_group_info ** __rcu *s_group_info;
 	struct inode *s_buddy_cache;
 	spinlock_t s_md_lock;
 	unsigned short *s_mb_offsets;

@@ -2934,13 +2934,13 @@ static inline
 struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
 					    ext4_group_t group)
 {
-	 struct ext4_group_info ***grp_info;
+	 struct ext4_group_info **grp_info;
 	 long indexv, indexh;
 	 BUG_ON(group >= EXT4_SB(sb)->s_groups_count);
-	 grp_info = EXT4_SB(sb)->s_group_info;
 	 indexv = group >> (EXT4_DESC_PER_BLOCK_BITS(sb));
 	 indexh = group & ((EXT4_DESC_PER_BLOCK(sb)) - 1);
-	 return grp_info[indexv][indexh];
+	 grp_info = sbi_array_rcu_deref(EXT4_SB(sb), s_group_info, indexv);
+	 return grp_info[indexh];
 }
 
 /*

fs/ext4/mballoc.c +35 ~~-17~~

114 lines not on this page · raw message

Greg Kroah-Hartman

author maintainer

2020-02-27 14:16 UTC #95 lore raw

PATCH 93/150 ext4: fix potential race between s_flex_groups online resizing and access

Link https://bugzilla.kernel.org/show_bug.cgi?id=206443

From: Suraj Jitindar Singh <[email protected]>

commit 7c990728b99ed6fbe9c75fc202fce1172d9916da upstream.

During an online resize an array of s_flex_groups structures gets replaced so it can get enlarged. If there is a concurrent access to the array and this memory has been reused then this can lead to an invalid memory access.

The s_flex_group array has been converted into an array of pointers rather than an array of structures. This is to ensure that the information contained in the structures cannot get out of sync during a resize due to an accessor updating the value in the old structure after it has been copied but before the array pointer is updated. Since the structures them- selves are no longer copied but only the pointers to them this case is mitigated.

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Suraj Jitindar Singh <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/ext4/ext4.h    |    2 -
 fs/ext4/ialloc.c  |   23 ++++++++++-------
 fs/ext4/mballoc.c |    9 ++++--
 fs/ext4/resize.c  |    7 +++--
 fs/ext4/super.c   |   72 +++++++++++++++++++++++++++++++++++++-----------------
 5 files changed, 76 insertions(+), 37 deletions(-)

fs/ext4/ext4.h +1 -1

@@ -1513,7 +1513,7 @@ struct ext4_sb_info {
 	unsigned int s_extent_max_zeroout_kb;
 
 	unsigned int s_log_groups_per_flex;
-	struct flex_groups *s_flex_groups;
+	struct flex_groups * __rcu *s_flex_groups;
 	ext4_group_t s_flex_groups_allocated;
 
 	/* workqueue for reserved extent conversions (buffered io) */

fs/ext4/ialloc.c +14 -9

@@ -325,11 +325,13 @@ void ext4_free_inode(handle_t *handle, s
 
 	percpu_counter_inc(&sbi->s_freeinodes_counter);
 	if (sbi->s_log_groups_per_flex) {
-		ext4_group_t f = ext4_flex_group(sbi, block_group);
+		struct flex_groups *fg;
 
-		atomic_inc(&sbi->s_flex_groups[f].free_inodes);
+		fg = sbi_array_rcu_deref(sbi, s_flex_groups,
+					 ext4_flex_group(sbi, block_group));
+		atomic_inc(&fg->free_inodes);
 		if (is_directory)
-			atomic_dec(&sbi->s_flex_groups[f].used_dirs);
+			atomic_dec(&fg->used_dirs);
 	}
 	BUFFER_TRACE(bh2, "call ext4_handle_dirty_metadata");
 	fatal = ext4_handle_dirty_metadata(handle, NULL, bh2);

@@ -365,12 +367,13 @@ static void get_orlov_stats(struct super
 			    int flex_size, struct orlov_stats *stats)
 {
 	struct ext4_group_desc *desc;
-	struct flex_groups *flex_group = EXT4_SB(sb)->s_flex_groups;
 
 	if (flex_size > 1) {
-		stats->free_inodes = atomic_read(&flex_group[g].free_inodes);
-		stats->free_clusters = atomic64_read(&flex_group[g].free_clusters);
-		stats->used_dirs = atomic_read(&flex_group[g].used_dirs);
+		struct flex_groups *fg = sbi_array_rcu_deref(EXT4_SB(sb),
+							     s_flex_groups, g);
+		stats->free_inodes = atomic_read(&fg->free_inodes);
+		stats->free_clusters = atomic64_read(&fg->free_clusters);
+		stats->used_dirs = atomic_read(&fg->used_dirs);
 		return;
 	}

@@ -1051,7 +1054,8 @@ got:
 		if (sbi->s_log_groups_per_flex) {
 			ext4_group_t f = ext4_flex_group(sbi, group);
 
-			atomic_inc(&sbi->s_flex_groups[f].used_dirs);
+			atomic_inc(&sbi_array_rcu_deref(sbi, s_flex_groups,
+							f)->used_dirs);
 		}
 	}
 	if (ext4_has_group_desc_csum(sb)) {

@@ -1074,7 +1078,8 @@ got:
 
 	if (sbi->s_log_groups_per_flex) {
 		flex_group = ext4_flex_group(sbi, group);
-		atomic_dec(&sbi->s_flex_groups[flex_group].free_inodes);
+		atomic_dec(&sbi_array_rcu_deref(sbi, s_flex_groups,
+						flex_group)->free_inodes);
 	}
 
 	inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb);

fs/ext4/mballoc.c +6 -3

@@ -3038,7 +3038,8 @@ ext4_mb_mark_diskspace_used(struct ext4_
 		ext4_group_t flex_group = ext4_flex_group(sbi,
 							  ac->ac_b_ex.fe_group);
 		atomic64_sub(ac->ac_b_ex.fe_len,
-			     &sbi->s_flex_groups[flex_group].free_clusters);
+			     &sbi_array_rcu_deref(sbi, s_flex_groups,
+						  flex_group)->free_clusters);
 	}
 
 	err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);

@@ -4932,7 +4933,8 @@ do_more:
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
 		atomic64_add(count_clusters,
-			     &sbi->s_flex_groups[flex_group].free_clusters);
+			     &sbi_array_rcu_deref(sbi, s_flex_groups,
+						  flex_group)->free_clusters);
 	}
 
 	/*

@@ -5089,7 +5091,8 @@ int ext4_group_add_blocks(handle_t *hand
 	if (sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
 		atomic64_add(clusters_freed,
-			     &sbi->s_flex_groups[flex_group].free_clusters);
+			     &sbi_array_rcu_deref(sbi, s_flex_groups,
+						  flex_group)->free_clusters);
 	}
 
 	ext4_mb_unload_buddy(&e4b);

fs/ext4/resize.c +5 -2

@@ -1432,11 +1432,14 @@ static void ext4_update_super(struct sup
 		   percpu_counter_read(&sbi->s_freeclusters_counter));
 	if (ext4_has_feature_flex_bg(sb) && sbi->s_log_groups_per_flex) {
 		ext4_group_t flex_group;
+		struct flex_groups *fg;
+
 		flex_group = ext4_flex_group(sbi, group_data[0].group);
+		fg = sbi_array_rcu_deref(sbi, s_flex_groups, flex_group);
 		atomic64_add(EXT4_NUM_B2C(sbi, free_blocks),
-			     &sbi->s_flex_groups[flex_group].free_clusters);
+			     &fg->free_clusters);
 		atomic_add(EXT4_INODES_PER_GROUP(sb) * flex_gd->count,
-			   &sbi->s_flex_groups[flex_group].free_inodes);
+			   &fg->free_inodes);
 	}
 
 	/*

fs/ext4/super.c +50 ~~-22~~

126 lines not on this page · raw message

Greg Kroah-Hartman

author maintainer

2020-02-27 14:16 UTC #96 lore raw

PATCH 94/150 ext4: fix mount failure with quota configured as module

From: Jan Kara <[email protected]>

commit 9db176bceb5c5df4990486709da386edadc6bd1d upstream.

When CONFIG_QFMT_V2 is configured as a module, the test in ext4_feature_set_ok() fails and so mount of filesystems with quota or project features fails. Fix the test to use IS_ENABLED macro which works properly even for modules.

Link https://lore.kernel.org/r/[email protected] open here

Fixes d65d87a07476 ("ext4: improve explanation of a mount failure caused by a misconfigured kernel")

Signed-off-by Jan Kara <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/ext4/super.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

fs/ext4/super.c +1 -1

@@ -2989,7 +2989,7 @@ static int ext4_feature_set_ok(struct su
 		return 0;
 	}
 
-#if !defined(CONFIG_QUOTA) || !defined(CONFIG_QFMT_V2)
+#if !IS_ENABLED(CONFIG_QUOTA) || !IS_ENABLED(CONFIG_QFMT_V2)
 	if (!readonly && (ext4_has_feature_quota(sb) ||
 			  ext4_has_feature_project(sb))) {
 		ext4_msg(sb, KERN_ERR,

Greg Kroah-Hartman

author maintainer

2020-02-27 14:16 UTC #97 lore raw

PATCH 95/150 ext4: rename s_journal_flag_rwsem to s_writepages_rwsem

From: Eric Biggers <[email protected]>

commit bbd55937de8f2754adc5792b0f8e5ff7d9c0420e upstream.

In preparation for making s_journal_flag_rwsem synchronize ext4_writepages() with changes to both the EXTENTS and JOURNAL_DATA flags (rather than just JOURNAL_DATA as it does currently), rename it to s_writepages_rwsem.

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Eric Biggers <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/ext4/ext4.h  |    2 +-
 fs/ext4/inode.c |   14 +++++++-------
 fs/ext4/super.c |    6 +++---
 3 files changed, 11 insertions(+), 11 deletions(-)

fs/ext4/ext4.h +1 -1

@@ -1554,7 +1554,7 @@ struct ext4_sb_info {
 	struct ratelimit_state s_msg_ratelimit_state;
 
 	/* Barrier between changing inodes' journal flags and writepages ops. */
-	struct percpu_rw_semaphore s_journal_flag_rwsem;
+	struct percpu_rw_semaphore s_writepages_rwsem;
 	struct dax_device *s_daxdev;
 };

fs/ext4/inode.c +7 -7

@@ -2627,7 +2627,7 @@ static int ext4_writepages(struct addres
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
 
-	percpu_down_read(&sbi->s_journal_flag_rwsem);
+	percpu_down_read(&sbi->s_writepages_rwsem);
 	trace_ext4_writepages(inode, wbc);
 
 	/*

@@ -2848,7 +2848,7 @@ unplug:
 out_writepages:
 	trace_ext4_writepages_result(inode, wbc, ret,
 				     nr_to_write - wbc->nr_to_write);
-	percpu_up_read(&sbi->s_journal_flag_rwsem);
+	percpu_up_read(&sbi->s_writepages_rwsem);
 	return ret;
 }

@@ -2863,13 +2863,13 @@ static int ext4_dax_writepages(struct ad
 	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
 		return -EIO;
 
-	percpu_down_read(&sbi->s_journal_flag_rwsem);
+	percpu_down_read(&sbi->s_writepages_rwsem);
 	trace_ext4_writepages(inode, wbc);
 
 	ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, wbc);
 	trace_ext4_writepages_result(inode, wbc, ret,
 				     nr_to_write - wbc->nr_to_write);
-	percpu_up_read(&sbi->s_journal_flag_rwsem);
+	percpu_up_read(&sbi->s_writepages_rwsem);
 	return ret;
 }

@@ -5830,7 +5830,7 @@ int ext4_change_inode_journal_flag(struc
 		}
 	}
 
-	percpu_down_write(&sbi->s_journal_flag_rwsem);
+	percpu_down_write(&sbi->s_writepages_rwsem);
 	jbd2_journal_lock_updates(journal);
 
 	/*

@@ -5847,7 +5847,7 @@ int ext4_change_inode_journal_flag(struc
 		err = jbd2_journal_flush(journal);
 		if (err < 0) {
 			jbd2_journal_unlock_updates(journal);
-			percpu_up_write(&sbi->s_journal_flag_rwsem);
+			percpu_up_write(&sbi->s_writepages_rwsem);
 			return err;
 		}
 		ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA);

@@ -5855,7 +5855,7 @@ int ext4_change_inode_journal_flag(struc
 	ext4_set_aops(inode);
 
 	jbd2_journal_unlock_updates(journal);
-	percpu_up_write(&sbi->s_journal_flag_rwsem);
+	percpu_up_write(&sbi->s_writepages_rwsem);
 
 	if (val)
 		up_write(&EXT4_I(inode)->i_mmap_sem);

fs/ext4/super.c +3 -3

@@ -1018,7 +1018,7 @@ static void ext4_put_super(struct super_
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
-	percpu_free_rwsem(&sbi->s_journal_flag_rwsem);
+	percpu_free_rwsem(&sbi->s_writepages_rwsem);
 #ifdef CONFIG_QUOTA
 	for (i = 0; i < EXT4_MAXQUOTAS; i++)
 		kfree(get_qf_name(sb, sbi, i));

@@ -4581,7 +4581,7 @@ no_journal:
 		err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
 					  GFP_KERNEL);
 	if (!err)
-		err = percpu_init_rwsem(&sbi->s_journal_flag_rwsem);
+		err = percpu_init_rwsem(&sbi->s_writepages_rwsem);
 
 	if (err) {
 		ext4_msg(sb, KERN_ERR, "insufficient memory");

@@ -4681,7 +4681,7 @@ failed_mount6:
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
-	percpu_free_rwsem(&sbi->s_journal_flag_rwsem);
+	percpu_free_rwsem(&sbi->s_writepages_rwsem);
 failed_mount5:
 	ext4_ext_release(sb);
 	ext4_release_system_zone(sb);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:16 UTC #98 lore raw

PATCH 96/150 ext4: fix race between writepages and enabling EXT4_EXTENTS_FL

From: Eric Biggers <[email protected]>

commit cb85f4d23f794e24127f3e562cb3b54b0803f456 upstream.

If EXT4_EXTENTS_FL is set on an inode while ext4_writepages() is running on it, the following warning in ext4_add_complete_io() can be hit:

WARNING: CPU: 1 PID: 0 at fs/ext4/page-io.c:234 ext4_put_io_end_defer+0xf0/0x120

Here's a minimal reproducer (not 100% reliable) (root isn't required):

while true; do
sync
done &
while true; do
rm -f file
touch file
chattr -e file
echo X >> file
chattr +e file
done

The problem is that in ext4_writepages(), ext4_should_dioread_nolock() (which only returns true on extent-based files) is checked once to set the number of reserved journal credits, and also again later to select the flags for ext4_map_blocks() and copy the reserved journal handle to ext4_io_end::handle. But if EXT4_EXTENTS_FL is being concurrently set, the first check can see dioread_nolock disabled while the later one can see it enabled, causing the reserved handle to unexpectedly be NULL.

Since changing EXT4_EXTENTS_FL is uncommon, and there may be other races related to doing so as well, fix this by synchronizing changing EXT4_EXTENTS_FL with ext4_writepages() via the existing s_writepages_rwsem (previously called s_journal_flag_rwsem).

This was originally reported by syzbot without a reproducer at
https://syzkaller.appspot.com/bug?extid=2202a584a00fffd19fbf,
but now that dioread_nolock is the default I also started seeing this when running syzkaller locally.

Link https://lore.kernel.org/r/[email protected] open here

Reported-by [email protected]

Fixes 6b523df4fb5a ("ext4: use transaction reservation for extent conversion in ext4_end_io")

Signed-off-by Eric Biggers <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/ext4/ext4.h    |    5 ++++-
 fs/ext4/migrate.c |   27 +++++++++++++++++++--------
 2 files changed, 23 insertions(+), 9 deletions(-)

fs/ext4/ext4.h +4 -1

@@ -1553,7 +1553,10 @@ struct ext4_sb_info {
 	struct ratelimit_state s_warning_ratelimit_state;
 	struct ratelimit_state s_msg_ratelimit_state;
 
-	/* Barrier between changing inodes' journal flags and writepages ops. */
+	/*
+	 * Barrier between writepages ops and changing any inode's JOURNAL_DATA
+	 * or EXTENTS flag.
+	 */
 	struct percpu_rw_semaphore s_writepages_rwsem;
 	struct dax_device *s_daxdev;
 };

fs/ext4/migrate.c +19 -8

@@ -407,6 +407,7 @@ static int free_ext_block(handle_t *hand
 
 int ext4_ext_migrate(struct inode *inode)
 {
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	handle_t *handle;
 	int retval = 0, i;
 	__le32 *i_data;

@@ -431,6 +432,8 @@ int ext4_ext_migrate(struct inode *inode
 		 */
 		return retval;
 
+	percpu_down_write(&sbi->s_writepages_rwsem);
+
 	/*
 	 * Worst case we can touch the allocation bitmaps, a bgd
 	 * block, and a block to link in the orphan list.  We do need

@@ -441,7 +444,7 @@ int ext4_ext_migrate(struct inode *inode
 
 	if (IS_ERR(handle)) {
 		retval = PTR_ERR(handle);
-		return retval;
+		goto out_unlock;
 	}
 	goal = (((inode->i_ino - 1) / EXT4_INODES_PER_GROUP(inode->i_sb)) *
 		EXT4_INODES_PER_GROUP(inode->i_sb)) + 1;

@@ -452,7 +455,7 @@ int ext4_ext_migrate(struct inode *inode
 	if (IS_ERR(tmp_inode)) {
 		retval = PTR_ERR(tmp_inode);
 		ext4_journal_stop(handle);
-		return retval;
+		goto out_unlock;
 	}
 	i_size_write(tmp_inode, i_size_read(inode));
 	/*

@@ -494,7 +497,7 @@ int ext4_ext_migrate(struct inode *inode
 		 */
 		ext4_orphan_del(NULL, tmp_inode);
 		retval = PTR_ERR(handle);
-		goto out;
+		goto out_tmp_inode;
 	}
 
 	ei = EXT4_I(inode);

@@ -576,10 +579,11 @@ err_out:
 	ext4_ext_tree_init(handle, tmp_inode);
 out_stop:
 	ext4_journal_stop(handle);
-out:
+out_tmp_inode:
 	unlock_new_inode(tmp_inode);
 	iput(tmp_inode);
-
+out_unlock:
+	percpu_up_write(&sbi->s_writepages_rwsem);
 	return retval;
 }

@@ -589,7 +593,8 @@ out:
 int ext4_ind_migrate(struct inode *inode)
 {
 	struct ext4_extent_header	*eh;
-	struct ext4_super_block		*es = EXT4_SB(inode->i_sb)->s_es;
+	struct ext4_sb_info		*sbi = EXT4_SB(inode->i_sb);
+	struct ext4_super_block		*es = sbi->s_es;
 	struct ext4_inode_info		*ei = EXT4_I(inode);
 	struct ext4_extent		*ex;
 	unsigned int			i, len;

@@ -613,9 +618,13 @@ int ext4_ind_migrate(struct inode *inode
 	if (test_opt(inode->i_sb, DELALLOC))
 		ext4_alloc_da_blocks(inode);
 
+	percpu_down_write(&sbi->s_writepages_rwsem);
+
 	handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
-	if (IS_ERR(handle))
-		return PTR_ERR(handle);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		goto out_unlock;
+	}
 
 	down_write(&EXT4_I(inode)->i_data_sem);
 	ret = ext4_ext_check_inode(inode);

@@ -650,5 +659,7 @@ int ext4_ind_migrate(struct inode *inode
 errout:
 	ext4_journal_stop(handle);
 	up_write(&EXT4_I(inode)->i_data_sem);
+out_unlock:
+	percpu_up_write(&sbi->s_writepages_rwsem);
 	return ret;
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:16 UTC #99 lore raw

PATCH 97/150 drm/i915/execlists: Always force a context reload when rewinding RING_TAIL

From: Chris Wilson <[email protected]>

commit b1339ecac661e1cf3e1dc78ac56bff3aeeaeb92c upstream.

If we rewind the RING_TAIL on a context, due to a preemption event, we must force the context restore for the RING_TAIL update to be properly handled. Rather than note which preemption events may cause us to rewind the tail, compare the new request's tail with the previously submitted RING_TAIL, as it turns out that timeslicing was causing unexpected rewinds.

   <idle>-0       0d.s2 1280851190us : __execlists_submission_tasklet: 0000:00:02.0 rcs0: expired last=130:4698, prio=3, hint=3
   <idle>-0       0d.s2 1280851192us : __i915_request_unsubmit: 0000:00:02.0 rcs0: fence 66:119966, current 119964
   <idle>-0       0d.s2 1280851195us : __i915_request_unsubmit: 0000:00:02.0 rcs0: fence 130:4698, current 4695
   <idle>-0       0d.s2 1280851198us : __i915_request_unsubmit: 0000:00:02.0 rcs0: fence 130:4696, current 4695

^---- Note we unwind 2 requests from the same context

<idle>-0 0d.s2 1280851208us : __i915_request_submit: 0000:00:02.0 rcs0: fence 130:4696, current 4695
<idle>-0 0d.s2 1280851213us : __i915_request_submit: 0000:00:02.0 rcs0: fence 134:1508, current 1506
^---- But to apply the new timeslice, we have to replay the first request
before the new client can start -- the unexpected RING_TAIL rewind

   <idle>-0       0d.s2 1280851219us : trace_ports: 0000:00:02.0 rcs0: submit { 130:4696*, 134:1508 }
 synmark2-5425    2..s. 1280851239us : process_csb: 0000:00:02.0 rcs0: cs-irq head=5, tail=0
 synmark2-5425    2..s. 1280851240us : process_csb: 0000:00:02.0 rcs0: csb[0]: status=0x00008002:0x00000000

^---- Preemption event for the ELSP update; note the lite-restore

 synmark2-5425    2..s. 1280851243us : trace_ports: 0000:00:02.0 rcs0: preempted { 130:4698, 66:119966 }
 synmark2-5425    2..s. 1280851246us : trace_ports: 0000:00:02.0 rcs0: promote { 130:4696*, 134:1508 }
 synmark2-5425    2.... 1280851462us : __i915_request_commit: 0000:00:02.0 rcs0: fence 130:4700, current 4695
 synmark2-5425    2.... 1280852111us : __i915_request_commit: 0000:00:02.0 rcs0: fence 130:4702, current 4695
 synmark2-5425    2.Ns1 1280852296us : process_csb: 0000:00:02.0 rcs0: cs-irq head=0, tail=2
 synmark2-5425    2.Ns1 1280852297us : process_csb: 0000:00:02.0 rcs0: csb[1]: status=0x00000814:0x00000000
 synmark2-5425    2.Ns1 1280852299us : trace_ports: 0000:00:02.0 rcs0: completed { 130:4696!, 134:1508 }
 synmark2-5425    2.Ns1 1280852301us : process_csb: 0000:00:02.0 rcs0: csb[2]: status=0x00000818:0x00000040
 synmark2-5425    2.Ns1 1280852302us : trace_ports: 0000:00:02.0 rcs0: completed { 134:1508, 0:0 }
 synmark2-5425    2.Ns1 1280852313us : process_csb: process_csb:2336 GEM_BUG_ON(!i915_request_completed(*execlists->active) && !reset_in_progress(execlists))

Fixes 8ee36e048c98 ("drm/i915/execlists: Minimalistic timeslicing")

Referenecs: 82c69bf58650 ("drm/i915/gt: Detect if we miss WaIdleLiteRestore")

Link https://patchwork.freedesktop.org/patch/msgid/[email protected]

Cc Mika Kuoppala <[email protected]>

Reviewed-by Mika Kuoppala <[email protected]>

Cc <[email protected]> # v5.4+

(cherry picked from commit 5ba32c7be81e53ea8a27190b0f6be98e6c6779af)

Signed-off-by Jani Nikula <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/i915/gt/intel_lrc.c        |   18 ++++++++----------
 drivers/gpu/drm/i915/gt/intel_ring.c       |    1 +
 drivers/gpu/drm/i915/gt/intel_ring.h       |    8 ++++++++
 drivers/gpu/drm/i915/gt/intel_ring_types.h |    1 +
 4 files changed, 18 insertions(+), 10 deletions(-)

drivers/gpu/drm/i915/gt/intel_lrc.c +8 ~~-10~~

@@ -1157,7 +1157,7 @@ static u64 execlists_update_context(stru
 {
 	struct intel_context *ce = rq->hw_context;
 	u64 desc = ce->lrc_desc;
-	u32 tail;
+	u32 tail, prev;
 
 	/*
 	 * WaIdleLiteRestore:bdw,skl

@@ -1170,9 +1170,15 @@ static u64 execlists_update_context(stru
 	 * subsequent resubmissions (for lite restore). Should that fail us,
 	 * and we try and submit the same tail again, force the context
 	 * reload.
+	 *
+	 * If we need to return to a preempted context, we need to skip the
+	 * lite-restore and force it to reload the RING_TAIL. Otherwise, the
+	 * HW has a tendency to ignore us rewinding the TAIL to the end of
+	 * an earlier request.
 	 */
 	tail = intel_ring_set_tail(rq->ring, rq->tail);
-	if (unlikely(ce->lrc_reg_state[CTX_RING_TAIL] == tail))
+	prev = ce->lrc_reg_state[CTX_RING_TAIL];
+	if (unlikely(intel_ring_direction(rq->ring, tail, prev) <= 0))
 		desc |= CTX_DESC_FORCE_RESTORE;
 	ce->lrc_reg_state[CTX_RING_TAIL] = tail;
 	rq->tail = rq->wa_tail;

@@ -1651,14 +1657,6 @@ static void execlists_dequeue(struct int
 			 */
 			__unwind_incomplete_requests(engine);
 
-			/*
-			 * If we need to return to the preempted context, we
-			 * need to skip the lite-restore and force it to
-			 * reload the RING_TAIL. Otherwise, the HW has a
-			 * tendency to ignore us rewinding the TAIL to the
-			 * end of an earlier request.
-			 */
-			last->hw_context->lrc_desc |= CTX_DESC_FORCE_RESTORE;
 			last = NULL;
 		} else if (need_timeslice(engine, last) &&
 			   timer_expired(&engine->execlists.timer)) {

drivers/gpu/drm/i915/gt/intel_ring.c +1 -0

@@ -145,6 +145,7 @@ intel_engine_create_ring(struct intel_en
 
 	kref_init(&ring->ref);
 	ring->size = size;
+	ring->wrap = BITS_PER_TYPE(ring->size) - ilog2(size);
 
 	/*
 	 * Workaround an erratum on the i830 which causes a hang if

drivers/gpu/drm/i915/gt/intel_ring.h +8 -0

@@ -56,6 +56,14 @@ static inline u32 intel_ring_wrap(const
 	return pos & (ring->size - 1);
 }
 
+static inline int intel_ring_direction(const struct intel_ring *ring,
+				       u32 next, u32 prev)
+{
+	typecheck(typeof(ring->size), next);
+	typecheck(typeof(ring->size), prev);
+	return (next - prev) << ring->wrap;
+}
+
 static inline bool
 intel_ring_offset_valid(const struct intel_ring *ring,
 			unsigned int pos)

drivers/gpu/drm/i915/gt/intel_ring_types.h +1 -0

@@ -45,6 +45,7 @@ struct intel_ring {
 
 	u32 space;
 	u32 size;
+	u32 wrap;
 	u32 effective_size;
 };

Greg Kroah-Hartman

author maintainer

2020-02-27 14:16 UTC #100 lore raw

PATCH 98/150 KVM: nVMX: Refactor IO bitmap checks into helper function

From: Oliver Upton <[email protected]>

commit e71237d3ff1abf9f3388337cfebf53b96df2020d upstream.

Checks against the IO bitmap are useful for both instruction emulation and VM-exit reflection. Refactor the IO bitmap checks into a helper function.

Signed-off-by Oliver Upton <[email protected]>

Reviewed-by Vitaly Kuznetsov <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/x86/kvm/vmx/nested.c |   39 +++++++++++++++++++++++++--------------
 arch/x86/kvm/vmx/nested.h |    2 ++
 2 files changed, 27 insertions(+), 14 deletions(-)

arch/x86/kvm/vmx/nested.c +25 ~~-14~~

@@ -5304,24 +5304,17 @@ fail:
 	return 1;
 }
 
-
-static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
-				       struct vmcs12 *vmcs12)
+/*
+ * Return true if an IO instruction with the specified port and size should cause
+ * a VM-exit into L1.
+ */
+bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port,
+				 int size)
 {
-	unsigned long exit_qualification;
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	gpa_t bitmap, last_bitmap;
-	unsigned int port;
-	int size;
 	u8 b;
 
-	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
-		return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING);
-
-	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-
-	port = exit_qualification >> 16;
-	size = (exit_qualification & 7) + 1;
-
 	last_bitmap = (gpa_t)-1;
 	b = -1;

@@ -5348,6 +5341,24 @@ static bool nested_vmx_exit_handled_io(s
 	return false;
 }
 
+static bool nested_vmx_exit_handled_io(struct kvm_vcpu *vcpu,
+				       struct vmcs12 *vmcs12)
+{
+	unsigned long exit_qualification;
+	unsigned int port;
+	int size;
+
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
+		return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING);
+
+	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+
+	port = exit_qualification >> 16;
+	size = (exit_qualification & 7) + 1;
+
+	return nested_vmx_check_io_bitmaps(vcpu, port, size);
+}
+
 /*
  * Return 1 if we should exit from L2 to L1 to handle an MSR access access,
  * rather than handle it ourselves in L0. I.e., check whether L1 expressed

arch/x86/kvm/vmx/nested.h +2 -0

@@ -34,6 +34,8 @@ int vmx_get_vmx_msr(struct nested_vmx_ms
 int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
 			u32 vmx_instruction_info, bool wr, int len, gva_t *ret);
 void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu);
+bool nested_vmx_check_io_bitmaps(struct kvm_vcpu *vcpu, unsigned int port,
+				 int size);
 
 static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
 {

Greg Kroah-Hartman

author maintainer

2020-02-27 14:16 UTC #101 lore raw

PATCH 99/150 KVM: nVMX: Check IO instruction VM-exit conditions

From: Oliver Upton <[email protected]>

commit 35a571346a94fb93b5b3b6a599675ef3384bc75c upstream.

Consult the 'unconditional IO exiting' and 'use IO bitmaps' VM-execution controls when checking instruction interception. If the 'use IO bitmaps' VM-execution control is 1, check the instruction access against the IO bitmaps to determine if the instruction causes a VM-exit.

Signed-off-by Oliver Upton <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/x86/kvm/vmx/nested.c |    2 -
 arch/x86/kvm/vmx/vmx.c    |   57 +++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 52 insertions(+), 7 deletions(-)

arch/x86/kvm/vmx/nested.c +1 -1

@@ -5345,7 +5345,7 @@ static bool nested_vmx_exit_handled_io(s
 				       struct vmcs12 *vmcs12)
 {
 	unsigned long exit_qualification;
-	unsigned int port;
+	unsigned short port;
 	int size;
 
 	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))

arch/x86/kvm/vmx/vmx.c +51 -6

75 lines not on this page · raw message

Greg Kroah-Hartman

author maintainer

2020-02-27 14:21 UTC #102 lore raw

PATCH 100/150 KVM: nVMX: clear PIN_BASED_POSTED_INTR from nested pinbased_ctls only when apicv is globally disabled

From: Vitaly Kuznetsov <[email protected]>

commit a4443267800af240072280c44521caab61924e55 upstream.

When apicv is disabled on a vCPU (e.g. by enabling KVM_CAP_HYPERV_SYNIC*), nothing happens to VMX MSRs on the already existing vCPUs, however, all new ones are created with PIN_BASED_POSTED_INTR filtered out. This is very confusing and results in the following picture inside the guest:

$ rdmsr -ax 0x48d
ff00000016
7f00000016
7f00000016
7f00000016

This is observed with QEMU and 4-vCPU guest: QEMU creates vCPU0, does KVM_CAP_HYPERV_SYNIC2 and then creates the remaining three.

L1 hypervisor may only check CPU0's controls to find out what features are available and it will be very confused later. Switch to setting PIN_BASED_POSTED_INTR control based on global 'enable_apicv' setting.

Signed-off-by Vitaly Kuznetsov <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/x86/kvm/vmx/capabilities.h |    1 +
 arch/x86/kvm/vmx/nested.c       |    5 ++---
 arch/x86/kvm/vmx/nested.h       |    3 +--
 arch/x86/kvm/vmx/vmx.c          |   10 ++++------
 4 files changed, 8 insertions(+), 11 deletions(-)

arch/x86/kvm/vmx/capabilities.h +1 -0

@@ -12,6 +12,7 @@ extern bool __read_mostly enable_ept;
 extern bool __read_mostly enable_unrestricted_guest;
 extern bool __read_mostly enable_ept_ad_bits;
 extern bool __read_mostly enable_pml;
+extern bool __read_mostly enable_apicv;
 extern int __read_mostly pt_mode;
 
 #define PT_MODE_SYSTEM		0

arch/x86/kvm/vmx/nested.c +2 -3

@@ -5979,8 +5979,7 @@ void nested_vmx_set_vmcs_shadowing_bitma
  * bit in the high half is on if the corresponding bit in the control field
  * may be on. See also vmx_control_verify().
  */
-void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
-				bool apicv)
+void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps)
 {
 	/*
 	 * Note that as a general rule, the high half of the MSRs (bits in

@@ -6007,7 +6006,7 @@ void nested_vmx_setup_ctls_msrs(struct n
 		PIN_BASED_EXT_INTR_MASK |
 		PIN_BASED_NMI_EXITING |
 		PIN_BASED_VIRTUAL_NMIS |
-		(apicv ? PIN_BASED_POSTED_INTR : 0);
+		(enable_apicv ? PIN_BASED_POSTED_INTR : 0);
 	msrs->pinbased_ctls_high |=
 		PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR |
 		PIN_BASED_VMX_PREEMPTION_TIMER;

arch/x86/kvm/vmx/nested.h +1 -2

@@ -17,8 +17,7 @@ enum nvmx_vmentry_status {
 };
 
 void vmx_leave_nested(struct kvm_vcpu *vcpu);
-void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
-				bool apicv);
+void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps);
 void nested_vmx_hardware_unsetup(void);
 __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
 void nested_vmx_set_vmcs_shadowing_bitmap(void);

arch/x86/kvm/vmx/vmx.c +4 -6

@@ -95,7 +95,7 @@ module_param(emulate_invalid_guest_state
 static bool __read_mostly fasteoi = 1;
 module_param(fasteoi, bool, S_IRUGO);
 
-static bool __read_mostly enable_apicv = 1;
+bool __read_mostly enable_apicv = 1;
 module_param(enable_apicv, bool, S_IRUGO);
 
 /*

@@ -6803,8 +6803,7 @@ static struct kvm_vcpu *vmx_create_vcpu(
 
 	if (nested)
 		nested_vmx_setup_ctls_msrs(&vmx->nested.msrs,
-					   vmx_capability.ept,
-					   kvm_vcpu_apicv_active(&vmx->vcpu));
+					   vmx_capability.ept);
 	else
 		memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs));

@@ -6884,8 +6883,7 @@ static int __init vmx_check_processor_co
 	if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0)
 		return -EIO;
 	if (nested)
-		nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept,
-					   enable_apicv);
+		nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept);
 	if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) {
 		printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n",
 				smp_processor_id());

@@ -7792,7 +7790,7 @@ static __init int hardware_setup(void)
 
 	if (nested) {
 		nested_vmx_setup_ctls_msrs(&vmcs_config.nested,
-					   vmx_capability.ept, enable_apicv);
+					   vmx_capability.ept);
 
 		r = nested_vmx_hardware_setup(kvm_vmx_exit_handlers);
 		if (r)

Greg Kroah-Hartman

author maintainer

2020-02-27 14:21 UTC #103 lore raw

PATCH 101/150 KVM: nVMX: handle nested posted interrupts when apicv is disabled for L1

From: Vitaly Kuznetsov <[email protected]>

commit 91a5f413af596ad01097e59bf487eb07cb3f1331 upstream.

Even when APICv is disabled for L1 it can (and, actually, is) still available for L2, this means we need to always call vmx_deliver_nested_posted_interrupt() when attempting an interrupt delivery.

Signed-off-by Vitaly Kuznetsov <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/x86/include/asm/kvm_host.h |    2 +-
 arch/x86/kvm/lapic.c            |    5 +----
 arch/x86/kvm/svm.c              |    7 ++++++-
 arch/x86/kvm/vmx/vmx.c          |   13 +++++++++----
 4 files changed, 17 insertions(+), 10 deletions(-)

arch/x86/include/asm/kvm_host.h +1 -1

@@ -1115,7 +1115,7 @@ struct kvm_x86_ops {
 	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
 	void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
 	void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
-	void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
+	int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
 	int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu);
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr);

arch/x86/kvm/lapic.c +1 -4

@@ -1049,11 +1049,8 @@ static int __apic_accept_irq(struct kvm_
 						       apic->regs + APIC_TMR);
 		}
 
-		if (vcpu->arch.apicv_active)
-			kvm_x86_ops->deliver_posted_interrupt(vcpu, vector);
-		else {
+		if (kvm_x86_ops->deliver_posted_interrupt(vcpu, vector)) {
 			kvm_lapic_set_irr(vector, apic);
-
 			kvm_make_request(KVM_REQ_EVENT, vcpu);
 			kvm_vcpu_kick(vcpu);
 		}

arch/x86/kvm/svm.c +6 -1

@@ -5160,8 +5160,11 @@ static void svm_load_eoi_exitmap(struct
 	return;
 }
 
-static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
+static int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
 {
+	if (!vcpu->arch.apicv_active)
+		return -1;
+
 	kvm_lapic_set_irr(vec, vcpu->arch.apic);
 	smp_mb__after_atomic();

@@ -5173,6 +5176,8 @@ static void svm_deliver_avic_intr(struct
 		put_cpu();
 	} else
 		kvm_vcpu_wake_up(vcpu);
+
+	return 0;
 }
 
 static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)

arch/x86/kvm/vmx/vmx.c +9 -4

@@ -3848,24 +3848,29 @@ static int vmx_deliver_nested_posted_int
  * 2. If target vcpu isn't running(root mode), kick it to pick up the
  * interrupt from PIR in next vmentry.
  */
-static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
+static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	int r;
 
 	r = vmx_deliver_nested_posted_interrupt(vcpu, vector);
 	if (!r)
-		return;
+		return 0;
+
+	if (!vcpu->arch.apicv_active)
+		return -1;
 
 	if (pi_test_and_set_pir(vector, &vmx->pi_desc))
-		return;
+		return 0;
 
 	/* If a previous notification has sent the IPI, nothing to do.  */
 	if (pi_test_and_set_on(&vmx->pi_desc))
-		return;
+		return 0;
 
 	if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
 		kvm_vcpu_kick(vcpu);
+
+	return 0;
 }
 
 /*

Greg Kroah-Hartman

author maintainer

2020-02-27 14:19 UTC #104 lore raw

PATCH 102/150 KVM: apic: avoid calculating pending eoi from an uninitialized val

From: Miaohe Lin <[email protected]>

commit 23520b2def95205f132e167cf5b25c609975e959 upstream.

When pv_eoi_get_user() fails, 'val' may remain uninitialized and the return value of pv_eoi_get_pending() becomes random. Fix the issue by initializing the variable.

Reviewed-by Vitaly Kuznetsov <[email protected]>

Signed-off-by Miaohe Lin <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/x86/kvm/lapic.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

arch/x86/kvm/lapic.c +3 -1

@@ -630,9 +630,11 @@ static inline bool pv_eoi_enabled(struct
 static bool pv_eoi_get_pending(struct kvm_vcpu *vcpu)
 {
 	u8 val;
-	if (pv_eoi_get_user(vcpu, &val) < 0)
+	if (pv_eoi_get_user(vcpu, &val) < 0) {
 		printk(KERN_WARNING "Can't read EOI MSR value: 0x%llx\n",
 			   (unsigned long long)vcpu->arch.pv_eoi.msr_val);
+		return false;
+	}
 	return val & 0x1;
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:17 UTC #105 lore raw

PATCH 103/150 crypto: chacha20poly1305 - prevent integer overflow on large input

From: Jason A. Donenfeld <[email protected]>

commit c9cc0517bba9f0213f1e55172feceb99e5512daf upstream.

This code assigns src_len (size_t) to sl (int), which causes problems when src_len is very large. Probably nobody in the kernel should be passing this much data to chacha20poly1305 all in one go anyway, so I don't think we need to change the algorithm or introduce larger types or anything. But we should at least error out early in this case and print a warning so that we get reports if this does happen and can look into why anybody is possibly passing it that much data or if they're accidently passing -1 or similar.

Fixes d95312a3ccc0 ("crypto: lib/chacha20poly1305 - reimplement crypt_from_sg() routine")

Cc Ard Biesheuvel <[email protected]>

Cc [email protected] # 5.5+

Signed-off-by Jason A. Donenfeld <[email protected]>

Acked-by Ard Biesheuvel <[email protected]>

Signed-off-by Herbert Xu <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 lib/crypto/chacha20poly1305.c |    3 +++
 1 file changed, 3 insertions(+)

lib/crypto/chacha20poly1305.c +3 -0

@@ -235,6 +235,9 @@ bool chacha20poly1305_crypt_sg_inplace(s
 		__le64 lens[2];
 	} b __aligned(16);
 
+	if (WARN_ON(src_len > INT_MAX))
+		return false;
+
 	chacha_load_key(b.k, key);
 
 	b.iv[0] = 0;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:17 UTC #106 lore raw

PATCH 104/150 btrfs: destroy qgroup extent records on transaction abort

From: Jeff Mahoney <[email protected]>

commit 81f7eb00ff5bb8326e82503a32809421d14abb8a upstream.

We clean up the delayed references when we abort a transaction but we leave the pending qgroup extent records behind, leaking memory.

This patch destroys the extent records when we destroy the delayed refs and makes sure ensure they're gone before releasing the transaction.

Fixes 3368d001ba5d ("btrfs: qgroup: Record possible quota-related extent for qgroup.")

CC [email protected] # 4.4+

Signed-off-by Jeff Mahoney <[email protected]>

[ Rebased to latest upstream, remove to_qgroup() helper, use
rbtree_postorder_for_each_entry_safe() wrapper ]

Signed-off-by Qu Wenruo <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/btrfs/disk-io.c     |    1 +
 fs/btrfs/qgroup.c      |   13 +++++++++++++
 fs/btrfs/qgroup.h      |    1 +
 fs/btrfs/transaction.c |    2 ++
 4 files changed, 17 insertions(+)

fs/btrfs/disk-io.c +1 -0

@@ -4272,6 +4272,7 @@ static int btrfs_destroy_delayed_refs(st
 		cond_resched();
 		spin_lock(&delayed_refs->lock);
 	}
+	btrfs_qgroup_destroy_extent_records(trans);
 
 	spin_unlock(&delayed_refs->lock);

fs/btrfs/qgroup.c +13 -0

@@ -4016,3 +4016,16 @@ out:
 	}
 	return ret;
 }
+
+void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans)
+{
+	struct btrfs_qgroup_extent_record *entry;
+	struct btrfs_qgroup_extent_record *next;
+	struct rb_root *root;
+
+	root = &trans->delayed_refs.dirty_extent_root;
+	rbtree_postorder_for_each_entry_safe(entry, next, root, node) {
+		ulist_free(entry->old_roots);
+		kfree(entry);
+	}
+}

fs/btrfs/qgroup.h +1 -0

@@ -414,5 +414,6 @@ int btrfs_qgroup_add_swapped_blocks(stru
 		u64 last_snapshot);
 int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans,
 		struct btrfs_root *root, struct extent_buffer *eb);
+void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans);
 
 #endif

fs/btrfs/transaction.c +2 -0

@@ -121,6 +121,8 @@ void btrfs_put_transaction(struct btrfs_
 		BUG_ON(!list_empty(&transaction->list));
 		WARN_ON(!RB_EMPTY_ROOT(
 				&transaction->delayed_refs.href_root.rb_root));
+		WARN_ON(!RB_EMPTY_ROOT(
+				&transaction->delayed_refs.dirty_extent_root));
 		if (transaction->delayed_refs.pending_csums)
 			btrfs_err(transaction->fs_info,
 				  "pending csums is %llu",

Greg Kroah-Hartman

author maintainer

2020-02-27 14:18 UTC #107 lore raw

PATCH 105/150 btrfs: fix bytes_may_use underflow in prealloc error condtition

From: Josef Bacik <[email protected]>

commit b778cf962d71a0e737923d55d0432f3bd287258e upstream.

I hit the following warning while running my error injection stress testing:

  WARNING: CPU: 3 PID: 1453 at fs/btrfs/space-info.h:108 btrfs_free_reserved_data_space_noquota+0xfd/0x160 [btrfs]
  RIP: 0010:btrfs_free_reserved_data_space_noquota+0xfd/0x160 [btrfs]
  Call Trace:
  btrfs_free_reserved_data_space+0x4f/0x70 [btrfs]
  __btrfs_prealloc_file_range+0x378/0x470 [btrfs]
  elfcorehdr_read+0x40/0x40
  ? elfcorehdr_read+0x40/0x40
  ? btrfs_commit_transaction+0xca/0xa50 [btrfs]
  ? dput+0xb4/0x2a0
  ? btrfs_log_dentry_safe+0x55/0x70 [btrfs]
  ? btrfs_sync_file+0x30e/0x420 [btrfs]
  ? do_fsync+0x38/0x70
  ? __x64_sys_fdatasync+0x13/0x20
  ? do_syscall_64+0x5b/0x1b0
  ? entry_SYSCALL_64_after_hwframe+0x44/0xa9

This happens if we fail to insert our reserved file extent. At this point we've already converted our reservation from ->bytes_may_use to ->bytes_reserved. However once we break we will attempt to free everything from [cur_offset, end] from ->bytes_may_use, but our extent reservation will overlap part of this.

Fix this problem by adding ins.offset (our extent allocation size) to cur_offset so we remove the actual remaining part from ->bytes_may_use.

I validated this fix using my inject-error.py script

python inject-error.py -o should_fail_bio -t cache_save_setup -t \
	__btrfs_prealloc_file_range \
	-t insert_reserved_file_extent.constprop.0 \
	-r "-5" ./run-fsstress.sh

where run-fsstress.sh simply mounts and runs fsstress on a disk.

CC [email protected] # 4.4+

Signed-off-by Josef Bacik <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/btrfs/inode.c |   16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

fs/btrfs/inode.c +13 -3

@@ -10487,6 +10487,7 @@ static int __btrfs_prealloc_file_range(s
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_key ins;
 	u64 cur_offset = start;
+	u64 clear_offset = start;
 	u64 i_size;
 	u64 cur_bytes;
 	u64 last_alloc = (u64)-1;

@@ -10521,6 +10522,15 @@ static int __btrfs_prealloc_file_range(s
 				btrfs_end_transaction(trans);
 			break;
 		}
+
+		/*
+		 * We've reserved this space, and thus converted it from
+		 * ->bytes_may_use to ->bytes_reserved.  Any error that happens
+		 * from here on out we will only need to clear our reservation
+		 * for the remaining unreserved area, so advance our
+		 * clear_offset by our extent size.
+		 */
+		clear_offset += ins.offset;
 		btrfs_dec_block_group_reservations(fs_info, ins.objectid);
 
 		last_alloc = ins.offset;

@@ -10600,9 +10610,9 @@ next:
 		if (own_trans)
 			btrfs_end_transaction(trans);
 	}
-	if (cur_offset < end)
-		btrfs_free_reserved_data_space(inode, NULL, cur_offset,
-			end - cur_offset + 1);
+	if (clear_offset < end)
+		btrfs_free_reserved_data_space(inode, NULL, clear_offset,
+			end - clear_offset + 1);
 	return ret;
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:19 UTC #108 lore raw

PATCH 106/150 btrfs: reset fs_root to NULL on error in open_ctree

From: Josef Bacik <[email protected]>

commit 315bf8ef914f31d51d084af950703aa1e09a728c upstream.

While running my error injection script I hit a panic when we tried to clean up the fs_root when freeing the fs_root. This is because fs_info->fs_root == PTR_ERR(-EIO), which isn't great. Fix this by setting fs_info->fs_root = NULL; if we fail to read the root.

CC [email protected] # 4.4+

Reviewed-by Nikolay Borisov <[email protected]>

Reviewed-by Johannes Thumshirn <[email protected]>

Signed-off-by Josef Bacik <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/btrfs/disk-io.c |    1 +
 1 file changed, 1 insertion(+)

fs/btrfs/disk-io.c +1 -0

@@ -3200,6 +3200,7 @@ int __cold open_ctree(struct super_block
 	if (IS_ERR(fs_info->fs_root)) {
 		err = PTR_ERR(fs_info->fs_root);
 		btrfs_warn(fs_info, "failed to read fs tree: %d", err);
+		fs_info->fs_root = NULL;
 		goto fail_qgroup;
 	}

Greg Kroah-Hartman

author maintainer

2020-02-27 14:18 UTC #109 lore raw

PATCH 107/150 btrfs: do not check delayed items are empty for single transaction cleanup

From: Josef Bacik <[email protected]>

commit 1e90315149f3fe148e114a5de86f0196d1c21fa5 upstream.

btrfs_assert_delayed_root_empty() will check if the delayed root is completely empty, but this is a filesystem-wide check. On cleanup we may have allowed other transactions to begin, for whatever reason, and thus the delayed root is not empty.

So remove this check from cleanup_one_transation(). This however can stay in btrfs_cleanup_transaction(), because it checks only after all of the transactions have been properly cleaned up, and thus is valid.

CC [email protected] # 4.4+

Reviewed-by Johannes Thumshirn <[email protected]>

Reviewed-by Nikolay Borisov <[email protected]>

Signed-off-by Josef Bacik <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/btrfs/disk-io.c |    1 -
 1 file changed, 1 deletion(-)

fs/btrfs/disk-io.c +0 -1

@@ -4499,7 +4499,6 @@ void btrfs_cleanup_one_transaction(struc
 	wake_up(&fs_info->transaction_wait);
 
 	btrfs_destroy_delayed_inodes(fs_info);
-	btrfs_assert_delayed_root_empty(fs_info);
 
 	btrfs_destroy_marked_extents(fs_info, &cur_trans->dirty_pages,
 				     EXTENT_DIRTY);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:19 UTC #110 lore raw

PATCH 108/150 Btrfs: fix btrfs_wait_ordered_range() so that it waits for all ordered extents

Link https://github.com/kdave/btrfs-progs/issues/228#issuecomment-569777554

From: Filipe Manana <[email protected]>

commit e75fd33b3f744f644061a4f9662bd63f5434f806 upstream.

In btrfs_wait_ordered_range() once we find an ordered extent that has finished with an error we exit the loop and don't wait for any other ordered extents that might be still in progress.

All the users of btrfs_wait_ordered_range() expect that there are no more ordered extents in progress after that function returns. So past fixes such like the ones from the two following commits:

ff612ba7849964 ("btrfs: fix panic during relocation after ENOSPC before
writeback happens")

28aeeac1dd3080 ("Btrfs: fix panic when starting bg cache writeout after
IO error")

don't work when there are multiple ordered extents in the range.

Fix that by making btrfs_wait_ordered_range() wait for all ordered extents even after it finds one that had an error.

CC [email protected] # 4.4+

Signed-off-by Filipe Manana <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/btrfs/ordered-data.c |    7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

fs/btrfs/ordered-data.c +6 -1

@@ -686,10 +686,15 @@ int btrfs_wait_ordered_range(struct inod
 		}
 		btrfs_start_ordered_extent(inode, ordered, 1);
 		end = ordered->file_offset;
+		/*
+		 * If the ordered extent had an error save the error but don't
+		 * exit without waiting first for all other ordered extents in
+		 * the range to complete.
+		 */
 		if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags))
 			ret = -EIO;
 		btrfs_put_ordered_extent(ordered);
-		if (ret || end == 0 || end == start)
+		if (end == 0 || end == start)
 			break;
 		end--;
 	}

Greg Kroah-Hartman

author maintainer

2020-02-27 14:18 UTC #111 lore raw

PATCH 109/150 Btrfs: fix deadlock during fast fsync when logging prealloc extents beyond eof

From: Filipe Manana <[email protected]>

commit a5ae50dea9111db63d30d700766dd5509602f7ad upstream.

While logging the prealloc extents of an inode during a fast fsync we call btrfs_truncate_inode_items(), through btrfs_log_prealloc_extents(), while holding a read lock on a leaf of the inode's root (not the log root, the fs/subvol root), and then that function locks the file range in the inode's iotree. This can lead to a deadlock when:

* the fsync is ranged

* the file has prealloc extents beyond eof

* writeback for a range different from the fsync range starts during the fsync

* the size of the file is not sector size aligned

Because when finishing an ordered extent we lock first a file range and then try to COW the fs/subvol tree to insert an extent item.

The following diagram shows how the deadlock can happen.

CPU 1 CPU 2

btrfs_sync_file()
--> for range [0, 1MiB)

--> inode has a size of
1MiB and has 1 prealloc
extent beyond the
i_size, starting at offset
4MiB

flushes all delalloc for the
range [0MiB, 1MiB) and waits
for the respective ordered
extents to complete

--> before task at CPU 1 locks the
inode, a write into file range [1MiB, 2MiB + 1KiB) is made

--> i_size is updated to 2MiB + 1KiB

--> writeback is started for that
range, [1MiB, 2MiB + 4KiB) --> end offset rounded up to
be sector size aligned

btrfs_log_dentry_safe()
btrfs_log_inode_parent()
btrfs_log_inode()

btrfs_log_changed_extents()
btrfs_log_prealloc_extents()
--> does a search on the
inode's root
--> holds a read lock on
leaf X

btrfs_finish_ordered_io()
--> locks range [1MiB, 2MiB + 4KiB)
--> end offset rounded up
to be sector size aligned

--> tries to cow leaf X, through
insert_reserved_file_extent() --> already locked by the
task at CPU 1

btrfs_truncate_inode_items()

--> gets an i_size of
2MiB + 1KiB, which is
not sector size
aligned

--> tries to lock file
range [2MiB, (u64)-1)
--> the start range
is rounded down
from 2MiB + 1K
to 2MiB to be sector
size aligned

--> but the subrange
[2MiB, 2MiB + 4KiB) is
already locked by
task at CPU 2 which
is waiting to get a
write lock on leaf X
for which we are
holding a read lock

*** deadlock ***

This results in a stack trace like the following, triggered by test case generic/561 from fstests:

  [ 2779.973608] INFO: task kworker/u8:6:247 blocked for more than 120 seconds.
  [ 2779.979536]       Not tainted 5.6.0-rc2-btrfs-next-53 #1
  [ 2779.984503] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
  [ 2779.990136] kworker/u8:6    D    0   247      2 0x80004000
  [ 2779.990457] Workqueue: btrfs-endio-write btrfs_work_helper [btrfs]
  [ 2779.990466] Call Trace:
  [ 2779.990491]  ? __schedule+0x384/0xa30
  [ 2779.990521]  schedule+0x33/0xe0
  [ 2779.990616]  btrfs_tree_read_lock+0x19e/0x2e0 [btrfs]
  [ 2779.990632]  ? remove_wait_queue+0x60/0x60
  [ 2779.990730]  btrfs_read_lock_root_node+0x2f/0x40 [btrfs]
  [ 2779.990782]  btrfs_search_slot+0x510/0x1000 [btrfs]
  [ 2779.990869]  btrfs_lookup_file_extent+0x4a/0x70 [btrfs]
  [ 2779.990944]  __btrfs_drop_extents+0x161/0x1060 [btrfs]
  [ 2779.990987]  ? mark_held_locks+0x6d/0xc0
  [ 2779.990994]  ? __slab_alloc.isra.49+0x99/0x100
  [ 2779.991060]  ? insert_reserved_file_extent.constprop.19+0x64/0x300 [btrfs]
  [ 2779.991145]  insert_reserved_file_extent.constprop.19+0x97/0x300 [btrfs]
  [ 2779.991222]  ? start_transaction+0xdd/0x5c0 [btrfs]
  [ 2779.991291]  btrfs_finish_ordered_io+0x4f4/0x840 [btrfs]
  [ 2779.991405]  btrfs_work_helper+0xaa/0x720 [btrfs]
  [ 2779.991432]  process_one_work+0x26d/0x6a0
  [ 2779.991460]  worker_thread+0x4f/0x3e0
  [ 2779.991481]  ? process_one_work+0x6a0/0x6a0
  [ 2779.991489]  kthread+0x103/0x140
  [ 2779.991499]  ? kthread_create_worker_on_cpu+0x70/0x70
  [ 2779.991515]  ret_from_fork+0x3a/0x50
  (...)
  [ 2780.026211] INFO: task fsstress:17375 blocked for more than 120 seconds.
  [ 2780.027480]       Not tainted 5.6.0-rc2-btrfs-next-53 #1
  [ 2780.028482] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
  [ 2780.030035] fsstress        D    0 17375  17373 0x00004000
  [ 2780.030038] Call Trace:
  [ 2780.030044]  ? __schedule+0x384/0xa30
  [ 2780.030052]  schedule+0x33/0xe0
  [ 2780.030075]  lock_extent_bits+0x20c/0x320 [btrfs]
  [ 2780.030094]  ? btrfs_truncate_inode_items+0xf4/0x1150 [btrfs]
  [ 2780.030098]  ? rcu_read_lock_sched_held+0x59/0xa0
  [ 2780.030102]  ? remove_wait_queue+0x60/0x60
  [ 2780.030122]  btrfs_truncate_inode_items+0x133/0x1150 [btrfs]
  [ 2780.030151]  ? btrfs_set_path_blocking+0xb2/0x160 [btrfs]
  [ 2780.030165]  ? btrfs_search_slot+0x379/0x1000 [btrfs]
  [ 2780.030195]  btrfs_log_changed_extents.isra.8+0x841/0x93e [btrfs]
  [ 2780.030202]  ? do_raw_spin_unlock+0x49/0xc0
  [ 2780.030215]  ? btrfs_get_num_csums+0x10/0x10 [btrfs]
  [ 2780.030239]  btrfs_log_inode+0xf83/0x1124 [btrfs]
  [ 2780.030251]  ? __mutex_unlock_slowpath+0x45/0x2a0
  [ 2780.030275]  btrfs_log_inode_parent+0x2a0/0xe40 [btrfs]
  [ 2780.030282]  ? dget_parent+0xa1/0x370
  [ 2780.030309]  btrfs_log_dentry_safe+0x4a/0x70 [btrfs]
  [ 2780.030329]  btrfs_sync_file+0x3f3/0x490 [btrfs]
  [ 2780.030339]  do_fsync+0x38/0x60
  [ 2780.030343]  __x64_sys_fdatasync+0x13/0x20
  [ 2780.030345]  do_syscall_64+0x5c/0x280
  [ 2780.030348]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
  [ 2780.030356] RIP: 0033:0x7f2d80f6d5f0
  [ 2780.030361] Code: Bad RIP value.
  [ 2780.030362] RSP: 002b:00007ffdba3c8548 EFLAGS: 00000246 ORIG_RAX: 000000000000004b
  [ 2780.030364] RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 00007f2d80f6d5f0
  [ 2780.030365] RDX: 00007ffdba3c84b0 RSI: 00007ffdba3c84b0 RDI: 0000000000000003
  [ 2780.030367] RBP: 000000000000004a R08: 0000000000000001 R09: 00007ffdba3c855c
  [ 2780.030368] R10: 0000000000000078 R11: 0000000000000246 R12: 00000000000001f4
  [ 2780.030369] R13: 0000000051eb851f R14: 00007ffdba3c85f0 R15: 0000557a49220d90

So fix this by making btrfs_truncate_inode_items() not lock the range in the inode's iotree when the target root is a log root, since it's not needed to lock the range for log roots as the protection from the inode's lock and log_mutex are all that's needed.

Fixes 28553fa992cb28 ("Btrfs: fix race between shrinking truncate and fiemap")

CC [email protected] # 4.4+

Signed-off-by Filipe Manana <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/btrfs/inode.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

fs/btrfs/inode.c +5 -5

@@ -4775,8 +4775,9 @@ int btrfs_truncate_inode_items(struct bt
 		return -ENOMEM;
 	path->reada = READA_BACK;
 
-	lock_extent_bits(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1,
-			 &cached_state);
+	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
+		lock_extent_bits(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1,
+				 &cached_state);
 
 	/*
 	 * We want to drop from the next block forward in case this new size is

@@ -5040,11 +5041,10 @@ out:
 		if (!ret && last_size > new_size)
 			last_size = new_size;
 		btrfs_ordered_update_i_size(inode, last_size, NULL);
+		unlock_extent_cached(&BTRFS_I(inode)->io_tree, lock_start,
+				     (u64)-1, &cached_state);
 	}
 
-	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lock_start, (u64)-1,
-			     &cached_state);
-
 	btrfs_free_path(path);
 	return ret;
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:19 UTC #112 lore raw

PATCH 110/150 Revert "dmaengine: imx-sdma: Fix memory leak"

From: Greg Kroah-Hartman <[email protected]>

This reverts commit 7ac78dd1e0992fd6d2ae375cc0dd6456c632f605 which is commit 02939cd167095f16328a1bd5cab5a90b550606df upstream.

Andreas writes:
This patch breaks our imx6 board with the attached trace. Reverting the patch makes it boot again.

Reported-by Andreas Tobler <[email protected]>

Cc Sascha Hauer <[email protected]>

Cc Robin Gong <[email protected]>

Cc Vinod Koul <[email protected]>

Cc Sasha Levin <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/dma/imx-sdma.c |   19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

drivers/dma/imx-sdma.c +8 ~~-11~~

@@ -760,8 +760,12 @@ static void sdma_start_desc(struct sdma_
 		return;
 	}
 	sdmac->desc = desc = to_sdma_desc(&vd->tx);
-
-	list_del(&vd->node);
+	/*
+	 * Do not delete the node in desc_issued list in cyclic mode, otherwise
+	 * the desc allocated will never be freed in vchan_dma_desc_free_list
+	 */
+	if (!(sdmac->flags & IMX_DMA_SG_LOOP))
+		list_del(&vd->node);
 
 	sdma->channel_control[channel].base_bd_ptr = desc->bd_phys;
 	sdma->channel_control[channel].current_bd_ptr = desc->bd_phys;

@@ -1067,6 +1071,7 @@ static void sdma_channel_terminate_work(
 
 	spin_lock_irqsave(&sdmac->vc.lock, flags);
 	vchan_get_all_descriptors(&sdmac->vc, &head);
+	sdmac->desc = NULL;
 	spin_unlock_irqrestore(&sdmac->vc.lock, flags);
 	vchan_dma_desc_free_list(&sdmac->vc, &head);
 	sdmac->context_loaded = false;

@@ -1075,19 +1080,11 @@ static void sdma_channel_terminate_work(
 static int sdma_disable_channel_async(struct dma_chan *chan)
 {
 	struct sdma_channel *sdmac = to_sdma_chan(chan);
-	unsigned long flags;
-
-	spin_lock_irqsave(&sdmac->vc.lock, flags);
 
 	sdma_disable_channel(chan);
 
-	if (sdmac->desc) {
-		vchan_terminate_vdesc(&sdmac->desc->vd);
-		sdmac->desc = NULL;
+	if (sdmac->desc)
 		schedule_work(&sdmac->terminate_worker);
-	}
-
-	spin_unlock_irqrestore(&sdmac->vc.lock, flags);
 
 	return 0;
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:19 UTC #113 lore raw

PATCH 111/150 drm/i915/selftests: Add a mock i915_vma to the mock_ring

From: Chris Wilson <[email protected]>

commit 1fdea0cb0dba0d42ffcfb619b349c1a2afa2492e upstream.

Add a i915_vma to the mock_engine/mock_ring so that the core code can always assume the presence of ring->vma.

Fixes 8ccfc20a7d56 ("drm/i915/gt: Mark ring->vma as active while pinned")

Link https://patchwork.freedesktop.org/patch/msgid/[email protected]

Reviewed-by Mika Kuoppala <[email protected]>

(cherry picked from commit b63b4feaef7363d2cf46dd76bb6e87e060b2b0de)

Signed-off-by Jani Nikula <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/i915/gt/mock_engine.c |   17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

drivers/gpu/drm/i915/gt/mock_engine.c +16 -1

@@ -59,11 +59,26 @@ static struct intel_ring *mock_ring(stru
 	ring->vaddr = (void *)(ring + 1);
 	atomic_set(&ring->pin_count, 1);
 
+	ring->vma = i915_vma_alloc();
+	if (!ring->vma) {
+		kfree(ring);
+		return NULL;
+	}
+	i915_active_init(&ring->vma->active, NULL, NULL);
+
 	intel_ring_update_space(ring);
 
 	return ring;
 }
 
+static void mock_ring_free(struct intel_ring *ring)
+{
+	i915_active_fini(&ring->vma->active);
+	i915_vma_free(ring->vma);
+
+	kfree(ring);
+}
+
 static struct i915_request *first_request(struct mock_engine *engine)
 {
 	return list_first_entry_or_null(&engine->hw_queue,

@@ -121,7 +136,7 @@ static void mock_context_destroy(struct
 	GEM_BUG_ON(intel_context_is_pinned(ce));
 
 	if (test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
-		kfree(ce->ring);
+		mock_ring_free(ce->ring);
 		mock_timeline_unpin(ce->timeline);
 	}

Greg Kroah-Hartman

author maintainer

2020-02-27 14:17 UTC #114 lore raw

PATCH 112/150 drm/i915/gvt: more locking for ppgtt mm LRU list

Link http://patchwork.freedesktop.org/patch/msgid/[email protected]

From: Igor Druzhinin <[email protected]>

commit 0e9d7bb293f3f9c3ee376b126141407efb265f31 upstream.

When the lock was introduced in commit 72aabfb862e40 ("drm/i915/gvt: Add mutual lock for ppgtt mm LRU list") one place got lost.

Fixes 72aabfb862e4 ("drm/i915/gvt: Add mutual lock for ppgtt mm LRU list")

Signed-off-by Igor Druzhinin <[email protected]>

Reviewed-by Zhenyu Wang <[email protected]>

Signed-off-by Zhenyu Wang <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/i915/gvt/gtt.c |    4 ++++
 1 file changed, 4 insertions(+)

drivers/gpu/drm/i915/gvt/gtt.c +4 -0

@@ -1956,7 +1956,11 @@ void _intel_vgpu_mm_release(struct kref
 
 	if (mm->type == INTEL_GVT_MM_PPGTT) {
 		list_del(&mm->ppgtt_mm.list);
+
+		mutex_lock(&mm->vgpu->gvt->gtt.ppgtt_mm_lock);
 		list_del(&mm->ppgtt_mm.lru_list);
+		mutex_unlock(&mm->vgpu->gvt->gtt.ppgtt_mm_lock);
+
 		invalidate_ppgtt_mm(mm);
 	} else {
 		vfree(mm->ggtt_mm.virtual_ggtt);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:21 UTC #115 lore raw

PATCH 113/150 ice: Remove possible null dereference

From: Tony Nguyen <[email protected]>

commit 0a6ea04e3bbd20833d2b49296e5adc1c5bb86386 upstream.

Commit 1f45ebe0d8fb ("ice: add extra check for null Rx descriptor") moved the call to ice_construct_skb() under a null check as Coverity reported a possible use of null skb. However, the original call was not deleted, do so now.

Fixes 1f45ebe0d8fb ("ice: add extra check for null Rx descriptor")

Reported-by Bruce Allan <[email protected]>

Signed-off-by Tony Nguyen <[email protected]>

Tested-by Andrew Bowers <[email protected]>

Signed-off-by Jeff Kirsher <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/net/ethernet/intel/ice/ice_txrx.c |    2 --
 1 file changed, 2 deletions(-)

drivers/net/ethernet/intel/ice/ice_txrx.c +0 -2

@@ -1078,8 +1078,6 @@ construct_skb:
 				skb = ice_build_skb(rx_ring, rx_buf, &xdp);
 			else
 				skb = ice_construct_skb(rx_ring, rx_buf, &xdp);
-		} else {
-			skb = ice_construct_skb(rx_ring, rx_buf, &xdp);
 		}
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {

Greg Kroah-Hartman

author maintainer

2020-02-27 14:17 UTC #116 lore raw

PATCH 114/150 drm/bridge: tc358767: fix poll timeouts

Link https://patchwork.freedesktop.org/patch/msgid/[email protected]

From: Tomi Valkeinen <[email protected]>

commit 8a6483ac634acda3f599f50082c652d2d37199c7 upstream.

Link training fails with:

Link training timeout waiting for LT_LOOPDONE!
main link enable error: -110

This is caused by too tight timeouts, which were changed recently in aa92213f388b ("drm/bridge: tc358767: Simplify polling in tc_link_training()").

With a quick glance, the commit does not change the timeouts. However, the method of delaying/sleeping is different, and as the timeout in the previous implementation was not explicit, the new version in practice has much tighter timeout.

The same change was made to other parts in the driver, but the link training timeout is the only one I have seen causing issues. Nevertheless, 1 us sleep is not very sane, and the timeouts look pretty tight, so lets fix all the timeouts.

One exception was the aux busy poll, where the poll sleep was much longer than necessary (or optimal).

I measured the times on my setup, and now the sleep times are set to such values that they result in multiple loops, but not too many (say, 5-10 loops). The timeouts were all increased to 100ms, which should be more than enough for all of these, but in case of bad errors, shouldn't stop the driver as multi-second timeouts could do.

Signed-off-by Tomi Valkeinen <[email protected]>

Fixes aa92213f388b ("drm/bridge: tc358767: Simplify polling in tc_link_training()")

Tested-by Andrey Smirnov <[email protected]>

Reviewed-by Neil Armstrong <[email protected]>

Signed-off-by Neil Armstrong <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/bridge/tc358767.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

drivers/gpu/drm/bridge/tc358767.c +4 -4

@@ -297,7 +297,7 @@ static inline int tc_poll_timeout(struct
 
 static int tc_aux_wait_busy(struct tc_data *tc)
 {
-	return tc_poll_timeout(tc, DP0_AUXSTATUS, AUX_BUSY, 0, 1000, 100000);
+	return tc_poll_timeout(tc, DP0_AUXSTATUS, AUX_BUSY, 0, 100, 100000);
 }
 
 static int tc_aux_write_data(struct tc_data *tc, const void *data,

@@ -640,7 +640,7 @@ static int tc_aux_link_setup(struct tc_d
 	if (ret)
 		goto err;
 
-	ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 1, 1000);
+	ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 100, 100000);
 	if (ret == -ETIMEDOUT) {
 		dev_err(tc->dev, "Timeout waiting for PHY to become ready");
 		return ret;

@@ -876,7 +876,7 @@ static int tc_wait_link_training(struct
 	int ret;
 
 	ret = tc_poll_timeout(tc, DP0_LTSTAT, LT_LOOPDONE,
-			      LT_LOOPDONE, 1, 1000);
+			      LT_LOOPDONE, 500, 100000);
 	if (ret) {
 		dev_err(tc->dev, "Link training timeout waiting for LT_LOOPDONE!\n");
 		return ret;

@@ -949,7 +949,7 @@ static int tc_main_link_enable(struct tc
 	dp_phy_ctrl &= ~(DP_PHY_RST | PHY_M1_RST | PHY_M0_RST);
 	ret = regmap_write(tc->regmap, DP_PHY_CTRL, dp_phy_ctrl);
 
-	ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 1, 1000);
+	ret = tc_poll_timeout(tc, DP_PHY_CTRL, PHY_RDY, PHY_RDY, 500, 100000);
 	if (ret) {
 		dev_err(dev, "timeout waiting for phy become ready");
 		return ret;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:17 UTC #117 lore raw

PATCH 115/150 drm/i915/gem: Require per-engine reset support for non-persistent contexts

From: Chris Wilson <[email protected]>

commit dea8d5ce46d7e7f7270b9804df7d1174f88bfd99 upstream.

To enable non-persistent contexts, we require a means of cancelling any inflight work from that context. This is first done "gracefully" by using preemption to kick the active context off the engine, and then forcefully by resetting the engine if it is active. If we are unable to reset the engine to remove hostile userspace, we should not allow userspace to opt into using non-persistent contexts.

If the per-engine reset fails, we still do a full GPU reset, but that is rare and usually indicative of much deeper issues. The damage is already done. However, the goal of the interface to allow long running compute jobs without causing collateral damage elsewhere, and if we are unable to support that we should make that known by not providing the interface (and falsely pretending we can).

Fixes a0e047156cde ("drm/i915/gem: Make context persistence optional")

Link https://patchwork.freedesktop.org/patch/msgid/[email protected]

Cc Joonas Lahtinen <[email protected]>

Cc Jon Bloomfield <[email protected]>

Reviewed-by Joonas Lahtinen <[email protected]>

(cherry picked from commit d1b9b5f127bc3797fc274cfa4f363e039f045c3a)

Signed-off-by Jani Nikula <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/i915/gem/i915_gem_context.c |   16 ++++++++++++++++
 1 file changed, 16 insertions(+)

drivers/gpu/drm/i915/gem/i915_gem_context.c +16 -0

@@ -484,6 +484,22 @@ static int __context_set_persistence(str
 		if (!(ctx->i915->caps.scheduler & I915_SCHEDULER_CAP_PREEMPTION))
 			return -ENODEV;
 
+		/*
+		 * If the cancel fails, we then need to reset, cleanly!
+		 *
+		 * If the per-engine reset fails, all hope is lost! We resort
+		 * to a full GPU reset in that unlikely case, but realistically
+		 * if the engine could not reset, the full reset does not fare
+		 * much better. The damage has been done.
+		 *
+		 * However, if we cannot reset an engine by itself, we cannot
+		 * cleanup a hanging persistent context without causing
+		 * colateral damage, and we should not pretend we can by
+		 * exposing the interface.
+		 */
+		if (!intel_has_reset_engine(&ctx->i915->gt))
+			return -ENODEV;
+
 		i915_gem_context_clear_persistence(ctx);
 	}

Greg Kroah-Hartman

author maintainer

2020-02-27 14:21 UTC #118 lore raw

PATCH 116/150 drm/i915/gt: Protect defer_request() from new waiters

From: Chris Wilson <[email protected]>

commit 19b5f3b419a61808ff2713f1f30b8a88fe14ac9b upstream.

Mika spotted

<4>[17436.705441] general protection fault: 0000 [#1] PREEMPT SMP PTI
<4>[17436.705447] CPU: 2 PID: 0 Comm: swapper/2 Not tainted 5.5.0+ #1
<4>[17436.705449] Hardware name: System manufacturer System Product Name/Z170M-PLUS, BIOS 3805 05/16/2018
<4>[17436.705512] RIP: 0010:__execlists_submission_tasklet+0xc4d/0x16e0 [i915]
<4>[17436.705516] Code: c5 4c 8d 60 e0 75 17 e9 8c 07 00 00 49 8b 44 24 20 49 39 c5 4c 8d 60 e0 0f 84 7a 07 00 00 49 8b 5c 24 08 49 8b 87 80 00 00 00 <48> 39 83 d8 fe ff ff 75 d9 48 8b 83 88 fe ff ff a8 01 0f 84 b6 05
<4>[17436.705518] RSP: 0018:ffffc9000012ce80 EFLAGS: 00010083
<4>[17436.705521] RAX: ffff88822ae42000 RBX: 5a5a5a5a5a5a5a5a RCX: dead000000000122
<4>[17436.705523] RDX: ffff88822ae42588 RSI: ffff8881e32a7908 RDI: ffff8881c429fd48
<4>[17436.705525] RBP: ffffc9000012cf00 R08: ffff88822ae42588 R09: 00000000fffffffe
<4>[17436.705527] R10: ffff8881c429fb80 R11: 00000000a677cf08 R12: ffff8881c42a0aa8
<4>[17436.705529] R13: ffff8881c429fd38 R14: ffff88822ae42588 R15: ffff8881c429fb80
<4>[17436.705532] FS:  0000000000000000(0000) GS:ffff88822ed00000(0000) knlGS:0000000000000000
<4>[17436.705534] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
<4>[17436.705536] CR2: 00007f858c76d000 CR3: 0000000005610003 CR4: 00000000003606e0
<4>[17436.705538] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
<4>[17436.705540] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
<4>[17436.705542] Call Trace:
<4>[17436.705545]  <IRQ>
<4>[17436.705603]  execlists_submission_tasklet+0xc0/0x130 [i915]

which is us consuming a partially initialised new waiter in defer_requests(). We can prevent this by initialising the i915_dependency prior to making it visible, and since we are using a concurrent list_add/iterator mark them up to the compiler.

Fixes 8ee36e048c98 ("drm/i915/execlists: Minimalistic timeslicing")

Link https://patchwork.freedesktop.org/patch/msgid/[email protected]

Cc Mika Kuoppala <[email protected]>

Reviewed-by Mika Kuoppala <[email protected]>

(cherry picked from commit f14f27b1663269a81ed62d3961fe70250a1a0623)

Signed-off-by Jani Nikula <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/i915/gt/intel_lrc.c   |    7 ++++++-
 drivers/gpu/drm/i915/i915_scheduler.c |    6 ++++--
 2 files changed, 10 insertions(+), 3 deletions(-)

drivers/gpu/drm/i915/gt/intel_lrc.c +6 -1

@@ -1433,6 +1433,11 @@ last_active(const struct intel_engine_ex
 	return *last;
 }
 
+#define for_each_waiter(p__, rq__) \
+	list_for_each_entry_lockless(p__, \
+				     &(rq__)->sched.waiters_list, \
+				     wait_link)
+
 static void defer_request(struct i915_request *rq, struct list_head * const pl)
 {
 	LIST_HEAD(list);

@@ -1450,7 +1455,7 @@ static void defer_request(struct i915_re
 		GEM_BUG_ON(i915_request_is_active(rq));
 		list_move_tail(&rq->sched.link, pl);
 
-		list_for_each_entry(p, &rq->sched.waiters_list, wait_link) {
+		for_each_waiter(p, rq) {
 			struct i915_request *w =
 				container_of(p->waiter, typeof(*w), sched);

drivers/gpu/drm/i915/i915_scheduler.c +4 -2

@@ -415,8 +415,6 @@ bool __i915_sched_node_add_dependency(st
 
 	if (!node_signaled(signal)) {
 		INIT_LIST_HEAD(&dep->dfs_link);
-		list_add(&dep->wait_link, &signal->waiters_list);
-		list_add(&dep->signal_link, &node->signalers_list);
 		dep->signaler = signal;
 		dep->waiter = node;
 		dep->flags = flags;

@@ -426,6 +424,10 @@ bool __i915_sched_node_add_dependency(st
 		    !node_started(signal))
 			node->flags |= I915_SCHED_HAS_SEMAPHORE_CHAIN;
 
+		/* All set, now publish. Beware the lockless walkers. */
+		list_add(&dep->signal_link, &node->signalers_list);
+		list_add_rcu(&dep->wait_link, &signal->waiters_list);
+
 		/*
 		 * As we do not allow WAIT to preempt inflight requests,
 		 * once we have executed a request, along with triggering

Greg Kroah-Hartman

author maintainer

2020-02-27 14:17 UTC #119 lore raw

PATCH 117/150 drm/i915/ehl: Update port clock voltage level requirements

Link https://patchwork.freedesktop.org/patch/msgid/[email protected]

From: Matt Roper <[email protected]>

commit 58e9121c32a245fab47f29ab4ad29dd62470a7e8 upstream.

Voltage level depends not only on the cdclk, but also on the DDI clock. Last time the bspec voltage level table for EHL was updated, we only updated the cdclk requirements, but forgot to account for the new port clock criteria.

Bspec: 21809

Fixes d147483884ed ("drm/i915/ehl: Update voltage level checks")

Cc José Roberto de Souza <[email protected]>

Signed-off-by Matt Roper <[email protected]>

Reviewed-by José Roberto de Souza <[email protected]>

(cherry picked from commit 9d5fd37ed7e26efdbe90f492d7eb8b53dcdb61d6)

Signed-off-by Jani Nikula <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/i915/display/intel_ddi.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

drivers/gpu/drm/i915/display/intel_ddi.c +3 -1

@@ -4227,7 +4227,9 @@ static bool intel_ddi_is_audio_enabled(s
 void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv,
 					 struct intel_crtc_state *crtc_state)
 {
-	if (INTEL_GEN(dev_priv) >= 11 && crtc_state->port_clock > 594000)
+	if (IS_ELKHARTLAKE(dev_priv) && crtc_state->port_clock > 594000)
+		crtc_state->min_voltage_level = 3;
+	else if (INTEL_GEN(dev_priv) >= 11 && crtc_state->port_clock > 594000)
 		crtc_state->min_voltage_level = 1;
 	else if (IS_CANNONLAKE(dev_priv) && crtc_state->port_clock > 594000)
 		crtc_state->min_voltage_level = 2;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:17 UTC #120 lore raw

PATCH 118/150 drm/msm/dpu: fix BGR565 vs RGB565 confusion

From: Rob Clark <[email protected]>

commit 8fc7036ee652207ca992fbb9abb64090c355a9e0 upstream.

The component order between the two was swapped, resulting in incorrect color when games with 565 visual hit the overlay path instead of GPU composition.

Fixes 25fdd5933e4c ("drm/msm: Add SDM845 DPU support")

Signed-off-by Rob Clark <[email protected]>

Reviewed-by Sean Paul <[email protected]>

Signed-off-by Rob Clark <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c +2 -2

@@ -255,13 +255,13 @@ static const struct dpu_format dpu_forma
 
 	INTERLEAVED_RGB_FMT(RGB565,
 		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
-		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
 		false, 2, 0,
 		DPU_FETCH_LINEAR, 1),
 
 	INTERLEAVED_RGB_FMT(BGR565,
 		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
-		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
 		false, 2, 0,
 		DPU_FETCH_LINEAR, 1),

Greg Kroah-Hartman

author maintainer

2020-02-27 14:17 UTC #121 lore raw

PATCH 119/150 scsi: Revert "RDMA/isert: Fix a recently introduced regression related to logout"

Link https://marc.info/?l=target-devel&m=158157054906196

From: Bart Van Assche <[email protected]>

commit 76261ada16dcc3be610396a46d35acc3efbda682 upstream.

Since commit 04060db41178 introduces soft lockups when toggling network interfaces, revert it.

Cc Rahul Kundu <[email protected]>

Cc Mike Marciniszyn <[email protected]>

Cc Sagi Grimberg <[email protected]>

Reported-by Dakshaja Uppalapati <[email protected]>

Fixes 04060db41178 ("scsi: RDMA/isert: Fix a recently introduced regression related to logout")

Signed-off-by Bart Van Assche <[email protected]>

Signed-off-by Martin K. Petersen <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/infiniband/ulp/isert/ib_isert.c |   12 ++++++++++++
 drivers/target/iscsi/iscsi_target.c     |    6 +++---
 2 files changed, 15 insertions(+), 3 deletions(-)

drivers/infiniband/ulp/isert/ib_isert.c +12 -0

@@ -2575,6 +2575,17 @@ isert_wait4logout(struct isert_conn *ise
 	}
 }
 
+static void
+isert_wait4cmds(struct iscsi_conn *conn)
+{
+	isert_info("iscsi_conn %p\n", conn);
+
+	if (conn->sess) {
+		target_sess_cmd_list_set_waiting(conn->sess->se_sess);
+		target_wait_for_sess_cmds(conn->sess->se_sess);
+	}
+}
+
 /**
  * isert_put_unsol_pending_cmds() - Drop commands waiting for
  *     unsolicitate dataout

@@ -2622,6 +2633,7 @@ static void isert_wait_conn(struct iscsi
 
 	ib_drain_qp(isert_conn->qp);
 	isert_put_unsol_pending_cmds(conn);
+	isert_wait4cmds(conn);
 	isert_wait4logout(isert_conn);
 
 	queue_work(isert_release_wq, &isert_conn->release_work);

drivers/target/iscsi/iscsi_target.c +3 -3

@@ -4149,6 +4149,9 @@ int iscsit_close_connection(
 	iscsit_stop_nopin_response_timer(conn);
 	iscsit_stop_nopin_timer(conn);
 
+	if (conn->conn_transport->iscsit_wait_conn)
+		conn->conn_transport->iscsit_wait_conn(conn);
+
 	/*
 	 * During Connection recovery drop unacknowledged out of order
 	 * commands for this connection, and prepare the other commands

@@ -4234,9 +4237,6 @@ int iscsit_close_connection(
 	target_sess_cmd_list_set_waiting(sess->se_sess);
 	target_wait_for_sess_cmds(sess->se_sess);
 
-	if (conn->conn_transport->iscsit_wait_conn)
-		conn->conn_transport->iscsit_wait_conn(conn);
-
 	ahash_request_free(conn->conn_tx_hash);
 	if (conn->conn_rx_hash) {
 		struct crypto_ahash *tfm;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:21 UTC #122 lore raw

PATCH 120/150 scsi: Revert "target: iscsi: Wait for all commands to finish before freeing a session"

Link https://marc.info/?l=target-devel&m=158157054906195

From: Bart Van Assche <[email protected]>

commit 807b9515b7d044cf77df31f1af9d842a76ecd5cb upstream.

Since commit e9d3009cb936 introduced a regression and since the fix for that regression was not perfect, revert this commit.

Cc Rahul Kundu <[email protected]>

Cc Mike Marciniszyn <[email protected]>

Cc Sagi Grimberg <[email protected]>

Reported-by Dakshaja Uppalapati <[email protected]>

Fixes e9d3009cb936 ("scsi: target: iscsi: Wait for all commands to finish before freeing a session")

Signed-off-by Bart Van Assche <[email protected]>

Signed-off-by Martin K. Petersen <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/target/iscsi/iscsi_target.c |   10 ++--------
 include/scsi/iscsi_proto.h          |    1 -
 2 files changed, 2 insertions(+), 9 deletions(-)

drivers/target/iscsi/iscsi_target.c +2 -8

@@ -1165,9 +1165,7 @@ int iscsit_setup_scsi_cmd(struct iscsi_c
 		hdr->cmdsn, be32_to_cpu(hdr->data_length), payload_length,
 		conn->cid);
 
-	if (target_get_sess_cmd(&cmd->se_cmd, true) < 0)
-		return iscsit_add_reject_cmd(cmd,
-				ISCSI_REASON_WAITING_FOR_LOGOUT, buf);
+	target_get_sess_cmd(&cmd->se_cmd, true);
 
 	cmd->sense_reason = transport_lookup_cmd_lun(&cmd->se_cmd,
 						     scsilun_to_int(&hdr->lun));

@@ -2004,9 +2002,7 @@ iscsit_handle_task_mgt_cmd(struct iscsi_
 			      conn->sess->se_sess, 0, DMA_NONE,
 			      TCM_SIMPLE_TAG, cmd->sense_buffer + 2);
 
-	if (target_get_sess_cmd(&cmd->se_cmd, true) < 0)
-		return iscsit_add_reject_cmd(cmd,
-				ISCSI_REASON_WAITING_FOR_LOGOUT, buf);
+	target_get_sess_cmd(&cmd->se_cmd, true);
 
 	/*
 	 * TASK_REASSIGN for ERL=2 / connection stays inside of

@@ -4234,8 +4230,6 @@ int iscsit_close_connection(
 	 * must wait until they have completed.
 	 */
 	iscsit_check_conn_usage_count(conn);
-	target_sess_cmd_list_set_waiting(sess->se_sess);
-	target_wait_for_sess_cmds(sess->se_sess);
 
 	ahash_request_free(conn->conn_tx_hash);
 	if (conn->conn_rx_hash) {

include/scsi/iscsi_proto.h +0 -1

@@ -627,7 +627,6 @@ struct iscsi_reject {
 #define ISCSI_REASON_BOOKMARK_INVALID	9
 #define ISCSI_REASON_BOOKMARK_NO_RESOURCES	10
 #define ISCSI_REASON_NEGOTIATION_RESET	11
-#define ISCSI_REASON_WAITING_FOR_LOGOUT	12
 
 /* Max. number of Key=Value pairs in a text message */
 #define MAX_KEY_VALUE_PAIRS	8192

Greg Kroah-Hartman

author maintainer

2020-02-27 14:17 UTC #123 lore raw

PATCH 121/150 usb: gadget: composite: Fix bMaxPower for SuperSpeedPlus

From: Jack Pham <[email protected]>

commit c724417baf162bd3e035659e22cdf990cfb0d917 upstream.

SuperSpeedPlus peripherals must report their bMaxPower of the configuration descriptor in units of 8mA as per the USB 3.2 specification. The current switch statement in encode_bMaxPower() only checks for USB_SPEED_SUPER but not USB_SPEED_SUPER_PLUS so the latter falls back to USB 2.0 encoding which uses 2mA units. Replace the switch with a simple if/else.

Fixes eae5820b852f ("usb: gadget: composite: Write SuperSpeedPlus config descriptors")

Signed-off-by Jack Pham <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/gadget/composite.c |    8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

drivers/usb/gadget/composite.c +3 -5

@@ -437,12 +437,10 @@ static u8 encode_bMaxPower(enum usb_devi
 		val = CONFIG_USB_GADGET_VBUS_DRAW;
 	if (!val)
 		return 0;
-	switch (speed) {
-	case USB_SPEED_SUPER:
-		return DIV_ROUND_UP(val, 8);
-	default:
+	if (speed < USB_SPEED_SUPER)
 		return DIV_ROUND_UP(val, 2);
-	}
+	else
+		return DIV_ROUND_UP(val, 8);
 }
 
 static int config_buf(struct usb_configuration *config,

Greg Kroah-Hartman

author maintainer

2020-02-27 14:17 UTC #124 lore raw

PATCH 122/150 usb: dwc2: Fix in ISOC request length checking

From: Minas Harutyunyan <[email protected]>

commit 860ef6cd3f90b84a1832f8a6485c90c34d3b588b upstream.

Moved ISOC request length checking from dwc2_hsotg_start_req() function to dwc2_hsotg_ep_queue().

Fixes 4fca54aa58293 ("usb: gadget: s3c-hsotg: add multi count support")

Signed-off-by Minas Harutyunyan <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/usb/dwc2/gadget.c |   12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

drivers/usb/dwc2/gadget.c +7 -5

@@ -1083,11 +1083,6 @@ static void dwc2_hsotg_start_req(struct
 	else
 		packets = 1;	/* send one packet if length is zero. */
 
-	if (hs_ep->isochronous && length > (hs_ep->mc * hs_ep->ep.maxpacket)) {
-		dev_err(hsotg->dev, "req length > maxpacket*mc\n");
-		return;
-	}
-
 	if (dir_in && index != 0)
 		if (hs_ep->isochronous)
 			epsize = DXEPTSIZ_MC(packets);

@@ -1391,6 +1386,13 @@ static int dwc2_hsotg_ep_queue(struct us
 	req->actual = 0;
 	req->status = -EINPROGRESS;
 
+	/* Don't queue ISOC request if length greater than mps*mc */
+	if (hs_ep->isochronous &&
+	    req->length > (hs_ep->mc * hs_ep->ep.maxpacket)) {
+		dev_err(hs->dev, "req length > maxpacket*mc\n");
+		return -EINVAL;
+	}
+
 	/* In DDMA mode for ISOC's don't queue request if length greater
 	 * than descriptor limits.
 	 */

Greg Kroah-Hartman

author maintainer

2020-02-27 14:17 UTC #125 lore raw

PATCH 123/150 staging: rtl8723bs: fix copy of overlapping memory

From: Colin Ian King <[email protected]>

commit 8ae9a588ca35eb9c32dc03299c5e1f4a1e9a9617 upstream.

Currently the rtw_sprintf prints the contents of thread_name onto thread_name and this can lead to a potential copy of a string over itself. Avoid this by printing the literal string RTWHALXT instread of the contents of thread_name.

Addresses-Coverity: ("copy of overlapping memory")

Fixes 554c0a3abf21 ("staging: Add rtl8723bs sdio wifi driver")

Signed-off-by Colin Ian King <[email protected]>

Reviewed-by Hans de Goede <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

drivers/staging/rtl8723bs/hal/rtl8723bs_xmit.c +2 -3

@@ -476,14 +476,13 @@ int rtl8723bs_xmit_thread(void *context)
 	s32 ret;
 	struct adapter *padapter;
 	struct xmit_priv *pxmitpriv;
-	u8 thread_name[20] = "RTWHALXT";
-
+	u8 thread_name[20];
 
 	ret = _SUCCESS;
 	padapter = context;
 	pxmitpriv = &padapter->xmitpriv;
 
-	rtw_sprintf(thread_name, 20, "%s-"ADPT_FMT, thread_name, ADPT_ARG(padapter));
+	rtw_sprintf(thread_name, 20, "RTWHALXT-" ADPT_FMT, ADPT_ARG(padapter));
 	thread_enter(thread_name);
 
 	DBG_871X("start "FUNC_ADPT_FMT"\n", FUNC_ADPT_ARG(padapter));

Greg Kroah-Hartman

author maintainer

2020-02-27 14:17 UTC #126 lore raw

PATCH 124/150 staging: greybus: use after free in gb_audio_manager_remove_all()

From: Dan Carpenter <[email protected]>

commit b7db58105b80fa9232719c8329b995b3addfab55 upstream.

When we call kobject_put() and it's the last reference to the kobject then it calls gb_audio_module_release() and frees module. We dereference "module" on the next line which is a use after free.

Fixes c77f85bbc91a ("greybus: audio: Fix incorrect counting of 'ida'")

Signed-off-by Dan Carpenter <[email protected]>

Acked-by Viresh Kumar <[email protected]>

Reviewed-by Vaibhav Agarwal <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/staging/greybus/audio_manager.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/staging/greybus/audio_manager.c +1 -1

@@ -92,8 +92,8 @@ void gb_audio_manager_remove_all(void)
 
 	list_for_each_entry_safe(module, next, &modules_list, list) {
 		list_del(&module->list);
-		kobject_put(&module->kobj);
 		ida_simple_remove(&module_id, module->id);
+		kobject_put(&module->kobj);
 	}
 
 	is_empty = list_empty(&modules_list);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:17 UTC #127 lore raw

PATCH 125/150 ASoC: atmel: fix atmel_ssc_set_audio link failure

From: Arnd Bergmann <[email protected]>

commit 9437bfda00f3b26eb5f475737ddaaf4dc07fee4f upstream.

The ssc audio driver can call into both pdc and dma backends. With the latest rework, the logic to do this in a safe way avoiding link errors was removed, bringing back link errors that were fixed long ago in commit 061981ff8cc8 ("ASoC: atmel: properly select dma driver state") such as

sound/soc/atmel/atmel_ssc_dai.o: In function `atmel_ssc_set_audio':
atmel_ssc_dai.c:(.text+0xac): undefined reference to `atmel_pcm_pdc_platform_register'

Fix it this time using Makefile hacks and a comment to prevent this from accidentally getting removed again rather than Kconfig hacks.

Fixes 18291410557f ("ASoC: atmel: enable SOC_SSC_PDC and SOC_SSC_DMA in Kconfig")

Signed-off-by Arnd Bergmann <[email protected]>

Signed-off-by Codrin Ciubotariu <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Reviewed-by Michał Mirosław <[email protected]>

Signed-off-by Mark Brown <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 sound/soc/atmel/Kconfig  |    4 ++--
 sound/soc/atmel/Makefile |   10 ++++++++--
 2 files changed, 10 insertions(+), 4 deletions(-)

sound/soc/atmel/Kconfig +2 -2

@@ -10,11 +10,11 @@ config SND_ATMEL_SOC
 if SND_ATMEL_SOC
 
 config SND_ATMEL_SOC_PDC
-	tristate
+	bool
 	depends on HAS_DMA
 
 config SND_ATMEL_SOC_DMA
-	tristate
+	bool
 	select SND_SOC_GENERIC_DMAENGINE_PCM
 
 config SND_ATMEL_SOC_SSC

sound/soc/atmel/Makefile +8 -2

@@ -6,8 +6,14 @@ snd-soc-atmel_ssc_dai-objs := atmel_ssc_
 snd-soc-atmel-i2s-objs := atmel-i2s.o
 snd-soc-mchp-i2s-mcc-objs := mchp-i2s-mcc.o
 
-obj-$(CONFIG_SND_ATMEL_SOC_PDC) += snd-soc-atmel-pcm-pdc.o
-obj-$(CONFIG_SND_ATMEL_SOC_DMA) += snd-soc-atmel-pcm-dma.o
+# pdc and dma need to both be built-in if any user of
+# ssc is built-in.
+ifdef CONFIG_SND_ATMEL_SOC_PDC
+obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel-pcm-pdc.o
+endif
+ifdef CONFIG_SND_ATMEL_SOC_DMA
+obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel-pcm-dma.o
+endif
 obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel_ssc_dai.o
 obj-$(CONFIG_SND_ATMEL_SOC_I2S) += snd-soc-atmel-i2s.o
 obj-$(CONFIG_SND_MCHP_SOC_I2S_MCC) += snd-soc-mchp-i2s-mcc.o

Greg Kroah-Hartman

author maintainer

2020-02-27 14:17 UTC #128 lore raw

PATCH 126/150 ASoC: fsl_sai: Fix exiting path on probing failure

From: Oleksandr Suvorov <[email protected]>

commit d1520889782dff58610c0b6b54d4cf3211ceb690 upstream.

If the imx-sdma driver is built as a module, the fsl-sai device doesn't disable on probing failure, which causes the warning in the next probing:

==================================================================
fsl-sai 308a0000.sai: Unbalanced pm_runtime_enable! fsl-sai 308a0000.sai: Unbalanced pm_runtime_enable! fsl-sai 308a0000.sai: Unbalanced pm_runtime_enable! fsl-sai 308a0000.sai: Unbalanced pm_runtime_enable! fsl-sai 308a0000.sai: Unbalanced pm_runtime_enable! fsl-sai 308a0000.sai: Unbalanced pm_runtime_enable!
==================================================================

Disabling the device properly fixes the issue.

Fixes 812ad463e089 ("ASoC: fsl_sai: Add support for runtime pm")

Signed-off-by Oleksandr Suvorov <[email protected]>

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Mark Brown <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 sound/soc/fsl/fsl_sai.c |   22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

sound/soc/fsl/fsl_sai.c +17 -5

@@ -1019,12 +1019,24 @@ static int fsl_sai_probe(struct platform
 	ret = devm_snd_soc_register_component(&pdev->dev, &fsl_component,
 			&fsl_sai_dai, 1);
 	if (ret)
-		return ret;
+		goto err_pm_disable;
 
-	if (sai->soc_data->use_imx_pcm)
-		return imx_pcm_dma_init(pdev, IMX_SAI_DMABUF_SIZE);
-	else
-		return devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0);
+	if (sai->soc_data->use_imx_pcm) {
+		ret = imx_pcm_dma_init(pdev, IMX_SAI_DMABUF_SIZE);
+		if (ret)
+			goto err_pm_disable;
+	} else {
+		ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0);
+		if (ret)
+			goto err_pm_disable;
+	}
+
+	return ret;
+
+err_pm_disable:
+	pm_runtime_disable(&pdev->dev);
+
+	return ret;
 }
 
 static int fsl_sai_remove(struct platform_device *pdev)

Greg Kroah-Hartman

author maintainer

2020-02-27 14:18 UTC #129 lore raw

PATCH 127/150 ecryptfs: replace BUG_ON with error handling code

From: Aditya Pakki <[email protected]>

commit 2c2a7552dd6465e8fde6bc9cccf8d66ed1c1eb72 upstream.

In crypt_scatterlist, if the crypt_stat argument is not set up correctly, the kernel crashes. Instead, by returning an error code upstream, the error is handled safely.

The issue is detected via a static analysis tool written by us.

Fixes 237fead619984 (ecryptfs: fs/Makefile and fs/Kconfig)

Signed-off-by Aditya Pakki <[email protected]>

Signed-off-by Tyler Hicks <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/ecryptfs/crypto.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

fs/ecryptfs/crypto.c +4 -2

@@ -311,8 +311,10 @@ static int crypt_scatterlist(struct ecry
 	struct extent_crypt_result ecr;
 	int rc = 0;
 
-	BUG_ON(!crypt_stat || !crypt_stat->tfm
-	       || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED));
+	if (!crypt_stat || !crypt_stat->tfm
+	       || !(crypt_stat->flags & ECRYPTFS_STRUCT_INITIALIZED))
+		return -EINVAL;
+
 	if (unlikely(ecryptfs_verbosity > 0)) {
 		ecryptfs_printk(KERN_DEBUG, "Key size [%zd]; key:\n",
 				crypt_stat->key_size);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:20 UTC #130 lore raw

PATCH 128/150 iommu/vt-d: Fix compile warning from intel-svm.h

From: Joerg Roedel <[email protected]>

commit e7598fac323aad0e502415edeffd567315994dd6 upstream.

The intel_svm_is_pasid_valid() needs to be marked inline, otherwise it causes the compile warning below:

CC [M] drivers/dma/idxd/cdev.o
In file included from drivers/dma/idxd/cdev.c:9:0:
./include/linux/intel-svm.h:125:12: warning: ‘intel_svm_is_pasid_valid’ defined but not used [-Wunused-function]
static int intel_svm_is_pasid_valid(struct device *dev, int pasid)

            ^~~~~~~~~~~~~~~~~~~~~~~~

Reported-by Borislav Petkov <[email protected]>

Fixes 15060aba71711 ('iommu/vt-d: Helper function to query if a pasid has any active users')

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 include/linux/intel-svm.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

include/linux/intel-svm.h +1 -1

@@ -122,7 +122,7 @@ static inline int intel_svm_unbind_mm(st
 	BUG();
 }
 
-static int intel_svm_is_pasid_valid(struct device *dev, int pasid)
+static inline int intel_svm_is_pasid_valid(struct device *dev, int pasid)
 {
 	return -EINVAL;
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:20 UTC #131 lore raw

PATCH 129/150 crypto: rename sm3-256 to sm3 in hash_algo_name

From: Tianjia Zhang <[email protected]>

commit 6a30e1b1dcad0ba94fae757f797812d7d8dcb72c upstream.

The name sm3-256 is defined in hash_algo_name in hash_info, but the algorithm name implemented in sm3_generic.c is sm3, which will cause the sm3-256 algorithm to be not found in some application scenarios of the hash algorithm, and an ENOENT error will occur. For example, IMA, keys, and other subsystems that reference hash_algo_name all use the hash algorithm of sm3.

Fixes 5ca4c20cfd37 ("keys, trusted: select hash algorithm for TPM2 chips")

Signed-off-by Tianjia Zhang <[email protected]>

Reviewed-by Pascal van Leeuwen <[email protected]>

Signed-off-by Mimi Zohar <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 crypto/hash_info.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

crypto/hash_info.c +1 -1

@@ -26,7 +26,7 @@ const char *const hash_algo_name[HASH_AL
 	[HASH_ALGO_TGR_128]	= "tgr128",
 	[HASH_ALGO_TGR_160]	= "tgr160",
 	[HASH_ALGO_TGR_192]	= "tgr192",
-	[HASH_ALGO_SM3_256]	= "sm3-256",
+	[HASH_ALGO_SM3_256]	= "sm3",
 	[HASH_ALGO_STREEBOG_256] = "streebog256",
 	[HASH_ALGO_STREEBOG_512] = "streebog512",
 };

Greg Kroah-Hartman

author maintainer

2020-02-27 14:18 UTC #132 lore raw

PATCH 130/150 genirq/proc: Reject invalid affinity masks (again)

From: Thomas Gleixner <[email protected]>

commit cba6437a1854fde5934098ec3bd0ee83af3129f5 upstream.

Qian Cai reported that the WARN_ON() in the x86/msi affinity setting code, which catches cases where the affinity setting is not done on the CPU which is the current target of the interrupt, triggers during CPU hotplug stress testing.

It turns out that the warning which was added with the commit addressing the MSI affinity race unearthed yet another long standing bug.

If user space writes a bogus affinity mask, i.e. it contains no online CPUs, then it calls irq_select_affinity_usr(). This was introduced for ALPHA in

eee45269b0f5 ("[PATCH] Alpha: convert to generic irq framework (generic part)")

and subsequently made available for all architectures in

18404756765c ("genirq: Expose default irq affinity mask (take 3)")

which introduced the circumvention of the affinity setting restrictions for interrupt which cannot be moved in process context.

The whole exercise is bogus in various aspects:

1) If the interrupt is already started up then there is absolutely no point to honour a bogus interrupt affinity setting from user space. The interrupt is already assigned to an online CPU and it does not make any sense to reassign it to some other randomly chosen online CPU.

2) If the interupt is not yet started up then there is no point either. A subsequent startup of the interrupt will invoke irq_setup_affinity() anyway which will chose a valid target CPU.

So the only correct solution is to just return -EINVAL in case user space wrote an affinity mask which does not contain any online CPUs, except for ALPHA which has it's own magic sauce for this.

Fixes 18404756765c ("genirq: Expose default irq affinity mask (take 3)")

Reported-by Qian Cai <[email protected]>

Tested-by Qian Cai <[email protected]>

Link https://lkml.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 kernel/irq/internals.h |    2 --
 kernel/irq/manage.c    |   18 ++----------------
 kernel/irq/proc.c      |   22 ++++++++++++++++++++++
 3 files changed, 24 insertions(+), 18 deletions(-)

kernel/irq/internals.h +0 -2

@@ -128,8 +128,6 @@ static inline void unregister_handler_pr
 
 extern bool irq_can_set_affinity_usr(unsigned int irq);
 
-extern int irq_select_affinity_usr(unsigned int irq);
-
 extern void irq_set_thread_affinity(struct irq_desc *desc);
 
 extern int irq_do_set_affinity(struct irq_data *data,

kernel/irq/manage.c +2 ~~-16~~

@@ -442,23 +442,9 @@ int irq_setup_affinity(struct irq_desc *
 {
 	return irq_select_affinity(irq_desc_get_irq(desc));
 }
-#endif
+#endif /* CONFIG_AUTO_IRQ_AFFINITY */
+#endif /* CONFIG_SMP */
 
-/*
- * Called when a bogus affinity is set via /proc/irq
- */
-int irq_select_affinity_usr(unsigned int irq)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned long flags;
-	int ret;
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	ret = irq_setup_affinity(desc);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	return ret;
-}
-#endif
 
 /**
  *	irq_set_vcpu_affinity - Set vcpu affinity for the interrupt

kernel/irq/proc.c +22 -0

@@ -111,6 +111,28 @@ static int irq_affinity_list_proc_show(s
 	return show_irq_affinity(AFFINITY_LIST, m);
 }
 
+#ifndef CONFIG_AUTO_IRQ_AFFINITY
+static inline int irq_select_affinity_usr(unsigned int irq)
+{
+	/*
+	 * If the interrupt is started up already then this fails. The
+	 * interrupt is assigned to an online CPU already. There is no
+	 * point to move it around randomly. Tell user space that the
+	 * selected mask is bogus.
+	 *
+	 * If not then any change to the affinity is pointless because the
+	 * startup code invokes irq_setup_affinity() which will select
+	 * a online CPU anyway.
+	 */
+	return -EINVAL;
+}
+#else
+/* ALPHA magic affinity auto selector. Keep it for historical reasons. */
+static inline int irq_select_affinity_usr(unsigned int irq)
+{
+	return irq_select_affinity(irq);
+}
+#endif
 
 static ssize_t write_irq_affinity(int type, struct file *file,
 		const char __user *buffer, size_t count, loff_t *pos)

Greg Kroah-Hartman

author maintainer

2020-02-27 14:18 UTC #133 lore raw

PATCH 131/150 bpf, offload: Replace bitwise AND by logical AND in bpf_prog_offload_info_fill

Link https://lore.kernel.org/bpf/[email protected] open here

From: Johannes Krude <[email protected]>

commit e20d3a055a457a10a4c748ce5b7c2ed3173a1324 upstream.

This if guards whether user-space wants a copy of the offload-jited bytecode and whether this bytecode exists. By erroneously doing a bitwise AND instead of a logical AND on user- and kernel-space buffer-size can lead to no data being copied to user-space especially when user-space size is a power of two and bigger then the kernel-space buffer.

Fixes fcfb126defda ("bpf: add new jited info fields in bpf_dev_offload and bpf_prog_info")

Signed-off-by Johannes Krude <[email protected]>

Signed-off-by Daniel Borkmann <[email protected]>

Acked-by Jakub Kicinski <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 kernel/bpf/offload.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

kernel/bpf/offload.c +1 -1

@@ -321,7 +321,7 @@ int bpf_prog_offload_info_fill(struct bp
 
 	ulen = info->jited_prog_len;
 	info->jited_prog_len = aux->offload->jited_len;
-	if (info->jited_prog_len & ulen) {
+	if (info->jited_prog_len && ulen) {
 		uinsns = u64_to_user_ptr(info->jited_prog_insns);
 		ulen = min_t(u32, info->jited_prog_len, ulen);
 		if (copy_to_user(uinsns, aux->offload->jited_image, ulen)) {

Greg Kroah-Hartman

author maintainer

2020-02-27 14:20 UTC #134 lore raw

PATCH 132/150 arm64: lse: Fix LSE atomics with LLVM

From: Vincenzo Frascino <[email protected]>

commit dd1f6308b28edf0452dd5dc7877992903ec61e69 upstream.

Commit e0d5896bd356 ("arm64: lse: fix LSE atomics with LLVM's integrated assembler") broke the build when clang is used in connjunction with the binutils assembler ("-no-integrated-as"). This happens because __LSE_PREAMBLE is defined as ".arch armv8-a+lse", which overrides the version of the CPU architecture passed via the "-march" paramter to gas:

$ aarch64-none-linux-gnu-as -EL -I ./arch/arm64/include
                                -I ./arch/arm64/include/generated
                                -I ./include -I ./include
                                -I ./arch/arm64/include/uapi
                                -I ./arch/arm64/include/generated/uapi
                                -I ./include/uapi -I ./include/generated/uapi
                                -I ./init -I ./init
                                -march=armv8.3-a -o init/do_mounts.o
                                /tmp/do_mounts-d7992a.s
/tmp/do_mounts-d7992a.s: Assembler messages:
/tmp/do_mounts-d7992a.s:1959: Error: selected processor does not support `autiasp'
/tmp/do_mounts-d7992a.s:2021: Error: selected processor does not support `paciasp'
/tmp/do_mounts-d7992a.s:2157: Error: selected processor does not support `autiasp'
/tmp/do_mounts-d7992a.s:2175: Error: selected processor does not support `paciasp'
/tmp/do_mounts-d7992a.s:2494: Error: selected processor does not support `autiasp'

Fix the issue by replacing ".arch armv8-a+lse" with ".arch_extension lse". Sami confirms that the clang integrated assembler does now support the '.arch_extension' directive, so this change will be fine even for LTO builds in future.

Fixes e0d5896bd356cd ("arm64: lse: fix LSE atomics with LLVM's integrated assembler")

Cc Catalin Marinas <[email protected]>

Cc Will Deacon <[email protected]>

Reported-by Amit Kachhap <[email protected]>

Tested-by Sami Tolvanen <[email protected]>

Signed-off-by Vincenzo Frascino <[email protected]>

Signed-off-by Will Deacon <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/arm64/include/asm/lse.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

arch/arm64/include/asm/lse.h +1 -1

@@ -6,7 +6,7 @@
 
 #if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS)
 
-#define __LSE_PREAMBLE	".arch armv8-a+lse\n"
+#define __LSE_PREAMBLE	".arch_extension lse\n"
 
 #include <linux/compiler_types.h>
 #include <linux/export.h>

Greg Kroah-Hartman

author maintainer

2020-02-27 14:18 UTC #135 lore raw

PATCH 133/150 scripts/get_maintainer.pl: deprioritize old Fixes: addresses

Link http://lkml.kernel.org/r/20200127095001.1.I41fba9f33590bfd92cd01960161d8384268c6569@changeid open here

From: Douglas Anderson <[email protected]>

commit 0ef82fcefb99300ede6f4d38a8100845b2dc8e30 upstream.

Recently, I found that get_maintainer was causing me to send emails to the old addresses for maintainers. Since I usually just trust the output of get_maintainer to know the right email address, I didn't even look carefully and fired off two patch series that went to the wrong place. Oops.

The problem was introduced recently when trying to add signatures from Fixes. The problem was that these email addresses were added too early in the process of compiling our list of places to send. Things added to the list earlier are considered more canonical and when we later added maintainer entries we ended up deduplicating to the old address.

Here are two examples using mainline commits (to make it easier to replicate) for the two maintainers that I messed up recently:

  $ git format-patch d8549bcd0529~..d8549bcd0529
  $ ./scripts/get_maintainer.pl 0001-clk-Add-clk_hw*.patch | grep Boyd
  Stephen Boyd <[email protected]>...

  $ git format-patch 6d1238aa3395~..6d1238aa3395
  $ ./scripts/get_maintainer.pl 0001-arm64-dts-qcom-qcs404*.patch | grep Andy
  Andy Gross <[email protected]>

Let's move the adding of addresses from Fixes: to the end since the email addresses from these are much more likely to be older.

After this patch the above examples get the right addresses for the two examples.

Fixes 2f5bd343694e ("scripts/get_maintainer.pl: add signatures from Fixes: <badcommit> lines in commit message")

Signed-off-by Douglas Anderson <[email protected]>

Acked-by Joe Perches <[email protected]>

Cc Stephen Boyd <[email protected]>

Cc Bjorn Andersson <[email protected]>

Cc Andy Gross <[email protected]>

Cc Kees Cook <[email protected]>

Cc Dan Carpenter <[email protected]>

Cc Greg Kroah-Hartman <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 scripts/get_maintainer.pl |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

scripts/get_maintainer.pl +4 -4

@@ -932,10 +932,6 @@ sub get_maintainers {
 	}
     }
 
-    foreach my $fix (@fixes) {
-	vcs_add_commit_signers($fix, "blamed_fixes");
-    }
-
     foreach my $email (@email_to, @list_to) {
 	$email->[0] = deduplicate_email($email->[0]);
     }

@@ -974,6 +970,10 @@ sub get_maintainers {
 	}
     }
 
+    foreach my $fix (@fixes) {
+	vcs_add_commit_signers($fix, "blamed_fixes");
+    }
+
     my @to = ();
     if ($email || $email_list) {
 	if ($email) {

Joe Perches

2020-02-27 15:22 UTC #136 lore raw

Re: [PATCH 5.5 133/150] scripts/get_maintainer.pl: deprioritize old Fixes: addresses

Quoted 3 lines · Greg Kroah-Hartman

From: Douglas Anderson <[email protected]>
commit 0ef82fcefb99300ede6f4d38a8100845b2dc8e30 upstream.

I think adding just about any checkpatch patch to stable a bit silly. Including patches to checkpatch.

Dan Carpenter

2020-02-27 16:18 UTC #137 lore raw

Re: [PATCH 5.5 133/150] scripts/get_maintainer.pl: deprioritize old Fixes: addresses

Quoted 8 lines · Joe Perches

Quoted 3 lines · Greg Kroah-Hartman
From: Douglas Anderson <[email protected]>
commit 0ef82fcefb99300ede6f4d38a8100845b2dc8e30 upstream.
I think adding just about any checkpatch patch to stable a bit silly. Including patches to checkpatch.

On the other hand, Greg is one of the worst affected by the old behavior since he has so many old email addresses and he's also the stable maintainer.

regards,
dan carpenter

Greg Kroah-Hartman

author maintainer

2020-02-28 07:13 UTC #138 lore raw

Re: [PATCH 5.5 133/150] scripts/get_maintainer.pl: deprioritize old Fixes: addresses

Quoted 6 lines · Dan Carpenter

Quoted 5 lines · Joe Perches
Quoted 3 lines · Greg Kroah-Hartman
From: Douglas Anderson <[email protected]>
commit 0ef82fcefb99300ede6f4d38a8100845b2dc8e30 upstream.

Quoted 7 lines

Quoted 3 lines
I think adding just about any checkpatch patch to stable a bit silly. Including patches to checkpatch.
On the other hand, Greg is one of the worst affected by the old behavior since he has so many old email addresses and he's also the stable maintainer.

Exactly, lots of people still do development against the latest released kernel, which is 5.5 here...

thanks,

greg kh-

Greg Kroah-Hartman

author maintainer

2020-02-27 14:18 UTC #139 lore raw

PATCH 134/150 io_uring: prevent sq_thread from spinning when it should stop

From: Stefano Garzarella <[email protected]>

commit 7143b5ac5750f404ff3a594b34fdf3fc2f99f828 upstream.

This patch drops 'cur_mm' before calling cond_resched(), to prevent the sq_thread from spinning even when the user process is finished.

Before this patch, if the user process ended without closing the io_uring fd, the sq_thread continues to spin until the 'sq_thread_idle' timeout ends.

In the worst case where the 'sq_thread_idle' parameter is bigger than INT_MAX, the sq_thread will spin forever.

Fixes 6c271ce2f1d5 ("io_uring: add submission polling")

Signed-off-by Stefano Garzarella <[email protected]>

Signed-off-by Jens Axboe <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/io_uring.c |   24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

fs/io_uring.c +12 ~~-12~~

@@ -3909,6 +3909,18 @@ static int io_sq_thread(void *data)
 		 */
 		if (!to_submit || ret == -EBUSY) {
 			/*
+			 * Drop cur_mm before scheduling, we can't hold it for
+			 * long periods (or over schedule()). Do this before
+			 * adding ourselves to the waitqueue, as the unuse/drop
+			 * may sleep.
+			 */
+			if (cur_mm) {
+				unuse_mm(cur_mm);
+				mmput(cur_mm);
+				cur_mm = NULL;
+			}
+
+			/*
 			 * We're polling. If we're within the defined idle
 			 * period, then let us spin without work before going
 			 * to sleep. The exception is if we got EBUSY doing

@@ -3922,18 +3934,6 @@ static int io_sq_thread(void *data)
 				continue;
 			}
 
-			/*
-			 * Drop cur_mm before scheduling, we can't hold it for
-			 * long periods (or over schedule()). Do this before
-			 * adding ourselves to the waitqueue, as the unuse/drop
-			 * may sleep.
-			 */
-			if (cur_mm) {
-				unuse_mm(cur_mm);
-				mmput(cur_mm);
-				cur_mm = NULL;
-			}
-
 			prepare_to_wait(&ctx->sqo_wait, &wait,
 						TASK_INTERRUPTIBLE);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:18 UTC #140 lore raw

PATCH 135/150 io_uring: fix __io_iopoll_check deadlock in io_sq_thread

From: Xiaoguang Wang <[email protected]>

commit c7849be9cc2dd2754c48ddbaca27c2de6d80a95d upstream.

Since commit a3a0e43fd770 ("io_uring: don't enter poll loop if we have CQEs pending"), if we already events pending, we won't enter poll loop. In case SETUP_IOPOLL and SETUP_SQPOLL are both enabled, if app has been terminated and don't reap pending events which are already in cq ring, and there are some reqs in poll_list, io_sq_thread will enter __io_iopoll_check(), and find pending events, then return, this loop will never have a chance to exit.

I have seen this issue in fio stress tests, to fix this issue, let io_sq_thread call io_iopoll_getevents() with argument 'min' being zero, and remove __io_iopoll_check().

Fixes a3a0e43fd770 ("io_uring: don't enter poll loop if we have CQEs pending")

Signed-off-by Xiaoguang Wang <[email protected]>

Signed-off-by Jens Axboe <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 fs/io_uring.c |   27 +++++++++------------------
 1 file changed, 9 insertions(+), 18 deletions(-)

fs/io_uring.c +9 ~~-18~~

@@ -1286,11 +1286,17 @@ static void io_iopoll_reap_events(struct
 	mutex_unlock(&ctx->uring_lock);
 }
 
-static int __io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
-			    long min)
+static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
+			   long min)
 {
 	int iters = 0, ret = 0;
 
+	/*
+	 * We disallow the app entering submit/complete with polling, but we
+	 * still need to lock the ring to prevent racing with polled issue
+	 * that got punted to a workqueue.
+	 */
+	mutex_lock(&ctx->uring_lock);
 	do {
 		int tmin = 0;

@@ -1326,21 +1332,6 @@ static int __io_iopoll_check(struct io_r
 		ret = 0;
 	} while (min && !*nr_events && !need_resched());
 
-	return ret;
-}
-
-static int io_iopoll_check(struct io_ring_ctx *ctx, unsigned *nr_events,
-			   long min)
-{
-	int ret;
-
-	/*
-	 * We disallow the app entering submit/complete with polling, but we
-	 * still need to lock the ring to prevent racing with polled issue
-	 * that got punted to a workqueue.
-	 */
-	mutex_lock(&ctx->uring_lock);
-	ret = __io_iopoll_check(ctx, nr_events, min);
 	mutex_unlock(&ctx->uring_lock);
 	return ret;
 }

@@ -3884,7 +3875,7 @@ static int io_sq_thread(void *data)
 				 */
 				mutex_lock(&ctx->uring_lock);
 				if (!list_empty(&ctx->poll_list))
-					__io_iopoll_check(ctx, &nr_events, 0);
+					io_iopoll_getevents(ctx, &nr_events, 0);
 				else
 					inflight = 0;
 				mutex_unlock(&ctx->uring_lock);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:18 UTC #141 lore raw

PATCH 136/150 dma-direct: relax addressability checks in dma_direct_supported

From: Christoph Hellwig <[email protected]>

commit 91ef26f914171cf753330f13724fd9142b5b1640 upstream.

dma_direct_supported tries to find the minimum addressable bitmask based on the end pfn and optional magic that architectures can use to communicate the size of the magic ZONE_DMA that can be used for bounce buffering. But between the DMA offsets that can change per device (or sometimes even region), the fact the ZONE_DMA isn't even guaranteed to be the lowest addresses and failure of having proper interfaces to the MM code this fails at least for one arm subarchitecture.

As all the legacy DMA implementations have supported 32-bit DMA masks, and 32-bit masks are guranteed to always work by the API contract (using bounce buffers if needed), we can short cut the complicated check and always return true without breaking existing assumptions. Hopefully we can properly clean up the interaction with the arch defined zones and the bootmem allocator eventually.

Fixes ad3c7b18c5b3 ("arm: use swiotlb for bounce buffering on LPAE configs")

Reported-by Peter Ujfalusi <[email protected]>

Signed-off-by Christoph Hellwig <[email protected]>

Tested-by Peter Ujfalusi <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 kernel/dma/direct.c |   24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

kernel/dma/direct.c +11 ~~-13~~

@@ -472,28 +472,26 @@ int dma_direct_mmap(struct device *dev,
 }
 #endif /* CONFIG_MMU */
 
-/*
- * Because 32-bit DMA masks are so common we expect every architecture to be
- * able to satisfy them - either by not supporting more physical memory, or by
- * providing a ZONE_DMA32.  If neither is the case, the architecture needs to
- * use an IOMMU instead of the direct mapping.
- */
 int dma_direct_supported(struct device *dev, u64 mask)
 {
-	u64 min_mask;
+	u64 min_mask = (max_pfn - 1) << PAGE_SHIFT;
 
-	if (IS_ENABLED(CONFIG_ZONE_DMA))
-		min_mask = DMA_BIT_MASK(zone_dma_bits);
-	else
-		min_mask = DMA_BIT_MASK(32);
-
-	min_mask = min_t(u64, min_mask, (max_pfn - 1) << PAGE_SHIFT);
+	/*
+	 * Because 32-bit DMA masks are so common we expect every architecture
+	 * to be able to satisfy them - either by not supporting more physical
+	 * memory, or by providing a ZONE_DMA32.  If neither is the case, the
+	 * architecture needs to use an IOMMU instead of the direct mapping.
+	 */
+	if (mask >= DMA_BIT_MASK(32))
+		return 1;
 
 	/*
 	 * This check needs to be against the actual bit mask value, so
 	 * use __phys_to_dma() here so that the SME encryption mask isn't
 	 * part of the check.
 	 */
+	if (IS_ENABLED(CONFIG_ZONE_DMA))
+		min_mask = min_t(u64, min_mask, DMA_BIT_MASK(zone_dma_bits));
 	return mask >= __phys_to_dma(dev, min_mask);
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:18 UTC #142 lore raw

PATCH 137/150 ALSA: rawmidi: Avoid bit fields for state flags

From: Takashi Iwai <[email protected]>

commit dfa9a5efe8b932a84b3b319250aa3ac60c20f876 upstream.

The rawmidi state flags (opened, append, active_sensing) are stored in bit fields that can be potentially racy when concurrently accessed without any locks. Although the current code should be fine, there is also no any real benefit by keeping the bitfields for this kind of short number of members.

This patch changes those bit fields flags to the simple bool fields. There should be no size increase of the snd_rawmidi_substream by this change.

Reported-by [email protected]

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 include/sound/rawmidi.h |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

include/sound/rawmidi.h +3 -3

@@ -77,9 +77,9 @@ struct snd_rawmidi_substream {
 	struct list_head list;		/* list of all substream for given stream */
 	int stream;			/* direction */
 	int number;			/* substream number */
-	unsigned int opened: 1,		/* open flag */
-		     append: 1,		/* append flag (merge more streams) */
-		     active_sensing: 1; /* send active sensing when close */
+	bool opened;			/* open flag */
+	bool append;			/* append flag (merge more streams) */
+	bool active_sensing;		/* send active sensing when close */
 	int use_count;			/* use counter (for output) */
 	size_t bytes;
 	struct snd_rawmidi *rmidi;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:20 UTC #143 lore raw

PATCH 138/150 ALSA: seq: Avoid concurrent access to queue flags

From: Takashi Iwai <[email protected]>

commit bb51e669fa49feb5904f452b2991b240ef31bc97 upstream.

The queue flags are represented in bit fields and the concurrent access may result in unexpected results. Although the current code should be mostly OK as it's only reading a field while writing other fields as KCSAN reported, it's safer to cover both with a proper spinlock protection.

This patch fixes the possible concurrent read by protecting with q->owner_lock. Also the queue owner field is protected as well since it's the field to be protected by the lock itself.

Reported-by [email protected]

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 sound/core/seq/seq_queue.c |   20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

sound/core/seq/seq_queue.c +16 -4

@@ -392,6 +392,7 @@ int snd_seq_queue_check_access(int queue
 int snd_seq_queue_set_owner(int queueid, int client, int locked)
 {
 	struct snd_seq_queue *q = queueptr(queueid);
+	unsigned long flags;
 
 	if (q == NULL)
 		return -EINVAL;

@@ -401,8 +402,10 @@ int snd_seq_queue_set_owner(int queueid,
 		return -EPERM;
 	}
 
+	spin_lock_irqsave(&q->owner_lock, flags);
 	q->locked = locked ? 1 : 0;
 	q->owner = client;
+	spin_unlock_irqrestore(&q->owner_lock, flags);
 	queue_access_unlock(q);
 	queuefree(q);

@@ -539,15 +542,17 @@ void snd_seq_queue_client_termination(in
 	unsigned long flags;
 	int i;
 	struct snd_seq_queue *q;
+	bool matched;
 
 	for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) {
 		if ((q = queueptr(i)) == NULL)
 			continue;
 		spin_lock_irqsave(&q->owner_lock, flags);
-		if (q->owner == client)
+		matched = (q->owner == client);
+		if (matched)
 			q->klocked = 1;
 		spin_unlock_irqrestore(&q->owner_lock, flags);
-		if (q->owner == client) {
+		if (matched) {
 			if (q->timer->running)
 				snd_seq_timer_stop(q->timer);
 			snd_seq_timer_reset(q->timer);

@@ -739,6 +744,8 @@ void snd_seq_info_queues_read(struct snd
 	int i, bpm;
 	struct snd_seq_queue *q;
 	struct snd_seq_timer *tmr;
+	bool locked;
+	int owner;
 
 	for (i = 0; i < SNDRV_SEQ_MAX_QUEUES; i++) {
 		if ((q = queueptr(i)) == NULL)

@@ -750,9 +757,14 @@ void snd_seq_info_queues_read(struct snd
 		else
 			bpm = 0;
 
+		spin_lock_irq(&q->owner_lock);
+		locked = q->locked;
+		owner = q->owner;
+		spin_unlock_irq(&q->owner_lock);
+
 		snd_iprintf(buffer, "queue %d: [%s]\n", q->queue, q->name);
-		snd_iprintf(buffer, "owned by client    : %d\n", q->owner);
-		snd_iprintf(buffer, "lock status        : %s\n", q->locked ? "Locked" : "Free");
+		snd_iprintf(buffer, "owned by client    : %d\n", owner);
+		snd_iprintf(buffer, "lock status        : %s\n", locked ? "Locked" : "Free");
 		snd_iprintf(buffer, "queued time events : %d\n", snd_seq_prioq_avail(q->timeq));
 		snd_iprintf(buffer, "queued tick events : %d\n", snd_seq_prioq_avail(q->tickq));
 		snd_iprintf(buffer, "timer state        : %s\n", tmr->running ? "Running" : "Stopped");

Greg Kroah-Hartman

author maintainer

2020-02-27 14:18 UTC #144 lore raw

PATCH 139/150 ALSA: seq: Fix concurrent access to queue current tick/time

From: Takashi Iwai <[email protected]>

commit dc7497795e014d84699c3b8809ed6df35352dd74 upstream.

snd_seq_check_queue() passes the current tick and time of the given queue as a pointer to snd_seq_prioq_cell_out(), but those might be updated concurrently by the seq timer update.

Fix it by retrieving the current tick and time via the proper helper functions at first, and pass those values to snd_seq_prioq_cell_out() later in the loops.

snd_seq_timer_get_cur_time() takes a new argument and adjusts with the current system time only when it's requested so; this update isn't needed for snd_seq_check_queue(), as it's called either from the interrupt handler or right after queuing.

Also, snd_seq_timer_get_cur_tick() is changed to read the value in the spinlock for the concurrency, too.

Reported-by [email protected]

Link https://lore.kernel.org/r/[email protected] open here

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 sound/core/seq/seq_clientmgr.c |    4 ++--
 sound/core/seq/seq_queue.c     |    9 ++++++---
 sound/core/seq/seq_timer.c     |   13 ++++++++++---
 sound/core/seq/seq_timer.h     |    3 ++-
 4 files changed, 20 insertions(+), 9 deletions(-)

sound/core/seq/seq_clientmgr.c +2 -2

@@ -580,7 +580,7 @@ static int update_timestamp_of_queue(str
 	event->queue = queue;
 	event->flags &= ~SNDRV_SEQ_TIME_STAMP_MASK;
 	if (real_time) {
-		event->time.time = snd_seq_timer_get_cur_time(q->timer);
+		event->time.time = snd_seq_timer_get_cur_time(q->timer, true);
 		event->flags |= SNDRV_SEQ_TIME_STAMP_REAL;
 	} else {
 		event->time.tick = snd_seq_timer_get_cur_tick(q->timer);

@@ -1659,7 +1659,7 @@ static int snd_seq_ioctl_get_queue_statu
 	tmr = queue->timer;
 	status->events = queue->tickq->cells + queue->timeq->cells;
 
-	status->time = snd_seq_timer_get_cur_time(tmr);
+	status->time = snd_seq_timer_get_cur_time(tmr, true);
 	status->tick = snd_seq_timer_get_cur_tick(tmr);
 
 	status->running = tmr->running;

sound/core/seq/seq_queue.c +6 -3

@@ -238,6 +238,8 @@ void snd_seq_check_queue(struct snd_seq_
 {
 	unsigned long flags;
 	struct snd_seq_event_cell *cell;
+	snd_seq_tick_time_t cur_tick;
+	snd_seq_real_time_t cur_time;
 
 	if (q == NULL)
 		return;

@@ -254,17 +256,18 @@ void snd_seq_check_queue(struct snd_seq_
 
       __again:
 	/* Process tick queue... */
+	cur_tick = snd_seq_timer_get_cur_tick(q->timer);
 	for (;;) {
-		cell = snd_seq_prioq_cell_out(q->tickq,
-					      &q->timer->tick.cur_tick);
+		cell = snd_seq_prioq_cell_out(q->tickq, &cur_tick);
 		if (!cell)
 			break;
 		snd_seq_dispatch_event(cell, atomic, hop);
 	}
 
 	/* Process time queue... */
+	cur_time = snd_seq_timer_get_cur_time(q->timer, false);
 	for (;;) {
-		cell = snd_seq_prioq_cell_out(q->timeq, &q->timer->cur_time);
+		cell = snd_seq_prioq_cell_out(q->timeq, &cur_time);
 		if (!cell)
 			break;
 		snd_seq_dispatch_event(cell, atomic, hop);

sound/core/seq/seq_timer.c +10 -3

@@ -428,14 +428,15 @@ int snd_seq_timer_continue(struct snd_se
 }
 
 /* return current 'real' time. use timeofday() to get better granularity. */
-snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr)
+snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr,
+					       bool adjust_ktime)
 {
 	snd_seq_real_time_t cur_time;
 	unsigned long flags;
 
 	spin_lock_irqsave(&tmr->lock, flags);
 	cur_time = tmr->cur_time;
-	if (tmr->running) { 
+	if (adjust_ktime && tmr->running) {
 		struct timespec64 tm;
 
 		ktime_get_ts64(&tm);

@@ -452,7 +453,13 @@ snd_seq_real_time_t snd_seq_timer_get_cu
  high PPQ values) */
 snd_seq_tick_time_t snd_seq_timer_get_cur_tick(struct snd_seq_timer *tmr)
 {
-	return tmr->tick.cur_tick;
+	snd_seq_tick_time_t cur_tick;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tmr->lock, flags);
+	cur_tick = tmr->tick.cur_tick;
+	spin_unlock_irqrestore(&tmr->lock, flags);
+	return cur_tick;
 }

sound/core/seq/seq_timer.h +2 -1

@@ -120,7 +120,8 @@ int snd_seq_timer_set_tempo_ppq(struct s
 int snd_seq_timer_set_position_tick(struct snd_seq_timer *tmr, snd_seq_tick_time_t position);
 int snd_seq_timer_set_position_time(struct snd_seq_timer *tmr, snd_seq_real_time_t position);
 int snd_seq_timer_set_skew(struct snd_seq_timer *tmr, unsigned int skew, unsigned int base);
-snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr);
+snd_seq_real_time_t snd_seq_timer_get_cur_time(struct snd_seq_timer *tmr,
+					       bool adjust_ktime);
 snd_seq_tick_time_t snd_seq_timer_get_cur_tick(struct snd_seq_timer *tmr);
 
 extern int seq_default_timer_class;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:19 UTC #145 lore raw

PATCH 140/150 netfilter: xt_hashlimit: limit the max size of hashtable

From: Cong Wang <[email protected]>

commit 8d0015a7ab76b8b1e89a3e5f5710a6e5103f2dd5 upstream.

The user-specified hashtable size is unbound, this could easily lead to an OOM or a hung task as we hold the global mutex while allocating and initializing the new hashtable.

Add a max value to cap both cfg->size and cfg->max, as suggested by Florian.

Reported-and-tested-by [email protected]

Signed-off-by Cong Wang <[email protected]>

Reviewed-by Florian Westphal <[email protected]>

Signed-off-by Pablo Neira Ayuso <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/netfilter/xt_hashlimit.c |   10 ++++++++++
 1 file changed, 10 insertions(+)

net/netfilter/xt_hashlimit.c +10 -0

@@ -851,6 +851,8 @@ hashlimit_mt(const struct sk_buff *skb,
 	return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 3);
 }
 
+#define HASHLIMIT_MAX_SIZE 1048576
+
 static int hashlimit_mt_check_common(const struct xt_mtchk_param *par,
 				     struct xt_hashlimit_htable **hinfo,
 				     struct hashlimit_cfg3 *cfg,

@@ -861,6 +863,14 @@ static int hashlimit_mt_check_common(con
 
 	if (cfg->gc_interval == 0 || cfg->expire == 0)
 		return -EINVAL;
+	if (cfg->size > HASHLIMIT_MAX_SIZE) {
+		cfg->size = HASHLIMIT_MAX_SIZE;
+		pr_info_ratelimited("size too large, truncated to %u\n", cfg->size);
+	}
+	if (cfg->max > HASHLIMIT_MAX_SIZE) {
+		cfg->max = HASHLIMIT_MAX_SIZE;
+		pr_info_ratelimited("max too large, truncated to %u\n", cfg->max);
+	}
 	if (par->family == NFPROTO_IPV4) {
 		if (cfg->srcmask > 32 || cfg->dstmask > 32)
 			return -EINVAL;

Greg Kroah-Hartman

author maintainer

2020-02-27 14:18 UTC #146 lore raw

PATCH 141/150 rxrpc: Fix call RCU cleanup using non-bh-safe locks

From: David Howells <[email protected]>

commit 963485d436ccc2810177a7b08af22336ec2af67b upstream.

rxrpc_rcu_destroy_call(), which is called as an RCU callback to clean up a put call, calls rxrpc_put_connection() which, deep in its bowels, takes a number of spinlocks in a non-BH-safe way, including rxrpc_conn_id_lock and local->client_conns_lock. RCU callbacks, however, are normally called from softirq context, which can cause lockdep to notice the locking inconsistency.

To get lockdep to detect this, it's necessary to have the connection cleaned up on the put at the end of the last of its calls, though normally the clean up is deferred. This can be induced, however, by starting a call on an AF_RXRPC socket and then closing the socket without reading the reply.

Fix this by having rxrpc_rcu_destroy_call() punt the destruction to a workqueue if in softirq-mode and defer the destruction to process context.

Note that another way to fix this could be to add a bunch of bh-disable annotations to the spinlocks concerned - and there might be more than just those two - but that means spending more time with BHs disabled.

Note also that some of these places were covered by bh-disable spinlocks belonging to the rxrpc_transport object, but these got removed without the _bh annotation being retained on the next lock in.

Fixes 999b69f89241 ("rxrpc: Kill the client connection bundle concept")

Reported-by [email protected]

Signed-off-by David Howells <[email protected]>

cc Hillf Danton <[email protected]>

Signed-off-by David S. Miller <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 net/rxrpc/call_object.c |   22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

net/rxrpc/call_object.c +19 -3

@@ -562,11 +562,11 @@ void rxrpc_put_call(struct rxrpc_call *c
 }
 
 /*
- * Final call destruction under RCU.
+ * Final call destruction - but must be done in process context.
  */
-static void rxrpc_rcu_destroy_call(struct rcu_head *rcu)
+static void rxrpc_destroy_call(struct work_struct *work)
 {
-	struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu);
+	struct rxrpc_call *call = container_of(work, struct rxrpc_call, processor);
 	struct rxrpc_net *rxnet = call->rxnet;
 
 	rxrpc_put_connection(call->conn);

@@ -579,6 +579,22 @@ static void rxrpc_rcu_destroy_call(struc
 }
 
 /*
+ * Final call destruction under RCU.
+ */
+static void rxrpc_rcu_destroy_call(struct rcu_head *rcu)
+{
+	struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu);
+
+	if (in_softirq()) {
+		INIT_WORK(&call->processor, rxrpc_destroy_call);
+		if (!rxrpc_queue_work(&call->processor))
+			BUG();
+	} else {
+		rxrpc_destroy_call(&call->processor);
+	}
+}
+
+/*
  * clean up a call
  */
 void rxrpc_cleanup_call(struct rxrpc_call *call)

Greg Kroah-Hartman

author maintainer

2020-02-27 14:18 UTC #147 lore raw

PATCH 142/150 ata: ahci: Add shutdown to freeze hardware resources of ahci

From: Prabhakar Kushwaha <[email protected]>

commit 10a663a1b15134a5a714aa515e11425a44d4fdf7 upstream.

device_shutdown() called from reboot or power_shutdown expect all devices to be shutdown. Same is true for even ahci pci driver. As no ahci shutdown function is implemented, the ata subsystem always remains alive with DMA & interrupt support. File system related calls should not be honored after device_shutdown().

So defining ahci pci driver shutdown to freeze hardware (mask interrupt, stop DMA engine and free DMA resources).

Signed-off-by Prabhakar Kushwaha <[email protected]>

Signed-off-by Jens Axboe <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/ata/ahci.c        |    7 +++++++
 drivers/ata/libata-core.c |   21 +++++++++++++++++++++
 include/linux/libata.h    |    1 +
 3 files changed, 29 insertions(+)

drivers/ata/ahci.c +7 -0

@@ -81,6 +81,7 @@ enum board_ids {
 
 static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent);
 static void ahci_remove_one(struct pci_dev *dev);
+static void ahci_shutdown_one(struct pci_dev *dev);
 static int ahci_vt8251_hardreset(struct ata_link *link, unsigned int *class,
 				 unsigned long deadline);
 static int ahci_avn_hardreset(struct ata_link *link, unsigned int *class,

@@ -606,6 +607,7 @@ static struct pci_driver ahci_pci_driver
 	.id_table		= ahci_pci_tbl,
 	.probe			= ahci_init_one,
 	.remove			= ahci_remove_one,
+	.shutdown		= ahci_shutdown_one,
 	.driver = {
 		.pm		= &ahci_pci_pm_ops,
 	},

@@ -1877,6 +1879,11 @@ static int ahci_init_one(struct pci_dev
 	return 0;
 }
 
+static void ahci_shutdown_one(struct pci_dev *pdev)
+{
+	ata_pci_shutdown_one(pdev);
+}
+
 static void ahci_remove_one(struct pci_dev *pdev)
 {
 	pm_runtime_get_noresume(&pdev->dev);

drivers/ata/libata-core.c +21 -0

@@ -6767,6 +6767,26 @@ void ata_pci_remove_one(struct pci_dev *
 	ata_host_detach(host);
 }
 
+void ata_pci_shutdown_one(struct pci_dev *pdev)
+{
+	struct ata_host *host = pci_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < host->n_ports; i++) {
+		struct ata_port *ap = host->ports[i];
+
+		ap->pflags |= ATA_PFLAG_FROZEN;
+
+		/* Disable port interrupts */
+		if (ap->ops->freeze)
+			ap->ops->freeze(ap);
+
+		/* Stop the port DMA engines */
+		if (ap->ops->port_stop)
+			ap->ops->port_stop(ap);
+	}
+}
+
 /* move to PCI subsystem */
 int pci_test_config_bits(struct pci_dev *pdev, const struct pci_bits *bits)
 {

@@ -7387,6 +7407,7 @@ EXPORT_SYMBOL_GPL(ata_timing_cycle2mode)
 
 #ifdef CONFIG_PCI
 EXPORT_SYMBOL_GPL(pci_test_config_bits);
+EXPORT_SYMBOL_GPL(ata_pci_shutdown_one);
 EXPORT_SYMBOL_GPL(ata_pci_remove_one);
 #ifdef CONFIG_PM
 EXPORT_SYMBOL_GPL(ata_pci_device_do_suspend);

include/linux/libata.h +1 -0

@@ -1221,6 +1221,7 @@ struct pci_bits {
 };
 
 extern int pci_test_config_bits(struct pci_dev *pdev, const struct pci_bits *bits);
+extern void ata_pci_shutdown_one(struct pci_dev *pdev);
 extern void ata_pci_remove_one(struct pci_dev *pdev);
 
 #ifdef CONFIG_PM

Greg Kroah-Hartman

author maintainer

2020-02-27 14:19 UTC #148 lore raw

PATCH 143/150 xen: Enable interrupts when calling _cond_resched()

From: Thomas Gleixner <[email protected]>

commit 8645e56a4ad6dcbf504872db7f14a2f67db88ef2 upstream.

xen_maybe_preempt_hcall() is called from the exception entry point xen_do_hypervisor_callback with interrupts disabled.

_cond_resched() evades the might_sleep() check in cond_resched() which would have caught that and schedule_debug() unfortunately lacks a check for irqs_disabled().

Enable interrupts around the call and use cond_resched() to catch future issues.

Fixes fdfd811ddde3 ("x86/xen: allow privcmd hypercalls to be preempted")

Link https://lore.kernel.org/r/[email protected] open here

Reviewed-by Juergen Gross <[email protected]>

Signed-off-by Boris Ostrovsky <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/xen/preempt.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

drivers/xen/preempt.c +3 -1

@@ -33,7 +33,9 @@ asmlinkage __visible void xen_maybe_pree
 		 * cpu.
 		 */
 		__this_cpu_write(xen_in_preemptible_hcall, false);
-		_cond_resched();
+		local_irq_enable();
+		cond_resched();
+		local_irq_disable();
 		__this_cpu_write(xen_in_preemptible_hcall, true);
 	}
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:18 UTC #149 lore raw

PATCH 144/150 net/mlx5e: Reset RQ doorbell counter before moving RQ state from RST to RDY

From: Aya Levin <[email protected]>

commit 5ee090ed0da649b1febae2b7c285ac77d1e55a0c upstream.

Initialize RQ doorbell counters to zero prior to moving an RQ from RST to RDY state. Per HW spec, when RQ is back to RDY state, the descriptor ID on the completion is reset. The doorbell record must comply.

Fixes 8276ea1353a4 ("net/mlx5e: Report and recover from CQE with error on RQ")

Signed-off-by Aya Levin <[email protected]>

Reported-by Tariq Toukan <[email protected]>

Reviewed-by Tariq Toukan <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h |    8 ++++
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |    3 +
 drivers/net/ethernet/mellanox/mlx5/core/wq.c      |   39 ++++++++++++++++------
 drivers/net/ethernet/mellanox/mlx5/core/wq.h      |    2 +
 4 files changed, 43 insertions(+), 9 deletions(-)

drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +8 -0

@@ -179,6 +179,14 @@ mlx5e_tx_dma_unmap(struct device *pdev,
 	}
 }
 
+static inline void mlx5e_rqwq_reset(struct mlx5e_rq *rq)
+{
+	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
+		mlx5_wq_ll_reset(&rq->mpwqe.wq);
+	else
+		mlx5_wq_cyc_reset(&rq->wqe.wq);
+}
+
 /* SW parser related functions */
 
 struct mlx5e_swp_spec {

drivers/net/ethernet/mellanox/mlx5/core/en_main.c +3 -0

@@ -721,6 +721,9 @@ int mlx5e_modify_rq_state(struct mlx5e_r
 	if (!in)
 		return -ENOMEM;
 
+	if (curr_state == MLX5_RQC_STATE_RST && next_state == MLX5_RQC_STATE_RDY)
+		mlx5e_rqwq_reset(rq);
+
 	rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx);
 
 	MLX5_SET(modify_rq_in, in, rq_state, curr_state);

drivers/net/ethernet/mellanox/mlx5/core/wq.c +30 -9

@@ -94,6 +94,13 @@ void mlx5_wq_cyc_wqe_dump(struct mlx5_wq
 	print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, wqe, len, false);
 }
 
+void mlx5_wq_cyc_reset(struct mlx5_wq_cyc *wq)
+{
+	wq->wqe_ctr = 0;
+	wq->cur_sz = 0;
+	mlx5_wq_cyc_update_db_record(wq);
+}
+
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl)

@@ -192,6 +199,19 @@ err_db_free:
 	return err;
 }
 
+static void mlx5_wq_ll_init_list(struct mlx5_wq_ll *wq)
+{
+	struct mlx5_wqe_srq_next_seg *next_seg;
+	int i;
+
+	for (i = 0; i < wq->fbc.sz_m1; i++) {
+		next_seg = mlx5_wq_ll_get_wqe(wq, i);
+		next_seg->next_wqe_index = cpu_to_be16(i + 1);
+	}
+	next_seg = mlx5_wq_ll_get_wqe(wq, i);
+	wq->tail_next = &next_seg->next_wqe_index;
+}
+
 int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *wqc, struct mlx5_wq_ll *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl)

@@ -199,9 +219,7 @@ int mlx5_wq_ll_create(struct mlx5_core_d
 	u8 log_wq_stride = MLX5_GET(wq, wqc, log_wq_stride);
 	u8 log_wq_sz     = MLX5_GET(wq, wqc, log_wq_sz);
 	struct mlx5_frag_buf_ctrl *fbc = &wq->fbc;
-	struct mlx5_wqe_srq_next_seg *next_seg;
 	int err;
-	int i;
 
 	err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node);
 	if (err) {

@@ -220,13 +238,7 @@ int mlx5_wq_ll_create(struct mlx5_core_d
 
 	mlx5_init_fbc(wq_ctrl->buf.frags, log_wq_stride, log_wq_sz, fbc);
 
-	for (i = 0; i < fbc->sz_m1; i++) {
-		next_seg = mlx5_wq_ll_get_wqe(wq, i);
-		next_seg->next_wqe_index = cpu_to_be16(i + 1);
-	}
-	next_seg = mlx5_wq_ll_get_wqe(wq, i);
-	wq->tail_next = &next_seg->next_wqe_index;
-
+	mlx5_wq_ll_init_list(wq);
 	wq_ctrl->mdev = mdev;
 
 	return 0;

@@ -237,6 +249,15 @@ err_db_free:
 	return err;
 }
 
+void mlx5_wq_ll_reset(struct mlx5_wq_ll *wq)
+{
+	wq->head = 0;
+	wq->wqe_ctr = 0;
+	wq->cur_sz = 0;
+	mlx5_wq_ll_init_list(wq);
+	mlx5_wq_ll_update_db_record(wq);
+}
+
 void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl)
 {
 	mlx5_frag_buf_free(wq_ctrl->mdev, &wq_ctrl->buf);

drivers/net/ethernet/mellanox/mlx5/core/wq.h +2 -0

@@ -80,6 +80,7 @@ int mlx5_wq_cyc_create(struct mlx5_core_
 		       void *wqc, struct mlx5_wq_cyc *wq,
 		       struct mlx5_wq_ctrl *wq_ctrl);
 void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides);
+void mlx5_wq_cyc_reset(struct mlx5_wq_cyc *wq);
 
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,

@@ -92,6 +93,7 @@ int mlx5_cqwq_create(struct mlx5_core_de
 int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *wqc, struct mlx5_wq_ll *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl);
+void mlx5_wq_ll_reset(struct mlx5_wq_ll *wq);
 
 void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl);

Greg Kroah-Hartman

author maintainer

2020-02-27 14:18 UTC #150 lore raw

PATCH 145/150 net/mlx5: Fix sleep while atomic in mlx5_eswitch_get_vepa

From: Huy Nguyen <[email protected]>

commit 3d9c5e023a0dbf3e117bb416cfefd9405bf5af0c upstream.

rtnl_bridge_getlink is protected by rcu lock, so mlx5_eswitch_get_vepa cannot take mutex lock. Two possible issues can happen:
1. User at the same time change vepa mode via RTM_SETLINK command.
2. User at the same time change the switchdev mode via devlink netlink interface.

Case 1 cannot happen because rtnl executes one message in order. Case 2 can happen but we do not expect user to change the switchdev mode when changing vepa. Even if a user does it, so he will read a value which is no longer valid.

Fixes 8da202b24913 ("net/mlx5: E-Switch, Add support for VEPA in legacy mode.")

Signed-off-by Huy Nguyen <[email protected]>

Reviewed-by Mark Bloch <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c |   14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +3 ~~-11~~

@@ -2449,25 +2449,17 @@ out:
 
 int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting)
 {
-	int err = 0;
-
 	if (!esw)
 		return -EOPNOTSUPP;
 
 	if (!ESW_ALLOWED(esw))
 		return -EPERM;
 
-	mutex_lock(&esw->state_lock);
-	if (esw->mode != MLX5_ESWITCH_LEGACY) {
-		err = -EOPNOTSUPP;
-		goto out;
-	}
+	if (esw->mode != MLX5_ESWITCH_LEGACY)
+		return -EOPNOTSUPP;
 
 	*setting = esw->fdb_table.legacy.vepa_uplink_rule ? 1 : 0;
-
-out:
-	mutex_unlock(&esw->state_lock);
-	return err;
+	return 0;
 }
 
 int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,

Greg Kroah-Hartman

author maintainer

2020-02-27 14:19 UTC #151 lore raw

PATCH 146/150 net/mlx5e: Dont clear the whole vf config when switching modes

From: Dmytro Linkin <[email protected]>

commit 383de108157c881074f32914b61125e299820bd2 upstream.

There is no need to reset all vf config (except link state) between legacy and switchdev modes changes.
Also, set link state to AUTO, when legacy enabled.

Fixes 3b83b6c2e024 ("net/mlx5e: Clear VF config when switching modes")

Signed-off-by Dmytro Linkin <[email protected]>

Reviewed-by Roi Dayan <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c          |    6 +++++-
 drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c |    4 ++--
 2 files changed, 7 insertions(+), 3 deletions(-)

drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +5 -1

@@ -456,12 +456,16 @@ static void esw_destroy_legacy_table(str
 
 static int esw_legacy_enable(struct mlx5_eswitch *esw)
 {
-	int ret;
+	struct mlx5_vport *vport;
+	int ret, i;
 
 	ret = esw_create_legacy_table(esw);
 	if (ret)
 		return ret;
 
+	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
+		vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
+
 	ret = mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_LEGACY_SRIOV_VPORT_EVENTS);
 	if (ret)
 		esw_destroy_legacy_table(esw);

drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +2 -2

@@ -1377,7 +1377,7 @@ static int esw_offloads_start(struct mlx
 		return -EINVAL;
 	}
 
-	mlx5_eswitch_disable(esw, true);
+	mlx5_eswitch_disable(esw, false);
 	mlx5_eswitch_update_num_of_vfs(esw, esw->dev->priv.sriov.num_vfs);
 	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS);
 	if (err) {

@@ -2271,7 +2271,7 @@ static int esw_offloads_stop(struct mlx5
 {
 	int err, err1;
 
-	mlx5_eswitch_disable(esw, true);
+	mlx5_eswitch_disable(esw, false);
 	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy");

Greg Kroah-Hartman

author maintainer

2020-02-27 14:19 UTC #152 lore raw

PATCH 147/150 net/mlx5e: Fix crash in recovery flow without devlink reporter

From: Aya Levin <[email protected]>

commit 1ad6c43c6a7b8627240c6cc19c69e31fedc596a7 upstream.

When health reporters are not supported, recovery function is invoked directly, not via devlink health reporters.

In this direct flow, the recover function input parameter was passed incorrectly and is causing a kernel oops. This patch is fixing the input parameter.

Following call trace is observed on rx error health reporting.

Internal error: Oops: 96000007 [#1] PREEMPT SMP
Process kworker/u16:4 (pid: 4584, stack limit = 0x00000000c9e45703)
Call trace:
mlx5e_rx_reporter_err_rq_cqe_recover+0x30/0x164 [mlx5_core]
mlx5e_health_report+0x60/0x6c [mlx5_core]
mlx5e_reporter_rq_cqe_err+0x6c/0x90 [mlx5_core]
mlx5e_rq_err_cqe_work+0x20/0x2c [mlx5_core]
process_one_work+0x168/0x3d0
worker_thread+0x58/0x3d0
kthread+0x108/0x134

Fixes c50de4af1d63 ("net/mlx5e: Generalize tx reporter's functionality")

Signed-off-by Aya Levin <[email protected]>

Signed-off-by Parav Pandit <[email protected]>

Reviewed-by Tariq Toukan <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 drivers/net/ethernet/mellanox/mlx5/core/en/health.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

drivers/net/ethernet/mellanox/mlx5/core/en/health.c +1 -1

@@ -200,7 +200,7 @@ int mlx5e_health_report(struct mlx5e_pri
 	netdev_err(priv->netdev, err_str);
 
 	if (!reporter)
-		return err_ctx->recover(&err_ctx->ctx);
+		return err_ctx->recover(err_ctx->ctx);
 
 	return devlink_health_report(reporter, err_str, err_ctx);
 }

Greg Kroah-Hartman

author maintainer

2020-02-27 14:19 UTC #153 lore raw

PATCH 148/150 s390/kaslr: Fix casts in get_random

Link https://github.com/ClangBuiltLinux/linux/issues/862

From: Nathan Chancellor <[email protected]>

commit 788d671517b5c81efbed9310ccbadb8cca86a08e upstream.

Clang warns:

../arch/s390/boot/kaslr.c:78:25: warning: passing 'char *' to parameter of type 'const u8 *' (aka 'const unsigned char *') converts between pointers to integer
types with different sign [-Wpointer-sign]
(char *) entropy, (char *) entropy,
^~~~~~~~~~~~~~~~
../arch/s390/include/asm/cpacf.h:280:28: note: passing argument to parameter 'src' here
u8 *dest, const u8 *src, long src_len)
^
2 warnings generated.

Fix the cast to match what else is done in this function.

Fixes b2d24b97b2a9 ("s390/kernel: add support for kernel address space layout randomization (KASLR)")

Link https://lkml.kernel.org/r/[email protected] open here

Signed-off-by Nathan Chancellor <[email protected]>

Signed-off-by Vasily Gorbik <[email protected]>

Signed-off-by Greg Kroah-Hartman <[email protected]>

---
 arch/s390/boot/kaslr.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

arch/s390/boot/kaslr.c +1 -1

@@ -75,7 +75,7 @@ static unsigned long get_random(unsigned
 		*(unsigned long *) prng.parm_block ^= seed;
 		for (i = 0; i < 16; i++) {
 			cpacf_kmc(CPACF_KMC_PRNG, prng.parm_block,
-				  (char *) entropy, (char *) entropy,
+				  (u8 *) entropy, (u8 *) entropy,
 				  sizeof(entropy));
 			memcpy(prng.parm_block, entropy, sizeof(entropy));
 		}

Greg Kroah-Hartman

author maintainer

2020-02-27 14:19 UTC #154 lore raw

PATCH 149/150 s390/mm: Explicitly compare PAGE_DEFAULT_KEY against zero in storage_key_init_range