Skip to contentSkip to conversation

ALSA: hda: Flush interrupts on disabling

PATCH In review Sasha Levin 4 participants 191 messages Sep 22, 2019 – Oct 2, 2019 Page 2 of 2

Subsystems (32)
lore
Share & tools
lore
author maintainer
#154 lore raw

PATCH 150/185 x86/mm: Fix cpumask_of_node() error condition

In reply to Sasha Levin

From: Peter Zijlstra <[email protected]>

[ Upstream commit bc04a049f058a472695aa22905d57e2b1f4c77d9 ]

When CONFIG_DEBUG_PER_CPU_MAPS=y we validate that the @node argument of cpumask_of_node() is a valid node_id. It however forgets to check for negative numbers. Fix this by explicitly casting to unsigned int.

(unsigned)node >= nr_node_ids

verifies: 0 <= node < nr_node_ids

Also ammend the error message to match the condition.

---
 arch/x86/mm/numa.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
arch/x86/mm/numa.c +2 -2
index e6dad600614c2..4123100e0eafe 100644
@@ -861,9 +861,9 @@ void numa_remove_cpu(int cpu)
  */
 const struct cpumask *cpumask_of_node(int node)
 {
-	if (node >= nr_node_ids) {
+	if ((unsigned)node >= nr_node_ids) {
 		printk(KERN_WARNING
-			"cpumask_of_node(%d): node > nr_node_ids(%u)\n",
+			"cpumask_of_node(%d): (unsigned)node >= nr_node_ids(%u)\n",
 			node, nr_node_ids);
 		dump_stack();
 		return cpu_none_mask;
Signature · 1 line
2.20.1
author maintainer
#155 lore raw

PATCH 151/185 irqchip/sifive-plic: set max threshold for ignored handlers

In reply to Sasha Levin

From: Christoph Hellwig <[email protected]>

[ Upstream commit 9ce06497c2722a0f9109e4cc3ce35b7a69617886 ]

When running in M-mode, the S-mode plic handlers are still listed in the device tree. Ignore them by setting the maximum threshold.

---
 drivers/irqchip/irq-sifive-plic.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)
drivers/irqchip/irq-sifive-plic.c +10 -2
index cf755964f2f8b..c72c036aea768 100644
@@ -244,6 +244,7 @@ static int __init plic_init(struct device_node *node,
 		struct plic_handler *handler;
 		irq_hw_number_t hwirq;
 		int cpu, hartid;
+		u32 threshold = 0;
 
 		if (of_irq_parse_one(node, i, &parent)) {
 			pr_err("failed to parse parent for context %d.\n", i);
@@ -266,10 +267,16 @@ static int __init plic_init(struct device_node *node,
 			continue;
 		}
 
+		/*
+		 * When running in M-mode we need to ignore the S-mode handler.
+		 * Here we assume it always comes later, but that might be a
+		 * little fragile.
+		 */
 		handler = per_cpu_ptr(&plic_handlers, cpu);
 		if (handler->present) {
 			pr_warn("handler already present for context %d.\n", i);
-			continue;
+			threshold = 0xffffffff;
+			goto done;
 		}
 
 		handler->present = true;
@@ -279,8 +286,9 @@ static int __init plic_init(struct device_node *node,
 		handler->enable_base =
 			plic_regs + ENABLE_BASE + i * ENABLE_PER_HART;
 
+done:
 		/* priority must be > threshold to trigger an interrupt */
-		writel(0, handler->hart_base + CONTEXT_THRESHOLD);
+		writel(threshold, handler->hart_base + CONTEXT_THRESHOLD);
 		for (hwirq = 1; hwirq <= nr_irqs; hwirq++)
 			plic_toggle(handler, hwirq, 0);
 		nr_handlers++;
Signature · 1 line
2.20.1
author maintainer
#156 lore raw

PATCH 152/185 s390/crypto: xts-aes-s390 fix extra run-time crypto self tests finding

In reply to Sasha Levin

From: Harald Freudenberger <[email protected]>

[ Upstream commit 9e323d45ba94262620a073a3f9945ca927c07c71 ]

With 'extra run-time crypto self tests' enabled, the selftest for s390-xts fails with

alg: skcipher: xts-aes-s390 encryption unexpectedly succeeded on test vector "random: len=0 klen=64"; expected_error=-22, cfg="random: inplace use_digest nosimd src_divs=[2.61%@+4006, 84.44%@+21, 1.55%@+13, 4.50%@+344, 4.26%@+21, 2.64%@+27]"

This special case with nbytes=0 is not handled correctly and this fix now makes sure that -EINVAL is returned when there is en/decrypt called with 0 bytes to en/decrypt.

---
 arch/s390/crypto/aes_s390.c | 6 ++++++
 1 file changed, 6 insertions(+)
arch/s390/crypto/aes_s390.c +6 -0
index d00f84add5f4c..6d2dbb5089d5c 100644
@@ -586,6 +586,9 @@ static int xts_aes_encrypt(struct blkcipher_desc *desc,
 	struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
+	if (!nbytes)
+		return -EINVAL;
+
 	if (unlikely(!xts_ctx->fc))
 		return xts_fallback_encrypt(desc, dst, src, nbytes);
 
@@ -600,6 +603,9 @@ static int xts_aes_decrypt(struct blkcipher_desc *desc,
 	struct s390_xts_ctx *xts_ctx = crypto_blkcipher_ctx(desc->tfm);
 	struct blkcipher_walk walk;
 
+	if (!nbytes)
+		return -EINVAL;
+
 	if (unlikely(!xts_ctx->fc))
 		return xts_fallback_decrypt(desc, dst, src, nbytes);
 
Signature · 1 line
2.20.1
author maintainer
#157 lore raw

PATCH 153/185 irqchip/gic-v3-its: Fix LPI release for Multi-MSI devices

In reply to Sasha Levin

From: Marc Zyngier <[email protected]>

[ Upstream commit c9c96e30ecaa0aafa225aa1a5392cb7db17c7a82 ]

When allocating a range of LPIs for a Multi-MSI capable device, this allocation extended to the closest power of 2.

But on the release path, the interrupts are released one by one. This results in not releasing the "extra" range, leaking the its_device. Trying to reprobe the device will then fail.

Fix it by releasing the LPIs the same way we allocate them.

Fixes 8208d1708b88 ("irqchip/gic-v3-its: Align PCI Multi-MSI allocation on their size")
---
 drivers/irqchip/irq-gic-v3-its.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)
drivers/irqchip/irq-gic-v3-its.c +4 -5
index 20e5482d91b94..fca8b90028522 100644
@@ -2641,14 +2641,13 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 	struct its_node *its = its_dev->its;
 	int i;
 
+	bitmap_release_region(its_dev->event_map.lpi_map,
+			      its_get_event_id(irq_domain_get_irq_data(domain, virq)),
+			      get_count_order(nr_irqs));
+
 	for (i = 0; i < nr_irqs; i++) {
 		struct irq_data *data = irq_domain_get_irq_data(domain,
 								virq + i);
-		u32 event = its_get_event_id(data);
-
-		/* Mark interrupt index as unused */
-		clear_bit(event, its_dev->event_map.lpi_map);
-
 		/* Nuke the entry in the domain */
 		irq_domain_reset_irq_data(data);
 	}
Signature · 1 line
2.20.1
author maintainer
#158 lore raw

PATCH 154/185 x86/platform/uv: Fix kmalloc() NULL check routine

In reply to Sasha Levin

From: Austin Kim <[email protected]>

[ Upstream commit 864b23f0169d5bff677e8443a7a90dfd6b090afc ]

The result of kmalloc() should have been checked ahead of below statement:

	pqp = (struct bau_pq_entry *)vp;

Move BUG_ON(!vp) before above statement.

---
 arch/x86/platform/uv/tlb_uv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
arch/x86/platform/uv/tlb_uv.c +2 -2
index 0c7dfec4acac8..5a66d73620ce4 100644
@@ -1815,9 +1815,9 @@ static void pq_init(int node, int pnode)
 
 	plsize = (DEST_Q_SIZE + 1) * sizeof(struct bau_pq_entry);
 	vp = kmalloc_node(plsize, GFP_KERNEL, node);
-	pqp = (struct bau_pq_entry *)vp;
-	BUG_ON(!pqp);
+	BUG_ON(!vp);
 
+	pqp = (struct bau_pq_entry *)vp;
 	cp = (char *)pqp + 31;
 	pqp = (struct bau_pq_entry *)(((unsigned long)cp >> 5) << 5);
 
Signature · 1 line
2.20.1
maintainer
#159 lore raw

Re: [PATCH AUTOSEL 5.2 154/185] x86/platform/uv: Fix kmalloc() NULL check routine

Quoted 41 lines · Sasha Levin

From: Austin Kim <[email protected]>

[ Upstream commit 864b23f0169d5bff677e8443a7a90dfd6b090afc ]

The result of kmalloc() should have been checked ahead of below statement:

	pqp = (struct bau_pq_entry *)vp;

Move BUG_ON(!vp) before above statement.

---
 arch/x86/platform/uv/tlb_uv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)
arch/x86/platform/uv/tlb_uv.c +0 -0
index 0c7dfec4acac8..5a66d73620ce4 100644
@@ -1815,9 +1815,9 @@ static void pq_init(int node, int pnode)
 

arch/x86/platform/uv/tlb_uv.c static void pq_init(int node, int pnode) · line 1823

Quoted 10 lines
arch/x86/platform/uv/tlb_uv.c +2 -2
 	plsize = (DEST_Q_SIZE + 1) * sizeof(struct bau_pq_entry);
 	vp = kmalloc_node(plsize, GFP_KERNEL, node);
-	pqp = (struct bau_pq_entry *)vp;
-	BUG_ON(!pqp);
+	BUG_ON(!vp);
 
+	pqp = (struct bau_pq_entry *)vp;
 	cp = (char *)pqp + 31;
 	pqp = (struct bau_pq_entry *)(((unsigned long)cp >> 5) << 5);
 

Please drop from everywhere.

thanks,

greg k-h

author maintainer
#160 lore raw

PATCH 155/185 x86/cpu: Add Tiger Lake to Intel family

In reply to Sasha Levin

From: Gayatri Kammela <[email protected]>

[ Upstream commit 6e1c32c5dbb4b90eea8f964c2869d0bde050dbe0 ]

Add the model numbers/CPUIDs of Tiger Lake mobile and desktop to the Intel family.

---
 arch/x86/include/asm/intel-family.h | 3 +++
 1 file changed, 3 insertions(+)
arch/x86/include/asm/intel-family.h +3 -0
index f60ddd655c787..82a57d344b9bc 100644
@@ -58,6 +58,9 @@
 #define INTEL_FAM6_ICELAKE_MOBILE	0x7E
 #define INTEL_FAM6_ICELAKE_NNPI		0x9D
 
+#define INTEL_FAM6_TIGERLAKE_L		0x8C
+#define INTEL_FAM6_TIGERLAKE		0x8D
+
 /* "Small Core" Processors (Atom) */
 
 #define INTEL_FAM6_ATOM_BONNELL		0x1C /* Diamondville, Pineview */
Signature · 1 line
2.20.1
author maintainer
#161 lore raw

PATCH 156/185 platform/x86: intel_pmc_core: Do not ioremap RAM

In reply to Sasha Levin

From: "M. Vefa Bicakci" <[email protected]>

[ Upstream commit 7d505758b1e556cdf65a5e451744fe0ae8063d17 ]

On a Xen-based PVH virtual machine with more than 4 GiB of RAM, intel_pmc_core fails initialization with the following warning message from the kernel, indicating that the driver is attempting to ioremap RAM:

ioremap on RAM at 0x00000000fe000000 - 0x00000000fe001fff

  WARNING: CPU: 1 PID: 434 at arch/x86/mm/ioremap.c:186 __ioremap_caller.constprop.0+0x2aa/0x2c0
...
  Call Trace:
   ? pmc_core_probe+0x87/0x2d0 [intel_pmc_core]
   pmc_core_probe+0x87/0x2d0 [intel_pmc_core]

This issue appears to manifest itself because of the following fallback mechanism in the driver:

	if (lpit_read_residency_count_address(&slp_s0_addr))
		pmcdev->base_addr = PMC_BASE_ADDR_DEFAULT;

The validity of address PMC_BASE_ADDR_DEFAULT (i.e., 0xFE000000) is not verified by the driver, which is what this patch introduces. With this patch, if address PMC_BASE_ADDR_DEFAULT is in RAM, then the driver will not attempt to ioremap the aforementioned address.

---
 drivers/platform/x86/intel_pmc_core.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
drivers/platform/x86/intel_pmc_core.c +6 -2
index be6cda89dcf5b..01a530e2f8017 100644
@@ -882,10 +882,14 @@ static int pmc_core_probe(struct platform_device *pdev)
 	if (pmcdev->map == &spt_reg_map && !pci_dev_present(pmc_pci_ids))
 		pmcdev->map = &cnp_reg_map;
 
-	if (lpit_read_residency_count_address(&slp_s0_addr))
+	if (lpit_read_residency_count_address(&slp_s0_addr)) {
 		pmcdev->base_addr = PMC_BASE_ADDR_DEFAULT;
-	else
+
+		if (page_is_ram(PHYS_PFN(pmcdev->base_addr)))
+			return -ENODEV;
+	} else {
 		pmcdev->base_addr = slp_s0_addr - pmcdev->map->slp_s0_offset;
+	}
 
 	pmcdev->regbase = ioremap(pmcdev->base_addr,
 				  pmcdev->map->regmap_length);
Signature · 1 line
2.20.1
author maintainer
#162 lore raw

PATCH 157/185 ASoC: es8316: support fixed and variable both clock rates

In reply to Sasha Levin

From: Katsuhiro Suzuki <[email protected]>

[ Upstream commit ebe02a5b9ef05e3b812af3d628cdf6206d9ba610 ]

This patch supports some type of machine drivers that set 0 to mclk when sound device goes to idle state. After applied this patch, sysclk == 0 means there is no constraint of sound rate and other values will set constraints which is derived by sysclk setting.

Original code refuses sysclk == 0 setting. But some boards and SoC (such as RockPro64 and RockChip I2S) has connected SoC MCLK out to ES8316 MCLK in. In this case, SoC side I2S will choose suitable frequency of MCLK such as fs * mclk-fs when user starts playing or capturing.

Bad scenario as follows (mclk-fs = 256):
- Initialize sysclk by correct value (Ex. 12.288MHz)

    - ES8316 set constraints of PCM rate by sysclk
      48kHz (1/256), 32kHz (1/384), 30.720kHz (1/400),
      24kHz (1/512), 16kHz (1/768), 12kHz (1/1024)

- Play 48kHz sound, it's acceptable
- Sysclk is not changed

- Play 32kHz sound, it's acceptable
- Set sysclk by 8.192MHz (= fs * mclk-fs = 32k * 256)

    - ES8316 set constraints of PCM rate by sysclk
      32kHz (1/256), 21.33kHz (1/384), 20.48kHz (1/400),
      16kHz (1/512), 10.66kHz (1/768), 8kHz (1/1024)

- Play 48kHz again, but it's NOT acceptable because constraints list does not allow 48kHz

---
 sound/soc/codecs/es8316.c | 35 ++++++++++++++++++++---------------
 1 file changed, 20 insertions(+), 15 deletions(-)
sound/soc/codecs/es8316.c +20 -15
index 96d04896193f2..c47b3c4bb06c7 100644
@@ -368,8 +368,12 @@ static int es8316_set_dai_sysclk(struct snd_soc_dai *codec_dai,
 
 	es8316->sysclk = freq;
 
-	if (freq == 0)
+	if (freq == 0) {
+		es8316->sysclk_constraints.list = NULL;
+		es8316->sysclk_constraints.count = 0;
+
 		return 0;
+	}
 
 	/* Limit supported sample rates to ones that can be autodetected
 	 * by the codec running in slave mode.
@@ -444,17 +448,10 @@ static int es8316_pcm_startup(struct snd_pcm_substream *substream,
 	struct snd_soc_component *component = dai->component;
 	struct es8316_priv *es8316 = snd_soc_component_get_drvdata(component);
 
-	if (es8316->sysclk == 0) {
-		dev_err(component->dev, "No sysclk provided\n");
-		return -EINVAL;
-	}
-
-	/* The set of sample rates that can be supported depends on the
-	 * MCLK supplied to the CODEC.
-	 */
-	snd_pcm_hw_constraint_list(substream->runtime, 0,
-				   SNDRV_PCM_HW_PARAM_RATE,
-				   &es8316->sysclk_constraints);
+	if (es8316->sysclk_constraints.list)
+		snd_pcm_hw_constraint_list(substream->runtime, 0,
+					   SNDRV_PCM_HW_PARAM_RATE,
+					   &es8316->sysclk_constraints);
 
 	return 0;
 }
@@ -466,11 +463,19 @@ static int es8316_pcm_hw_params(struct snd_pcm_substream *substream,
 	struct snd_soc_component *component = dai->component;
 	struct es8316_priv *es8316 = snd_soc_component_get_drvdata(component);
 	u8 wordlen = 0;
+	int i;
 
-	if (!es8316->sysclk) {
-		dev_err(component->dev, "No MCLK configured\n");
-		return -EINVAL;
+	/* Validate supported sample rates that are autodetected from MCLK */
+	for (i = 0; i < NR_SUPPORTED_MCLK_LRCK_RATIOS; i++) {
+		const unsigned int ratio = supported_mclk_lrck_ratios[i];
+
+		if (es8316->sysclk % ratio != 0)
+			continue;
+		if (es8316->sysclk / ratio == params_rate(params))
+			break;
 	}
+	if (i == NR_SUPPORTED_MCLK_LRCK_RATIOS)
+		return -EINVAL;
 
 	switch (params_format(params)) {
 	case SNDRV_PCM_FORMAT_S16_LE:
Signature · 1 line
2.20.1
author maintainer
#163 lore raw

PATCH 158/185 SoC: simple-card-utils: set 0Hz to sysclk when shutdown

In reply to Sasha Levin

From: Katsuhiro Suzuki <[email protected]>

[ Upstream commit 2458adb8f92ad4d07ef7ab27c5bafa1d3f4678d6 ]

This patch set 0Hz to sysclk when shutdown the card.

Some codecs set rate constraints that derives from sysclk. This mechanism works correctly if machine drivers give fixed frequency.

But simple-audio and audio-graph card set variable clock rate if 'mclk-fs' property exists. In this case, rate constraints will go bad scenario. For example a codec accepts three limited rates (mclk / 256, mclk / 384, mclk / 512).

Bad scenario as follows (mclk-fs = 256):
- Initialize sysclk by correct value (Ex. 12.288MHz)
- Codec set constraints of PCM rate by sysclk 48kHz (1/256), 32kHz (1/384), 24kHz (1/512)
- Play 48kHz sound, it's acceptable
- Sysclk is not changed

- Play 32kHz sound, it's acceptable
- Set sysclk to 8.192MHz (= fs * mclk-fs = 32k * 256)
- Codec set constraints of PCM rate by sysclk 32kHz (1/256), 21.33kHz (1/384), 16kHz (1/512)

- Play 48kHz again, but it's NOT acceptable because constraints do not allow 48kHz

So codecs treat 0Hz sysclk as signal of applying no constraints to avoid this problem.

---
 sound/soc/generic/simple-card-utils.c | 7 +++++++
 1 file changed, 7 insertions(+)
sound/soc/generic/simple-card-utils.c +7 -0
index f4c6375d11c7a..ef1adf87cbc8b 100644
@@ -224,10 +224,17 @@ EXPORT_SYMBOL_GPL(asoc_simple_startup);
 void asoc_simple_shutdown(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_dai *codec_dai = rtd->codec_dai;
+	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	struct asoc_simple_priv *priv = snd_soc_card_get_drvdata(rtd->card);
 	struct simple_dai_props *dai_props =
 		simple_priv_to_props(priv, rtd->num);
 
+	if (dai_props->mclk_fs) {
+		snd_soc_dai_set_sysclk(codec_dai, 0, 0, SND_SOC_CLOCK_IN);
+		snd_soc_dai_set_sysclk(cpu_dai, 0, 0, SND_SOC_CLOCK_OUT);
+	}
+
 	asoc_simple_clk_disable(dai_props->cpu_dai);
 
 	asoc_simple_clk_disable(dai_props->codec_dai);
Signature · 1 line
2.20.1
author maintainer
#164 lore raw

PATCH 159/185 ASoC: dmaengine: Make the pcm->name equal to pcm->id if the name is not set

In reply to Sasha Levin

From: Peter Ujfalusi <[email protected]>

[ Upstream commit 2ec42f3147e1610716f184b02e65d7f493eed925 ]

Some tools use the snd_pcm_info_get_name() to try to identify PCMs or for other purposes.

Currently it is left empty with the dmaengine-pcm, in this case copy the pcm->id string as pcm->name.

For example IGT is using this to find the HDMI PCM for testing audio on it.

---
 sound/soc/soc-generic-dmaengine-pcm.c | 6 ++++++
 1 file changed, 6 insertions(+)
sound/soc/soc-generic-dmaengine-pcm.c +6 -0
index 748f5f641002e..d93db2c2b5270 100644
@@ -306,6 +306,12 @@ static int dmaengine_pcm_new(struct snd_soc_pcm_runtime *rtd)
 
 		if (!dmaengine_pcm_can_report_residue(dev, pcm->chan[i]))
 			pcm->flags |= SND_DMAENGINE_PCM_FLAG_NO_RESIDUE;
+
+		if (rtd->pcm->streams[i].pcm->name[0] == '\0') {
+			strncpy(rtd->pcm->streams[i].pcm->name,
+				rtd->pcm->streams[i].pcm->id,
+				sizeof(rtd->pcm->streams[i].pcm->name));
+		}
 	}
 
 	return 0;
Signature · 1 line
2.20.1
author maintainer
#165 lore raw

PATCH 160/185 io_uring: fix wrong sequence setting logic

In reply to Sasha Levin

From: Jackie Liu <[email protected]>

[ Upstream commit 8776f3fa15a5cd213c4dfab7ddaf557983374ea6 ]

Sqo_thread will get sqring in batches, which will cause ctx->cached_sq_head to be added in batches. if one of these sqes is set with the DRAIN flag, then he will never get a chance to process, and finally sqo_thread will not exit.

Fixes de0617e4671 ("io_uring: add support for marking commands as draining")
---
 fs/io_uring.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
fs/io_uring.c +3 -1
index 03cd8f5bba850..701936f2bde39 100644
@@ -288,6 +288,7 @@ struct io_ring_ctx {
 struct sqe_submit {
 	const struct io_uring_sqe	*sqe;
 	unsigned short			index;
+	u32				sequence;
 	bool				has_user;
 	bool				needs_lock;
 	bool				needs_fixed_file;
@@ -1894,7 +1895,7 @@ static int io_req_set_file(struct io_ring_ctx *ctx, const struct sqe_submit *s,
 
 	if (flags & IOSQE_IO_DRAIN) {
 		req->flags |= REQ_F_IO_DRAIN;
-		req->sequence = ctx->cached_sq_head - 1;
+		req->sequence = s->sequence;
 	}
 
 	if (!io_op_needs_file(s->sqe))
@@ -2050,6 +2051,7 @@ static bool io_get_sqring(struct io_ring_ctx *ctx, struct sqe_submit *s)
 	if (head < ctx->sq_entries) {
 		s->index = head;
 		s->sqe = &ctx->sq_sqes[head];
+		s->sequence = ctx->cached_sq_head;
 		ctx->cached_sq_head++;
 		return true;
 	}
Signature · 1 line
2.20.1
author maintainer
#166 lore raw

PATCH 161/185 block: make rq sector size accessible for block stats

In reply to Sasha Levin

From: Hou Tao <[email protected]>

[ Upstream commit 3d24430694077313c75c6b89f618db09943621e4 ]

Currently rq->data_len will be decreased by partial completion or zeroed by completion, so when blk_stat_add() is invoked, data_len will be zero and there will never be samples in poll_cb because blk_mq_poll_stats_bkt() will return -1 if data_len is zero.

We could move blk_stat_add() back to __blk_mq_complete_request(), but that would make the effort of trying to call ktime_get_ns() once in vain. Instead we can reuse throtl_size field, and use it for both block stats and block throttle, and adjust the logic in blk_mq_poll_stats_bkt() accordingly.

Fixes 4bc6339a583c ("block: move blk_stat_add() to __blk_mq_end_request()")
---
 block/blk-mq.c         | 11 +++++------
 block/blk-throttle.c   |  3 ++-
 include/linux/blkdev.h | 15 ++++++++++++---
 3 files changed, 19 insertions(+), 10 deletions(-)
block/blk-mq.c +5 -6
index f934e8afe5b43..af93ca28ce4f0 100644
@@ -44,12 +44,12 @@ static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
 
 static int blk_mq_poll_stats_bkt(const struct request *rq)
 {
-	int ddir, bytes, bucket;
+	int ddir, sectors, bucket;
 
 	ddir = rq_data_dir(rq);
-	bytes = blk_rq_bytes(rq);
+	sectors = blk_rq_stats_sectors(rq);
 
-	bucket = ddir + 2*(ilog2(bytes) - 9);
+	bucket = ddir + 2 * ilog2(sectors);
 
 	if (bucket < 0)
 		return -1;
@@ -330,6 +330,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 	else
 		rq->start_time_ns = 0;
 	rq->io_start_time_ns = 0;
+	rq->stats_sectors = 0;
 	rq->nr_phys_segments = 0;
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 	rq->nr_integrity_segments = 0;
@@ -679,9 +680,7 @@ void blk_mq_start_request(struct request *rq)
 
 	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
 		rq->io_start_time_ns = ktime_get_ns();
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-		rq->throtl_size = blk_rq_sectors(rq);
-#endif
+		rq->stats_sectors = blk_rq_sectors(rq);
 		rq->rq_flags |= RQF_STATS;
 		rq_qos_issue(q, rq);
 	}
block/blk-throttle.c +2 -1
index 8ab6c81532236..ee74bffe3504d 100644
@@ -2246,7 +2246,8 @@ void blk_throtl_stat_add(struct request *rq, u64 time_ns)
 	struct request_queue *q = rq->q;
 	struct throtl_data *td = q->td;
 
-	throtl_track_latency(td, rq->throtl_size, req_op(rq), time_ns >> 10);
+	throtl_track_latency(td, blk_rq_stats_sectors(rq), req_op(rq),
+			     time_ns >> 10);
 }
 
 void blk_throtl_bio_endio(struct bio *bio)
include/linux/blkdev.h +12 -3
index 93baef66b9424..4c6754e536725 100644
@@ -202,9 +202,12 @@ struct request {
 #ifdef CONFIG_BLK_WBT
 	unsigned short wbt_flags;
 #endif
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-	unsigned short throtl_size;
-#endif
+	/*
+	 * rq sectors used for blk stats. It has the same value
+	 * with blk_rq_sectors(rq), except that it never be zeroed
+	 * by completion.
+	 */
+	unsigned short stats_sectors;
 
 	/*
 	 * Number of scatter-gather DMA addr+len pairs after
@@ -902,6 +905,7 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev)
  * blk_rq_err_bytes()		: bytes left till the next error boundary
  * blk_rq_sectors()		: sectors left in the entire request
  * blk_rq_cur_sectors()		: sectors left in the current segment
+ * blk_rq_stats_sectors()	: sectors of the entire request used for stats
  */
 static inline sector_t blk_rq_pos(const struct request *rq)
 {
@@ -930,6 +934,11 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 	return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
 }
 
+static inline unsigned int blk_rq_stats_sectors(const struct request *rq)
+{
+	return rq->stats_sectors;
+}
+
 #ifdef CONFIG_BLK_DEV_ZONED
 static inline unsigned int blk_rq_zone_no(struct request *rq)
 {
Signature · 1 line
2.20.1
author maintainer
#167 lore raw

PATCH 162/185 raid5: don't set STRIPE_HANDLE to stripe which is in batch list

In reply to Sasha Levin

From: Guoqing Jiang <[email protected]>

[ Upstream commit 6ce220dd2f8ea71d6afc29b9a7524c12e39f374a ]

If stripe in batch list is set with STRIPE_HANDLE flag, then the stripe could be set with STRIPE_ACTIVE by the handle_stripe function. And if error happens to the batch_head at the same time, break_stripe_batch_list is called, then below warning could happen (the same report in [1]), it means a member of batch list was set with STRIPE_ACTIVE.

[7028915.431770] stripe state: 2001
[7028915.431815] ------------[ cut here ]------------
[7028915.431828] WARNING: CPU: 18 PID: 29089 at drivers/md/raid5.c:4614 break_stripe_batch_list+0x203/0x240 [raid456]
[...]
[7028915.431879] CPU: 18 PID: 29089 Comm: kworker/u82:5 Tainted: G           O    4.14.86-1-storage #4.14.86-1.2~deb9
[7028915.431881] Hardware name: Supermicro SSG-2028R-ACR24L/X10DRH-iT, BIOS 3.1 06/18/2018
[7028915.431888] Workqueue: raid5wq raid5_do_work [raid456]
[7028915.431890] task: ffff9ab0ef36d7c0 task.stack: ffffb72926f84000
[7028915.431896] RIP: 0010:break_stripe_batch_list+0x203/0x240 [raid456]
[7028915.431898] RSP: 0018:ffffb72926f87ba8 EFLAGS: 00010286
[7028915.431900] RAX: 0000000000000012 RBX: ffff9aaa84a98000 RCX: 0000000000000000
[7028915.431901] RDX: 0000000000000000 RSI: ffff9ab2bfa15458 RDI: ffff9ab2bfa15458
[7028915.431902] RBP: ffff9aaa8fb4e900 R08: 0000000000000001 R09: 0000000000002eb4
[7028915.431903] R10: 00000000ffffffff R11: 0000000000000000 R12: ffff9ab1736f1b00
[7028915.431904] R13: 0000000000000000 R14: ffff9aaa8fb4e900 R15: 0000000000000001
[7028915.431906] FS:  0000000000000000(0000) GS:ffff9ab2bfa00000(0000) knlGS:0000000000000000
[7028915.431907] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[7028915.431908] CR2: 00007ff953b9f5d8 CR3: 0000000bf4009002 CR4: 00000000003606e0
[7028915.431909] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[7028915.431910] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[7028915.431910] Call Trace:
[7028915.431923]  handle_stripe+0x8e7/0x2020 [raid456]
[7028915.431930]  ? __wake_up_common_lock+0x89/0xc0
[7028915.431935]  handle_active_stripes.isra.58+0x35f/0x560 [raid456]
[7028915.431939]  raid5_do_work+0xc6/0x1f0 [raid456]

Also commit 59fc630b8b5f9f ("RAID5: batch adjacent full stripe write") said "If a stripe is added to batch list, then only the first stripe of the list should be put to handle_list and run handle_stripe."

So don't set STRIPE_HANDLE to stripe which is already in batch list, otherwise the stripe could be put to handle_list and run handle_stripe, then the above warning could be triggered.

[1]. https://www.spinics.net/lists/raid/msg62552.html

---
 drivers/md/raid5.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/md/raid5.c +2 -1
index da94cbaa1a9ed..8d2811e436b93 100644
@@ -5719,7 +5719,8 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
 				do_flush = false;
 			}
 
-			set_bit(STRIPE_HANDLE, &sh->state);
+			if (!sh->batch_head)
+				set_bit(STRIPE_HANDLE, &sh->state);
 			clear_bit(STRIPE_DELAYED, &sh->state);
 			if ((!sh->batch_head || sh == sh->batch_head) &&
 			    (bi->bi_opf & REQ_SYNC) &&
Signature · 1 line
2.20.1
author maintainer
#168 lore raw

PATCH 163/185 mmc: core: Clarify sdio_irq_pending flag for MMC_CAP2_SDIO_IRQ_NOTHREAD

In reply to Sasha Levin

From: Ulf Hansson <[email protected]>

[ Upstream commit 36d57efb4af534dd6b442ea0b9a04aa6dfa37abe ]

The sdio_irq_pending flag is used to let host drivers indicate that it has signaled an IRQ. If that is the case and we only have a single SDIO func that have claimed an SDIO IRQ, our assumption is that we can avoid reading the SDIO_CCCR_INTx register and just call the SDIO func irq handler immediately. This makes sense, but the flag is set/cleared in a somewhat messy order, let's fix that up according to below.

First, the flag is currently set in sdio_run_irqs(), which is executed as a work that was scheduled from sdio_signal_irq(). To make it more implicit that the host have signaled an IRQ, let's instead immediately set the flag in sdio_signal_irq(). This also makes the behavior consistent with host drivers that uses the legacy, mmc_signal_sdio_irq() API. This have no functional impact, because we don't expect host drivers to call sdio_signal_irq() until after the work (sdio_run_irqs()) have been executed anyways.

Second, currently we never clears the flag when using the sdio_run_irqs() work, but only when using the sdio_irq_thread(). Let make the behavior consistent, by moving the flag to be cleared inside the common process_sdio_pending_irqs() function. Additionally, tweak the behavior of the flag slightly, by avoiding to clear it unless we processed the SDIO IRQ. The purpose with this at this point, is to keep the information about whether there have been an SDIO IRQ signaled by the host, so at system resume we can decide to process it without reading the SDIO_CCCR_INTx register.

---
 drivers/mmc/core/sdio_irq.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)
drivers/mmc/core/sdio_irq.c +6 -3
index 9f54a259a1b36..e4823ef0a0de9 100644
@@ -31,6 +31,7 @@ static int process_sdio_pending_irqs(struct mmc_host *host)
 {
 	struct mmc_card *card = host->card;
 	int i, ret, count;
+	bool sdio_irq_pending = host->sdio_irq_pending;
 	unsigned char pending;
 	struct sdio_func *func;
 
@@ -38,13 +39,16 @@ static int process_sdio_pending_irqs(struct mmc_host *host)
 	if (mmc_card_suspended(card))
 		return 0;
 
+	/* Clear the flag to indicate that we have processed the IRQ. */
+	host->sdio_irq_pending = false;
+
 	/*
 	 * Optimization, if there is only 1 function interrupt registered
 	 * and we know an IRQ was signaled then call irq handler directly.
 	 * Otherwise do the full probe.
 	 */
 	func = card->sdio_single_irq;
-	if (func && host->sdio_irq_pending) {
+	if (func && sdio_irq_pending) {
 		func->irq_handler(func);
 		return 1;
 	}
@@ -96,7 +100,6 @@ void sdio_run_irqs(struct mmc_host *host)
 {
 	mmc_claim_host(host);
 	if (host->sdio_irqs) {
-		host->sdio_irq_pending = true;
 		process_sdio_pending_irqs(host);
 		if (host->ops->ack_sdio_irq)
 			host->ops->ack_sdio_irq(host);
@@ -115,6 +118,7 @@ void sdio_irq_work(struct work_struct *work)
 
 void sdio_signal_irq(struct mmc_host *host)
 {
+	host->sdio_irq_pending = true;
 	queue_delayed_work(system_wq, &host->sdio_irq_work, 0);
 }
 EXPORT_SYMBOL_GPL(sdio_signal_irq);
@@ -160,7 +164,6 @@ static int sdio_irq_thread(void *_host)
 		if (ret)
 			break;
 		ret = process_sdio_pending_irqs(host);
-		host->sdio_irq_pending = false;
 		mmc_release_host(host);
 
 		/*
Signature · 1 line
2.20.1
author maintainer
#169 lore raw

PATCH 164/185 sched/psi: Correct overly pessimistic size calculation

In reply to Sasha Levin

From: Miles Chen <miles.chen-NuS5LvNUpcJWk0Htik3J/[email protected]>

[ Upstream commit 4adcdcea717cb2d8436bef00dd689aa5bc76f11b ]

When passing a equal or more then 32 bytes long string to psi_write(), psi_write() copies 31 bytes to its buf and overwrites buf[30] with '\0'. Which makes the input string 1 byte shorter than it should be.

Fix it by copying sizeof(buf) bytes when nbytes >= sizeof(buf).

This does not cause problems in normal use case like:
"some 500000 10000000" or "full 500000 10000000" because they are less than 32 bytes in length.

	/* assuming nbytes == 35 */
	char buf[32];

	buf_size = min(nbytes, (sizeof(buf) - 1)); /* buf_size = 31 */
	if (copy_from_user(buf, user_buf, buf_size))
		return -EFAULT;

	buf[buf_size - 1] = '\0'; /* buf[30] = '\0' */

Before:

%cd /proc/pressure/
%echo "123456789|123456789|123456789|1234" > memory

 [   22.473497] nbytes=35,buf_size=31
 [   22.473775] 123456789|123456789|123456789| (print 30 chars)
 %sh: write error: Invalid argument

%echo "123456789|123456789|123456789|1" > memory

 [   64.916162] nbytes=32,buf_size=31
 [   64.916331] 123456789|123456789|123456789| (print 30 chars)
 %sh: write error: Invalid argument

After:

%cd /proc/pressure/
%echo "123456789|123456789|123456789|1234" > memory

 [  254.837863] nbytes=35,buf_size=32
 [  254.838541] 123456789|123456789|123456789|1 (print 31 chars)
 %sh: write error: Invalid argument

%echo "123456789|123456789|123456789|1" > memory

 [ 9965.714935] nbytes=32,buf_size=32
 [ 9965.715096] 123456789|123456789|123456789|1 (print 31 chars)
 %sh: write error: Invalid argument

Also remove the superfluous parentheses.

---
 kernel/sched/psi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/sched/psi.c +1 -1
index 6e52b67b420e7..517e3719027e6 100644
@@ -1198,7 +1198,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf,
 	if (static_branch_likely(&psi_disabled))
 		return -EOPNOTSUPP;
 
-	buf_size = min(nbytes, (sizeof(buf) - 1));
+	buf_size = min(nbytes, sizeof(buf));
 	if (copy_from_user(buf, user_buf, buf_size))
 		return -EFAULT;
 
Signature · 1 line
2.20.1
author maintainer
#170 lore raw

PATCH 165/185 mmc: sdhci: Fix incorrect switch to HS mode

In reply to Sasha Levin

From: Al Cooper <[email protected]>

[ Upstream commit c894e33ddc1910e14d6f2a2016f60ab613fd8b37 ]

When switching from any MMC speed mode that requires 1.8v (HS200, HS400 and HS400ES) to High Speed (HS) mode, the system ends up configured for SDR12 with a 50MHz clock which is an illegal mode.

This happens because the SDHCI_CTRL_VDD_180 bit in the SDHCI_HOST_CONTROL2 register is left set and when this bit is set, the speed mode is controlled by the SDHCI_CTRL_UHS field in the SDHCI_HOST_CONTROL2 register. The SDHCI_CTRL_UHS field will end up being set to 0 (SDR12) by sdhci_set_uhs_signaling() because there is no UHS mode being set.

The fix is to change sdhci_set_uhs_signaling() to set the SDHCI_CTRL_UHS field to SDR25 (which is the same as HS) for any switch to HS mode.

This was found on a new eMMC controller that does strict checking of the speed mode and the corresponding clock rate. It caused the switch to HS400 mode to fail because part of the sequence to switch to HS400 requires a switch from HS200 to HS before going to HS400.

---
 drivers/mmc/host/sdhci.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/mmc/host/sdhci.c +3 -1
index a5dc5aae973e6..c66e66fbaeb40 100644
@@ -1849,7 +1849,9 @@ void sdhci_set_uhs_signaling(struct sdhci_host *host, unsigned timing)
 		ctrl_2 |= SDHCI_CTRL_UHS_SDR104;
 	else if (timing == MMC_TIMING_UHS_SDR12)
 		ctrl_2 |= SDHCI_CTRL_UHS_SDR12;
-	else if (timing == MMC_TIMING_UHS_SDR25)
+	else if (timing == MMC_TIMING_SD_HS ||
+		 timing == MMC_TIMING_MMC_HS ||
+		 timing == MMC_TIMING_UHS_SDR25)
 		ctrl_2 |= SDHCI_CTRL_UHS_SDR25;
 	else if (timing == MMC_TIMING_UHS_SDR50)
 		ctrl_2 |= SDHCI_CTRL_UHS_SDR50;
Signature · 1 line
2.20.1
author maintainer
#171 lore raw

PATCH 166/185 mmc: core: Add helper function to indicate if SDIO IRQs is enabled

In reply to Sasha Levin

From: Ulf Hansson <[email protected]>

[ Upstream commit bd880b00697befb73eff7220ee20bdae4fdd487b ]

To avoid each host driver supporting SDIO IRQs, from keeping track internally about if SDIO IRQs has been claimed, let's introduce a common helper function, sdio_irq_claimed().

The function returns true if SDIO IRQs are claimed, via using the information about the number of claimed irqs. This is safe, even without any locks, as long as the helper function is called only from runtime/system suspend callbacks of the host driver.

---
 include/linux/mmc/host.h | 9 +++++++++
 1 file changed, 9 insertions(+)
include/linux/mmc/host.h +9 -0
index 7ac3755444d3d..56a8ad506072c 100644
@@ -493,6 +493,15 @@ void mmc_command_done(struct mmc_host *host, struct mmc_request *mrq);
 
 void mmc_cqe_request_done(struct mmc_host *host, struct mmc_request *mrq);
 
+/*
+ * May be called from host driver's system/runtime suspend/resume callbacks,
+ * to know if SDIO IRQs has been claimed.
+ */
+static inline bool sdio_irq_claimed(struct mmc_host *host)
+{
+	return host->sdio_irqs > 0;
+}
+
 static inline void mmc_signal_sdio_irq(struct mmc_host *host)
 {
 	host->ops->enable_sdio_irq(host, 0);
Signature · 1 line
2.20.1
author maintainer
#172 lore raw

PATCH 167/185 mmc: dw_mmc: Re-store SDIO IRQs mask at system resume

In reply to Sasha Levin

From: Ulf Hansson <[email protected]>

[ Upstream commit 7c526608d5afb62cbc967225e2ccaacfdd142e9d ]

In cases when SDIO IRQs have been enabled, runtime suspend is prevented by the driver. However, this still means dw_mci_runtime_suspend|resume() gets called during system suspend/resume, via pm_runtime_force_suspend|resume(). This means during system suspend/resume, the register context of the dw_mmc device most likely loses its register context, even in cases when SDIO IRQs have been enabled.

To re-enable the SDIO IRQs during system resume, the dw_mmc driver currently relies on the mmc core to re-enable the SDIO IRQs when it resumes the SDIO card, but this isn't the recommended solution. Instead, it's better to deal with this locally in the dw_mmc driver, so let's do that.

---
 drivers/mmc/host/dw_mmc.c | 4 ++++
 1 file changed, 4 insertions(+)
drivers/mmc/host/dw_mmc.c +4 -0
index 60c3a06e3469a..45c3490546839 100644
@@ -3482,6 +3482,10 @@ int dw_mci_runtime_resume(struct device *dev)
 	/* Force setup bus to guarantee available clock output */
 	dw_mci_setup_bus(host->slot, true);
 
+	/* Re-enable SDIO interrupts. */
+	if (sdio_irq_claimed(host->slot->mmc))
+		__dw_mci_enable_sdio_irq(host->slot, 1);
+
 	/* Now that slots are all setup, we can enable card detect */
 	dw_mci_enable_cd(host);
 
Signature · 1 line
2.20.1
author maintainer
#173 lore raw

PATCH 168/185 raid5: don't increment read_errors on EILSEQ return

In reply to Sasha Levin

From: Nigel Croxon <[email protected]>

[ Upstream commit b76b4715eba0d0ed574f58918b29c1b2f0fa37a8 ]

While MD continues to count read errors returned by the lower layer. If those errors are -EILSEQ, instead of -EIO, it should NOT increase the read_errors count.

When RAID6 is set up on dm-integrity target that detects massive corruption, the leg will be ejected from the array. Even if the issue is correctable with a sector re-write and the array has necessary redundancy to correct it.

The leg is ejected because it runs up the rdev->read_errors beyond conf->max_nr_stripes. The return status in dm-drypt when there is a data integrity error is -EILSEQ (BLK_STS_PROTECTION).

---
 drivers/md/raid5.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/md/raid5.c +2 -1
index 8d2811e436b93..f04e867b38211 100644
@@ -2526,7 +2526,8 @@ static void raid5_end_read_request(struct bio * bi)
 		int set_bad = 0;
 
 		clear_bit(R5_UPTODATE, &sh->dev[i].flags);
-		atomic_inc(&rdev->read_errors);
+		if (!(bi->bi_status == BLK_STS_PROTECTION))
+			atomic_inc(&rdev->read_errors);
 		if (test_bit(R5_ReadRepl, &sh->dev[i].flags))
 			pr_warn_ratelimited(
 				"md/raid:%s: read error on replacement device (sector %llu on %s).\n",
Signature · 1 line
2.20.1
author maintainer
#174 lore raw

PATCH 169/185 mmc: mtk-sd: Re-store SDIO IRQs mask at system resume

In reply to Sasha Levin

From: Ulf Hansson <[email protected]>

[ Upstream commit 1c81d69d4c98aab56c5a7d5a810f84aefdb37e9b ]

In cases when SDIO IRQs have been enabled, runtime suspend is prevented by the driver. However, this still means msdc_runtime_suspend|resume() gets called during system suspend/resume, via pm_runtime_force_suspend|resume().

This means during system suspend/resume, the register context of the mtk-sd device most likely loses its register context, even in cases when SDIO IRQs have been enabled.

To re-enable the SDIO IRQs during system resume, the mtk-sd driver currently relies on the mmc core to re-enable the SDIO IRQs when it resumes the SDIO card, but this isn't the recommended solution. Instead, it's better to deal with this locally in the mtk-sd driver, so let's do that.

---
 drivers/mmc/host/mtk-sd.c | 3 +++
 1 file changed, 3 insertions(+)
drivers/mmc/host/mtk-sd.c +3 -0
index 33f4b6387ef71..978c8ccce7e31 100644
@@ -2421,6 +2421,9 @@ static void msdc_restore_reg(struct msdc_host *host)
 	} else {
 		writel(host->save_para.pad_tune, host->base + tune_reg);
 	}
+
+	if (sdio_irq_claimed(host->mmc))
+		__msdc_enable_sdio_irq(host, 1);
 }
 
 static int msdc_runtime_suspend(struct device *dev)
Signature · 1 line
2.20.1
author maintainer
#175 lore raw

PATCH 170/185 media: technisat-usb2: break out of loop at end of buffer

In reply to Sasha Levin

From: Sean Young <[email protected]>

[ Upstream commit 0c4df39e504bf925ab666132ac3c98d6cbbe380b ]

Ensure we do not access the buffer beyond the end if no 0xff byte is encountered.

---
 drivers/media/usb/dvb-usb/technisat-usb2.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)
drivers/media/usb/dvb-usb/technisat-usb2.c +10 -12
index c659e18b358b8..676d233d46d53 100644
@@ -608,10 +608,9 @@ static int technisat_usb2_frontend_attach(struct dvb_usb_adapter *a)
 static int technisat_usb2_get_ir(struct dvb_usb_device *d)
 {
 	struct technisat_usb2_state *state = d->priv;
-	u8 *buf = state->buf;
-	u8 *b;
-	int ret;
 	struct ir_raw_event ev;
+	u8 *buf = state->buf;
+	int i, ret;
 
 	buf[0] = GET_IR_DATA_VENDOR_REQUEST;
 	buf[1] = 0x08;
@@ -647,26 +646,25 @@ static int technisat_usb2_get_ir(struct dvb_usb_device *d)
 		return 0; /* no key pressed */
 
 	/* decoding */
-	b = buf+1;
 
 #if 0
 	deb_rc("RC: %d ", ret);
-	debug_dump(b, ret, deb_rc);
+	debug_dump(buf + 1, ret, deb_rc);
 #endif
 
 	ev.pulse = 0;
-	while (1) {
-		ev.pulse = !ev.pulse;
-		ev.duration = (*b * FIRMWARE_CLOCK_DIVISOR * FIRMWARE_CLOCK_TICK) / 1000;
-		ir_raw_event_store(d->rc_dev, &ev);
-
-		b++;
-		if (*b == 0xff) {
+	for (i = 1; i < ARRAY_SIZE(state->buf); i++) {
+		if (buf[i] == 0xff) {
 			ev.pulse = 0;
 			ev.duration = 888888*2;
 			ir_raw_event_store(d->rc_dev, &ev);
 			break;
 		}
+
+		ev.pulse = !ev.pulse;
+		ev.duration = (buf[i] * FIRMWARE_CLOCK_DIVISOR *
+			       FIRMWARE_CLOCK_TICK) / 1000;
+		ir_raw_event_store(d->rc_dev, &ev);
 	}
 
 	ir_raw_event_handle(d->rc_dev);
Signature · 1 line
2.20.1
author maintainer
#176 lore raw

PATCH 171/185 libertas: Add missing sentinel at end of if_usb.c fw_table

In reply to Sasha Levin

From: Kevin Easton <[email protected]>

[ Upstream commit 764f3f1ecffc434096e0a2b02f1a6cc964a89df6 ]

This sentinel tells the firmware loading process when to stop.

---
 drivers/net/wireless/marvell/libertas/if_usb.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
drivers/net/wireless/marvell/libertas/if_usb.c +2 -1
index f1622f0ff8c9e..fe3142d85d1e4 100644
@@ -50,7 +50,8 @@ static const struct lbs_fw_table fw_table[] = {
 	{ MODEL_8388, "libertas/usb8388_v5.bin", NULL },
 	{ MODEL_8388, "libertas/usb8388.bin", NULL },
 	{ MODEL_8388, "usb8388.bin", NULL },
-	{ MODEL_8682, "libertas/usb8682.bin", NULL }
+	{ MODEL_8682, "libertas/usb8682.bin", NULL },
+	{ 0, NULL, NULL }
 };
 
 static const struct usb_device_id if_usb_table[] = {
Signature · 1 line
2.20.1
author maintainer
#177 lore raw

PATCH 172/185 e1000e: add workaround for possible stalled packet

In reply to Sasha Levin

From: Kai-Heng Feng <[email protected]>

[ Upstream commit e5e9a2ecfe780975820e157b922edee715710b66 ]

This works around a possible stalled packet issue, which may occur due to clock recovery from the PCH being too slow, when the LAN is transitioning from K1 at 1G link speed.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=204057

---
 drivers/net/ethernet/intel/e1000e/ich8lan.c | 10 ++++++++++
 drivers/net/ethernet/intel/e1000e/ich8lan.h |  2 +-
 2 files changed, 11 insertions(+), 1 deletion(-)
drivers/net/ethernet/intel/e1000e/ich8lan.c +10 -0
index cdae0efde8e64..7998a73b6a0fa 100644
@@ -1429,6 +1429,16 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw)
 			else
 				phy_reg |= 0xFA;
 			e1e_wphy_locked(hw, I217_PLL_CLOCK_GATE_REG, phy_reg);
+
+			if (speed == SPEED_1000) {
+				hw->phy.ops.read_reg_locked(hw, HV_PM_CTRL,
+							    &phy_reg);
+
+				phy_reg |= HV_PM_CTRL_K1_CLK_REQ;
+
+				hw->phy.ops.write_reg_locked(hw, HV_PM_CTRL,
+							     phy_reg);
+			}
 		}
 		hw->phy.ops.release(hw);
 
drivers/net/ethernet/intel/e1000e/ich8lan.h +1 -1
index eb09c755fa172..1502895eb45dd 100644
@@ -210,7 +210,7 @@
 
 /* PHY Power Management Control */
 #define HV_PM_CTRL		PHY_REG(770, 17)
-#define HV_PM_CTRL_PLL_STOP_IN_K1_GIGA	0x100
+#define HV_PM_CTRL_K1_CLK_REQ		0x200
 #define HV_PM_CTRL_K1_ENABLE		0x4000
 
 #define I217_PLL_CLOCK_GATE_REG	PHY_REG(772, 28)
Signature · 1 line
2.20.1
author maintainer
#178 lore raw

PATCH 173/185 ALSA: hda - Add a quirk model for fixing Huawei Matebook X right speaker

In reply to Sasha Levin

From: Tomas Espeleta <[email protected]>

[ Upstream commit a2ef03fe617a8365fb7794531b11ba587509a9b9 ]

[ This is rather a revival of the patch Tomas sent in months ago, but
applying only with the quirk model option -- tiwai ]

Hard coded coefficients to make Huawuei Matebook X right speaker work. The Matebook X has a ALC298, please refer to bug 197801 on how these numbers were reverse engineered from the Windows driver

The reversed engineered sequence represents a repeating pattern of verbs, and the only values that are changing periodically are written on indexes 0x23 and 0x25:

0x500, 0x23
0x400, VALUE1
0x500, 0x25
0x400, VALUE2

* skipped reading sequences (0x500 - 0xc00 sequences are ignored)
* static values from reverse engineering are used

NOTE: since a significant risk is still considered, this is provided as an experimental fix that isn't applied as default for now. For enabling the fix, you'll have to choose huawei-mbx-stereo via model option of snd-hda-intel module.

If we get feedback from users that this works stably, we may apply it per default.

[ Some coding style fixes and replacement with AC_VERB_* by tiwai ]

---
 Documentation/sound/hd-audio/models.rst |  3 +
 sound/pci/hda/patch_realtek.c           | 74 +++++++++++++++++++++++++
 2 files changed, 77 insertions(+)
Documentation/sound/hd-audio/models.rst +3 -0
index 7d7c191102a73..11298f0ce44db 100644
@@ -260,6 +260,9 @@ alc295-hp-x360
     HP Spectre X360 fixups
 alc-sense-combo
     Headset button support for Chrome platform
+huawei-mbx-stereo
+    Enable initialization verbs for Huawei MBX stereo speakers;
+    might be risky, try this at your own risk
 
 ALC66x/67x/892
 ==============
sound/pci/hda/patch_realtek.c +74 -0

98 lines not on this page · raw message

Signature · 1 line
2.20.1
author maintainer
#179 lore raw

PATCH 174/185 ALSA: hda - Drop unsol event handler for Intel HDMI codecs

In reply to Sasha Levin

From: Takashi Iwai <[email protected]>

[ Upstream commit f2dbe87c5ac1f88e6007ba1f1374f4bd8a197fb6 ]

We don't need to deal with the unsol events for Intel chips that are tied with the graphics via audio component notifier. Although the presence of the audio component is checked at the beginning of hdmi_unsol_event(), better to short cut by dropping unsol_event ops.

---
 sound/pci/hda/patch_hdmi.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)
sound/pci/hda/patch_hdmi.c +8 -1
index e49c1c00f5ce1..ca0404edd939e 100644
@@ -2611,6 +2611,8 @@ static void i915_pin_cvt_fixup(struct hda_codec *codec,
 /* precondition and allocation for Intel codecs */
 static int alloc_intel_hdmi(struct hda_codec *codec)
 {
+	int err;
+
 	/* requires i915 binding */
 	if (!codec->bus->core.audio_component) {
 		codec_info(codec, "No i915 binding for Intel HDMI/DP codec\n");
@@ -2619,7 +2621,12 @@ static int alloc_intel_hdmi(struct hda_codec *codec)
 		return -ENODEV;
 	}
 
-	return alloc_generic_hdmi(codec);
+	err = alloc_generic_hdmi(codec);
+	if (err < 0)
+		return err;
+	/* no need to handle unsol events */
+	codec->patch_ops.unsol_event = NULL;
+	return 0;
 }
 
 /* parse and post-process for Intel codecs */
Signature · 1 line
2.20.1
author maintainer
#180 lore raw

PATCH 175/185 drm/amd/powerplay/smu7: enforce minimal VBITimeout (v2)

In reply to Sasha Levin

From: Ahzo <[email protected]>

[ Upstream commit f659bb6dae58c113805f92822e4c16ddd3156b79 ]

This fixes screen corruption/flickering on 75 Hz displays.

v2: make print statement debug only (Alex)

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=102646

---
 drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 5 +++++
 1 file changed, 5 insertions(+)
drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c +5 -0
index 048757e8f4949..d1919d343cce4 100644
@@ -4064,6 +4064,11 @@ static int smu7_program_display_gap(struct pp_hwmgr *hwmgr)
 
 	data->frame_time_x2 = frame_time_in_us * 2 / 100;
 
+	if (data->frame_time_x2 < 280) {
+		pr_debug("%s: enforce minimal VBITimeout: %d -> 280\n", __func__, data->frame_time_x2);
+		data->frame_time_x2 = 280;
+	}
+
 	display_gap2 = pre_vbi_time_in_us * (ref_clock / 100);
 
 	cgs_write_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixCG_DISPLAY_GAP_CNTL2, display_gap2);
Signature · 1 line
2.20.1
author maintainer
#181 lore raw

PATCH 176/185 media: ttusb-dec: Fix info-leak in ttusb_dec_send_command()

In reply to Sasha Levin

From: Tomas Bortoli <[email protected]>

[ Upstream commit a10feaf8c464c3f9cfdd3a8a7ce17e1c0d498da1 ]

The function at issue does not always initialize each byte allocated for 'b' and can therefore leak uninitialized memory to a USB device in the call to usb_bulk_msg()

Use kzalloc() instead of kmalloc()

---
 drivers/media/usb/ttusb-dec/ttusb_dec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/media/usb/ttusb-dec/ttusb_dec.c +1 -1
index 1d0afa340f47c..3198f9624b7c0 100644
@@ -319,7 +319,7 @@ static int ttusb_dec_send_command(struct ttusb_dec *dec, const u8 command,
 
 	dprintk("%s\n", __func__);
 
-	b = kmalloc(COMMAND_PACKET_SIZE + 4, GFP_KERNEL);
+	b = kzalloc(COMMAND_PACKET_SIZE + 4, GFP_KERNEL);
 	if (!b)
 		return -ENOMEM;
 
Signature · 1 line
2.20.1
author maintainer
#182 lore raw

PATCH 177/185 drm: fix module name in edid_firmware log message

In reply to Sasha Levin

From: Jani Nikula <[email protected]>

[ Upstream commit ade925995b172f1d7410d1c665b2f47c5e99bef0 ]

The module is drm_kms_helper, not drm_kms_firmware.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=204549

Fixes ac6c35a4d8c7 ("drm: add backwards compatibility support for drm_kms_helper.edid_firmware")
---
 drivers/gpu/drm/drm_kms_helper_common.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/drm_kms_helper_common.c +1 -1
index 9c5ae825c5078..69917ecd4af67 100644
@@ -39,7 +39,7 @@ MODULE_LICENSE("GPL and additional rights");
 /* Backward compatibility for drm_kms_helper.edid_firmware */
 static int edid_firmware_set(const char *val, const struct kernel_param *kp)
 {
-	DRM_NOTE("drm_kms_firmware.edid_firmware is deprecated, please use drm.edid_firmware instead.\n");
+	DRM_NOTE("drm_kms_helper.edid_firmware is deprecated, please use drm.edid_firmware instead.\n");
 
 	return __drm_set_edid_firmware_path(val);
 }
Signature · 1 line
2.20.1
author maintainer
#183 lore raw

PATCH 178/185 ALSA: hda/realtek - Blacklist PC beep for Lenovo ThinkCentre M73/93

In reply to Sasha Levin

From: Takashi Iwai <[email protected]>

[ Upstream commit 051c78af14fcd74a22b5af45548ad9d588247cc7 ]

Lenovo ThinkCentre M73 and M93 don't seem to have a proper beep although the driver tries to probe and set up blindly. Blacklist these machines for suppressing the beep creation.

---
 sound/pci/hda/patch_realtek.c | 3 +++
 1 file changed, 3 insertions(+)
sound/pci/hda/patch_realtek.c +3 -0
index 1bec62720374d..d223a79ac934f 100644
@@ -1058,6 +1058,9 @@ static const struct snd_pci_quirk beep_white_list[] = {
 	SND_PCI_QUIRK(0x1043, 0x834a, "EeePC", 1),
 	SND_PCI_QUIRK(0x1458, 0xa002, "GA-MA790X", 1),
 	SND_PCI_QUIRK(0x8086, 0xd613, "Intel", 1),
+	/* blacklist -- no beep available */
+	SND_PCI_QUIRK(0x17aa, 0x309e, "Lenovo ThinkCentre M73", 0),
+	SND_PCI_QUIRK(0x17aa, 0x30a3, "Lenovo ThinkCentre M93", 0),
 	{}
 };
 
Signature · 1 line
2.20.1
author maintainer
#184 lore raw

PATCH 179/185 iommu/amd: Override wrong IVRS IOAPIC on Raven Ridge systems

In reply to Sasha Levin

From: Kai-Heng Feng <[email protected]>

[ Upstream commit 93d051550ee02eaff9a2541d825605a7bd778027 ]

Raven Ridge systems may have malfunction touchpad or hang at boot if incorrect IVRS IOAPIC is provided by BIOS.

Users already found correct "ivrs_ioapic=" values, let's put them inside kernel to workaround buggy BIOS.

---
 drivers/iommu/Makefile           |  2 +-
 drivers/iommu/amd_iommu.h        | 14 +++++
 drivers/iommu/amd_iommu_init.c   |  5 +-
 drivers/iommu/amd_iommu_quirks.c | 92 ++++++++++++++++++++++++++++++++
 4 files changed, 111 insertions(+), 2 deletions(-)
 create mode 100644 drivers/iommu/amd_iommu.h
 create mode 100644 drivers/iommu/amd_iommu_quirks.c
drivers/iommu/Makefile +1 -1
index 8c71a15e986b5..826a5bbe0d09b 100644
@@ -10,7 +10,7 @@ obj-$(CONFIG_IOMMU_IO_PGTABLE_LPAE) += io-pgtable-arm.o
 obj-$(CONFIG_IOMMU_IOVA) += iova.o
 obj-$(CONFIG_OF_IOMMU)	+= of_iommu.o
 obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o
-obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o
+obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o amd_iommu_quirks.o
 obj-$(CONFIG_AMD_IOMMU_DEBUGFS) += amd_iommu_debugfs.o
 obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o
 obj-$(CONFIG_ARM_SMMU) += arm-smmu.o
drivers/iommu/amd_iommu.h new file +14 -0
new file mode 100644
index 0000000000000..12d540d9b59b0
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef AMD_IOMMU_H
+#define AMD_IOMMU_H
+
+int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line);
+
+#ifdef CONFIG_DMI
+void amd_iommu_apply_ivrs_quirks(void);
+#else
+static void amd_iommu_apply_ivrs_quirks(void) { }
+#endif
+
+#endif
drivers/iommu/amd_iommu_init.c +4 -1
index 07d84dbab564e..6469f51282427 100644
@@ -30,6 +30,7 @@
 #include <asm/irq_remapping.h>
 
 #include <linux/crash_dump.h>
+#include "amd_iommu.h"
 #include "amd_iommu_proto.h"
 #include "amd_iommu_types.h"
 #include "irq_remapping.h"
@@ -997,7 +998,7 @@ static void __init set_dev_entry_from_acpi(struct amd_iommu *iommu,
 	set_iommu_for_device(iommu, devid);
 }
 
-static int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line)
+int __init add_special_device(u8 type, u8 id, u16 *devid, bool cmd_line)
 {
 	struct devid_map *entry;
 	struct list_head *list;
@@ -1148,6 +1149,8 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 	if (ret)
 		return ret;
 
+	amd_iommu_apply_ivrs_quirks();
+
 	/*
 	 * First save the recommended feature enable bits from ACPI
 	 */
drivers/iommu/amd_iommu_quirks.c new file +92 -0

92 lines not on this page · raw message

Signature · 6 lines
2.20.1

_______________________________________________
iommu mailing list
[email protected]
https://lists.linuxfoundation.org/mailman/listinfo/iommu
author maintainer
#185 lore raw

PATCH 180/185 zd1211rw: remove false assertion from zd_mac_clear()

In reply to Sasha Levin

From: Oliver Neukum <[email protected]>

[ Upstream commit 7a2eb7367fdea72e448d1a847aa857f6caf8ea2f ]

The function is called before the lock which is asserted was ever used. Just remove it.

---
 drivers/net/wireless/zydas/zd1211rw/zd_mac.c | 1 -
 1 file changed, 1 deletion(-)
drivers/net/wireless/zydas/zd1211rw/zd_mac.c +0 -1
index da7e63fca9f57..a9999d10ae81f 100644
@@ -223,7 +223,6 @@ void zd_mac_clear(struct zd_mac *mac)
 {
 	flush_workqueue(zd_workqueue);
 	zd_chip_clear(&mac->chip);
-	lockdep_assert_held(&mac->lock);
 	ZD_MEMCLEAR(mac, sizeof(struct zd_mac));
 }
 
Signature · 1 line
2.20.1
author maintainer
#186 lore raw

PATCH 181/185 btrfs: delayed-inode: Kill the BUG_ON() in btrfs_delete_delayed_dir_index()

In reply to Sasha Levin

From: Qu Wenruo <[email protected]>

[ Upstream commit 933c22a7512c5c09b1fdc46b557384efe8d03233 ]

There is one report of fuzzed image which leads to BUG_ON() in btrfs_delete_delayed_dir_index().

Although that fuzzed image can already be addressed by enhanced extent-tree error handler, it's still better to hunt down more BUG_ON().

This patch will hunt down two BUG_ON()s in btrfs_delete_delayed_dir_index():
- One for error from btrfs_delayed_item_reserve_metadata() Instead of BUG_ON(), we output an error message and free the item. And return the error.
All callers of this function handles the error by aborting current trasaction.

- One for possible EEXIST from __btrfs_add_delayed_deletion_item() That function can return -EEXIST.
We already have a good enough error message for that, only need to clean up the reserved metadata space and allocated item.

To help above cleanup, also modifiy __btrfs_remove_delayed_item() called in btrfs_release_delayed_item(), to skip unassociated item.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203253

---
 fs/btrfs/delayed-inode.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)
fs/btrfs/delayed-inode.c +11 -2
index 43fdb2992956a..6858a05606dd3 100644
@@ -474,6 +474,9 @@ static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item)
 	struct rb_root_cached *root;
 	struct btrfs_delayed_root *delayed_root;
 
+	/* Not associated with any delayed_node */
+	if (!delayed_item->delayed_node)
+		return;
 	delayed_root = delayed_item->delayed_node->root->fs_info->delayed_root;
 
 	BUG_ON(!delayed_root);
@@ -1525,7 +1528,12 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
 	 * we have reserved enough space when we start a new transaction,
 	 * so reserving metadata failure is impossible.
 	 */
-	BUG_ON(ret);
+	if (ret < 0) {
+		btrfs_err(trans->fs_info,
+"metadata reservation failed for delayed dir item deltiona, should have been reserved");
+		btrfs_release_delayed_item(item);
+		goto end;
+	}
 
 	mutex_lock(&node->mutex);
 	ret = __btrfs_add_delayed_deletion_item(node, item);
@@ -1534,7 +1542,8 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
 			  "err add delayed dir index item(index: %llu) into the deletion tree of the delayed node(root id: %llu, inode id: %llu, errno: %d)",
 			  index, node->root->root_key.objectid,
 			  node->inode_id, ret);
-		BUG();
+		btrfs_delayed_item_release_metadata(dir->root, item);
+		btrfs_release_delayed_item(item);
 	}
 	mutex_unlock(&node->mutex);
 end:
Signature · 1 line
2.20.1
author maintainer
#187 lore raw

PATCH 182/185 btrfs: extent-tree: Make sure we only allocate extents from block groups with the same type

In reply to Sasha Levin

From: Qu Wenruo <[email protected]>

[ Upstream commit 2a28468e525f3924efed7f29f2bc5a2926e7e19a ]

[BUG]
With fuzzed image and MIXED_GROUPS super flag, we can hit the following BUG_ON():

kernel BUG at fs/btrfs/delayed-ref.c:491!
invalid opcode: 0000 [#1] PREEMPT SMP NOPTI

  CPU: 0 PID: 1849 Comm: sync Tainted: G           O      5.2.0-custom #27
  RIP: 0010:update_existing_head_ref.cold+0x44/0x46 [btrfs]
  Call Trace:
   add_delayed_ref_head+0x20c/0x2d0 [btrfs]
   btrfs_add_delayed_tree_ref+0x1fc/0x490 [btrfs]
   btrfs_free_tree_block+0x123/0x380 [btrfs]
   __btrfs_cow_block+0x435/0x500 [btrfs]
   btrfs_cow_block+0x110/0x240 [btrfs]
   btrfs_search_slot+0x230/0xa00 [btrfs]
   ? __lock_acquire+0x105e/0x1e20
   btrfs_insert_empty_items+0x67/0xc0 [btrfs]
   alloc_reserved_file_extent+0x9e/0x340 [btrfs]
   __btrfs_run_delayed_refs+0x78e/0x1240 [btrfs]
   ? kvm_clock_read+0x18/0x30
   ? __sched_clock_gtod_offset+0x21/0x50
   btrfs_run_delayed_refs.part.0+0x4e/0x180 [btrfs]
   btrfs_run_delayed_refs+0x23/0x30 [btrfs]
   btrfs_commit_transaction+0x53/0x9f0 [btrfs]
   btrfs_sync_fs+0x7c/0x1c0 [btrfs]
   ? __ia32_sys_fdatasync+0x20/0x20
   sync_fs_one_sb+0x23/0x30
   iterate_supers+0x95/0x100
   ksys_sync+0x62/0xb0
   __ia32_sys_sync+0xe/0x20
   do_syscall_64+0x65/0x240
   entry_SYSCALL_64_after_hwframe+0x49/0xbe

[CAUSE]
This situation is caused by several factors:
- Fuzzed image
The extent tree of this fs missed one backref for extent tree root. So we can allocated space from that slot.

- MIXED_BG feature
Super block has MIXED_BG flag.

- No mixed block groups exists
All block groups are just regular ones.

This makes data space_info->block_groups[] contains metadata block groups. And when we reserve space for data, we can use space in metadata block group.

Then we hit the following file operations:

- fallocate
We need to allocate data extents.
find_free_extent() choose to use the metadata block to allocate space from, and choose the space of extent tree root, since its backref is missing.

This generate one delayed ref head with is_data = 1.

- extent tree update
We need to update extent tree at run_delayed_ref time.

This generate one delayed ref head with is_data = 0, for the same bytenr of old extent tree root.

Then we trigger the BUG_ON().

[FIX]
The quick fix here is to check block_group->flags before using it.

The problem can only happen for MIXED_GROUPS fs. Regular filesystems won't have space_info with DATA|METADATA flag, and no way to hit the bug.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203255

---
 fs/btrfs/extent-tree.c | 8 ++++++++
 1 file changed, 8 insertions(+)
fs/btrfs/extent-tree.c +8 -0
index b8f4720879021..37865929fdc22 100644
@@ -7875,6 +7875,14 @@ static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
 			 */
 			if ((flags & extra) && !(block_group->flags & extra))
 				goto loop;
+
+			/*
+			 * This block group has different flags than we want.
+			 * It's possible that we have MIXED_GROUP flag but no
+			 * block group is mixed.  Just skip such block group.
+			 */
+			btrfs_release_block_group(block_group, delalloc);
+			continue;
 		}
 
 have_block_group:
Signature · 1 line
2.20.1
author maintainer
#188 lore raw

PATCH 183/185 btrfs: tree-checker: Add ROOT_ITEM check

In reply to Sasha Levin

From: Qu Wenruo <[email protected]>

[ Upstream commit 259ee7754b6793af8bdd77f9ca818bc41cfe9541 ]

This patch will introduce ROOT_ITEM check, which includes:
- Key->objectid and key->offset check
Currently only some easy check, e.g. 0 as rootid is invalid.

- Item size check
Root item size is fixed.

- Generation checks
Generation, generation_v2 and last_snapshot should not be greater than super generation + 1

- Level and alignment check
Level should be in [0, 7], and bytenr must be aligned to sector size.

- Flags check

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=203261

---
 fs/btrfs/tree-checker.c | 92 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 92 insertions(+)
fs/btrfs/tree-checker.c +92 -0
index ccd5706199d76..d83adda6c090a 100644
@@ -821,6 +821,95 @@ static int check_inode_item(struct extent_buffer *leaf,
 	return 0;
 }
 
+static int check_root_item(struct extent_buffer *leaf, struct btrfs_key *key,
+			   int slot)
+{
+	struct btrfs_fs_info *fs_info = leaf->fs_info;
+	struct btrfs_root_item ri;
+	const u64 valid_root_flags = BTRFS_ROOT_SUBVOL_RDONLY |
+				     BTRFS_ROOT_SUBVOL_DEAD;
+
+	/* No such tree id */
+	if (key->objectid == 0) {
+		generic_err(leaf, slot, "invalid root id 0");
+		return -EUCLEAN;
+	}
+
+	/*
+	 * Some older kernel may create ROOT_ITEM with non-zero offset, so here
+	 * we only check offset for reloc tree whose key->offset must be a
+	 * valid tree.
+	 */
+	if (key->objectid == BTRFS_TREE_RELOC_OBJECTID && key->offset == 0) {
+		generic_err(leaf, slot, "invalid root id 0 for reloc tree");
+		return -EUCLEAN;
+	}
+
+	if (btrfs_item_size_nr(leaf, slot) != sizeof(ri)) {
+		generic_err(leaf, slot,
+			    "invalid root item size, have %u expect %zu",
+			    btrfs_item_size_nr(leaf, slot), sizeof(ri));
+	}
+
+	read_extent_buffer(leaf, &ri, btrfs_item_ptr_offset(leaf, slot),
+			   sizeof(ri));
+
+	/* Generation related */
+	if (btrfs_root_generation(&ri) >
+	    btrfs_super_generation(fs_info->super_copy) + 1) {
+		generic_err(leaf, slot,
+			"invalid root generation, have %llu expect (0, %llu]",
+			    btrfs_root_generation(&ri),
+			    btrfs_super_generation(fs_info->super_copy) + 1);
+		return -EUCLEAN;
+	}
+	if (btrfs_root_generation_v2(&ri) >
+	    btrfs_super_generation(fs_info->super_copy) + 1) {
+		generic_err(leaf, slot,
+		"invalid root v2 generation, have %llu expect (0, %llu]",
+			    btrfs_root_generation_v2(&ri),
+			    btrfs_super_generation(fs_info->super_copy) + 1);
+		return -EUCLEAN;
+	}
+	if (btrfs_root_last_snapshot(&ri) >
+	    btrfs_super_generation(fs_info->super_copy) + 1) {
+		generic_err(leaf, slot,
+		"invalid root last_snapshot, have %llu expect (0, %llu]",
+			    btrfs_root_last_snapshot(&ri),
+			    btrfs_super_generation(fs_info->super_copy) + 1);
+		return -EUCLEAN;
+	}
+
+	/* Alignment and level check */
+	if (!IS_ALIGNED(btrfs_root_bytenr(&ri), fs_info->sectorsize)) {
+		generic_err(leaf, slot,
+		"invalid root bytenr, have %llu expect to be aligned to %u",
+			    btrfs_root_bytenr(&ri), fs_info->sectorsize);
+		return -EUCLEAN;
+	}
+	if (btrfs_root_level(&ri) >= BTRFS_MAX_LEVEL) {
+		generic_err(leaf, slot,
+			    "invalid root level, have %u expect [0, %u]",
+			    btrfs_root_level(&ri), BTRFS_MAX_LEVEL - 1);
+		return -EUCLEAN;
+	}
+	if (ri.drop_level >= BTRFS_MAX_LEVEL) {
+		generic_err(leaf, slot,
+			    "invalid root level, have %u expect [0, %u]",
+			    ri.drop_level, BTRFS_MAX_LEVEL - 1);
+		return -EUCLEAN;
+	}
+
+	/* Flags check */
+	if (btrfs_root_flags(&ri) & ~valid_root_flags) {
+		generic_err(leaf, slot,
+			    "invalid root flags, have 0x%llx expect mask 0x%llx",
+			    btrfs_root_flags(&ri), valid_root_flags);
+		return -EUCLEAN;
+	}
+	return 0;
+}
+
 /*
  * Common point to switch the item-specific validation.
  */
@@ -856,6 +945,9 @@ static int check_leaf_item(struct extent_buffer *leaf,
 	case BTRFS_INODE_ITEM_KEY:
 		ret = check_inode_item(leaf, key, slot);
 		break;
+	case BTRFS_ROOT_ITEM_KEY:
+		ret = check_root_item(leaf, key, slot);
+		break;
 	}
 	return ret;
 }
Signature · 1 line
2.20.1
author maintainer
#189 lore raw

PATCH 184/185 btrfs: Detect unbalanced tree with empty leaf before crashing btree operations

In reply to Sasha Levin

From: Qu Wenruo <[email protected]>

[ Upstream commit 62fdaa52a3d00a875da771719b6dc537ca79fce1 ]

[BUG]
With crafted image, btrfs will panic at btree operations:

kernel BUG at fs/btrfs/ctree.c:3894!
invalid opcode: 0000 [#1] SMP PTI

  CPU: 0 PID: 1138 Comm: btrfs-transacti Not tainted 5.0.0-rc8+ #9
  RIP: 0010:__push_leaf_left+0x6b6/0x6e0
  RSP: 0018:ffffc0bd4128b990 EFLAGS: 00010246
  RAX: 0000000000000000 RBX: ffffa0a4ab8f0e38 RCX: 0000000000000000
  RDX: ffffa0a280000000 RSI: 0000000000000000 RDI: ffffa0a4b3814000
  RBP: ffffc0bd4128ba38 R08: 0000000000001000 R09: ffffc0bd4128b948
  R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000240
  R13: ffffa0a4b556fb60 R14: ffffa0a4ab8f0af0 R15: ffffa0a4ab8f0af0
  FS: 0000000000000000(0000) GS:ffffa0a4b7a00000(0000) knlGS:0000000000000000
  CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 00007f2461c80020 CR3: 000000022b32a006 CR4: 00000000000206f0
  Call Trace:
  ? _cond_resched+0x1a/0x50
  push_leaf_left+0x179/0x190
  btrfs_del_items+0x316/0x470
  btrfs_del_csums+0x215/0x3a0
  __btrfs_free_extent.isra.72+0x5a7/0xbe0
  __btrfs_run_delayed_refs+0x539/0x1120
  btrfs_run_delayed_refs+0xdb/0x1b0
  btrfs_commit_transaction+0x52/0x950
  ? start_transaction+0x94/0x450
  transaction_kthread+0x163/0x190
  kthread+0x105/0x140
  ? btrfs_cleanup_transaction+0x560/0x560
  ? kthread_destroy_worker+0x50/0x50
  ret_from_fork+0x35/0x40
  Modules linked in:
  ---[ end trace c2425e6e89b5558f ]---

[CAUSE]
The offending csum tree looks like this:

checksum tree key (CSUM_TREE ROOT_ITEM 0)
node 29741056 level 1 items 14 free 107 generation 19 owner CSUM_TREE

	  ...
	  key (EXTENT_CSUM EXTENT_CSUM 85975040) block 29630464 gen 17
	  key (EXTENT_CSUM EXTENT_CSUM 89911296) block 29642752 gen 17 <<<
	  key (EXTENT_CSUM EXTENT_CSUM 92274688) block 29646848 gen 17
	  ...

leaf 29630464 items 6 free space 1 generation 17 owner CSUM_TREE

	  item 0 key (EXTENT_CSUM EXTENT_CSUM 85975040) itemoff 3987 itemsize 8
		  range start 85975040 end 85983232 length 8192
	  ...

leaf 29642752 items 0 free space 3995 generation 17 owner 0
^ empty leaf invalid owner ^

leaf 29646848 items 1 free space 602 generation 17 owner CSUM_TREE

	  item 0 key (EXTENT_CSUM EXTENT_CSUM 92274688) itemoff 627 itemsize 3368
		  range start 92274688 end 95723520 length 3448832

So we have a corrupted csum tree where one tree leaf is completely empty, causing unbalanced btree, thus leading to unexpected btree balance error.

[FIX]
For this particular case, we handle it in two directions to catch it:
- Check if the tree block is empty through btrfs_verify_level_key() So that invalid tree blocks won't be read out through btrfs_search_slot() and its variants.

- Check 0 tree owner in tree checker
NO tree is using 0 as its tree owner, detect it and reject at tree block read time.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202821

---
 fs/btrfs/disk-io.c      | 10 ++++++++++
 fs/btrfs/tree-checker.c |  6 ++++++
 2 files changed, 16 insertions(+)
fs/btrfs/disk-io.c +10 -0
index deb74a8c191a4..6d26d38a2e12c 100644
@@ -423,6 +423,16 @@ int btrfs_verify_level_key(struct extent_buffer *eb, int level,
 	 */
 	if (btrfs_header_generation(eb) > fs_info->last_trans_committed)
 		return 0;
+
+	/* We have @first_key, so this @eb must have at least one item */
+	if (btrfs_header_nritems(eb) == 0) {
+		btrfs_err(fs_info,
+		"invalid tree nritems, bytenr=%llu nritems=0 expect >0",
+			  eb->start);
+		WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
+		return -EUCLEAN;
+	}
+
 	if (found_level)
 		btrfs_node_key_to_cpu(eb, &found_key, 0);
 	else
fs/btrfs/tree-checker.c +6 -0
index d83adda6c090a..9634cae1e1b1d 100644
@@ -991,6 +991,12 @@ static int check_leaf(struct extent_buffer *leaf, bool check_item_data)
 				    owner);
 			return -EUCLEAN;
 		}
+		/* Unknown tree */
+		if (owner == 0) {
+			generic_err(leaf, 0,
+				"invalid owner, root 0 is not defined");
+			return -EUCLEAN;
+		}
 		return 0;
 	}
 
Signature · 1 line
2.20.1
author maintainer
#190 lore raw

PATCH 185/185 kvm: Nested KVM MMUs need PAE root too

In reply to Sasha Levin

From: Jiří Paleček <[email protected]>

[ Upstream commit 1cfff4d9a5d01fa61e5768a6afffc81ae1c8ecb9 ]

On AMD processors, in PAE 32bit mode, nested KVM instances don't work. The L0 host get a kernel OOPS, which is related to arch.mmu->pae_root being NULL.

The reason for this is that when setting up nested KVM instance, arch.mmu is set to &arch.guest_mmu (while normally, it would be &arch.root_mmu). However, the initialization and allocation of pae_root only creates it in root_mmu. KVM code (ie. in mmu_alloc_shadow_roots) then accesses arch.mmu->pae_root, which is the unallocated arch.guest_mmu->pae_root.

This fix just allocates (and frees) pae_root in both guest_mmu and root_mmu (and also lm_root if it was allocated). The allocation is subject to previous restrictions ie. it won't allocate anything on 64-bit and AFAIK not on Intel.

---
 arch/x86/kvm/mmu.c | 30 ++++++++++++++++++++++--------
 1 file changed, 22 insertions(+), 8 deletions(-)
arch/x86/kvm/mmu.c +22 -8
index 66055ca29b6b4..9130152d5ed83 100644
@@ -5607,13 +5607,13 @@ slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot,
 				 PT_PAGE_TABLE_LEVEL, lock_flush_tlb);
 }
 
-static void free_mmu_pages(struct kvm_vcpu *vcpu)
+static void free_mmu_pages(struct kvm_mmu *mmu)
 {
-	free_page((unsigned long)vcpu->arch.mmu->pae_root);
-	free_page((unsigned long)vcpu->arch.mmu->lm_root);
+	free_page((unsigned long)mmu->pae_root);
+	free_page((unsigned long)mmu->lm_root);
 }
 
-static int alloc_mmu_pages(struct kvm_vcpu *vcpu)
+static int alloc_mmu_pages(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
 {
 	struct page *page;
 	int i;
@@ -5634,9 +5634,9 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu)
 	if (!page)
 		return -ENOMEM;
 
-	vcpu->arch.mmu->pae_root = page_address(page);
+	mmu->pae_root = page_address(page);
 	for (i = 0; i < 4; ++i)
-		vcpu->arch.mmu->pae_root[i] = INVALID_PAGE;
+		mmu->pae_root[i] = INVALID_PAGE;
 
 	return 0;
 }
@@ -5644,6 +5644,7 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu)
 int kvm_mmu_create(struct kvm_vcpu *vcpu)
 {
 	uint i;
+	int ret;
 
 	vcpu->arch.mmu = &vcpu->arch.root_mmu;
 	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
@@ -5661,7 +5662,19 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
 		vcpu->arch.guest_mmu.prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID;
 
 	vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;
-	return alloc_mmu_pages(vcpu);
+
+	ret = alloc_mmu_pages(vcpu, &vcpu->arch.guest_mmu);
+	if (ret)
+		return ret;
+
+	ret = alloc_mmu_pages(vcpu, &vcpu->arch.root_mmu);
+	if (ret)
+		goto fail_allocate_root;
+
+	return ret;
+ fail_allocate_root:
+	free_mmu_pages(&vcpu->arch.guest_mmu);
+	return ret;
 }
 
 
@@ -6134,7 +6147,8 @@ unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
 void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
 {
 	kvm_mmu_unload(vcpu);
-	free_mmu_pages(vcpu);
+	free_mmu_pages(&vcpu->arch.root_mmu);
+	free_mmu_pages(&vcpu->arch.guest_mmu);
 	mmu_free_memory_caches(vcpu);
 }
 
Signature · 1 line
2.20.1