4.19.31-stable review

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

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

From: Anders Roxell <[email protected]>

commit 206b8cc514d7ff2b79dd2d5ad939adc7c493f07a upstream.

When CONFIG_PROC_FS isn't set the variable cn isn't used.

net/ipv4/netfilter/ipt_CLUSTERIP.c: In function ‘clusterip_net_exit’:
net/ipv4/netfilter/ipt_CLUSTERIP.c:849:24: warning: unused variable ‘cn’ [-Wunused-variable]

  struct clusterip_net *cn = clusterip_pernet(net);
                        ^~

Rework so the variable 'cn' is declared inside "#ifdef CONFIG_PROC_FS".

---
 net/ipv4/netfilter/ipt_CLUSTERIP.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -846,9 +846,9 @@ static int clusterip_net_init(struct net
 
 static void clusterip_net_exit(struct net *net)
 {
+#ifdef CONFIG_PROC_FS
 	struct clusterip_net *cn = clusterip_pernet(net);
 
-#ifdef CONFIG_PROC_FS
 	mutex_lock(&cn->mutex);
 	proc_remove(cn->procdir);
 	cn->procdir = NULL;

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

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

From: Vignesh R <[email protected]>

commit 673c865efbdc5fec3cc525c46d71844d42c60072 upstream.

Commit 4dea6c9b0b64 ("spi: spi-ti-qspi: add mmap mode read support") has has got order of parameter wrong when calling regmap_update_bits() to select CS for mmap access. Mask and value arguments are interchanged. Code will work on a system with single slave, but fails when more than one CS is in use. Fix this by correcting the order of parameters when calling regmap_update_bits().

---
 drivers/spi/spi-ti-qspi.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -490,8 +490,8 @@ static void ti_qspi_enable_memory_map(st
 	ti_qspi_write(qspi, MM_SWITCH, QSPI_SPI_SWITCH_REG);
 	if (qspi->ctrl_base) {
 		regmap_update_bits(qspi->ctrl_base, qspi->ctrl_reg,
-				   MEM_CS_EN(spi->chip_select),
-				   MEM_CS_MASK);
+				   MEM_CS_MASK,
+				   MEM_CS_EN(spi->chip_select));
 	}
 	qspi->mmap_enabled = true;
 }

@@ -503,7 +503,7 @@ static void ti_qspi_disable_memory_map(s
 	ti_qspi_write(qspi, 0, QSPI_SPI_SWITCH_REG);
 	if (qspi->ctrl_base)
 		regmap_update_bits(qspi->ctrl_base, qspi->ctrl_reg,
-				   0, MEM_CS_MASK);
+				   MEM_CS_MASK, 0);
 	qspi->mmap_enabled = false;
 }
 

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

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

From: Andy Shevchenko <[email protected]>

commit ef070b4e4aa25bb5f8632ad196644026c11903bf upstream.

When the commit b6ced294fb61

("spi: pxa2xx: Switch to SPI core DMA mapping functionality")

switches to SPI core provided DMA helpers, it missed to setup maximum supported DMA transfer length for the controller and thus users mistakenly try to send more data than supported with the following warning:

ili9341 spi-PRP0001:01: DMA disabled for transfer length 153600 greater than 65536

Setup maximum supported DMA transfer length in order to make users know the limit.

---
 drivers/spi/spi-pxa2xx.c |    1 +
 1 file changed, 1 insertion(+)

@@ -1612,6 +1612,7 @@ static int pxa2xx_spi_probe(struct platf
 			platform_info->enable_dma = false;
 		} else {
 			master->can_dma = pxa2xx_spi_can_dma;
+			master->max_dma_len = MAX_DMA_LEN;
 		}
 	}
 

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

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

From: Krzysztof Kozlowski <[email protected]>

commit 56b5d4ea778c1b0989c5cdb5406d4a488144c416 upstream.

LDO35 uses 25 mV step, not 50 mV. Bucks 7 and 8 use 12.5 mV step instead of 6.25 mV. Wrong step caused over-voltage (LDO35) or under-voltage (buck7 and 8) if regulators were used (e.g. on Exynos5420 Arndale Octa board).

---
 drivers/regulator/s2mps11.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -363,7 +363,7 @@ static const struct regulator_desc s2mps
 	regulator_desc_s2mps11_ldo(32, STEP_50_MV),
 	regulator_desc_s2mps11_ldo(33, STEP_50_MV),
 	regulator_desc_s2mps11_ldo(34, STEP_50_MV),
-	regulator_desc_s2mps11_ldo(35, STEP_50_MV),
+	regulator_desc_s2mps11_ldo(35, STEP_25_MV),
 	regulator_desc_s2mps11_ldo(36, STEP_50_MV),
 	regulator_desc_s2mps11_ldo(37, STEP_50_MV),
 	regulator_desc_s2mps11_ldo(38, STEP_50_MV),

@@ -373,8 +373,8 @@ static const struct regulator_desc s2mps
 	regulator_desc_s2mps11_buck1_4(4),
 	regulator_desc_s2mps11_buck5,
 	regulator_desc_s2mps11_buck67810(6, MIN_600_MV, STEP_6_25_MV),
-	regulator_desc_s2mps11_buck67810(7, MIN_600_MV, STEP_6_25_MV),
-	regulator_desc_s2mps11_buck67810(8, MIN_600_MV, STEP_6_25_MV),
+	regulator_desc_s2mps11_buck67810(7, MIN_600_MV, STEP_12_5_MV),
+	regulator_desc_s2mps11_buck67810(8, MIN_600_MV, STEP_12_5_MV),
 	regulator_desc_s2mps11_buck9,
 	regulator_desc_s2mps11_buck67810(10, MIN_750_MV, STEP_12_5_MV),
 };

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

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

From: Mark Zhang <[email protected]>

commit 0ab66b3c326ef8f77dae9f528118966365757c0c upstream.

If regulator DT node doesn't exist, its of_parse_cb callback function isn't called. Then all values for DT properties are filled with zero. This leads to wrong register update for FPS and POK settings.

---
 drivers/regulator/max77620-regulator.c |   10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

@@ -1,7 +1,7 @@
 /*
  * Maxim MAX77620 Regulator driver
  *
- * Copyright (c) 2016, NVIDIA CORPORATION.  All rights reserved.
+ * Copyright (c) 2016-2018, NVIDIA CORPORATION.  All rights reserved.
  *
  * Author: Mallikarjun Kasoju <[email protected]>
  *	Laxman Dewangan <[email protected]>

@@ -803,6 +803,14 @@ static int max77620_regulator_probe(stru
 		rdesc = &rinfo[id].desc;
 		pmic->rinfo[id] = &max77620_regs_info[id];
 		pmic->enable_power_mode[id] = MAX77620_POWER_MODE_NORMAL;
+		pmic->reg_pdata[id].active_fps_src = -1;
+		pmic->reg_pdata[id].active_fps_pd_slot = -1;
+		pmic->reg_pdata[id].active_fps_pu_slot = -1;
+		pmic->reg_pdata[id].suspend_fps_src = -1;
+		pmic->reg_pdata[id].suspend_fps_pd_slot = -1;
+		pmic->reg_pdata[id].suspend_fps_pu_slot = -1;
+		pmic->reg_pdata[id].power_ok = -1;
+		pmic->reg_pdata[id].ramp_rate_setting = -1;
 
 		ret = max77620_read_slew_rate(pmic, id);
 		if (ret < 0)

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

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

From: Stuart Menefy <[email protected]>

commit 28c4f730d2a44f2591cb104091da29a38dac49fe upstream.

The step values for some of the LDOs appears to be incorrect, resulting in incorrect voltages (or at least, ones which are different from the Samsung 3.4 vendor kernel).

---
 drivers/regulator/s2mpa01.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

@@ -298,13 +298,13 @@ static const struct regulator_desc regul
 	regulator_desc_ldo(2, STEP_50_MV),
 	regulator_desc_ldo(3, STEP_50_MV),
 	regulator_desc_ldo(4, STEP_50_MV),
-	regulator_desc_ldo(5, STEP_50_MV),
+	regulator_desc_ldo(5, STEP_25_MV),
 	regulator_desc_ldo(6, STEP_25_MV),
 	regulator_desc_ldo(7, STEP_50_MV),
 	regulator_desc_ldo(8, STEP_50_MV),
 	regulator_desc_ldo(9, STEP_50_MV),
 	regulator_desc_ldo(10, STEP_50_MV),
-	regulator_desc_ldo(11, STEP_25_MV),
+	regulator_desc_ldo(11, STEP_50_MV),
 	regulator_desc_ldo(12, STEP_50_MV),
 	regulator_desc_ldo(13, STEP_50_MV),
 	regulator_desc_ldo(14, STEP_50_MV),

@@ -315,11 +315,11 @@ static const struct regulator_desc regul
 	regulator_desc_ldo(19, STEP_50_MV),
 	regulator_desc_ldo(20, STEP_50_MV),
 	regulator_desc_ldo(21, STEP_50_MV),
-	regulator_desc_ldo(22, STEP_25_MV),
-	regulator_desc_ldo(23, STEP_25_MV),
+	regulator_desc_ldo(22, STEP_50_MV),
+	regulator_desc_ldo(23, STEP_50_MV),
 	regulator_desc_ldo(24, STEP_50_MV),
 	regulator_desc_ldo(25, STEP_50_MV),
-	regulator_desc_ldo(26, STEP_50_MV),
+	regulator_desc_ldo(26, STEP_25_MV),
 	regulator_desc_buck1_4(1),
 	regulator_desc_buck1_4(2),
 	regulator_desc_buck1_4(3),

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

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

From: Stuart Menefy <[email protected]>

commit a5719a40aef956ba704f2aa1c7b977224d60fa96 upstream.

When a timer tick occurs and the clock is in one-shot mode, the timer needs to be stopped to prevent it triggering subsequent interrupts. Currently this code is in exynos4_mct_tick_clear(), but as it is only needed when an ISR occurs move it into exynos4_mct_tick_isr(), leaving exynos4_mct_tick_clear() just doing what its name suggests it should.

---
 drivers/clocksource/exynos_mct.c |   22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

@@ -388,6 +388,13 @@ static void exynos4_mct_tick_start(unsig
 	exynos4_mct_write(tmp, mevt->base + MCT_L_TCON_OFFSET);
 }
 
+static void exynos4_mct_tick_clear(struct mct_clock_event_device *mevt)
+{
+	/* Clear the MCT tick interrupt */
+	if (readl_relaxed(reg_base + mevt->base + MCT_L_INT_CSTAT_OFFSET) & 1)
+		exynos4_mct_write(0x1, mevt->base + MCT_L_INT_CSTAT_OFFSET);
+}
+
 static int exynos4_tick_set_next_event(unsigned long cycles,
 				       struct clock_event_device *evt)
 {

@@ -420,8 +427,11 @@ static int set_state_periodic(struct clo
 	return 0;
 }
 
-static void exynos4_mct_tick_clear(struct mct_clock_event_device *mevt)
+static irqreturn_t exynos4_mct_tick_isr(int irq, void *dev_id)
 {
+	struct mct_clock_event_device *mevt = dev_id;
+	struct clock_event_device *evt = &mevt->evt;
+
 	/*
 	 * This is for supporting oneshot mode.
 	 * Mct would generate interrupt periodically

@@ -430,16 +440,6 @@ static void exynos4_mct_tick_clear(struc
 	if (!clockevent_state_periodic(&mevt->evt))
 		exynos4_mct_tick_stop(mevt);
 
-	/* Clear the MCT tick interrupt */
-	if (readl_relaxed(reg_base + mevt->base + MCT_L_INT_CSTAT_OFFSET) & 1)
-		exynos4_mct_write(0x1, mevt->base + MCT_L_INT_CSTAT_OFFSET);
-}
-
-static irqreturn_t exynos4_mct_tick_isr(int irq, void *dev_id)
-{
-	struct mct_clock_event_device *mevt = dev_id;
-	struct clock_event_device *evt = &mevt->evt;
-
 	exynos4_mct_tick_clear(mevt);
 
 	evt->event_handler(evt);

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

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

From: Stuart Menefy <[email protected]>

commit d2f276c8d3c224d5b493c42b6cf006ae4e64fb1c upstream.

When shutting down the timer, ensure that after we have stopped the timer any pending interrupts are cleared. This fixes a problem when suspending, as interrupts are disabled before the timer is stopped, so the timer interrupt may still be asserted, preventing the system entering a low power state when the wfi is executed.

---
 drivers/clocksource/exynos_mct.c |    1 +
 1 file changed, 1 insertion(+)

@@ -411,6 +411,7 @@ static int set_state_shutdown(struct clo
 
 	mevt = container_of(evt, struct mct_clock_event_device, evt);
 	exynos4_mct_tick_stop(mevt);
+	exynos4_mct_tick_clear(mevt);
 	return 0;
 }
 

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

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

From: Samuel Holland <[email protected]>

commit c950ca8c35eeb32224a63adc47e12f9e226da241 upstream.

The Allwinner A64 SoC is known[1] to have an unstable architectural timer, which manifests itself most obviously in the time jumping forward a multiple of 95 years[2][3]. This coincides with 2^56 cycles at a timer frequency of 24 MHz, implying that the time went slightly backward (and this was interpreted by the kernel as it jumping forward and wrapping around past the epoch).

Investigation revealed instability in the low bits of CNTVCT at the point a high bit rolls over. This leads to power-of-two cycle forward and backward jumps. (Testing shows that forward jumps are about twice as likely as backward jumps.) Since the counter value returns to normal after an indeterminate read, each "jump" really consists of both a forward and backward jump from the software perspective.

Unless the kernel is trapping CNTVCT reads, a userspace program is able to read the register in a loop faster than it changes. A test program running on all 4 CPU cores that reported jumps larger than 100 ms was run for 13.6 hours and reported the following:

Count | Event
-------+---------------------------

  9940 | jumped backward      699ms
   268 | jumped backward     1398ms
     1 | jumped backward     2097ms
 16020 | jumped forward       175ms
  6443 | jumped forward       699ms
  2976 | jumped forward      1398ms
     9 | jumped forward    356516ms
     9 | jumped forward    357215ms
     4 | jumped forward    714430ms
     1 | jumped forward   3578440ms

This works out to a jump larger than 100 ms about every 5.5 seconds on each CPU core.

The largest jump (almost an hour!) was the following sequence of reads:

    0x0000007fffffffff → 0x00000093feffffff → 0x0000008000000000

Note that the middle bits don't necessarily all read as all zeroes or all ones during the anomalous behavior; however the low 10 bits checked by the function in this patch have never been observed with any other value.

Also note that smaller jumps are much more common, with backward jumps of 2048 (2^11) cycles observed over 400 times per second on each core. (Of course, this is partially explained by lower bits rolling over more frequently.) Any one of these could have caused the 95 year time skip.

Similar anomalies were observed while reading CNTPCT (after patching the kernel to allow reads from userspace). However, the CNTPCT jumps are much less frequent, and only small jumps were observed. The same program as before (except now reading CNTPCT) observed after 72 hours:

Count | Event
-------+---------------------------

    17 | jumped backward      699ms
    52 | jumped forward       175ms
  2831 | jumped forward       699ms
     5 | jumped forward      1398ms

Further investigation showed that the instability in CNTPCT/CNTVCT also affected the respective timer's TVAL register. The following values were observed immediately after writing CNVT_TVAL to 0x10000000:

CNTVCT | CNTV_TVAL | CNTV_CVAL | CNTV_TVAL Error
--------------------+------------+--------------------+-----------------

 0x000000d4a2d8bfff | 0x10003fff | 0x000000d4b2d8bfff | +0x00004000
 0x000000d4a2d94000 | 0x0fffffff | 0x000000d4b2d97fff | -0x00004000
 0x000000d4a2d97fff | 0x10003fff | 0x000000d4b2d97fff | +0x00004000
 0x000000d4a2d9c000 | 0x0fffffff | 0x000000d4b2d9ffff | -0x00004000

The pattern of errors in CNTV_TVAL seemed to depend on exactly which value was written to it. For example, after writing 0x10101010:

CNTVCT | CNTV_TVAL | CNTV_CVAL | CNTV_TVAL Error
--------------------+------------+--------------------+-----------------

 0x000001ac3effffff | 0x1110100f | 0x000001ac4f10100f | +0x1000000
 0x000001ac40000000 | 0x1010100f | 0x000001ac5110100f | -0x1000000
 0x000001ac58ffffff | 0x1110100f | 0x000001ac6910100f | +0x1000000
 0x000001ac66000000 | 0x1010100f | 0x000001ac7710100f | -0x1000000
 0x000001ac6affffff | 0x1110100f | 0x000001ac7b10100f | +0x1000000
 0x000001ac6e000000 | 0x1010100f | 0x000001ac7f10100f | -0x1000000

I was also twice able to reproduce the issue covered by Allwinner's workaround[4], that writing to TVAL sometimes fails, and both CVAL and TVAL are left with entirely bogus values. One was the following values:

CNTVCT | CNTV_TVAL | CNTV_CVAL
--------------------+------------+--------------------------------------
0x000000d4a2d6014c | 0x8fbd5721 | 0x000000d132935fff (615s in the past)

========================================================================

Because the CPU can read the CNTPCT/CNTVCT registers faster than they change, performing two reads of the register and comparing the high bits (like other workarounds) is not a workable solution. And because the timer can jump both forward and backward, no pair of reads can distinguish a good value from a bad one. The only way to guarantee a good value from consecutive reads would be to read _three_ times, and take the middle value only if the three values are 1) each unique and
2) increasing. This takes at minimum 3 counter cycles (125 ns), or more if an anomaly is detected.

However, since there is a distinct pattern to the bad values, we can optimize the common case (1022/1024 of the time) to a single read by simply ignoring values that match the error pattern. This still takes no more than 3 cycles in the worst case, and requires much less code. As an additional safety check, we still limit the loop iteration to the number of max-frequency (1.2 GHz) CPU cycles in three 24 MHz counter periods.

For the TVAL registers, the simple solution is to not use them. Instead, read or write the CVAL and calculate the TVAL value in software.

Although the manufacturer is aware of at least part of the erratum[4], there is no official name for it. For now, use the kernel-internal name "UNKNOWN1".

[1]: https://github.com/armbian/build/commit/a08cd6fe7ae9
[2]: https://forum.armbian.com/topic/3458-a64-datetime-clock-issue/
[3]: https://irclog.whitequark.org/linux-sunxi/2018-01-26
[4]: https://github.com/Allwinner-Homlet/H6-BSP4.9-linux/blob/master/drivers/clocksource/arm_arch_timer.c#L272

---
 Documentation/arm64/silicon-errata.txt |    2 +
 drivers/clocksource/Kconfig            |   10 ++++++
 drivers/clocksource/arm_arch_timer.c   |   55 +++++++++++++++++++++++++++++++++
 3 files changed, 67 insertions(+)

@@ -44,6 +44,8 @@ stable kernels.
 
 | Implementor    | Component       | Erratum ID      | Kconfig                     |
 +----------------+-----------------+-----------------+-----------------------------+
+| Allwinner      | A64/R18         | UNKNOWN1        | SUN50I_ERRATUM_UNKNOWN1     |
+|                |                 |                 |                             |
 | ARM            | Cortex-A53      | #826319         | ARM64_ERRATUM_826319        |
 | ARM            | Cortex-A53      | #827319         | ARM64_ERRATUM_827319        |
 | ARM            | Cortex-A53      | #824069         | ARM64_ERRATUM_824069        |

@@ -365,6 +365,16 @@ config ARM64_ERRATUM_858921
 	  The workaround will be dynamically enabled when an affected
 	  core is detected.
 
+config SUN50I_ERRATUM_UNKNOWN1
+	bool "Workaround for Allwinner A64 erratum UNKNOWN1"
+	default y
+	depends on ARM_ARCH_TIMER && ARM64 && ARCH_SUNXI
+	select ARM_ARCH_TIMER_OOL_WORKAROUND
+	help
+	  This option enables a workaround for instability in the timer on
+	  the Allwinner A64 SoC. The workaround will only be active if the
+	  allwinner,erratum-unknown1 property is found in the timer node.
+
 config ARM_GLOBAL_TIMER
 	bool "Support for the ARM global timer" if COMPILE_TEST
 	select TIMER_OF if OF

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

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

From: Martin Schwidefsky <[email protected]>

commit 8727638426b0aea59d7f904ad8ddf483f9234f88 upstream.

The setup_lowcore() function creates a new prefix page for the boot CPU. The PSW mask for the system_call, external interrupt, i/o interrupt and the program check handler have the DAT bit set in this new prefix page.

At the time setup_lowcore is called the system still runs without virtual address translation, the paging_init() function creates the kernel page table and loads the CR13 with the kernel ASCE.

Any code between setup_lowcore() and the end of paging_init() that has a BUG or WARN statement will create a program check that can not be handled correctly as there is no kernel page table yet.

To allow early WARN statements initially setup the lowcore with DAT off and set the DAT bit only after paging_init() has completed.

---
 arch/s390/kernel/setup.c |   32 +++++++++++++++++++++++---------
 1 file changed, 23 insertions(+), 9 deletions(-)

@@ -303,7 +303,7 @@ early_param("vmalloc", parse_vmalloc);
 
 void *restart_stack __section(.data);
 
-static void __init setup_lowcore(void)
+static void __init setup_lowcore_dat_off(void)
 {
 	struct lowcore *lc;
 

@@ -314,19 +314,16 @@ static void __init setup_lowcore(void)
 	lc = memblock_virt_alloc_low(sizeof(*lc), sizeof(*lc));
 	lc->restart_psw.mask = PSW_KERNEL_BITS;
 	lc->restart_psw.addr = (unsigned long) restart_int_handler;
-	lc->external_new_psw.mask = PSW_KERNEL_BITS |
-		PSW_MASK_DAT | PSW_MASK_MCHECK;
+	lc->external_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK;
 	lc->external_new_psw.addr = (unsigned long) ext_int_handler;
 	lc->svc_new_psw.mask = PSW_KERNEL_BITS |
-		PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
+		PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
 	lc->svc_new_psw.addr = (unsigned long) system_call;
-	lc->program_new_psw.mask = PSW_KERNEL_BITS |
-		PSW_MASK_DAT | PSW_MASK_MCHECK;
+	lc->program_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK;
 	lc->program_new_psw.addr = (unsigned long) pgm_check_handler;
 	lc->mcck_new_psw.mask = PSW_KERNEL_BITS;
 	lc->mcck_new_psw.addr = (unsigned long) mcck_int_handler;
-	lc->io_new_psw.mask = PSW_KERNEL_BITS |
-		PSW_MASK_DAT | PSW_MASK_MCHECK;
+	lc->io_new_psw.mask = PSW_KERNEL_BITS | PSW_MASK_MCHECK;
 	lc->io_new_psw.addr = (unsigned long) io_int_handler;
 	lc->clock_comparator = clock_comparator_max;
 	lc->kernel_stack = ((unsigned long) &init_thread_union)

@@ -388,6 +385,17 @@ static void __init setup_lowcore(void)
 	lowcore_ptr[0] = lc;
 }
 
+static void __init setup_lowcore_dat_on(void)
+{
+	struct lowcore *lc;
+
+	lc = lowcore_ptr[0];
+	lc->external_new_psw.mask |= PSW_MASK_DAT;
+	lc->svc_new_psw.mask |= PSW_MASK_DAT;
+	lc->program_new_psw.mask |= PSW_MASK_DAT;
+	lc->io_new_psw.mask |= PSW_MASK_DAT;
+}
+
 static struct resource code_resource = {
 	.name  = "Kernel code",
 	.flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM,

@@ -946,7 +954,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	setup_resources();
-	setup_lowcore();
+	setup_lowcore_dat_off();
 	smp_fill_possible_mask();
 	cpu_detect_mhz_feature();
         cpu_init();

@@ -959,6 +967,12 @@ void __init setup_arch(char **cmdline_p)
 	 */
         paging_init();
 
+	/*
+	 * After paging_init created the kernel page table, the new PSWs
+	 * in lowcore can now run with DAT enabled.
+	 */
+	setup_lowcore_dat_on();
+
         /* Setup default console */
 	conmode_default();
 	set_preferred_console();

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

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

From: Halil Pasic <[email protected]>

commit 3438b2c039b4bf26881786a1f3450f016d66ad11 upstream.

A queue with a capacity of zero is clearly not a valid virtio queue. Some emulators report zero queue size if queried with an invalid queue index. Instead of crashing in this case let us just return -ENOENT. To make that work properly, let us fix the notifier cleanup logic as well.

---
 drivers/s390/virtio/virtio_ccw.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -272,6 +272,8 @@ static void virtio_ccw_drop_indicators(s
 {
 	struct virtio_ccw_vq_info *info;
 
+	if (!vcdev->airq_info)
+		return;
 	list_for_each_entry(info, &vcdev->virtqueues, node)
 		drop_airq_indicator(info->vq, vcdev->airq_info);
 }

@@ -413,7 +415,7 @@ static int virtio_ccw_read_vq_conf(struc
 	ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_VQ_CONF);
 	if (ret)
 		return ret;
-	return vcdev->config_block->num;
+	return vcdev->config_block->num ?: -ENOENT;
 }
 
 static void virtio_ccw_del_vq(struct virtqueue *vq, struct ccw1 *ccw)

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

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

From: Felipe Franciosi <[email protected]>

commit 3722e6a52174d7c3a00e6f5efd006ca093f346c1 upstream.

The virtio scsi spec defines struct virtio_scsi_ctrl_tmf as a set of device-readable records and a single device-writable response entry:

    struct virtio_scsi_ctrl_tmf
    {
        // Device-readable part
        le32 type;
        le32 subtype;
        u8 lun[8];
        le64 id;
        // Device-writable part
        u8 response;
    }

The above should be organised as two descriptor entries (or potentially more if using VIRTIO_F_ANY_LAYOUT), but without any extra data after "le64 id" or after "u8 response".

The Linux driver doesn't respect that, with virtscsi_abort() and virtscsi_device_reset() setting cmd->sc before calling virtscsi_tmf(). It results in the original scsi command payload (or writable buffers) added to the tmf.

This fixes the problem by leaving cmd->sc zeroed out, which makes virtscsi_kick_cmd() add the tmf to the control vq without any payload.

---
 drivers/scsi/virtio_scsi.c |    2 --
 1 file changed, 2 deletions(-)

@@ -621,7 +621,6 @@ static int virtscsi_device_reset(struct
 		return FAILED;
 
 	memset(cmd, 0, sizeof(*cmd));
-	cmd->sc = sc;
 	cmd->req.tmf = (struct virtio_scsi_ctrl_tmf_req){
 		.type = VIRTIO_SCSI_T_TMF,
 		.subtype = cpu_to_virtio32(vscsi->vdev,

@@ -680,7 +679,6 @@ static int virtscsi_abort(struct scsi_cm
 		return FAILED;
 
 	memset(cmd, 0, sizeof(*cmd));
-	cmd->sc = sc;
 	cmd->req.tmf = (struct virtio_scsi_ctrl_tmf_req){
 		.type = VIRTIO_SCSI_T_TMF,
 		.subtype = VIRTIO_SCSI_T_TMF_ABORT_TASK,

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

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

From: Sagar Biradar <[email protected]>

commit 0015437cc046e5ec2b57b00ff8312b8d432eac7c upstream.

Fix performance issue where the queue depth for SmartIOC logical volumes is set to 1, and allow the usual logical volume code to be executed

---
 drivers/scsi/aacraid/linit.c |   13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

@@ -413,13 +413,16 @@ static int aac_slave_configure(struct sc
 	if (chn < AAC_MAX_BUSES && tid < AAC_MAX_TARGETS && aac->sa_firmware) {
 		devtype = aac->hba_map[chn][tid].devtype;
 
-		if (devtype == AAC_DEVTYPE_NATIVE_RAW)
+		if (devtype == AAC_DEVTYPE_NATIVE_RAW) {
 			depth = aac->hba_map[chn][tid].qd_limit;
-		else if (devtype == AAC_DEVTYPE_ARC_RAW)
+			set_timeout = 1;
+			goto common_config;
+		}
+		if (devtype == AAC_DEVTYPE_ARC_RAW) {
 			set_qd_dev_type = true;
-
-		set_timeout = 1;
-		goto common_config;
+			set_timeout = 1;
+			goto common_config;
+		}
 	}
 
 	if (aac->jbod && (sdev->type == TYPE_DISK))

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

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

From: Martin K. Petersen <[email protected]>

commit a83da8a4509d3ebfe03bb7fffce022e4d5d4764f upstream.

It was reported that some devices report an OPTIMAL TRANSFER LENGTH of 0xFFFF blocks. That looks bogus, especially for a device with a 4096-byte physical block size.

Ignore OPTIMAL TRANSFER LENGTH if it is not a multiple of the device's reported physical block size.

To make the sanity checking conditionals more readable--and to facilitate printing warnings--relocate the checking to a helper function. No functional change aside from the printks.

Cc: <[email protected]>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=199759

---
 drivers/scsi/sd.c |   59 +++++++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 50 insertions(+), 9 deletions(-)

@@ -3066,6 +3066,55 @@ static void sd_read_security(struct scsi
 		sdkp->security = 1;
 }
 
+/*
+ * Determine the device's preferred I/O size for reads and writes
+ * unless the reported value is unreasonably small, large, not a
+ * multiple of the physical block size, or simply garbage.
+ */
+static bool sd_validate_opt_xfer_size(struct scsi_disk *sdkp,
+				      unsigned int dev_max)
+{
+	struct scsi_device *sdp = sdkp->device;
+	unsigned int opt_xfer_bytes =
+		logical_to_bytes(sdp, sdkp->opt_xfer_blocks);
+
+	if (sdkp->opt_xfer_blocks > dev_max) {
+		sd_first_printk(KERN_WARNING, sdkp,
+				"Optimal transfer size %u logical blocks " \
+				"> dev_max (%u logical blocks)\n",
+				sdkp->opt_xfer_blocks, dev_max);
+		return false;
+	}
+
+	if (sdkp->opt_xfer_blocks > SD_DEF_XFER_BLOCKS) {
+		sd_first_printk(KERN_WARNING, sdkp,
+				"Optimal transfer size %u logical blocks " \
+				"> sd driver limit (%u logical blocks)\n",
+				sdkp->opt_xfer_blocks, SD_DEF_XFER_BLOCKS);
+		return false;
+	}
+
+	if (opt_xfer_bytes < PAGE_SIZE) {
+		sd_first_printk(KERN_WARNING, sdkp,
+				"Optimal transfer size %u bytes < " \
+				"PAGE_SIZE (%u bytes)\n",
+				opt_xfer_bytes, (unsigned int)PAGE_SIZE);
+		return false;
+	}
+
+	if (opt_xfer_bytes & (sdkp->physical_block_size - 1)) {
+		sd_first_printk(KERN_WARNING, sdkp,
+				"Optimal transfer size %u bytes not a " \
+				"multiple of physical block size (%u bytes)\n",
+				opt_xfer_bytes, sdkp->physical_block_size);
+		return false;
+	}
+
+	sd_first_printk(KERN_INFO, sdkp, "Optimal transfer size %u bytes\n",
+			opt_xfer_bytes);
+	return true;
+}
+
 /**
  *	sd_revalidate_disk - called the first time a new disk is seen,
  *	performs disk spin up, read_capacity, etc.

@@ -3144,15 +3193,7 @@ static int sd_revalidate_disk(struct gen
 	dev_max = min_not_zero(dev_max, sdkp->max_xfer_blocks);
 	q->limits.max_dev_sectors = logical_to_sectors(sdp, dev_max);
 
-	/*
-	 * Determine the device's preferred I/O size for reads and writes
-	 * unless the reported value is unreasonably small, large, or
-	 * garbage.
-	 */
-	if (sdkp->opt_xfer_blocks &&
-	    sdkp->opt_xfer_blocks <= dev_max &&
-	    sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS &&
-	    logical_to_bytes(sdp, sdkp->opt_xfer_blocks) >= PAGE_SIZE) {
+	if (sd_validate_opt_xfer_size(sdkp, dev_max)) {
 		q->limits.io_opt = logical_to_bytes(sdp, sdkp->opt_xfer_blocks);
 		rw_max = logical_to_sectors(sdp, sdkp->opt_xfer_blocks);
 	} else

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

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

From: Bart Van Assche <[email protected]>

commit 32e36bfbcf31452a854263e7c7f32fbefc4b44d8 upstream.

When using SCSI passthrough in combination with the iSCSI target driver then cmd->t_state_lock may be obtained from interrupt context. Hence, all code that obtains cmd->t_state_lock from thread context must disable interrupts first. This patch avoids that lockdep reports the following:

WARNING: inconsistent lock state
4.18.0-dbg+ #1 Not tainted
--------------------------------
inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage.
iscsi_ttx/1800 [HC1[1]:SC0[2]:HE0:SE0] takes:
000000006e7b0ceb (&(&cmd->t_state_lock)->rlock){?...}, at: target_complete_cmd+0x47/0x2c0 [target_core_mod] {HARDIRQ-ON-W} state was registered at:

 lock_acquire+0xd2/0x260
 _raw_spin_lock+0x32/0x50
 iscsit_close_connection+0x97e/0x1020 [iscsi_target_mod]
 iscsit_take_action_for_connection_exit+0x108/0x200 [iscsi_target_mod]
 iscsi_target_rx_thread+0x180/0x190 [iscsi_target_mod]
 kthread+0x1cf/0x1f0
 ret_from_fork+0x24/0x30
irq event stamp: 1281
hardirqs last  enabled at (1279): [<ffffffff970ade79>] __local_bh_enable_ip+0xa9/0x160
hardirqs last disabled at (1281): [<ffffffff97a008a5>] interrupt_entry+0xb5/0xd0
softirqs last  enabled at (1278): [<ffffffff977cd9a1>] lock_sock_nested+0x51/0xc0
softirqs last disabled at (1280): [<ffffffffc07a6e04>] ip6_finish_output2+0x124/0xe40 [ipv6]

other info that might help us debug this:

Possible unsafe locking scenario:

      CPU0
      ----

lock(&(&cmd->t_state_lock)->rlock);
<Interrupt>
lock(&(&cmd->t_state_lock)->rlock);

---
 drivers/target/iscsi/iscsi_target.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -4045,9 +4045,9 @@ static void iscsit_release_commands_from
 		struct se_cmd *se_cmd = &cmd->se_cmd;
 
 		if (se_cmd->se_tfo != NULL) {
-			spin_lock(&se_cmd->t_state_lock);
+			spin_lock_irq(&se_cmd->t_state_lock);
 			se_cmd->transport_state |= CMD_T_FABRIC_STOP;
-			spin_unlock(&se_cmd->t_state_lock);
+			spin_unlock_irq(&se_cmd->t_state_lock);
 		}
 	}
 	spin_unlock_bh(&conn->cmd_lock);

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

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

From: Himanshu Madhani <[email protected]>

commit ec322937a7f152d68755dc8316523bf6f831b48f upstream.

This patch fixes LUN discovery when loop ID is not yet assigned by the firmware during driver load/sg_reset operations. Driver will now search for new loop id before retrying login.

---
 drivers/scsi/qla2xxx/qla_init.c |   13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

@@ -643,11 +643,14 @@ static void qla24xx_handle_gnl_done_even
 				break;
 			case DSC_LS_PORT_UNAVAIL:
 			default:
-				if (fcport->loop_id != FC_NO_LOOP_ID)
-					qla2x00_clear_loop_id(fcport);
-
-				fcport->loop_id = loop_id;
-				fcport->fw_login_state = DSC_LS_PORT_UNAVAIL;
+				if (fcport->loop_id == FC_NO_LOOP_ID) {
+					qla2x00_find_new_loop_id(vha, fcport);
+					fcport->fw_login_state =
+					    DSC_LS_PORT_UNAVAIL;
+				}
+				ql_dbg(ql_dbg_disc, vha, 0x20e5,
+				    "%s %d %8phC\n", __func__, __LINE__,
+				    fcport->port_name);
 				qla24xx_fcport_handle_login(vha, fcport);
 				break;
 			}

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

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

From: Varad Gautam <[email protected]>

commit 73052b0daee0b750b39af18460dfec683e4f5887 upstream.

d_delete only unhashes an entry if it is reached with dentry->d_lockref.count != 1. Prior to commit 8ead9dd54716 ("devpts:
more pty driver interface cleanups"), d_delete was called on a dentry from devpts_pty_kill with two references held, which would trigger the unhashing, and the subsequent dputs would release it.

Commit 8ead9dd54716 reworked devpts_pty_kill to stop acquiring the second reference from d_find_alias, and the d_delete call left the dentries still on the hashed list without actually ever being dropped from dcache before explicit cleanup. This causes the number of negative dentries for devpts to pile up, and an ls /dev/pts invocation can take seconds to return.

Provide always_delete_dentry() from simple_dentry_operations as .d_delete for devpts, to make the dentry be dropped from dcache.

Without this cleanup, the number of dentries in /dev/pts/ can be grown arbitrarily as:

python -c 'import pty; pty.spawn(["ls", "/dev/pts"])'

A systemtap probe on dcache_readdir to count d_subdirs shows this count to increase with each pty spawn invocation above:

probe kernel.function("dcache_readdir") {
    subdirs = &@cast($file->f_path->dentry, "dentry")->d_subdirs;
    p = subdirs;
    p = @cast(p, "list_head")->next;
    i = 0
    while (p != subdirs) {
      p = @cast(p, "list_head")->next;
      i = i+1;
    }
    printf("number of dentries: %d\n", i);
}

---
 fs/devpts/inode.c |    1 +
 1 file changed, 1 insertion(+)

@@ -455,6 +455,7 @@ devpts_fill_super(struct super_block *s,
 	s->s_blocksize_bits = 10;
 	s->s_magic = DEVPTS_SUPER_MAGIC;
 	s->s_op = &devpts_sops;
+	s->s_d_op = &simple_dentry_operations;
 	s->s_time_gran = 1;
 
 	error = -ENOMEM;

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

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

From: Jann Horn <[email protected]>

commit a0ce2f0aa6ad97c3d4927bf2ca54bcebdf062d55 upstream.

Before this patch, it was possible for two pipes to affect each other after data had been transferred between them with tee():

============

$ cat tee_test.c

int main(void) {
int pipe_a[2];
if (pipe(pipe_a)) err(1, "pipe");
int pipe_b[2];
if (pipe(pipe_b)) err(1, "pipe");
if (write(pipe_a[1], "abcd", 4) != 4) err(1, "write"); if (tee(pipe_a[0], pipe_b[1], 2, 0) != 2) err(1, "tee"); if (write(pipe_b[1], "xx", 2) != 2) err(1, "write");

char buf[5];
if (read(pipe_a[0], buf, 4) != 4) err(1, "read"); buf[4] = 0;
printf("got back: '%s'\n", buf);
}

$ gcc -o tee_test tee_test.c
$ ./tee_test
got back: 'abxx'
$
============

As suggested by Al Viro, fix it by creating a separate type for non-mergeable pipe buffers, then changing the types of buffers in splice_pipe_to_pipe() and link_pipe().

---
 fs/pipe.c                 |   14 ++++++++++++++
 fs/splice.c               |    4 ++++
 include/linux/pipe_fs_i.h |    1 +
 3 files changed, 19 insertions(+)

@@ -234,6 +234,14 @@ static const struct pipe_buf_operations
 	.get = generic_pipe_buf_get,
 };
 
+static const struct pipe_buf_operations anon_pipe_buf_nomerge_ops = {
+	.can_merge = 0,
+	.confirm = generic_pipe_buf_confirm,
+	.release = anon_pipe_buf_release,
+	.steal = anon_pipe_buf_steal,
+	.get = generic_pipe_buf_get,
+};
+
 static const struct pipe_buf_operations packet_pipe_buf_ops = {
 	.can_merge = 0,
 	.confirm = generic_pipe_buf_confirm,

@@ -242,6 +250,12 @@ static const struct pipe_buf_operations
 	.get = generic_pipe_buf_get,
 };
 
+void pipe_buf_mark_unmergeable(struct pipe_buffer *buf)
+{
+	if (buf->ops == &anon_pipe_buf_ops)
+		buf->ops = &anon_pipe_buf_nomerge_ops;
+}
+
 static ssize_t
 pipe_read(struct kiocb *iocb, struct iov_iter *to)
 {

@@ -1593,6 +1593,8 @@ retry:
 			 */
 			obuf->flags &= ~PIPE_BUF_FLAG_GIFT;
 
+			pipe_buf_mark_unmergeable(obuf);
+
 			obuf->len = len;
 			opipe->nrbufs++;
 			ibuf->offset += obuf->len;

@@ -1667,6 +1669,8 @@ static int link_pipe(struct pipe_inode_i
 		 */
 		obuf->flags &= ~PIPE_BUF_FLAG_GIFT;
 
+		pipe_buf_mark_unmergeable(obuf);
+
 		if (obuf->len > len)
 			obuf->len = len;
 

@@ -182,6 +182,7 @@ void generic_pipe_buf_get(struct pipe_in
 int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
 void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);
+void pipe_buf_mark_unmergeable(struct pipe_buffer *buf);
 
 extern const struct pipe_buf_operations nosteal_pipe_buf_ops;
 

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

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

From: Vivek Goyal <[email protected]>

commit 5f32879ea35523b9842bdbdc0065e13635caada2 upstream.

If a file with capability set (and hence security.capability xattr) is written kernel clears security.capability xattr. For overlay, during file copy up if xattrs are copied up first and then data is, copied up. This means data copy up will result in clearing of security.capability xattr file on lower has. And this can result into surprises. If a lower file has CAP_SETUID, then it should not be cleared over copy up (if nothing was actually written to file).

This also creates problems with chown logic where it first copies up file and then tries to clear setuid bit. But by that time security.capability xattr is already gone (due to data copy up), and caller gets -ENODATA. This has been reported by Giuseppe here.

https://github.com/containers/libpod/issues/2015#issuecomment-447824842

Fix this by copying up data first and then metadta. This is a regression which has been introduced by my commit as part of metadata only copy up patches.

TODO: There will be some corner cases where a file is copied up metadata only and later data copy up happens and that will clear security.capability xattr. Something needs to be done about that too.

---
 fs/overlayfs/copy_up.c |   31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)

@@ -501,6 +501,24 @@ static int ovl_copy_up_inode(struct ovl_
 {
 	int err;
 
+	/*
+	 * Copy up data first and then xattrs. Writing data after
+	 * xattrs will remove security.capability xattr automatically.
+	 */
+	if (S_ISREG(c->stat.mode) && !c->metacopy) {
+		struct path upperpath, datapath;
+
+		ovl_path_upper(c->dentry, &upperpath);
+		if (WARN_ON(upperpath.dentry != NULL))
+			return -EIO;
+		upperpath.dentry = temp;
+
+		ovl_path_lowerdata(c->dentry, &datapath);
+		err = ovl_copy_up_data(&datapath, &upperpath, c->stat.size);
+		if (err)
+			return err;
+	}
+
 	err = ovl_copy_xattr(c->lowerpath.dentry, temp);
 	if (err)
 		return err;

@@ -517,19 +535,6 @@ static int ovl_copy_up_inode(struct ovl_
 		if (err)
 			return err;
 	}
-
-	if (S_ISREG(c->stat.mode) && !c->metacopy) {
-		struct path upperpath, datapath;
-
-		ovl_path_upper(c->dentry, &upperpath);
-		BUG_ON(upperpath.dentry != NULL);
-		upperpath.dentry = temp;
-
-		ovl_path_lowerdata(c->dentry, &datapath);
-		err = ovl_copy_up_data(&datapath, &upperpath, c->stat.size);
-		if (err)
-			return err;
-	}
 
 	if (c->metacopy) {
 		err = ovl_check_setxattr(c->dentry, temp, OVL_XATTR_METACOPY,

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

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

From: Vivek Goyal <[email protected]>

commit 993a0b2aec52754f0897b1dab4c453be8217cae5 upstream.

If a file has been copied up metadata only, and later data is copied up, upper loses any security.capability xattr it has (underlying filesystem clears it as upon file write).

not result in losing security.capability xattr. Hence, before data copy up, save security.capability xattr (if any) and restore it on upper after data copy up is complete.

---
 fs/overlayfs/copy_up.c   |   28 ++++++++++++++++++++++-
 fs/overlayfs/overlayfs.h |    2 +
 fs/overlayfs/util.c      |   55 +++++++++++++++++++++++++++++------------------
 3 files changed, 63 insertions(+), 22 deletions(-)

@@ -711,6 +711,8 @@ static int ovl_copy_up_meta_inode_data(s
 {
 	struct path upperpath, datapath;
 	int err;
+	char *capability = NULL;
+	ssize_t uninitialized_var(cap_size);
 
 	ovl_path_upper(c->dentry, &upperpath);
 	if (WARN_ON(upperpath.dentry == NULL))

@@ -720,15 +722,37 @@ static int ovl_copy_up_meta_inode_data(s
 	if (WARN_ON(datapath.dentry == NULL))
 		return -EIO;
 
+	if (c->stat.size) {
+		err = cap_size = ovl_getxattr(upperpath.dentry, XATTR_NAME_CAPS,
+					      &capability, 0);
+		if (err < 0 && err != -ENODATA)
+			goto out;
+	}
+
 	err = ovl_copy_up_data(&datapath, &upperpath, c->stat.size);
 	if (err)
-		return err;
+		goto out_free;
+
+	/*
+	 * Writing to upper file will clear security.capability xattr. We
+	 * don't want that to happen for normal copy-up operation.
+	 */
+	if (capability) {
+		err = ovl_do_setxattr(upperpath.dentry, XATTR_NAME_CAPS,
+				      capability, cap_size, 0);
+		if (err)
+			goto out_free;
+	}
+
 
 	err = vfs_removexattr(upperpath.dentry, OVL_XATTR_METACOPY);
 	if (err)
-		return err;
+		goto out_free;
 
 	ovl_set_upperdata(d_inode(c->dentry));
+out_free:
+	kfree(capability);
+out:
 	return err;
 }
 

@@ -277,6 +277,8 @@ int ovl_lock_rename_workdir(struct dentr
 int ovl_check_metacopy_xattr(struct dentry *dentry);
 bool ovl_is_metacopy_dentry(struct dentry *dentry);
 char *ovl_get_redirect_xattr(struct dentry *dentry, int padding);
+ssize_t ovl_getxattr(struct dentry *dentry, char *name, char **value,
+		     size_t padding);
 
 static inline bool ovl_is_impuredir(struct dentry *dentry)
 {

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

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

From: Finn Thain <[email protected]>

commit 28713169d879b67be2ef2f84dcf54905de238294 upstream.

This patch fixes a build failure when using GCC 8.1:

/usr/bin/ld: block/partitions/ldm.o: in function `ldm_parse_tocblock':
block/partitions/ldm.c:153: undefined reference to `strcmp'

This is caused by a new optimization which effectively replaces a strncmp() call with a strcmp() call. This affects a number of strncmp() call sites in the kernel.

The entire class of optimizations is avoided with -fno-builtin, which gets enabled by -ffreestanding. This may avoid possible future build failures in case new optimizations appear in future compilers.

I haven't done any performance measurements with this patch but I did count the function calls in a defconfig build. For example, there are now 23 more sprintf() calls and 39 fewer strcpy() calls. The effect on the other libc functions is smaller.

If this harms performance we can tackle that regression by optimizing the call sites, ideally using semantic patches. That way, clang and ICC builds might benfit too.

Cc: [email protected]
Reference: https://marc.info/?l=linux-m68k&m=154514816222244&w=2

---
 arch/m68k/Makefile |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -58,7 +58,10 @@ cpuflags-$(CONFIG_M5206e)	:= $(call cc-o
 cpuflags-$(CONFIG_M5206)	:= $(call cc-option,-mcpu=5206,-m5200)
 
 KBUILD_AFLAGS += $(cpuflags-y)
-KBUILD_CFLAGS += $(cpuflags-y) -pipe
+KBUILD_CFLAGS += $(cpuflags-y)
+
+KBUILD_CFLAGS += -pipe -ffreestanding
+
 ifdef CONFIG_MMU
 # without -fno-strength-reduce the 53c7xx.c driver fails ;-(
 KBUILD_CFLAGS += -fno-strength-reduce -ffixed-a2

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

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

From: Filipe Manana <[email protected]>

commit b89f6d1fcb30a8cbdc18ce00c7d93792076af453 upstream.

We are holding a transaction handle when creating a tree, therefore we can not allocate the root using GFP_KERNEL, as we could deadlock if reclaim is triggered by the allocation, therefore setup a nofs context.

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

@@ -17,6 +17,7 @@
 #include <linux/semaphore.h>
 #include <linux/error-injection.h>
 #include <linux/crc32c.h>
+#include <linux/sched/mm.h>
 #include <asm/unaligned.h>
 #include "ctree.h"
 #include "disk-io.h"

@@ -1236,10 +1237,17 @@ struct btrfs_root *btrfs_create_tree(str
 	struct btrfs_root *tree_root = fs_info->tree_root;
 	struct btrfs_root *root;
 	struct btrfs_key key;
+	unsigned int nofs_flag;
 	int ret = 0;
 	uuid_le uuid = NULL_UUID_LE;
 
+	/*
+	 * We're holding a transaction handle, so use a NOFS memory allocation
+	 * context to avoid deadlock if reclaim happens.
+	 */
+	nofs_flag = memalloc_nofs_save();
 	root = btrfs_alloc_root(fs_info, GFP_KERNEL);
+	memalloc_nofs_restore(nofs_flag);
 	if (!root)
 		return ERR_PTR(-ENOMEM);
 

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

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

From: Filipe Manana <[email protected]>

commit a0873490660246db587849a9e172f2b7b21fa88a upstream.

We are holding a transaction handle when setting an acl, therefore we can not allocate the xattr value buffer using GFP_KERNEL, as we could deadlock if reclaim is triggered by the allocation, therefore setup a nofs context.

---
 fs/btrfs/acl.c |    9 +++++++++
 1 file changed, 9 insertions(+)

@@ -9,6 +9,7 @@
 #include <linux/posix_acl_xattr.h>
 #include <linux/posix_acl.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/slab.h>
 
 #include "ctree.h"

@@ -72,8 +73,16 @@ static int __btrfs_set_acl(struct btrfs_
 	}
 
 	if (acl) {
+		unsigned int nofs_flag;
+
 		size = posix_acl_xattr_size(acl->a_count);
+		/*
+		 * We're holding a transaction handle, so use a NOFS memory
+		 * allocation context to avoid deadlock if reclaim happens.
+		 */
+		nofs_flag = memalloc_nofs_save();
 		value = kmalloc(size, GFP_KERNEL);
+		memalloc_nofs_restore(nofs_flag);
 		if (!value) {
 			ret = -ENOMEM;
 			goto out;

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

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

From: Johannes Thumshirn <[email protected]>

commit 349ae63f40638a28c6fce52e8447c2d14b84cc0c upstream.

We recently had a customer issue with a corrupted filesystem. When trying to mount this image btrfs panicked with a division by zero in calc_stripe_length().

The corrupt chunk had a 'num_stripes' value of 1. calc_stripe_length() takes this value and divides it by the number of copies the RAID profile is expected to have to calculate the amount of data stripes. As a DUP profile is expected to have 2 copies this division resulted in 1/2 = 0. Later then the 'data_stripes' variable is used as a divisor in the stripe length calculation which results in a division by 0 and thus a kernel panic.

When encountering a filesystem with a DUP block group and a 'num_stripes' value unequal to 2, refuse mounting as the image is corrupted and will lead to unexpected behaviour.

Code inspection showed a RAID1 block group has the same issues.

---
 fs/btrfs/volumes.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -6425,10 +6425,10 @@ static int btrfs_check_chunk_valid(struc
 	}
 
 	if ((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) ||
-	    (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes < 1) ||
+	    (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes != 2) ||
 	    (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) ||
 	    (type & BTRFS_BLOCK_GROUP_RAID6 && num_stripes < 3) ||
-	    (type & BTRFS_BLOCK_GROUP_DUP && num_stripes > 2) ||
+	    (type & BTRFS_BLOCK_GROUP_DUP && num_stripes != 2) ||
 	    ((type & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 &&
 	     num_stripes != 1)) {
 		btrfs_err(fs_info,

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

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

From: Filipe Manana <[email protected]>

commit 8e928218780e2f1cf2f5891c7575e8f0b284fcce upstream.

In the past we had data corruption when reading compressed extents that are shared within the same file and they are consecutive, this got fixed by commit 005efedf2c7d0 ("Btrfs: fix read corruption of compressed and shared extents") and by commit 808f80b46790f ("Btrfs: update fix for read corruption of compressed and shared extents"). However there was a case that was missing in those fixes, which is when the shared and compressed extents are referenced with a non-zero offset. The following shell script creates a reproducer for this issue:

#!/bin/bash

mkfs.btrfs -f /dev/sdc &> /dev/null
mount -o compress /dev/sdc /mnt/sdc

# Create a file with 3 consecutive compressed extents, each has an

  # uncompressed size of 128Kb and a compressed size of 4Kb.
  for ((i = 1; i <= 3; i++)); do
      head -c 4096 /dev/zero
      for ((j = 1; j <= 31; j++)); do
          head -c 4096 /dev/zero | tr '\0' "\377"
      done
  done > /mnt/sdc/foobar
  sync

  echo "Digest after file creation:   $(md5sum /mnt/sdc/foobar)"

# Clone the first extent into offsets 128K and 256K. xfs_io -c "reflink /mnt/sdc/foobar 0 128K 128K" /mnt/sdc/foobar xfs_io -c "reflink /mnt/sdc/foobar 0 256K 128K" /mnt/sdc/foobar sync

  echo "Digest after cloning:         $(md5sum /mnt/sdc/foobar)"

# Punch holes into the regions that are already full of zeroes. xfs_io -c "fpunch 0 4K" /mnt/sdc/foobar
xfs_io -c "fpunch 128K 4K" /mnt/sdc/foobar
xfs_io -c "fpunch 256K 4K" /mnt/sdc/foobar
sync

  echo "Digest after hole punching:   $(md5sum /mnt/sdc/foobar)"

  echo "Dropping page cache..."
  sysctl -q vm.drop_caches=1
  echo "Digest after hole punching:   $(md5sum /mnt/sdc/foobar)"

umount /dev/sdc

When running the script we get the following output:

Digest after file creation: 5a0888d80d7ab1fd31c229f83a3bbcc8 /mnt/sdc/foobar
linked 131072/131072 bytes at offset 131072
128 KiB, 1 ops; 0.0033 sec (36.960 MiB/sec and 295.6830 ops/sec) linked 131072/131072 bytes at offset 262144
128 KiB, 1 ops; 0.0015 sec (78.567 MiB/sec and 628.5355 ops/sec)

  Digest after cloning:         5a0888d80d7ab1fd31c229f83a3bbcc8  /mnt/sdc/foobar
  Digest after hole punching:   5a0888d80d7ab1fd31c229f83a3bbcc8  /mnt/sdc/foobar

Dropping page cache...
Digest after hole punching: fba694ae8664ed0c2e9ff8937e7f1484 /mnt/sdc/foobar

This happens because after reading all the pages of the extent in the range from 128K to 256K for example, we read the hole at offset 256K and then when reading the page at offset 260K we don't submit the existing bio, which is responsible for filling all the page in the range 128K to 256K only, therefore adding the pages from range 260K to 384K to the existing bio and submitting it after iterating over the entire range. Once the bio completes, the uncompressed data fills only the pages in the range 128K to 256K because there's no more data read from disk, leaving the pages in the range 260K to 384K unfilled. It is just a slightly different variant of what was solved by commit 005efedf2c7d0 ("Btrfs: fix read corruption of compressed and shared extents").

Fix this by forcing a bio submit, during readpages(), whenever we find a compressed extent map for a page that is different from the extent map for the previous page or has a different starting offset (in case it's the same compressed extent), instead of the extent map's original start offset.

A test case for fstests follows soon.

---
 fs/btrfs/extent_io.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -3002,11 +3002,11 @@ static int __do_readpage(struct extent_i
 		 */
 		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) &&
 		    prev_em_start && *prev_em_start != (u64)-1 &&
-		    *prev_em_start != em->orig_start)
+		    *prev_em_start != em->start)
 			force_bio_submit = true;
 
 		if (prev_em_start)
-			*prev_em_start = em->orig_start;
+			*prev_em_start = em->start;
 
 		free_extent_map(em);
 		em = NULL;

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

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

From: Stephen Boyd <[email protected]>

commit baef1c90aac7e5bf13f0360a3b334825a23d31a1 upstream.

Using the batch API from the interconnect driver sometimes leads to a KASAN error due to an access to freed memory. This is easier to trigger with threadirqs on the kernel commandline.

 BUG: KASAN: use-after-free in rpmh_tx_done+0x114/0x12c
 Read of size 1 at addr fffffff51414ad84 by task irq/110-apps_rs/57

 CPU: 0 PID: 57 Comm: irq/110-apps_rs Tainted: G        W         4.19.10 #72
 Call trace:
  dump_backtrace+0x0/0x2f8
  show_stack+0x20/0x2c
  __dump_stack+0x20/0x28
  dump_stack+0xcc/0x10c
  print_address_description+0x74/0x240
  kasan_report+0x250/0x26c
  __asan_report_load1_noabort+0x20/0x2c
  rpmh_tx_done+0x114/0x12c
  tcs_tx_done+0x450/0x768
  irq_forced_thread_fn+0x58/0x9c
  irq_thread+0x120/0x1dc
  kthread+0x248/0x260
  ret_from_fork+0x10/0x18

 Allocated by task 385:
  kasan_kmalloc+0xac/0x148
  __kmalloc+0x170/0x1e4
  rpmh_write_batch+0x174/0x540
  qcom_icc_set+0x8dc/0x9ac
  icc_set+0x288/0x2e8
  a6xx_gmu_stop+0x320/0x3c0
  a6xx_pm_suspend+0x108/0x124
  adreno_suspend+0x50/0x60
  pm_generic_runtime_suspend+0x60/0x78
  __rpm_callback+0x214/0x32c
  rpm_callback+0x54/0x184
  rpm_suspend+0x3f8/0xa90
  pm_runtime_work+0xb4/0x178
  process_one_work+0x544/0xbc0
  worker_thread+0x514/0x7d0
  kthread+0x248/0x260
  ret_from_fork+0x10/0x18

 Freed by task 385:
  __kasan_slab_free+0x12c/0x1e0
  kasan_slab_free+0x10/0x1c
  kfree+0x134/0x588
  rpmh_write_batch+0x49c/0x540
  qcom_icc_set+0x8dc/0x9ac
  icc_set+0x288/0x2e8
  a6xx_gmu_stop+0x320/0x3c0
  a6xx_pm_suspend+0x108/0x124
  adreno_suspend+0x50/0x60
 cr50_spi spi5.0: SPI transfer timed out
  pm_generic_runtime_suspend+0x60/0x78
  __rpm_callback+0x214/0x32c
  rpm_callback+0x54/0x184
  rpm_suspend+0x3f8/0xa90
  pm_runtime_work+0xb4/0x178
  process_one_work+0x544/0xbc0
  worker_thread+0x514/0x7d0
  kthread+0x248/0x260
  ret_from_fork+0x10/0x18

 The buggy address belongs to the object at fffffff51414ac80
  which belongs to the cache kmalloc-512 of size 512
 The buggy address is located 260 bytes inside of
  512-byte region [fffffff51414ac80, fffffff51414ae80)
 The buggy address belongs to the page:
 page:ffffffbfd4505200 count:1 mapcount:0 mapping:fffffff51e00c680 index:0x0 compound_mapcount: 0
 flags: 0x4000000000008100(slab|head)
 raw: 4000000000008100 ffffffbfd4529008 ffffffbfd44f9208 fffffff51e00c680
 raw: 0000000000000000 0000000000200020 00000001ffffffff 0000000000000000
 page dumped because: kasan: bad access detected

 Memory state around the buggy address:
  fffffff51414ac80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
  fffffff51414ad00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 >fffffff51414ad80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                    ^
  fffffff51414ae00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
  fffffff51414ae80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc

The batch API sets the same completion for each rpmh message that's sent and then loops through all the messages and waits for that single completion declared on the stack to be completed before returning from the function and freeing the message structures. Unfortunately, some messages may still be in process and 'stuck' in the TCS. At some later point, the tcs_tx_done() interrupt will run and try to process messages that have already been freed at the end of rpmh_write_batch(). This will in turn access the 'needs_free' member of the rpmh_request structure and cause KASAN to complain. Furthermore, if there's a message that's completed in rpmh_tx_done() and freed immediately after the complete() call is made we'll be racing with potentially freed memory when accessing the 'needs_free' member:

	CPU0                         CPU1
	----                         ----
	rpmh_tx_done()
	 complete(&compl)
	                             wait_for_completion(&compl)
	                             kfree(rpm_msg)
	 if (rpm_msg->needs_free)
	 <KASAN warning splat>

Let's fix this by allocating a chunk of completions for each message and waiting for all of them to be completed before returning from the batch API. Alternatively, we could wait for the last message in the batch, but that may be a more complicated change because it looks like tcs_tx_done() just iterates through the indices of the queue and completes each message instead of tracking the last inserted message and completing that first.

---
 drivers/soc/qcom/rpmh.c |   34 +++++++++++++++++++++-------------
 1 file changed, 21 insertions(+), 13 deletions(-)

@@ -80,6 +80,7 @@ void rpmh_tx_done(const struct tcs_reque
 	struct rpmh_request *rpm_msg = container_of(msg, struct rpmh_request,
 						    msg);
 	struct completion *compl = rpm_msg->completion;
+	bool free = rpm_msg->needs_free;
 
 	rpm_msg->err = r;
 

@@ -94,7 +95,7 @@ void rpmh_tx_done(const struct tcs_reque
 	complete(compl);
 
 exit:
-	if (rpm_msg->needs_free)
+	if (free)
 		kfree(rpm_msg);
 }
 

@@ -348,11 +349,12 @@ int rpmh_write_batch(const struct device
 {
 	struct batch_cache_req *req;
 	struct rpmh_request *rpm_msgs;
-	DECLARE_COMPLETION_ONSTACK(compl);
+	struct completion *compls;
 	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
 	unsigned long time_left;
 	int count = 0;
-	int ret, i, j;
+	int ret, i;
+	void *ptr;
 
 	if (!cmd || !n)
 		return -EINVAL;

@@ -362,10 +364,15 @@ int rpmh_write_batch(const struct device
 	if (!count)
 		return -EINVAL;
 
-	req = kzalloc(sizeof(*req) + count * sizeof(req->rpm_msgs[0]),
+	ptr = kzalloc(sizeof(*req) +
+		      count * (sizeof(req->rpm_msgs[0]) + sizeof(*compls)),
 		      GFP_ATOMIC);
-	if (!req)
+	if (!ptr)
 		return -ENOMEM;
+
+	req = ptr;
+	compls = ptr + sizeof(*req) + count * sizeof(*rpm_msgs);
+
 	req->count = count;
 	rpm_msgs = req->rpm_msgs;
 

@@ -380,25 +387,26 @@ int rpmh_write_batch(const struct device
 	}
 
 	for (i = 0; i < count; i++) {
-		rpm_msgs[i].completion = &compl;
+		struct completion *compl = &compls[i];
+
+		init_completion(compl);
+		rpm_msgs[i].completion = compl;
 		ret = rpmh_rsc_send_data(ctrlr_to_drv(ctrlr), &rpm_msgs[i].msg);
 		if (ret) {
 			pr_err("Error(%d) sending RPMH message addr=%#x\n",
 			       ret, rpm_msgs[i].msg.cmds[0].addr);
-			for (j = i; j < count; j++)
-				rpmh_tx_done(&rpm_msgs[j].msg, ret);
 			break;
 		}
 	}
 
 	time_left = RPMH_TIMEOUT_MS;
-	for (i = 0; i < count; i++) {
-		time_left = wait_for_completion_timeout(&compl, time_left);
+	while (i--) {
+		time_left = wait_for_completion_timeout(&compls[i], time_left);
 		if (!time_left) {
 			/*
 			 * Better hope they never finish because they'll signal
-			 * the completion on our stack and that's bad once
-			 * we've returned from the function.
+			 * the completion that we're going to free once
+			 * we've returned from this function.
 			 */
 			WARN_ON(1);
 			ret = -ETIMEDOUT;

@@ -407,7 +415,7 @@ int rpmh_write_batch(const struct device
 	}
 
 exit:
-	kfree(req);
+	kfree(ptr);
 
 	return ret;
 }

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

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

From: Lubomir Rintel <[email protected]>

commit 607076a904c435f2677fadaadd4af546279db68b upstream.

It doesn't make sense and the USB core warns on each submit of such URB, easily flooding the message buffer with tracebacks.

Analogous issue was fixed in regular libertas driver in commit 6528d8804780 ("libertas: don't set URB_ZERO_PACKET on IN USB transfer").

---
 drivers/net/wireless/marvell/libertas_tf/if_usb.c |    2 --
 1 file changed, 2 deletions(-)

@@ -433,8 +433,6 @@ static int __if_usb_submit_rx_urb(struct
 			  skb_tail_pointer(skb),
 			  MRVDRV_ETH_RX_PACKET_BUFFER_SIZE, callbackfn, cardp);
 
-	cardp->rx_urb->transfer_flags |= URB_ZERO_PACKET;
-
 	lbtf_deb_usb2(&cardp->udev->dev, "Pointer for rx_urb %p\n",
 		cardp->rx_urb);
 	ret = usb_submit_urb(cardp->rx_urb, GFP_ATOMIC);

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

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

From: Zenghui Yu <[email protected]>

commit 8d565748b6035eeda18895c213396a4c9fac6a4c upstream.

In current logic, its_parse_indirect_baser() will be invoked twice when allocating Device tables. Add a *break* to omit the unnecessary and annoying (might be ...) invoking.

---
 drivers/irqchip/irq-gic-v3-its.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -1893,6 +1893,8 @@ static int its_alloc_tables(struct its_n
 			indirect = its_parse_indirect_baser(its, baser,
 							    psz, &order,
 							    its->device_ids);
+			break;
+
 		case GITS_BASER_TYPE_VCPU:
 			indirect = its_parse_indirect_baser(its, baser,
 							    psz, &order,

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

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

From: Doug Berger <[email protected]>

commit 33517881ede742107f416533b8c3e4abc56763da upstream.

Using the irq_gc_lock/irq_gc_unlock functions in the suspend and resume functions creates the opportunity for a deadlock during suspend, resume, and shutdown. Using the irq_gc_lock_irqsave/ irq_gc_unlock_irqrestore variants prevents this possible deadlock.

---
 drivers/irqchip/irq-brcmstb-l2.c |   10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

@@ -129,8 +129,9 @@ static void brcmstb_l2_intc_suspend(stru
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	struct brcmstb_l2_intc_data *b = gc->private;
+	unsigned long flags;
 
-	irq_gc_lock(gc);
+	irq_gc_lock_irqsave(gc, flags);
 	/* Save the current mask */
 	b->saved_mask = irq_reg_readl(gc, ct->regs.mask);
 

@@ -139,7 +140,7 @@ static void brcmstb_l2_intc_suspend(stru
 		irq_reg_writel(gc, ~gc->wake_active, ct->regs.disable);
 		irq_reg_writel(gc, gc->wake_active, ct->regs.enable);
 	}
-	irq_gc_unlock(gc);
+	irq_gc_unlock_irqrestore(gc, flags);
 }
 
 static void brcmstb_l2_intc_resume(struct irq_data *d)

@@ -147,8 +148,9 @@ static void brcmstb_l2_intc_resume(struc
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 	struct irq_chip_type *ct = irq_data_get_chip_type(d);
 	struct brcmstb_l2_intc_data *b = gc->private;
+	unsigned long flags;
 
-	irq_gc_lock(gc);
+	irq_gc_lock_irqsave(gc, flags);
 	if (ct->chip.irq_ack) {
 		/* Clear unmasked non-wakeup interrupts */
 		irq_reg_writel(gc, ~b->saved_mask & ~gc->wake_active,

@@ -158,7 +160,7 @@ static void brcmstb_l2_intc_resume(struc
 	/* Restore the saved mask */
 	irq_reg_writel(gc, b->saved_mask, ct->regs.disable);
 	irq_reg_writel(gc, ~b->saved_mask, ct->regs.enable);
-	irq_gc_unlock(gc);
+	irq_gc_unlock_irqrestore(gc, flags);
 }
 
 static int __init brcmstb_l2_intc_of_init(struct device_node *np,

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

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

From: Masami Hiramatsu <[email protected]>

commit 0192e6535ebe9af68614198ced4fd6d37b778ebf upstream.

Prohibit probing on optprobe template code, since it is not a code but a template instruction sequence. If we modify this template, copied template must be broken.

---
 arch/x86/kernel/kprobes/opt.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -141,6 +141,11 @@ asm (
 
 void optprobe_template_func(void);
 STACK_FRAME_NON_STANDARD(optprobe_template_func);
+NOKPROBE_SYMBOL(optprobe_template_func);
+NOKPROBE_SYMBOL(optprobe_template_entry);
+NOKPROBE_SYMBOL(optprobe_template_val);
+NOKPROBE_SYMBOL(optprobe_template_call);
+NOKPROBE_SYMBOL(optprobe_template_end);
 
 #define TMPL_MOVE_IDX \
 	((long)optprobe_template_val - (long)optprobe_template_entry)

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

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

From: Viresh Kumar <[email protected]>

commit 0334906c06967142c8805fbe88acf787f65d3d26 upstream.

Commit 5ad7346b4ae2 ("cpufreq: kryo: Add module remove and exit") made it possible to build the kryo cpufreq driver as a module, but it failed to release all the resources, i.e. OPP tables, when the module is unloaded.

This patch fixes it by releasing the OPP tables, by calling dev_pm_opp_put_supported_hw() for them, from the qcom_cpufreq_kryo_remove() routine. The array of pointers to the OPP tables is also allocated dynamically now in qcom_cpufreq_kryo_probe(), as the pointers will be required while releasing the resources.

Compile tested only.

---
 drivers/cpufreq/qcom-cpufreq-kryo.c |   20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

@@ -75,7 +75,7 @@ static enum _msm8996_version qcom_cpufre
 
 static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
 {
-	struct opp_table *opp_tables[NR_CPUS] = {0};
+	struct opp_table **opp_tables;
 	enum _msm8996_version msm8996_version;
 	struct nvmem_cell *speedbin_nvmem;
 	struct device_node *np;

@@ -133,6 +133,10 @@ static int qcom_cpufreq_kryo_probe(struc
 	}
 	kfree(speedbin);
 
+	opp_tables = kcalloc(num_possible_cpus(), sizeof(*opp_tables), GFP_KERNEL);
+	if (!opp_tables)
+		return -ENOMEM;
+
 	for_each_possible_cpu(cpu) {
 		cpu_dev = get_cpu_device(cpu);
 		if (NULL == cpu_dev) {

@@ -151,8 +155,10 @@ static int qcom_cpufreq_kryo_probe(struc
 
 	cpufreq_dt_pdev = platform_device_register_simple("cpufreq-dt", -1,
 							  NULL, 0);
-	if (!IS_ERR(cpufreq_dt_pdev))
+	if (!IS_ERR(cpufreq_dt_pdev)) {
+		platform_set_drvdata(pdev, opp_tables);
 		return 0;
+	}
 
 	ret = PTR_ERR(cpufreq_dt_pdev);
 	dev_err(cpu_dev, "Failed to register platform device\n");

@@ -163,13 +169,23 @@ free_opp:
 			break;
 		dev_pm_opp_put_supported_hw(opp_tables[cpu]);
 	}
+	kfree(opp_tables);
 
 	return ret;
 }
 
 static int qcom_cpufreq_kryo_remove(struct platform_device *pdev)
 {
+	struct opp_table **opp_tables = platform_get_drvdata(pdev);
+	unsigned int cpu;
+
 	platform_device_unregister(cpufreq_dt_pdev);
+
+	for_each_possible_cpu(cpu)
+		dev_pm_opp_put_supported_hw(opp_tables[cpu]);
+
+	kfree(opp_tables);
+
 	return 0;
 }
 

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

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

From: Yangtao Li <[email protected]>

commit 446fae2bb5395f3028d8e3aae1508737e5a72ea1 upstream.

of_cpu_device_node_get() will increase the refcount of device_node, it is necessary to call of_node_put() at the end to release the refcount.

---
 drivers/cpufreq/tegra124-cpufreq.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -134,6 +134,8 @@ static int tegra124_cpufreq_probe(struct
 
 	platform_set_drvdata(pdev, priv);
 
+	of_node_put(np);
+
 	return 0;
 
 out_switch_to_pllx:

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

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

From: Arnd Bergmann <[email protected]>

commit 9505b98ccddc454008ca7efff90044e3e857c827 upstream.

pxa_cpufreq_init_voltages() is marked __init but usually inlined into the non-__init pxa_cpufreq_init() function. When building with clang, it can stay as a standalone function in a discarded section, and produce this warning:

WARNING: vmlinux.o(.text+0x616a00): Section mismatch in reference from the function pxa_cpufreq_init() to the function .init.text:pxa_cpufreq_init_voltages() The function pxa_cpufreq_init() references
the function __init pxa_cpufreq_init_voltages().
This is often because pxa_cpufreq_init lacks a __init
annotation or the annotation of pxa_cpufreq_init_voltages is wrong.

---
 drivers/cpufreq/pxa2xx-cpufreq.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

@@ -143,7 +143,7 @@ static int pxa_cpufreq_change_voltage(co
 	return ret;
 }
 
-static void __init pxa_cpufreq_init_voltages(void)
+static void pxa_cpufreq_init_voltages(void)
 {
 	vcc_core = regulator_get(NULL, "vcc_core");
 	if (IS_ERR(vcc_core)) {

@@ -159,7 +159,7 @@ static int pxa_cpufreq_change_voltage(co
 	return 0;
 }
 
-static void __init pxa_cpufreq_init_voltages(void) { }
+static void pxa_cpufreq_init_voltages(void) { }
 #endif
 
 static void find_freq_tables(struct cpufreq_frequency_table **freq_table,

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

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

From: yangerkun <[email protected]>

commit 67a11611e1a5211f6569044fbf8150875764d1d0 upstream.

Before really do swap between inode and boot inode, something need to check to avoid invalid or not permitted operation, like does this inode has inline data. But the condition check should be protected by inode lock to avoid change while swapping. Also some other condition will not change between swapping, but there has no problem to do this under inode lock.

---
 fs/ext4/ioctl.c |   22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

@@ -116,15 +116,6 @@ static long swap_inode_boot_loader(struc
 	struct inode *inode_bl;
 	struct ext4_inode_info *ei_bl;
 
-	if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode) ||
-	    IS_SWAPFILE(inode) || IS_ENCRYPTED(inode) ||
-	    ext4_has_inline_data(inode))
-		return -EINVAL;
-
-	if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) ||
-	    !inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
 	inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO, EXT4_IGET_SPECIAL);
 	if (IS_ERR(inode_bl))
 		return PTR_ERR(inode_bl);

@@ -137,6 +128,19 @@ static long swap_inode_boot_loader(struc
 	 * that only 1 swap_inode_boot_loader is running. */
 	lock_two_nondirectories(inode, inode_bl);
 
+	if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode) ||
+	    IS_SWAPFILE(inode) || IS_ENCRYPTED(inode) ||
+	    ext4_has_inline_data(inode)) {
+		err = -EINVAL;
+		goto journal_err_out;
+	}
+
+	if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) ||
+	    !inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) {
+		err = -EPERM;
+		goto journal_err_out;
+	}
+
 	/* Wait for all existing dio workers */
 	inode_dio_wait(inode);
 	inode_dio_wait(inode_bl);

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

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

From: yangerkun <[email protected]>

commit a46c68a318b08f819047843abf349aeee5d10ac2 upstream.

While do swap, we should make sure there has no new dirty page since we should swap i_data between two inode:
1.We should lock i_mmap_sem with write to avoid new pagecache from mmap read/write;
2.Change filemap_flush to filemap_write_and_wait and move them to the space protected by inode lock to avoid new pagecache from buffer read/write.

---
 fs/ext4/ioctl.c |   16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

@@ -121,9 +121,6 @@ static long swap_inode_boot_loader(struc
 		return PTR_ERR(inode_bl);
 	ei_bl = EXT4_I(inode_bl);
 
-	filemap_flush(inode->i_mapping);
-	filemap_flush(inode_bl->i_mapping);
-
 	/* Protect orig inodes against a truncate and make sure,
 	 * that only 1 swap_inode_boot_loader is running. */
 	lock_two_nondirectories(inode, inode_bl);

@@ -141,6 +138,15 @@ static long swap_inode_boot_loader(struc
 		goto journal_err_out;
 	}
 
+	down_write(&EXT4_I(inode)->i_mmap_sem);
+	err = filemap_write_and_wait(inode->i_mapping);
+	if (err)
+		goto err_out;
+
+	err = filemap_write_and_wait(inode_bl->i_mapping);
+	if (err)
+		goto err_out;
+
 	/* Wait for all existing dio workers */
 	inode_dio_wait(inode);
 	inode_dio_wait(inode_bl);

@@ -151,7 +157,7 @@ static long swap_inode_boot_loader(struc
 	handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2);
 	if (IS_ERR(handle)) {
 		err = -EINVAL;
-		goto journal_err_out;
+		goto err_out;
 	}
 
 	/* Protect extent tree against block allocations via delalloc */

@@ -208,6 +214,8 @@ static long swap_inode_boot_loader(struc
 	ext4_journal_stop(handle);
 	ext4_double_up_write_data_sem(inode, inode_bl);
 
+err_out:
+	up_write(&EXT4_I(inode)->i_mmap_sem);
 journal_err_out:
 	unlock_two_nondirectories(inode, inode_bl);
 	iput(inode_bl);

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

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

From: yangerkun <[email protected]>

commit aa507b5faf38784defe49f5e64605ac3c4425e26 upstream.

While do swap between two inode, they swap i_data without update quota information. Also, swap_inode_boot_loader can do "revert" somtimes, so update the quota while all operations has been finished.

---
 fs/ext4/ioctl.c |   56 +++++++++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 43 insertions(+), 13 deletions(-)

@@ -68,8 +68,6 @@ static void swap_inode_data(struct inode
 	ei2 = EXT4_I(inode2);
 
 	swap(inode1->i_version, inode2->i_version);
-	swap(inode1->i_blocks, inode2->i_blocks);
-	swap(inode1->i_bytes, inode2->i_bytes);
 	swap(inode1->i_atime, inode2->i_atime);
 	swap(inode1->i_mtime, inode2->i_mtime);
 

@@ -115,6 +113,9 @@ static long swap_inode_boot_loader(struc
 	int err;
 	struct inode *inode_bl;
 	struct ext4_inode_info *ei_bl;
+	qsize_t size, size_bl, diff;
+	blkcnt_t blocks;
+	unsigned short bytes;
 
 	inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO, EXT4_IGET_SPECIAL);
 	if (IS_ERR(inode_bl))

@@ -180,6 +181,13 @@ static long swap_inode_boot_loader(struc
 			memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data));
 	}
 
+	err = dquot_initialize(inode);
+	if (err)
+		goto err_out1;
+
+	size = (qsize_t)(inode->i_blocks) * (1 << 9) + inode->i_bytes;
+	size_bl = (qsize_t)(inode_bl->i_blocks) * (1 << 9) + inode_bl->i_bytes;
+	diff = size - size_bl;
 	swap_inode_data(inode, inode_bl);
 
 	inode->i_ctime = inode_bl->i_ctime = current_time(inode);

@@ -193,24 +201,46 @@ static long swap_inode_boot_loader(struc
 
 	err = ext4_mark_inode_dirty(handle, inode);
 	if (err < 0) {
+		/* No need to update quota information. */
 		ext4_warning(inode->i_sb,
 			"couldn't mark inode #%lu dirty (err %d)",
 			inode->i_ino, err);
 		/* Revert all changes: */
 		swap_inode_data(inode, inode_bl);
 		ext4_mark_inode_dirty(handle, inode);
-	} else {
-		err = ext4_mark_inode_dirty(handle, inode_bl);
-		if (err < 0) {
-			ext4_warning(inode_bl->i_sb,
-				"couldn't mark inode #%lu dirty (err %d)",
-				inode_bl->i_ino, err);
-			/* Revert all changes: */
-			swap_inode_data(inode, inode_bl);
-			ext4_mark_inode_dirty(handle, inode);
-			ext4_mark_inode_dirty(handle, inode_bl);
-		}
+		goto err_out1;
+	}
+
+	blocks = inode_bl->i_blocks;
+	bytes = inode_bl->i_bytes;
+	inode_bl->i_blocks = inode->i_blocks;
+	inode_bl->i_bytes = inode->i_bytes;
+	err = ext4_mark_inode_dirty(handle, inode_bl);
+	if (err < 0) {
+		/* No need to update quota information. */
+		ext4_warning(inode_bl->i_sb,
+			"couldn't mark inode #%lu dirty (err %d)",
+			inode_bl->i_ino, err);
+		goto revert;
+	}
+
+	/* Bootloader inode should not be counted into quota information. */
+	if (diff > 0)
+		dquot_free_space(inode, diff);
+	else
+		err = dquot_alloc_space(inode, -1 * diff);
+
+	if (err < 0) {
+revert:
+		/* Revert all changes: */
+		inode_bl->i_blocks = blocks;
+		inode_bl->i_bytes = bytes;
+		swap_inode_data(inode, inode_bl);
+		ext4_mark_inode_dirty(handle, inode);
+		ext4_mark_inode_dirty(handle, inode_bl);
 	}
+
+err_out1:
 	ext4_journal_stop(handle);
 	ext4_double_up_write_data_sem(inode, inode_bl);
 

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

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

From: yangerkun <[email protected]>

commit abdc644e8cbac2e9b19763680e5a7cf9bab2bee7 upstream.

The reason is that while swapping two inode, we swap the flags too. Some flags such as EXT4_JOURNAL_DATA_FL can really confuse the things since we're not resetting the address operations structure. The simplest way to keep things sane is to restrict the flags that can be swapped.

---
 fs/ext4/ext4.h  |    3 +++
 fs/ext4/ioctl.c |    6 +++++-
 2 files changed, 8 insertions(+), 1 deletion(-)

@@ -435,6 +435,9 @@ struct flex_groups {
 /* Flags that are appropriate for non-directories/regular files. */
 #define EXT4_OTHER_FLMASK (EXT4_NODUMP_FL | EXT4_NOATIME_FL)
 
+/* The only flags that should be swapped */
+#define EXT4_FL_SHOULD_SWAP (EXT4_HUGE_FILE_FL | EXT4_EXTENTS_FL)
+
 /* Mask out flags that are inappropriate for the given type of inode. */
 static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
 {

@@ -63,6 +63,7 @@ static void swap_inode_data(struct inode
 	loff_t isize;
 	struct ext4_inode_info *ei1;
 	struct ext4_inode_info *ei2;
+	unsigned long tmp;
 
 	ei1 = EXT4_I(inode1);
 	ei2 = EXT4_I(inode2);

@@ -72,7 +73,10 @@ static void swap_inode_data(struct inode
 	swap(inode1->i_mtime, inode2->i_mtime);
 
 	memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data));
-	swap(ei1->i_flags, ei2->i_flags);
+	tmp = ei1->i_flags & EXT4_FL_SHOULD_SWAP;
+	ei1->i_flags = (ei2->i_flags & EXT4_FL_SHOULD_SWAP) |
+		(ei1->i_flags & ~EXT4_FL_SHOULD_SWAP);
+	ei2->i_flags = tmp | (ei2->i_flags & ~EXT4_FL_SHOULD_SWAP);
 	swap(ei1->i_disksize, ei2->i_disksize);
 	ext4_es_remove_extent(inode1, 0, EXT_MAX_BLOCKS);
 	ext4_es_remove_extent(inode2, 0, EXT_MAX_BLOCKS);

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

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

From: Jan Kara <[email protected]>

commit f96c3ac8dfc24b4e38fc4c2eba5fea2107b929d1 upstream.

When computing maximum size of filesystem possible with given number of group descriptor blocks, we forget to include s_first_data_block into the number of blocks. Thus for filesystems with non-zero s_first_data_block it can happen that computed maximum filesystem size is actually lower than current filesystem size which confuses the code and eventually leads to a BUG_ON in ext4_alloc_group_tables() hitting on flex_gd->count == 0. The problem can be reproduced like:

truncate -s 100g /tmp/image
mkfs.ext4 -b 1024 -E resize=262144 /tmp/image 32768 mount -t ext4 -o loop /tmp/image /mnt resize2fs /dev/loop0 262145
resize2fs /dev/loop0 300000

Fix the problem by properly including s_first_data_block into the computed number of filesystem blocks.

---
 fs/ext4/resize.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

@@ -1960,7 +1960,8 @@ retry:
 				le16_to_cpu(es->s_reserved_gdt_blocks);
 			n_group = n_desc_blocks * EXT4_DESC_PER_BLOCK(sb);
 			n_blocks_count = (ext4_fsblk_t)n_group *
-				EXT4_BLOCKS_PER_GROUP(sb);
+				EXT4_BLOCKS_PER_GROUP(sb) +
+				le32_to_cpu(es->s_first_data_block);
 			n_group--; /* set to last group number */
 		}
 

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

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

From: Bjorn Helgaas <[email protected]>

commit 10ecc818ea7319b5d0d2b4e1aa6a77323e776f76 upstream.

RussianNeuroMancer reported that the Intel 7265 wifi on a Dell Venue 11 Pro 7140 table stopped working after wakeup from suspend and bisected the problem to 9ab105deb60f ("PCI/ASPM: Disable ASPM L1.2 Substate if we don't have LTR"). David Ward reported the same problem on a Dell Latitude 7350.

After af8bb9f89838 ("PCI/ACPI: Request LTR control from platform before using it"), we don't enable LTR unless the platform has granted LTR control to us. In addition, we don't notice if the platform had already enabled LTR itself.

After 9ab105deb60f ("PCI/ASPM: Disable ASPM L1.2 Substate if we don't have LTR"), we avoid using LTR if we don't think the path to the device has LTR enabled.

The combination means that if the platform itself enables LTR but declines to give the OS control over LTR, we unnecessarily avoided using ASPM L1.2.

---
 drivers/pci/probe.c |   36 +++++++++++++++++++++++-------------
 1 file changed, 23 insertions(+), 13 deletions(-)

@@ -2038,11 +2038,8 @@ static void pci_configure_ltr(struct pci
 {
 #ifdef CONFIG_PCIEASPM
 	struct pci_host_bridge *host = pci_find_host_bridge(dev->bus);
-	u32 cap;
 	struct pci_dev *bridge;
-
-	if (!host->native_ltr)
-		return;
+	u32 cap, ctl;
 
 	if (!pci_is_pcie(dev))
 		return;

@@ -2051,22 +2048,35 @@ static void pci_configure_ltr(struct pci
 	if (!(cap & PCI_EXP_DEVCAP2_LTR))
 		return;
 
-	/*
-	 * Software must not enable LTR in an Endpoint unless the Root
-	 * Complex and all intermediate Switches indicate support for LTR.
-	 * PCIe r3.1, sec 6.18.
-	 */
-	if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT)
-		dev->ltr_path = 1;
-	else {
+	pcie_capability_read_dword(dev, PCI_EXP_DEVCTL2, &ctl);
+	if (ctl & PCI_EXP_DEVCTL2_LTR_EN) {
+		if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) {
+			dev->ltr_path = 1;
+			return;
+		}
+
 		bridge = pci_upstream_bridge(dev);
 		if (bridge && bridge->ltr_path)
 			dev->ltr_path = 1;
+
+		return;
 	}
 
-	if (dev->ltr_path)
+	if (!host->native_ltr)
+		return;
+
+	/*
+	 * Software must not enable LTR in an Endpoint unless the Root
+	 * Complex and all intermediate Switches indicate support for LTR.
+	 * PCIe r4.0, sec 6.18.
+	 */
+	if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT ||
+	    ((bridge = pci_upstream_bridge(dev)) &&
+	      bridge->ltr_path)) {
 		pcie_capability_set_word(dev, PCI_EXP_DEVCTL2,
 					 PCI_EXP_DEVCTL2_LTR_EN);
+		dev->ltr_path = 1;
+	}
 #endif
 }
 

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

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

From: Dongdong Liu <[email protected]>

commit 9f08a5d896ce43380314c34ed3f264c8e6075b80 upstream.

Previously dpc_handler() called aer_get_device_error_info() without initializing info->severity, so aer_get_device_error_info() relied on uninitialized data.

Add dpc_get_aer_uncorrect_severity() to read the port's AER status, mask, and severity registers and set info->severity.

Also, clear the port's AER fatal error status bits.

---
 drivers/pci/pcie/dpc.c |   27 ++++++++++++++++++++++++++-
 1 file changed, 26 insertions(+), 1 deletion(-)

@@ -153,6 +153,28 @@ static void dpc_process_rp_pio_error(str
 	pci_write_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_STATUS, status);
 }
 
+static int dpc_get_aer_uncorrect_severity(struct pci_dev *dev,
+					  struct aer_err_info *info)
+{
+	int pos = dev->aer_cap;
+	u32 status, mask, sev;
+
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_MASK, &mask);
+	status &= ~mask;
+	if (!status)
+		return 0;
+
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &sev);
+	status &= sev;
+	if (status)
+		info->severity = AER_FATAL;
+	else
+		info->severity = AER_NONFATAL;
+
+	return 1;
+}
+
 static irqreturn_t dpc_handler(int irq, void *context)
 {
 	struct aer_err_info info;

@@ -180,9 +202,12 @@ static irqreturn_t dpc_handler(int irq,
 	/* show RP PIO error detail information */
 	if (dpc->rp_extensions && reason == 3 && ext_reason == 0)
 		dpc_process_rp_pio_error(dpc);
-	else if (reason == 0 && aer_get_device_error_info(pdev, &info)) {
+	else if (reason == 0 &&
+		 dpc_get_aer_uncorrect_severity(pdev, &info) &&
+		 aer_get_device_error_info(pdev, &info)) {
 		aer_print_error(pdev, &info);
 		pci_cleanup_aer_uncorrect_error_status(pdev);
+		pci_aer_clear_fatal_status(pdev);
 	}
 
 	/* We configure DPC so it only triggers on ERR_FATAL */

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

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

From: Lucas Stach <[email protected]>

commit 3afc8299f39a27b60e1519a28e18878ce878e7dd upstream.

Since 7c5925afbc58 (PCI: dwc: Move MSI IRQs allocation to IRQ domains hierarchical API) the MSI init claims one of the controller IRQs as a chained IRQ line for the MSI controller. On some designs, like the i.MX6, this line is shared with a PCIe legacy IRQ. When the line is claimed for the MSI domain, any device trying to use this legacy IRQs will fail to request this IRQ line.

As MSI and legacy IRQs are already mutually exclusive on the DWC core, as the core won't forward any legacy IRQs once any MSI has been enabled, users wishing to use legacy IRQs already need to explictly disable MSI support (usually via the pci=nomsi kernel commandline option). To avoid any issues with MSI conflicting with legacy IRQs, just skip all of the DWC MSI initalization, including the IRQ line claim, when MSI is disabled.

---
 drivers/pci/controller/dwc/pcie-designware-host.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -439,7 +439,7 @@ int dw_pcie_host_init(struct pcie_port *
 	if (ret)
 		pci->num_viewport = 2;
 
-	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+	if (IS_ENABLED(CONFIG_PCI_MSI) && pci_msi_enabled()) {
 		/*
 		 * If a specific SoC driver needs to change the
 		 * default number of vectors, it needs to implement

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

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

From: Michael J. Ruhl <[email protected]>

commit bc5add09764c123f58942a37c8335247e683d234 upstream.

When disabling and removing a receive context, it is possible for an asynchronous event (i.e IRQ) to occur. Because of this, there is a race between cleaning up the context, and the context being used by the asynchronous event.

cpu 0 (context cleanup)

    rc->ref_count-- (ref_count == 0)
    hfi1_rcd_free()
cpu 1  (IRQ (with rcd index))
	rcd_get_by_index()
	lock
	ref_count+++     <-- reference count race (WARNING)
	return rcd
	unlock

cpu 0
hfi1_free_ctxtdata() <-- incorrect free location lock
remove rcd from array
unlock
free rcd

This race will cause the following WARNING trace:

WARNING: CPU: 0 PID: 175027 at include/linux/kref.h:52 hfi1_rcd_get_by_index+0x84/0xa0 [hfi1]
CPU: 0 PID: 175027 Comm: IMB-MPI1 Kdump: loaded Tainted: G OE ------------ 3.10.0-957.el7.x86_64 #1
Hardware name: Intel Corporation S2600KP/S2600KP, BIOS SE5C610.86B.11.01.0076.C4.111920150602 11/19/2015
Call Trace:
  dump_stack+0x19/0x1b
  __warn+0xd8/0x100
  warn_slowpath_null+0x1d/0x20
  hfi1_rcd_get_by_index+0x84/0xa0 [hfi1]
  is_rcv_urgent_int+0x24/0x90 [hfi1]
  general_interrupt+0x1b6/0x210 [hfi1]
  __handle_irq_event_percpu+0x44/0x1c0
  handle_irq_event_percpu+0x32/0x80
  handle_irq_event+0x3c/0x60
  handle_edge_irq+0x7f/0x150
  handle_irq+0xe4/0x1a0
  do_IRQ+0x4d/0xf0
  common_interrupt+0x162/0x162

The race can also lead to a use after free which could be similar to:

general protection fault: 0000 1 SMP
CPU: 71 PID: 177147 Comm: IMB-MPI1 Kdump: loaded Tainted: G W OE ------------ 3.10.0-957.el7.x86_64 #1
Hardware name: Intel Corporation S2600KP/S2600KP, BIOS SE5C610.86B.11.01.0076.C4.111920150602 11/19/2015
task: ffff9962a8098000 ti: ffff99717a508000 task.ti: ffff99717a508000 __kmalloc+0x94/0x230
Call Trace:
  ? hfi1_user_sdma_process_request+0x9c8/0x1250 [hfi1]
  hfi1_user_sdma_process_request+0x9c8/0x1250 [hfi1]
  hfi1_aio_write+0xba/0x110 [hfi1]
  do_sync_readv_writev+0x7b/0xd0
  do_readv_writev+0xce/0x260
  ? handle_mm_fault+0x39d/0x9b0
  ? pick_next_task_fair+0x5f/0x1b0
  ? sched_clock_cpu+0x85/0xc0
  ? __schedule+0x13a/0x890
  vfs_writev+0x35/0x60
  SyS_writev+0x7f/0x110
  system_call_fastpath+0x22/0x27

Use the appropriate kref API to verify access.

Reorder context cleanup to ensure context removal before cleanup occurs correctly.

---
 drivers/infiniband/hw/hfi1/hfi.h  |    2 +-
 drivers/infiniband/hw/hfi1/init.c |   14 +++++++++-----
 2 files changed, 10 insertions(+), 6 deletions(-)

@@ -1425,7 +1425,7 @@ void hfi1_init_pportdata(struct pci_dev
 			 struct hfi1_devdata *dd, u8 hw_pidx, u8 port);
 void hfi1_free_ctxtdata(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd);
 int hfi1_rcd_put(struct hfi1_ctxtdata *rcd);
-void hfi1_rcd_get(struct hfi1_ctxtdata *rcd);
+int hfi1_rcd_get(struct hfi1_ctxtdata *rcd);
 struct hfi1_ctxtdata *hfi1_rcd_get_by_index_safe(struct hfi1_devdata *dd,
 						 u16 ctxt);
 struct hfi1_ctxtdata *hfi1_rcd_get_by_index(struct hfi1_devdata *dd, u16 ctxt);

@@ -213,12 +213,12 @@ static void hfi1_rcd_free(struct kref *k
 	struct hfi1_ctxtdata *rcd =
 		container_of(kref, struct hfi1_ctxtdata, kref);
 
-	hfi1_free_ctxtdata(rcd->dd, rcd);
-
 	spin_lock_irqsave(&rcd->dd->uctxt_lock, flags);
 	rcd->dd->rcd[rcd->ctxt] = NULL;
 	spin_unlock_irqrestore(&rcd->dd->uctxt_lock, flags);
 
+	hfi1_free_ctxtdata(rcd->dd, rcd);
+
 	kfree(rcd);
 }
 

@@ -241,10 +241,13 @@ int hfi1_rcd_put(struct hfi1_ctxtdata *r
  * @rcd: pointer to an initialized rcd data structure
  *
  * Use this to get a reference after the init.
+ *
+ * Return : reflect kref_get_unless_zero(), which returns non-zero on
+ * increment, otherwise 0.
  */
-void hfi1_rcd_get(struct hfi1_ctxtdata *rcd)
+int hfi1_rcd_get(struct hfi1_ctxtdata *rcd)
 {
-	kref_get(&rcd->kref);
+	return kref_get_unless_zero(&rcd->kref);
 }
 
 /**

@@ -324,7 +327,8 @@ struct hfi1_ctxtdata *hfi1_rcd_get_by_in
 	spin_lock_irqsave(&dd->uctxt_lock, flags);
 	if (dd->rcd[ctxt]) {
 		rcd = dd->rcd[ctxt];
-		hfi1_rcd_get(rcd);
+		if (!hfi1_rcd_get(rcd))
+			rcd = NULL;
 	}
 	spin_unlock_irqrestore(&dd->uctxt_lock, flags);
 

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

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

From: Vaibhav Jain <[email protected]>

commit edeb304f659792fb5bab90d7d6f3408b4c7301fb upstream.

Within cxl module, iteration over array 'adapter->afu' may be racy at few points as it might be simultaneously read during an EEH and its contents being set to NULL while driver is being unloaded or unbound from the adapter. This might result in a NULL pointer to 'struct afu' being de-referenced during an EEH thereby causing a kernel oops.

This patch fixes this by making sure that all access to the array 'adapter->afu' is wrapped within the context of spin-lock 'adapter->afu_list_lock'.

---
 drivers/misc/cxl/guest.c |    2 ++
 drivers/misc/cxl/pci.c   |   39 ++++++++++++++++++++++++++++++---------
 2 files changed, 32 insertions(+), 9 deletions(-)

@@ -267,6 +267,7 @@ static int guest_reset(struct cxl *adapt
 	int i, rc;
 
 	pr_devel("Adapter reset request\n");
+	spin_lock(&adapter->afu_list_lock);
 	for (i = 0; i < adapter->slices; i++) {
 		if ((afu = adapter->afu[i])) {
 			pci_error_handlers(afu, CXL_ERROR_DETECTED_EVENT,

@@ -283,6 +284,7 @@ static int guest_reset(struct cxl *adapt
 			pci_error_handlers(afu, CXL_RESUME_EVENT, 0);
 		}
 	}
+	spin_unlock(&adapter->afu_list_lock);
 	return rc;
 }
 

@@ -1807,7 +1807,7 @@ static pci_ers_result_t cxl_vphb_error_d
 	/* There should only be one entry, but go through the list
 	 * anyway
 	 */
-	if (afu->phb == NULL)
+	if (afu == NULL || afu->phb == NULL)
 		return result;
 
 	list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {

@@ -1834,7 +1834,8 @@ static pci_ers_result_t cxl_pci_error_de
 {
 	struct cxl *adapter = pci_get_drvdata(pdev);
 	struct cxl_afu *afu;
-	pci_ers_result_t result = PCI_ERS_RESULT_NEED_RESET, afu_result;
+	pci_ers_result_t result = PCI_ERS_RESULT_NEED_RESET;
+	pci_ers_result_t afu_result = PCI_ERS_RESULT_NEED_RESET;
 	int i;
 
 	/* At this point, we could still have an interrupt pending.

@@ -1845,6 +1846,7 @@ static pci_ers_result_t cxl_pci_error_de
 
 	/* If we're permanently dead, give up. */
 	if (state == pci_channel_io_perm_failure) {
+		spin_lock(&adapter->afu_list_lock);
 		for (i = 0; i < adapter->slices; i++) {
 			afu = adapter->afu[i];
 			/*

@@ -1853,6 +1855,7 @@ static pci_ers_result_t cxl_pci_error_de
 			 */
 			cxl_vphb_error_detected(afu, state);
 		}
+		spin_unlock(&adapter->afu_list_lock);
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 

@@ -1934,11 +1937,17 @@ static pci_ers_result_t cxl_pci_error_de
 	 *     * In slot_reset, free the old resources and allocate new ones.
 	 *     * In resume, clear the flag to allow things to start.
 	 */
+
+	/* Make sure no one else changes the afu list */
+	spin_lock(&adapter->afu_list_lock);
+
 	for (i = 0; i < adapter->slices; i++) {
 		afu = adapter->afu[i];
 
-		afu_result = cxl_vphb_error_detected(afu, state);
+		if (afu == NULL)
+			continue;
 
+		afu_result = cxl_vphb_error_detected(afu, state);
 		cxl_context_detach_all(afu);
 		cxl_ops->afu_deactivate_mode(afu, afu->current_mode);
 		pci_deconfigure_afu(afu);

@@ -1950,6 +1959,7 @@ static pci_ers_result_t cxl_pci_error_de
 			 (result == PCI_ERS_RESULT_NEED_RESET))
 			result = PCI_ERS_RESULT_NONE;
 	}
+	spin_unlock(&adapter->afu_list_lock);
 
 	/* should take the context lock here */
 	if (cxl_adapter_context_lock(adapter) != 0)

@@ -1982,14 +1992,18 @@ static pci_ers_result_t cxl_pci_slot_res
 	 */
 	cxl_adapter_context_unlock(adapter);
 
+	spin_lock(&adapter->afu_list_lock);
 	for (i = 0; i < adapter->slices; i++) {
 		afu = adapter->afu[i];
 
+		if (afu == NULL)
+			continue;
+
 		if (pci_configure_afu(afu, adapter, pdev))
-			goto err;
+			goto err_unlock;
 
 		if (cxl_afu_select_best_mode(afu))
-			goto err;
+			goto err_unlock;
 
 		if (afu->phb == NULL)
 			continue;

@@ -2001,16 +2015,16 @@ static pci_ers_result_t cxl_pci_slot_res
 			ctx = cxl_get_context(afu_dev);
 
 			if (ctx && cxl_release_context(ctx))
-				goto err;
+				goto err_unlock;
 
 			ctx = cxl_dev_context_init(afu_dev);
 			if (IS_ERR(ctx))
-				goto err;
+				goto err_unlock;
 
 			afu_dev->dev.archdata.cxl_ctx = ctx;
 
 			if (cxl_ops->afu_check_and_enable(afu))
-				goto err;
+				goto err_unlock;
 
 			afu_dev->error_state = pci_channel_io_normal;
 

@@ -2031,8 +2045,13 @@ static pci_ers_result_t cxl_pci_slot_res
 				result = PCI_ERS_RESULT_DISCONNECT;
 		}
 	}
+
+	spin_unlock(&adapter->afu_list_lock);
 	return result;
 
+err_unlock:
+	spin_unlock(&adapter->afu_list_lock);
+
 err:
 	/* All the bits that happen in both error_detected and cxl_remove
 	 * should be idempotent, so we don't need to worry about leaving a mix

@@ -2053,10 +2072,11 @@ static void cxl_pci_resume(struct pci_de
 	 * This is not the place to be checking if everything came back up
 	 * properly, because there's no return value: do that in slot_reset.
 	 */
+	spin_lock(&adapter->afu_list_lock);
 	for (i = 0; i < adapter->slices; i++) {
 		afu = adapter->afu[i];
 
-		if (afu->phb == NULL)
+		if (afu == NULL || afu->phb == NULL)
 			continue;
 
 		list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {

@@ -2065,6 +2085,7 @@ static void cxl_pci_resume(struct pci_de
 				afu_dev->driver->err_handler->resume(afu_dev);
 		}
 	}
+	spin_unlock(&adapter->afu_list_lock);
 }
 
 static const struct pci_error_handlers cxl_err_handler = {

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

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

From: Jan Kara <[email protected]>

commit 1c2d14212b15a60300a2d4f6364753e87394c521 upstream.

When ext2 filesystem is created with 64k block size, ext2_max_size() will return value less than 0. Also, we cannot write any file in this fs since the sb->maxbytes is less than 0. The core of the problem is that the size of block index tree for such large block size is more than i_blocks can carry. So fix the computation to count with this possibility.

File size limits computed with the new function for the full range of possible block sizes look like:

bits file_size
10 17247252480
11 275415851008

12   2196873666560
13   2197948973056
14   2198486220800
15   2198754754560
16   2198888906752

---
 fs/ext2/super.c |   41 ++++++++++++++++++++++++++---------------
 1 file changed, 26 insertions(+), 15 deletions(-)

@@ -761,7 +761,8 @@ static loff_t ext2_max_size(int bits)
 {
 	loff_t res = EXT2_NDIR_BLOCKS;
 	int meta_blocks;
-	loff_t upper_limit;
+	unsigned int upper_limit;
+	unsigned int ppb = 1 << (bits-2);
 
 	/* This is calculated to be the largest file size for a
 	 * dense, file such that the total number of

@@ -775,24 +776,34 @@ static loff_t ext2_max_size(int bits)
 	/* total blocks in file system block size */
 	upper_limit >>= (bits - 9);
 
-
-	/* indirect blocks */
-	meta_blocks = 1;
-	/* double indirect blocks */
-	meta_blocks += 1 + (1LL << (bits-2));
-	/* tripple indirect blocks */
-	meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2)));
-
-	upper_limit -= meta_blocks;
-	upper_limit <<= bits;
-
+	/* Compute how many blocks we can address by block tree */
 	res += 1LL << (bits-2);
 	res += 1LL << (2*(bits-2));
 	res += 1LL << (3*(bits-2));
+	/* Does block tree limit file size? */
+	if (res < upper_limit)
+		goto check_lfs;
+
+	res = upper_limit;
+	/* How many metadata blocks are needed for addressing upper_limit? */
+	upper_limit -= EXT2_NDIR_BLOCKS;
+	/* indirect blocks */
+	meta_blocks = 1;
+	upper_limit -= ppb;
+	/* double indirect blocks */
+	if (upper_limit < ppb * ppb) {
+		meta_blocks += 1 + DIV_ROUND_UP(upper_limit, ppb);
+		res -= meta_blocks;
+		goto check_lfs;
+	}
+	meta_blocks += 1 + ppb;
+	upper_limit -= ppb * ppb;
+	/* tripple indirect blocks for the rest */
+	meta_blocks += 1 + DIV_ROUND_UP(upper_limit, ppb) +
+		DIV_ROUND_UP(upper_limit, ppb*ppb);
+	res -= meta_blocks;
+check_lfs:
 	res <<= bits;
-	if (res > upper_limit)
-		res = upper_limit;
-
 	if (res > MAX_LFS_FILESIZE)
 		res = MAX_LFS_FILESIZE;
 

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

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

From: Kunihiko Hayashi <[email protected]>

commit 521282237b9d78b9bff423ec818becd4c95841c2 upstream.

Need to set the update bit in UNIPHIER_CLK_CPUGEAR_UPD to update the CPU-gear value.

---
 drivers/clk/uniphier/clk-uniphier-cpugear.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -47,7 +47,7 @@ static int uniphier_clk_cpugear_set_pare
 		return ret;
 
 	ret = regmap_write_bits(gear->regmap,
-				gear->regbase + UNIPHIER_CLK_CPUGEAR_SET,
+				gear->regbase + UNIPHIER_CLK_CPUGEAR_UPD,
 				UNIPHIER_CLK_CPUGEAR_UPD_BIT,
 				UNIPHIER_CLK_CPUGEAR_UPD_BIT);
 	if (ret)

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

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

From: Tony Lindgren <[email protected]>

commit 5ae51d67aec95f6f9386aa8dd5db424964895575 upstream.

I noticed that modprobe clk-twl6040 can fail after a cold boot with:
abe_cm:clk:0010:0: failed to enable
...
Unhandled fault: imprecise external abort (0x1406) at 0xbe896b20

WARNING: CPU: 1 PID: 29 at drivers/clk/clk.c:828 clk_core_disable_lock+0x18/0x24

...
(clk_core_disable_lock) from [<c0123534>] (_disable_clocks+0x18/0x90) (_disable_clocks) from [<c0124040>] (_idle+0x17c/0x244) (_idle) from [<c0125ad4>] (omap_hwmod_idle+0x24/0x44) (omap_hwmod_idle) from [<c053a038>] (sysc_runtime_suspend+0x48/0x108) (sysc_runtime_suspend) from [<c06084c4>] (__rpm_callback+0x144/0x1d8) (__rpm_callback) from [<c0608578>] (rpm_callback+0x20/0x80) (rpm_callback) from [<c0607034>] (rpm_suspend+0x120/0x694) (rpm_suspend) from [<c0607a78>] (__pm_runtime_idle+0x60/0x84) (__pm_runtime_idle) from [<c053aaf0>] (sysc_probe+0x874/0xf2c) (sysc_probe) from [<c05fecd4>] (platform_drv_probe+0x48/0x98)

After searching around for a similar issue, I came across an earlier fix that never got merged upstream in the Android tree for glass-omap-xrr02. There is patch "MFD: twl6040-codec: Implement PDMCLK cold temp errata" by Misael Lopez Cruz <[email protected]>.

Based on my observations, this fix is also needed when cold booting devices, and not just for deeper idle modes. Since we now have a clock driver for pdmclk, let's fix the issue in twl6040_pdmclk_prepare().

---
 drivers/clk/clk-twl6040.c |   53 ++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 51 insertions(+), 2 deletions(-)

@@ -41,6 +41,43 @@ static int twl6040_pdmclk_is_prepared(st
 	return pdmclk->enabled;
 }
 
+static int twl6040_pdmclk_reset_one_clock(struct twl6040_pdmclk *pdmclk,
+					  unsigned int reg)
+{
+	const u8 reset_mask = TWL6040_HPLLRST;	/* Same for HPPLL and LPPLL */
+	int ret;
+
+	ret = twl6040_set_bits(pdmclk->twl6040, reg, reset_mask);
+	if (ret < 0)
+		return ret;
+
+	ret = twl6040_clear_bits(pdmclk->twl6040, reg, reset_mask);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+/*
+ * TWL6040A2 Phoenix Audio IC erratum #6: "PDM Clock Generation Issue At
+ * Cold Temperature". This affects cold boot and deeper idle states it
+ * seems. The workaround consists of resetting HPPLL and LPPLL.
+ */
+static int twl6040_pdmclk_quirk_reset_clocks(struct twl6040_pdmclk *pdmclk)
+{
+	int ret;
+
+	ret = twl6040_pdmclk_reset_one_clock(pdmclk, TWL6040_REG_HPPLLCTL);
+	if (ret)
+		return ret;
+
+	ret = twl6040_pdmclk_reset_one_clock(pdmclk, TWL6040_REG_LPPLLCTL);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
 static int twl6040_pdmclk_prepare(struct clk_hw *hw)
 {
 	struct twl6040_pdmclk *pdmclk = container_of(hw, struct twl6040_pdmclk,

@@ -48,8 +85,20 @@ static int twl6040_pdmclk_prepare(struct
 	int ret;
 
 	ret = twl6040_power(pdmclk->twl6040, 1);
-	if (!ret)
-		pdmclk->enabled = 1;
+	if (ret)
+		return ret;
+
+	ret = twl6040_pdmclk_quirk_reset_clocks(pdmclk);
+	if (ret)
+		goto out_err;
+
+	pdmclk->enabled = 1;
+
+	return 0;
+
+out_err:
+	dev_err(pdmclk->dev, "%s: error %i\n", __func__, ret);
+	twl6040_power(pdmclk->twl6040, 0);
 
 	return ret;
 }

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

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

From: Krzysztof Kozlowski <[email protected]>

commit 5f0b6216ea381b43c0dff88702d6cc5673d63922 upstream.

During initialization of subdevices if platform_device_alloc() failed, returned NULL pointer will be later dereferenced. Add proper error paths to exynos5_clk_register_subcmu(). The return value of this function is still ignored because at this stage of init there is nothing we can do.

---
 drivers/clk/samsung/clk-exynos5-subcmu.c |   10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

@@ -136,15 +136,21 @@ static int __init exynos5_clk_register_s
 {
 	struct of_phandle_args genpdspec = { .np = pd_node };
 	struct platform_device *pdev;
+	int ret;
 
 	pdev = platform_device_alloc(info->pd_name, -1);
+	if (!pdev)
+		return -ENOMEM;
+
 	pdev->dev.parent = parent;
 	pdev->driver_override = "exynos5-subcmu";
 	platform_set_drvdata(pdev, (void *)info);
 	of_genpd_add_device(&genpdspec, &pdev->dev);
-	platform_device_add(pdev);
+	ret = platform_device_add(pdev);
+	if (ret)
+		platform_device_put(pdev);
 
-	return 0;
+	return ret;
 }
 
 static int __init exynos5_clk_probe(struct platform_device *pdev)

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

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

From: Krzysztof Kozlowski <[email protected]>

commit 785c9f411eb2d9a6076d3511c631587d5e676bf3 upstream.

Platform driver driver_override field should not be initialized from const memory because the core later kfree() it. If driver_override is manually set later through sysfs, kfree() of old value leads to:

    $ echo "new_value" > /sys/bus/platform/drivers/.../driver_override

    kernel BUG at ../mm/slub.c:3960!
    Internal error: Oops - BUG: 0 [#1] PREEMPT SMP ARM
    ...
    (kfree) from [<c058e8c0>] (platform_set_driver_override+0x84/0xac)
    (platform_set_driver_override) from [<c058e908>] (driver_override_store+0x20/0x34)
    (driver_override_store) from [<c031f778>] (kernfs_fop_write+0x100/0x1dc)
    (kernfs_fop_write) from [<c0296de8>] (__vfs_write+0x2c/0x17c)
    (__vfs_write) from [<c02970c4>] (vfs_write+0xa4/0x188)
    (vfs_write) from [<c02972e8>] (ksys_write+0x4c/0xac)
    (ksys_write) from [<c0101000>] (ret_fast_syscall+0x0/0x28)

The clk-exynos5-subcmu driver uses override only for the purpose of creating meaningful names for children devices (matching names of power domains, e.g. DISP, MFC). The driver_override was not developed for this purpose so just switch to default names of devices to fix the issue.

---
 drivers/clk/samsung/clk-exynos5-subcmu.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -138,12 +138,11 @@ static int __init exynos5_clk_register_s
 	struct platform_device *pdev;
 	int ret;
 
-	pdev = platform_device_alloc(info->pd_name, -1);
+	pdev = platform_device_alloc("exynos5-subcmu", PLATFORM_DEVID_AUTO);
 	if (!pdev)
 		return -ENOMEM;
 
 	pdev->dev.parent = parent;
-	pdev->driver_override = "exynos5-subcmu";
 	platform_set_drvdata(pdev, (void *)info);
 	of_genpd_add_device(&genpdspec, &pdev->dev);
 	ret = platform_device_add(pdev);

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

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

From: Paul Cercueil <[email protected]>

commit bc5d922c93491878c44c9216e9d227c7eeb81d7f upstream.

Take a parent rate of 180 MHz, and a requested rate of 4.285715 MHz. This results in a theorical divider of 41.999993 which is then rounded up to 42. The .round_rate function would then return (180 MHz / 42) as the clock, rounded down, so 4.285714 MHz.

Calling clk_set_rate on 4.285714 MHz would round the rate again, and give a theorical divider of 42,0000028, now rounded up to 43, and the rate returned would be (180 MHz / 43) which is 4.186046 MHz, aka. not what we requested.

Fix this by rounding up the divisions.

---
 drivers/clk/ingenic/cgu.c |   10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

@@ -426,16 +426,16 @@ ingenic_clk_round_rate(struct clk_hw *hw
 	struct ingenic_clk *ingenic_clk = to_ingenic_clk(hw);
 	struct ingenic_cgu *cgu = ingenic_clk->cgu;
 	const struct ingenic_cgu_clk_info *clk_info;
-	long rate = *parent_rate;
+	unsigned int div = 1;
 
 	clk_info = &cgu->clock_info[ingenic_clk->idx];
 
 	if (clk_info->type & CGU_CLK_DIV)
-		rate /= ingenic_clk_calc_div(clk_info, *parent_rate, req_rate);
+		div = ingenic_clk_calc_div(clk_info, *parent_rate, req_rate);
 	else if (clk_info->type & CGU_CLK_FIXDIV)
-		rate /= clk_info->fixdiv.div;
+		div = clk_info->fixdiv.div;
 
-	return rate;
+	return DIV_ROUND_UP(*parent_rate, div);
 }
 
 static int

@@ -455,7 +455,7 @@ ingenic_clk_set_rate(struct clk_hw *hw,
 
 	if (clk_info->type & CGU_CLK_DIV) {
 		div = ingenic_clk_calc_div(clk_info, parent_rate, req_rate);
-		rate = parent_rate / div;
+		rate = DIV_ROUND_UP(parent_rate, div);
 
 		if (rate != req_rate)
 			return -EINVAL;

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

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

From: Paul Cercueil <[email protected]>

commit 7ca4c922aad2e3c46767a12f80d01c6b25337b59 upstream.

The 'div' field does not represent a number of bits used to divide (understand: right-shift) the divider, but a number itself used to divide the divider.

---
 drivers/clk/ingenic/cgu.h |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -80,7 +80,7 @@ struct ingenic_cgu_mux_info {
  * @reg: offset of the divider control register within the CGU
  * @shift: number of bits to left shift the divide value by (ie. the index of
  *         the lowest bit of the divide value within its control register)
- * @div: number of bits to divide the divider value by (i.e. if the
+ * @div: number to divide the divider value by (i.e. if the
  *	 effective divider value is the value written to the register
  *	 multiplied by some constant)
  * @bits: the size of the divide value in bits

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

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

From: Dmitry Osipenko <[email protected]>

commit 563b9372f7ec57e44e8f9a8600c5107d7ffdd166 upstream.

The ChipIdea's platform device need to be unregistered on Tegra's driver module removal.

---
 drivers/usb/chipidea/ci_hdrc_tegra.c |    1 +
 1 file changed, 1 insertion(+)

@@ -130,6 +130,7 @@ static int tegra_udc_remove(struct platf
 {
 	struct tegra_udc *udc = platform_get_drvdata(pdev);
 
+	ci_hdrc_remove_device(udc->dev);
 	usb_phy_set_suspend(udc->phy, 1);
 	clk_disable_unprepare(udc->clk);
 

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

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

From: Nikolaus Voss <[email protected]>

commit 8a863a608d47fa5d9dd15cf841817f73f804cf91 upstream.

Commit 1a2f474d328f handles block _reads_ separately with plain-I2C adapters, but the problem described with regmap-i2c not handling SMBus block transfers (i.e. read and writes) correctly also exists with writes.

As workaround, this patch adds a block write function the same way 1a2f474d328f adds a block read function.

---
 drivers/usb/typec/tps6598x.c |   26 ++++++++++++++++++++------
 1 file changed, 20 insertions(+), 6 deletions(-)

@@ -110,6 +110,20 @@ tps6598x_block_read(struct tps6598x *tps
 	return 0;
 }
 
+static int tps6598x_block_write(struct tps6598x *tps, u8 reg,
+				void *val, size_t len)
+{
+	u8 data[TPS_MAX_LEN + 1];
+
+	if (!tps->i2c_protocol)
+		return regmap_raw_write(tps->regmap, reg, val, len);
+
+	data[0] = len;
+	memcpy(&data[1], val, len);
+
+	return regmap_raw_write(tps->regmap, reg, data, sizeof(data));
+}
+
 static inline int tps6598x_read16(struct tps6598x *tps, u8 reg, u16 *val)
 {
 	return tps6598x_block_read(tps, reg, val, sizeof(u16));

@@ -127,23 +141,23 @@ static inline int tps6598x_read64(struct
 
 static inline int tps6598x_write16(struct tps6598x *tps, u8 reg, u16 val)
 {
-	return regmap_raw_write(tps->regmap, reg, &val, sizeof(u16));
+	return tps6598x_block_write(tps, reg, &val, sizeof(u16));
 }
 
 static inline int tps6598x_write32(struct tps6598x *tps, u8 reg, u32 val)
 {
-	return regmap_raw_write(tps->regmap, reg, &val, sizeof(u32));
+	return tps6598x_block_write(tps, reg, &val, sizeof(u32));
 }
 
 static inline int tps6598x_write64(struct tps6598x *tps, u8 reg, u64 val)
 {
-	return regmap_raw_write(tps->regmap, reg, &val, sizeof(u64));
+	return tps6598x_block_write(tps, reg, &val, sizeof(u64));
 }
 
 static inline int
 tps6598x_write_4cc(struct tps6598x *tps, u8 reg, const char *val)
 {
-	return regmap_raw_write(tps->regmap, reg, &val, sizeof(u32));
+	return tps6598x_block_write(tps, reg, &val, sizeof(u32));
 }
 
 static int tps6598x_read_partner_identity(struct tps6598x *tps)

@@ -229,8 +243,8 @@ static int tps6598x_exec_cmd(struct tps6
 		return -EBUSY;
 
 	if (in_len) {
-		ret = regmap_raw_write(tps->regmap, TPS_REG_DATA1,
-				       in_data, in_len);
+		ret = tps6598x_block_write(tps, TPS_REG_DATA1,
+					   in_data, in_len);
 		if (ret)
 			return ret;
 	}

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

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

From: Phuong Nguyen <[email protected]>

commit d9140a0da4a230a03426d175145989667758aa6a upstream.

This commit fixes the issue that USB-DMAC hangs silently after system resumes on R-Car Gen3 hence renesas_usbhs will not work correctly when using USB-DMAC for bulk transfer e.g. ethernet or serial gadgets.

The issue can be reproduced by these steps:
1. modprobe g_serial
2. Suspend and resume system.
3. connect a usb cable to host side
4. Transfer data from Host to Target
5. cat /dev/ttyGS0 (Target side)
6. echo "test" > /dev/ttyACM0 (Host side)

The 'cat' will not result anything. However, system still can work normally.

Currently, USB-DMAC driver does not have system sleep callbacks hence this driver relies on the PM core to force runtime suspend/resume to suspend and reinitialize USB-DMAC during system resume. After the commit 17218e0092f8 ("PM / genpd: Stop/start devices without pm_runtime_force_suspend/resume()"), PM core will not force runtime suspend/resume anymore so this issue happens.

To solve this, make system suspend resume explicit by using pm_runtime_force_{suspend,resume}() as the system sleep callbacks. SET_NOIRQ_SYSTEM_SLEEP_PM_OPS() is used to make sure USB-DMAC suspended after and initialized before renesas_usbhs."

---
 drivers/dma/sh/usb-dmac.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -697,6 +697,8 @@ static int usb_dmac_runtime_resume(struc
 #endif /* CONFIG_PM */
 
 static const struct dev_pm_ops usb_dmac_pm = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				      pm_runtime_force_resume)
 	SET_RUNTIME_PM_OPS(usb_dmac_runtime_suspend, usb_dmac_runtime_resume,
 			   NULL)
 };

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

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

From: zhongjiang <[email protected]>

commit 46612b751c4941c5c0472ddf04027e877ae5990f upstream.

When soft_offline_in_use_page() runs on a thp tail page after pmd is split, we trigger the following VM_BUG_ON_PAGE():

Memory failure: 0x3755ff: non anonymous thp
__get_any_page: 0x3755ff: unknown zero refcount page type 2fffff80000000 Soft offlining pfn 0x34d805 at process virtual address 0x20fff000 page:ffffea000d360140 count:0 mapcount:0 mapping:0000000000000000 index:0x1
flags: 0x2fffff80000000()

  raw: 002fffff80000000 ffffea000d360108 ffffea000d360188 0000000000000000
  raw: 0000000000000001 0000000000000000 00000000ffffffff 0000000000000000
  page dumped because: VM_BUG_ON_PAGE(page_ref_count(page) == 0)
  ------------[ cut here ]------------
  kernel BUG at ./include/linux/mm.h:519!

soft_offline_in_use_page() passed refcount and page lock from tail page to head page, which is not needed because we can pass any subpage to split_huge_page().

Naoya had fixed a similar issue in c3901e722b29 ("mm: hwpoison: fix thp split handling in memory_failure()"). But he missed fixing soft offline.

---
 mm/memory-failure.c |   14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

@@ -1823,19 +1823,17 @@ static int soft_offline_in_use_page(stru
 	struct page *hpage = compound_head(page);
 
 	if (!PageHuge(page) && PageTransHuge(hpage)) {
-		lock_page(hpage);
-		if (!PageAnon(hpage) || unlikely(split_huge_page(hpage))) {
-			unlock_page(hpage);
-			if (!PageAnon(hpage))
+		lock_page(page);
+		if (!PageAnon(page) || unlikely(split_huge_page(page))) {
+			unlock_page(page);
+			if (!PageAnon(page))
 				pr_info("soft offline: %#lx: non anonymous thp\n", page_to_pfn(page));
 			else
 				pr_info("soft offline: %#lx: thp split failed\n", page_to_pfn(page));
-			put_hwpoison_page(hpage);
+			put_hwpoison_page(page);
 			return -EBUSY;
 		}
-		unlock_page(hpage);
-		get_hwpoison_page(page);
-		put_hwpoison_page(hpage);
+		unlock_page(page);
 	}
 
 	/*

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

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

From: Roman Penyaev <[email protected]>

commit 401592d2e095947344e10ec0623adbcd58934dd4 upstream.

When VM_NO_GUARD is not set area->size includes adjacent guard page, thus for correct size checking get_vm_area_size() should be used, but not area->size.

This fixes possible kernel oops when userspace tries to mmap an area on 1 page bigger than was allocated by vmalloc_user() call: the size check inside remap_vmalloc_range_partial() accounts non-existing guard page also, so check successfully passes but vmalloc_to_page() returns NULL (guard page does not physically exist).

The following code pattern example should trigger an oops:

  static int oops_mmap(struct file *file, struct vm_area_struct *vma)
  {
        void *mem;

        mem = vmalloc_user(4096);
        BUG_ON(!mem);
        /* Do not care about mem leak */

        return remap_vmalloc_range(vma, mem, 0);

}

And userspace simply mmaps size + PAGE_SIZE:

  mmap(NULL, 8192, PROT_WRITE|PROT_READ, MAP_PRIVATE, fd, 0);

Possible candidates for oops which do not have any explicit size checks:

   *** drivers/media/usb/stkwebcam/stk-webcam.c:
   v4l_stk_mmap[789]   ret = remap_vmalloc_range(vma, sbuf->buffer, 0);

Or the following one:

   *** drivers/video/fbdev/core/fbmem.c
   static int
   fb_mmap(struct file *file, struct vm_area_struct * vma)
        ...
        res = fb->fb_mmap(info, vma);

Where fb_mmap callback calls remap_vmalloc_range() directly without any explicit checks:

   *** drivers/video/fbdev/vfb.c
   static int vfb_mmap(struct fb_info *info,
             struct vm_area_struct *vma)
   {
       return remap_vmalloc_range(vma, (void *)info->fix.smem_start, vma->vm_pgoff);
   }

---
 mm/vmalloc.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -2244,7 +2244,7 @@ int remap_vmalloc_range_partial(struct v
 	if (!(area->flags & VM_USERMAP))
 		return -EINVAL;
 
-	if (kaddr + size > area->addr + area->size)
+	if (kaddr + size > area->addr + get_vm_area_size(area))
 		return -EINVAL;
 
 	do {

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

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

From: Jan Stancek <[email protected]>

commit fc8efd2ddfed3f343c11b693e87140ff358d7ff5 upstream.

LTP testcase mtest06 [1] can trigger a crash on s390x running 5.0.0-rc8. This is a stress test, where one thread mmaps/writes/munmaps memory area and other thread is trying to read from it:

  CPU: 0 PID: 2611 Comm: mmap1 Not tainted 5.0.0-rc8+ #51
  Hardware name: IBM 2964 N63 400 (z/VM 6.4.0)
  Krnl PSW : 0404e00180000000 00000000001ac8d8 (__lock_acquire+0x7/0x7a8)
  Call Trace:
  ([<0000000000000000>]           (null))
   [<00000000001adae4>] lock_acquire+0xec/0x258
   [<000000000080d1ac>] _raw_spin_lock_bh+0x5c/0x98
   [<000000000012a780>] page_table_free+0x48/0x1a8
   [<00000000002f6e54>] do_fault+0xdc/0x670
   [<00000000002fadae>] __handle_mm_fault+0x416/0x5f0
   [<00000000002fb138>] handle_mm_fault+0x1b0/0x320
   [<00000000001248cc>] do_dat_exception+0x19c/0x2c8
   [<000000000080e5ee>] pgm_check_handler+0x19e/0x200

page_table_free() is called with NULL mm parameter, but because "0" is a valid address on s390 (see S390_lowcore), it keeps going until it eventually crashes in lockdep's lock_acquire. This crash is reproducible at least since 4.14.

Problem is that "vmf->vma" used in do_fault() can become stale. Because mmap_sem may be released, other threads can come in, call munmap() and cause "vma" be returned to kmem cache, and get zeroed/re-initialized and re-used:

handle_mm_fault                           |
  __handle_mm_fault                       |
    do_fault                              |
      vma = vmf->vma                      |
      do_read_fault                       |
        __do_fault                        |
          vma->vm_ops->fault(vmf);        |
            mmap_sem is released          |
                                          |
                                          | do_munmap()
                                          |   remove_vma_list()
                                          |     remove_vma()
                                          |       vm_area_free()
                                          |         # vma is released
                                          | ...
                                          | # same vma is allocated
                                          | # from kmem cache
                                          | do_mmap()
                                          |   vm_area_alloc()
                                          |     memset(vma, 0, ...)
                                          |
      pte_free(vma->vm_mm, ...);          |
        page_table_free                   |
          spin_lock_bh(&mm->context.lock);|
            <crash>                       |

Cache mm_struct to avoid using potentially stale "vma".

[1] https://github.com/linux-test-project/ltp/blob/master/testcases/kernel/mem/mtest06/mmap1.c

---
 mm/memory.c |    5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

@@ -3762,10 +3762,13 @@ static vm_fault_t do_shared_fault(struct
  * but allow concurrent faults).
  * The mmap_sem may have been released depending on flags and our
  * return value.  See filemap_fault() and __lock_page_or_retry().
+ * If mmap_sem is released, vma may become invalid (for example
+ * by other thread calling munmap()).
  */
 static vm_fault_t do_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
+	struct mm_struct *vm_mm = vma->vm_mm;
 	vm_fault_t ret;
 
 	/*