4.9.138-stable review

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

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

From: Sam Bobroff <[email protected]>

[ Upstream commit f9bc28aedfb5bbd572d2d365f3095c1becd7209b ]

If an error occurs during an unplug operation, it's possible for eeh_dump_dev_log() to be called when edev->pdn is null, which currently leads to dereferencing a null pointer.

Handle this by skipping the error log for those devices.

---
 arch/powerpc/kernel/eeh.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -169,6 +169,11 @@ static size_t eeh_dump_dev_log(struct ee
 	int n = 0, l = 0;
 	char buffer[128];
 
+	if (!pdn) {
+		pr_warn("EEH: Note: No error log for absent device.\n");
+		return 0;
+	}
+
 	n += scnprintf(buf+n, len-n, "%04x:%02x:%02x.%01x\n",
 		       edev->phb->global_number, pdn->busno,
 		       PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));

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

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

From: Miles Chen <[email protected]>

[ Upstream commit 33a1a7be198657c8ca26ad406c4d2a89b7162bcc ]

The issue is found by a fuzzing test.
If tty_find_polling_driver() recevies an incorrect input such as ',,' or '0b', the len becomes 0 and strncmp() always return 0. In this case, a null p->ops->poll_init() is called and it causes a kernel panic.

Fix this by checking name length against zero in tty_find_polling_driver().

$echo ,, > /sys/module/kgdboc/parameters/kgdboc

[   20.804451] WARNING: CPU: 1 PID: 104 at drivers/tty/serial/serial_core.c:457
uart_get_baud_rate+0xe8/0x190
[   20.804917] Modules linked in:
[   20.805317] CPU: 1 PID: 104 Comm: sh Not tainted 4.19.0-rc7ajb #8
[   20.805469] Hardware name: linux,dummy-virt (DT)
[   20.805732] pstate: 20000005 (nzCv daif -PAN -UAO)
[   20.805895] pc : uart_get_baud_rate+0xe8/0x190
[   20.806042] lr : uart_get_baud_rate+0xc0/0x190
[   20.806476] sp : ffffffc06acff940
[   20.806676] x29: ffffffc06acff940 x28: 0000000000002580
[   20.806977] x27: 0000000000009600 x26: 0000000000009600
[   20.807231] x25: ffffffc06acffad0 x24: 00000000ffffeff0
[   20.807576] x23: 0000000000000001 x22: 0000000000000000
[   20.807807] x21: 0000000000000001 x20: 0000000000000000
[   20.808049] x19: ffffffc06acffac8 x18: 0000000000000000
[   20.808277] x17: 0000000000000000 x16: 0000000000000000
[   20.808520] x15: ffffffffffffffff x14: ffffffff00000000
[   20.808757] x13: ffffffffffffffff x12: 0000000000000001
[   20.809011] x11: 0101010101010101 x10: ffffff880d59ff5f
[   20.809292] x9 : ffffff880d59ff5e x8 : ffffffc06acffaf3
[   20.809549] x7 : 0000000000000000 x6 : ffffff880d59ff5f
[   20.809803] x5 : 0000000080008001 x4 : 0000000000000003
[   20.810056] x3 : ffffff900853e6b4 x2 : dfffff9000000000
[   20.810693] x1 : ffffffc06acffad0 x0 : 0000000000000cb0
[   20.811005] Call trace:
[   20.811214]  uart_get_baud_rate+0xe8/0x190
[   20.811479]  serial8250_do_set_termios+0xe0/0x6f4
[   20.811719]  serial8250_set_termios+0x48/0x54
[   20.811928]  uart_set_options+0x138/0x1bc
[   20.812129]  uart_poll_init+0x114/0x16c
[   20.812330]  tty_find_polling_driver+0x158/0x200
[   20.812545]  configure_kgdboc+0xbc/0x1bc
[   20.812745]  param_set_kgdboc_var+0xb8/0x150
[   20.812960]  param_attr_store+0xbc/0x150
[   20.813160]  module_attr_store+0x40/0x58
[   20.813364]  sysfs_kf_write+0x8c/0xa8
[   20.813563]  kernfs_fop_write+0x154/0x290
[   20.813764]  vfs_write+0xf0/0x278
[   20.813951]  __arm64_sys_write+0x84/0xf4
[   20.814400]  el0_svc_common+0xf4/0x1dc
[   20.814616]  el0_svc_handler+0x98/0xbc
[   20.814804]  el0_svc+0x8/0xc
[   20.822005] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000
[   20.826913] Mem abort info:
[   20.827103]   ESR = 0x84000006
[   20.827352]   Exception class = IABT (current EL), IL = 16 bits
[   20.827655]   SET = 0, FnV = 0
[   20.827855]   EA = 0, S1PTW = 0
[   20.828135] user pgtable: 4k pages, 39-bit VAs, pgdp = (____ptrval____)
[   20.828484] [0000000000000000] pgd=00000000aadee003, pud=00000000aadee003, pmd=0000000000000000
[   20.829195] Internal error: Oops: 84000006 [#1] SMP
[   20.829564] Modules linked in:
[   20.829890] CPU: 1 PID: 104 Comm: sh Tainted: G        W         4.19.0-rc7ajb #8
[   20.830545] Hardware name: linux,dummy-virt (DT)
[   20.830829] pstate: 60000085 (nZCv daIf -PAN -UAO)
[   20.831174] pc :           (null)
[   20.831457] lr : serial8250_do_set_termios+0x358/0x6f4
[   20.831727] sp : ffffffc06acff9b0
[   20.831936] x29: ffffffc06acff9b0 x28: ffffff9008d7c000
[   20.832267] x27: ffffff900969e16f x26: 0000000000000000
[   20.832589] x25: ffffff900969dfb0 x24: 0000000000000000
[   20.832906] x23: ffffffc06acffad0 x22: ffffff900969e160
[   20.833232] x21: 0000000000000000 x20: ffffffc06acffac8
[   20.833559] x19: ffffff900969df90 x18: 0000000000000000
[   20.833878] x17: 0000000000000000 x16: 0000000000000000
[   20.834491] x15: ffffffffffffffff x14: ffffffff00000000
[   20.834821] x13: ffffffffffffffff x12: 0000000000000001
[   20.835143] x11: 0101010101010101 x10: ffffff880d59ff5f
[   20.835467] x9 : ffffff880d59ff5e x8 : ffffffc06acffaf3
[   20.835790] x7 : 0000000000000000 x6 : ffffff880d59ff5f
[   20.836111] x5 : c06419717c314100 x4 : 0000000000000007
[   20.836419] x3 : 0000000000000000 x2 : 0000000000000000
[   20.836732] x1 : 0000000000000001 x0 : ffffff900969df90
[   20.837100] Process sh (pid: 104, stack limit = 0x(____ptrval____))
[   20.837396] Call trace:
[   20.837566]            (null)
[   20.837816]  serial8250_set_termios+0x48/0x54
[   20.838089]  uart_set_options+0x138/0x1bc
[   20.838570]  uart_poll_init+0x114/0x16c
[   20.838834]  tty_find_polling_driver+0x158/0x200
[   20.839119]  configure_kgdboc+0xbc/0x1bc
[   20.839380]  param_set_kgdboc_var+0xb8/0x150
[   20.839658]  param_attr_store+0xbc/0x150
[   20.839920]  module_attr_store+0x40/0x58
[   20.840183]  sysfs_kf_write+0x8c/0xa8
[   20.840183]  sysfs_kf_write+0x8c/0xa8
[   20.840440]  kernfs_fop_write+0x154/0x290
[   20.840702]  vfs_write+0xf0/0x278
[   20.840942]  __arm64_sys_write+0x84/0xf4
[   20.841209]  el0_svc_common+0xf4/0x1dc
[   20.841471]  el0_svc_handler+0x98/0xbc
[   20.841713]  el0_svc+0x8/0xc
[   20.842057] Code: bad PC value
[   20.842764] ---[ end trace a8835d7de79aaadf ]---
[   20.843134] Kernel panic - not syncing: Fatal exception
[   20.843515] SMP: stopping secondary CPUs
[   20.844289] Kernel Offset: disabled
[   20.844634] CPU features: 0x0,21806002
[   20.844857] Memory Limit: none
[   20.845172] ---[ end Kernel panic - not syncing: Fatal exception ]---

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

@@ -354,7 +354,7 @@ struct tty_driver *tty_find_polling_driv
 	mutex_lock(&tty_mutex);
 	/* Search through the tty devices to look for a match */
 	list_for_each_entry(p, &tty_drivers, tty_drivers) {
-		if (strncmp(name, p->name, len) != 0)
+		if (!len || strncmp(name, p->name, len) != 0)
 			continue;
 		stp = str;
 		if (*stp == ',')

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

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

From: Fabio Estevam <[email protected]>

[ Upstream commit 35d3cbe84544da74e39e1cec01374092467e3119 ]

Andreas Müller reports:

"Fixes:

| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[220]: Failed to apply ACL on /dev/v4l-subdev0: Operation not supported
| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[224]: Failed to apply ACL on /dev/v4l-subdev1: Operation not supported
| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[215]: Failed to apply ACL on /dev/v4l-subdev10: Operation not supported
| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[228]: Failed to apply ACL on /dev/v4l-subdev2: Operation not supported
| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[232]: Failed to apply ACL on /dev/v4l-subdev5: Operation not supported
| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[217]: Failed to apply ACL on /dev/v4l-subdev11: Operation not supported
| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[214]: Failed to apply ACL on /dev/dri/card1: Operation not supported
| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[216]: Failed to apply ACL on /dev/v4l-subdev8: Operation not supported
| Sep 04 09:05:10 imx6qdl-variscite-som systemd-udevd[226]: Failed to apply ACL on /dev/v4l-subdev9: Operation not supported

and nasty follow-ups: Starting weston from sddm as unpriviledged user fails with some hints on missing access rights."

Select the CONFIG_TMPFS_POSIX_ACL option to fix these issues.

---
 arch/arm/configs/imx_v6_v7_defconfig |    1 +
 1 file changed, 1 insertion(+)

@@ -361,6 +361,7 @@ CONFIG_ZISOFS=y
 CONFIG_UDF_FS=m
 CONFIG_MSDOS_FS=m
 CONFIG_VFAT_FS=y
+CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_JFFS2_FS=y
 CONFIG_UBIFS_FS=y
 CONFIG_NFS_FS=y

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

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

From: Daniel Axtens <[email protected]>

[ Upstream commit f5e284803a7206d43e26f9ffcae5de9626d95e37 ]

When enumerating page size definitions to check hardware support, we construct a constant which is (1U << (def->shift - 10)).

However, the array of page size definitions is only initalised for various MMU_PAGE_* constants, so it contains a number of 0-initialised elements with def->shift == 0. This means we end up shifting by a very large number, which gives the following UBSan splat:

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

UBSAN: Undefined behaviour in /home/dja/dev/linux/linux/arch/powerpc/mm/tlb_nohash.c:506:21
shift exponent 4294967286 is too large for 32-bit type 'unsigned int'
CPU: 0 PID: 0 Comm: swapper Not tainted 4.19.0-rc3-00045-ga604f927b012-dirty #6
Call Trace:
[c00000000101bc20] [c000000000a13d54] .dump_stack+0xa8/0xec (unreliable)
[c00000000101bcb0] [c0000000004f20a8] .ubsan_epilogue+0x18/0x64
[c00000000101bd30] [c0000000004f2b10] .__ubsan_handle_shift_out_of_bounds+0x110/0x1a4
[c00000000101be20] [c000000000d21760] .early_init_mmu+0x1b4/0x5a0
[c00000000101bf10] [c000000000d1ba28] .early_setup+0x100/0x130
[c00000000101bf90] [c000000000000528] start_here_multiplatform+0x68/0x80
================================================================================

Fix this by first checking if the element exists (shift != 0) before constructing the constant.

---
 arch/powerpc/mm/tlb_nohash.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -481,6 +481,9 @@ static void setup_page_sizes(void)
 		for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
 			struct mmu_psize_def *def = &mmu_psize_defs[psize];
 
+			if (!def->shift)
+				continue;
+
 			if (tlb1ps & (1U << (def->shift - 10))) {
 				def->flags |= MMU_PAGE_SIZE_DIRECT;
 

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

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

From: Tomi Valkeinen <[email protected]>

[ Upstream commit 538f66ba204944470a653a4cccc5f8befdf97c22 ]

A DMM timeout "timed out waiting for done" has been observed on DRA7 devices. The timeout happens rarely, and only when the system is under heavy load.

Debugging showed that the timeout can be made to happen much more frequently by optimizing the DMM driver, so that there's almost no code between writing the last DMM descriptors to RAM, and writing to DMM register which starts the DMM transaction.

The current theory is that a wmb() does not properly ensure that the data written to RAM is observable by all the components in the system.

This DMM timeout has caused interesting (and rare) bugs as the error handling was not functioning properly (the error handling has been fixed in previous commits):

* If a DMM timeout happened when a GEM buffer was being pinned for display on the screen, a timeout error would be shown, but the driver would continue programming DSS HW with broken buffer, leading to SYNCLOST floods and possible crashes.

* If a DMM timeout happened when other user (say, video decoder) was pinning a GEM buffer, a timeout would be shown but if the user handled the error properly, no other issues followed.

* If a DMM timeout happened when a GEM buffer was being released, the driver does not even notice the error, leading to crashes or hang later.

This patch adds wmb() and readl() calls after the last bit is written to RAM, which should ensure that the execution proceeds only after the data is actually in RAM, and thus observable by DMM.

The read-back should not be needed. Further study is required to understand if DMM is somehow special case and read-back is ok, or if DRA7's memory barriers do not work correctly.

---
 drivers/gpu/drm/omapdrm/omap_dmm_tiler.c |   11 +++++++++++
 1 file changed, 11 insertions(+)

@@ -273,6 +273,17 @@ static int dmm_txn_commit(struct dmm_txn
 	}
 
 	txn->last_pat->next_pa = 0;
+	/* ensure that the written descriptors are visible to DMM */
+	wmb();
+
+	/*
+	 * NOTE: the wmb() above should be enough, but there seems to be a bug
+	 * in OMAP's memory barrier implementation, which in some rare cases may
+	 * cause the writes not to be observable after wmb().
+	 */
+
+	/* read back to ensure the data is in RAM */
+	readl(&txn->last_pat->next_pa);
 
 	/* write to PAT_DESCR to clear out any pending transaction */
 	dmm_write(dmm, 0x0, reg[PAT_DESCR][engine->id]);

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

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

From: Nicholas Mc Guire <[email protected]>

[ Upstream commit c5d59528e24ad22500347b199d52b9368e686a42 ]

altera_hw_filt_init() which calls append_internal() assumes that the node was successfully linked in while in fact it can silently fail. So the call-site needs to set return to -ENOMEM on append_internal() returning NULL and exit through the err path.

---
 drivers/media/pci/cx23885/altera-ci.c |   10 ++++++++++
 1 file changed, 10 insertions(+)

@@ -660,6 +660,10 @@ static int altera_hw_filt_init(struct al
 		}
 
 		temp_int = append_internal(inter);
+		if (!temp_int) {
+			ret = -ENOMEM;
+			goto err;
+		}
 		inter->filts_used = 1;
 		inter->dev = config->dev;
 		inter->fpga_rw = config->fpga_rw;

@@ -694,6 +698,7 @@ err:
 		     __func__, ret);
 
 	kfree(pid_filt);
+	kfree(inter);
 
 	return ret;
 }

@@ -728,6 +733,10 @@ int altera_ci_init(struct altera_ci_conf
 		}
 
 		temp_int = append_internal(inter);
+		if (!temp_int) {
+			ret = -ENOMEM;
+			goto err;
+		}
 		inter->cis_used = 1;
 		inter->dev = config->dev;
 		inter->fpga_rw = config->fpga_rw;

@@ -796,6 +805,7 @@ err:
 	ci_dbg_print("%s: Cannot initialize CI: Error %d.\n", __func__, ret);
 
 	kfree(state);
+	kfree(inter);
 
 	return ret;
 }

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

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

From: Dengcheng Zhu <[email protected]>

[ Upstream commit dc57aaf95a516f70e2d527d8287a0332c481a226 ]

After changing CPU online status, it will not be sent any IPIs such as in __flush_cache_all() on software coherency systems. Do this before disabling local IRQ.

Patchwork: https://patchwork.linux-mips.org/patch/20571/

---
 arch/mips/kernel/crash.c         |    3 +++
 arch/mips/kernel/machine_kexec.c |    3 +++
 2 files changed, 6 insertions(+)

@@ -34,6 +34,9 @@ static void crash_shutdown_secondary(voi
 	if (!cpu_online(cpu))
 		return;
 
+	/* We won't be sent IPIs any more. */
+	set_cpu_online(cpu, false);
+
 	local_irq_disable();
 	if (!cpumask_test_cpu(cpu, &cpus_in_crash))
 		crash_save_cpu(regs, cpu);

@@ -96,6 +96,9 @@ machine_kexec(struct kimage *image)
 			*ptr = (unsigned long) phys_to_virt(*ptr);
 	}
 
+	/* Mark offline BEFORE disabling local irq. */
+	set_cpu_online(smp_processor_id(), false);
+
 	/*
 	 * we do not want to be bothered.
 	 */

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

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

From: Joel Stanley <[email protected]>

[ Upstream commit ee9d21b3b3583712029a0db65a4b7c081d08d3b3 ]

When building with clang crt0's _zimage_start is not marked weak, which breaks the build when linking the kernel image:

 $ objdump -t arch/powerpc/boot/crt0.o |grep _zimage_start$
 0000000000000058 g       .text  0000000000000000 _zimage_start

ld: arch/powerpc/boot/wrapper.a(crt0.o): in function '_zimage_start':
(.text+0x58): multiple definition of '_zimage_start'; arch/powerpc/boot/pseries-head.o:(.text+0x0): first defined here

Clang requires the .weak directive to appear after the symbol is declared. The binutils manual says:

This directive sets the weak attribute on the comma separated list of symbol names. If the symbols do not already exist, they will be created.

So it appears this is different with clang. The only reference I could see for this was an OpenBSD mailing list post[1].

Changing it to be after the declaration fixes building with Clang, and still works with GCC.

 $ objdump -t arch/powerpc/boot/crt0.o |grep _zimage_start$
 0000000000000058  w      .text	0000000000000000 _zimage_start

Reported to clang as https://bugs.llvm.org/show_bug.cgi?id=38921

[1] https://groups.google.com/forum/#!topic/fa.openbsd.tech/PAgKKen2YCY

---
 arch/powerpc/boot/crt0.S |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -47,8 +47,10 @@ p_end:		.long	_end
 p_pstack:	.long	_platform_stack_top
 #endif
 
-	.weak	_zimage_start
 	.globl	_zimage_start
+	/* Clang appears to require the .weak directive to be after the symbol
+	 * is defined. See https://bugs.llvm.org/show_bug.cgi?id=38921  */
+	.weak	_zimage_start
 _zimage_start:
 	.globl	_zimage_start_lib
 _zimage_start_lib:

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

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

From: Huacai Chen <[email protected]>

[ Upstream commit 2794f688b2c336e0da85e9f91fed33febbd9f54a ]

Call pcie_bus_configure_settings() on MIPS, like for other platforms. The function pcie_bus_configure_settings() makes sure the MPS (Max Payload Size) across the bus is uniform and provides the ability to tune the MRSS (Max Read Request Size) and MPS (Max Payload Size) to higher performance values. Some devices will not operate properly if these aren't set correctly because the firmware doesn't always do it.

Patchwork: https://patchwork.linux-mips.org/patch/20649/

---
 arch/mips/pci/pci-legacy.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -116,8 +116,12 @@ static void pcibios_scanbus(struct pci_c
 	if (pci_has_flag(PCI_PROBE_ONLY)) {
 		pci_bus_claim_resources(bus);
 	} else {
+		struct pci_bus *child;
+
 		pci_bus_size_bridges(bus);
 		pci_bus_assign_resources(bus);
+		list_for_each_entry(child, &bus->children, node)
+			pcie_bus_configure_settings(child);
 	}
 	pci_bus_add_devices(bus);
 }

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

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

From: Phil Elwell <[email protected]>

[ Upstream commit 8344498721059754e09d30fe255a12dab8fb03ef ]

The SC16IS752 is a dual-channel device. The two channels are largely independent, but the IRQ signals are wired together as an open-drain, active low signal which will be driven low while either of the channels requires attention, which can be for significant periods of time until operations complete and the interrupt can be acknowledged. In that respect it is should be treated as a true level-sensitive IRQ.

The kernel, however, needs to be able to exit interrupt context in order to use I2C or SPI to access the device registers (which may involve sleeping). Therefore the interrupt needs to be masked out or paused in some way.

The usual way to manage sleeping from within an interrupt handler is to use a threaded interrupt handler - a regular interrupt routine does the minimum amount of work needed to triage the interrupt before waking the interrupt service thread. If the threaded IRQ is marked as IRQF_ONESHOT the kernel will automatically mask out the interrupt until the thread runs to completion. The sc16is7xx driver used to use a threaded IRQ, but a patch switched to using a kthread_worker in order to set realtime priorities on the handler thread and for other optimisations. The end result is non-threaded IRQ that schedules some work then returns IRQ_HANDLED, making the kernel think that all IRQ processing has completed.

The work-around to prevent a constant stream of interrupts is to mark the interrupt as edge-sensitive rather than level-sensitive, but interpreting an active-low source as a falling-edge source requires care to prevent a total cessation of interrupts. Whereas an edge-triggering source will generate a new edge for every interrupt condition a level-triggering source will keep the signal at the interrupting level until it no longer requires attention; in other words, the host won't see another edge until all interrupt conditions are cleared. It is therefore vital that the interrupt handler does not exit with an outstanding interrupt condition, otherwise the kernel will not receive another interrupt unless some other operation causes the interrupt state on the device to be cleared.

The existing sc16is7xx driver has a very simple interrupt "thread" (kthread_work job) that processes interrupts on each channel in turn until there are no more. If both channels are active and the first channel starts interrupting while the handler for the second channel is running then it will not be detected and an IRQ stall ensues. This could be handled easily if there was a shared IRQ status register, or a convenient way to determine if the IRQ had been deasserted for any length of time, but both appear to be lacking.

Avoid this problem (or at least make it much less likely to happen) by reducing the granularity of per-channel interrupt processing to one condition per iteration, only exiting the overall loop when both channels are no longer interrupting.

---
 drivers/tty/serial/sc16is7xx.c |   19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

@@ -661,7 +661,7 @@ static void sc16is7xx_handle_tx(struct u
 		uart_write_wakeup(port);
 }
 
-static void sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno)
+static bool sc16is7xx_port_irq(struct sc16is7xx_port *s, int portno)
 {
 	struct uart_port *port = &s->p[portno].port;
 

@@ -670,7 +670,7 @@ static void sc16is7xx_port_irq(struct sc
 
 		iir = sc16is7xx_port_read(port, SC16IS7XX_IIR_REG);
 		if (iir & SC16IS7XX_IIR_NO_INT_BIT)
-			break;
+			return false;
 
 		iir &= SC16IS7XX_IIR_ID_MASK;
 

@@ -692,16 +692,23 @@ static void sc16is7xx_port_irq(struct sc
 					    port->line, iir);
 			break;
 		}
-	} while (1);
+	} while (0);
+	return true;
 }
 
 static void sc16is7xx_ist(struct kthread_work *ws)
 {
 	struct sc16is7xx_port *s = to_sc16is7xx_port(ws, irq_work);
-	int i;
 
-	for (i = 0; i < s->devtype->nr_uart; ++i)
-		sc16is7xx_port_irq(s, i);
+	while (1) {
+		bool keep_polling = false;
+		int i;
+
+		for (i = 0; i < s->devtype->nr_uart; ++i)
+			keep_polling |= sc16is7xx_port_irq(s, i);
+		if (!keep_polling)
+			break;
+	}
 }
 
 static irqreturn_t sc16is7xx_irq(int irq, void *dev_id)

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

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

From: Marco Felsch <[email protected]>

[ Upstream commit bd24db04101f45a9c1d874fe21b0c7eab7bcadec ]

The driver ignored the width alignment which exists due to the UYVY colorspace format. Fix the width alignment and make use of the the provided v4l2 helper function to set the width, height and all alignments in one.

---
 drivers/media/i2c/tvp5150.c |   14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

@@ -897,9 +897,6 @@ static int tvp5150_set_selection(struct
 
 	/* tvp5150 has some special limits */
 	rect.left = clamp(rect.left, 0, TVP5150_MAX_CROP_LEFT);
-	rect.width = clamp_t(unsigned int, rect.width,
-			     TVP5150_H_MAX - TVP5150_MAX_CROP_LEFT - rect.left,
-			     TVP5150_H_MAX - rect.left);
 	rect.top = clamp(rect.top, 0, TVP5150_MAX_CROP_TOP);
 
 	/* Calculate height based on current standard */

@@ -913,9 +910,16 @@ static int tvp5150_set_selection(struct
 	else
 		hmax = TVP5150_V_MAX_OTHERS;
 
-	rect.height = clamp_t(unsigned int, rect.height,
+	/*
+	 * alignments:
+	 *  - width = 2 due to UYVY colorspace
+	 *  - height, image = no special alignment
+	 */
+	v4l_bound_align_image(&rect.width,
+			      TVP5150_H_MAX - TVP5150_MAX_CROP_LEFT - rect.left,
+			      TVP5150_H_MAX - rect.left, 1, &rect.height,
 			      hmax - TVP5150_MAX_CROP_TOP - rect.top,
-			      hmax - rect.top);
+			      hmax - rect.top, 0, 0);
 
 	tvp5150_write(sd, TVP5150_VERT_BLANKING_START, rect.top);
 	tvp5150_write(sd, TVP5150_VERT_BLANKING_STOP,

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

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

From: Breno Leitao <[email protected]>

[ Upstream commit 693b31b2fc1636f0aa7af53136d3b49f6ad9ff39 ]

Test tm-tmspr might exit before all threads stop executing, because it just waits for the very last thread to join before proceeding/exiting.

This patch makes sure that all threads that were created will join before proceeding/exiting.

This patch also guarantees that the amount of threads being created is equal to thread_num.

---
 tools/testing/selftests/powerpc/tm/tm-tmspr.c |   27 ++++++++++++++++----------
 1 file changed, 17 insertions(+), 10 deletions(-)

@@ -98,7 +98,7 @@ void texasr(void *in)
 
 int test_tmspr()
 {
-	pthread_t 	thread;
+	pthread_t	*thread;
 	int	   	thread_num;
 	unsigned long	i;
 

@@ -107,21 +107,28 @@ int test_tmspr()
 	/* To cause some context switching */
 	thread_num = 10 * sysconf(_SC_NPROCESSORS_ONLN);
 
+	thread = malloc(thread_num * sizeof(pthread_t));
+	if (thread == NULL)
+		return EXIT_FAILURE;
+
 	/* Test TFIAR and TFHAR */
-	for (i = 0 ; i < thread_num ; i += 2){
-		if (pthread_create(&thread, NULL, (void*)tfiar_tfhar, (void *)i))
+	for (i = 0; i < thread_num; i += 2) {
+		if (pthread_create(&thread[i], NULL, (void *)tfiar_tfhar,
+				   (void *)i))
 			return EXIT_FAILURE;
 	}
-	if (pthread_join(thread, NULL) != 0)
-		return EXIT_FAILURE;
-
 	/* Test TEXASR */
-	for (i = 0 ; i < thread_num ; i++){
-		if (pthread_create(&thread, NULL, (void*)texasr, (void *)i))
+	for (i = 1; i < thread_num; i += 2) {
+		if (pthread_create(&thread[i], NULL, (void *)texasr, (void *)i))
 			return EXIT_FAILURE;
 	}
-	if (pthread_join(thread, NULL) != 0)
-		return EXIT_FAILURE;
+
+	for (i = 0; i < thread_num; i++) {
+		if (pthread_join(thread[i], NULL) != 0)
+			return EXIT_FAILURE;
+	}
+
+	free(thread);
 
 	if (passed)
 		return 0;

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

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

From: Dominique Martinet <[email protected]>

[ Upstream commit b4dc44b3cac9e8327e0655f530ed0c46f2e6214c ]

the 9p client code overwrites our glock.client_id pointing to a static buffer by an allocated string holding the network provided value which we do not care about; free and reset the value as appropriate.

This is almost identical to the leak in v9fs_file_getlock() fixed by Al Viro in commit ce85dd58ad5a6 ("9p: we are leaking glock.client_id in v9fs_file_getlock()"), which was returned as an error by a coverity false positive -- while we are here attempt to make the code slightly more robust to future change of the net/9p/client code and hopefully more clear to coverity that there is no problem.

---
 fs/9p/vfs_file.c |   16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

@@ -204,6 +204,14 @@ static int v9fs_file_do_lock(struct file
 			break;
 		if (schedule_timeout_interruptible(P9_LOCK_TIMEOUT) != 0)
 			break;
+		/*
+		 * p9_client_lock_dotl overwrites flock.client_id with the
+		 * server message, free and reuse the client name
+		 */
+		if (flock.client_id != fid->clnt->name) {
+			kfree(flock.client_id);
+			flock.client_id = fid->clnt->name;
+		}
 	}
 
 	/* map 9p status to VFS status */

@@ -235,6 +243,8 @@ out_unlock:
 		locks_lock_file_wait(filp, fl);
 		fl->fl_type = fl_type;
 	}
+	if (flock.client_id != fid->clnt->name)
+		kfree(flock.client_id);
 out:
 	return res;
 }

@@ -269,7 +279,7 @@ static int v9fs_file_getlock(struct file
 
 	res = p9_client_getlock_dotl(fid, &glock);
 	if (res < 0)
-		return res;
+		goto out;
 	/* map 9p lock type to os lock type */
 	switch (glock.type) {
 	case P9_LOCK_TYPE_RDLCK:

@@ -290,7 +300,9 @@ static int v9fs_file_getlock(struct file
 			fl->fl_end = glock.start + glock.length - 1;
 		fl->fl_pid = glock.proc_id;
 	}
-	kfree(glock.client_id);
+out:
+	if (glock.client_id != fid->clnt->name)
+		kfree(glock.client_id);
 	return res;
 }
 

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

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

From: Dominique Martinet <[email protected]>

[ Upstream commit 62e3941776fea8678bb8120607039410b1b61a65 ]

p9stat_free is more of a cleanup function than a 'free' function as it only frees the content of the struct; there are chances of use-after-free if it is improperly used (e.g. p9stat_free called twice as it used to be possible to)

Clearing dangling pointers makes the function idempotent and safer to use.

---
 net/9p/protocol.c |    5 +++++
 1 file changed, 5 insertions(+)

@@ -46,10 +46,15 @@ p9pdu_writef(struct p9_fcall *pdu, int p
 void p9stat_free(struct p9_wstat *stbuf)
 {
 	kfree(stbuf->name);
+	stbuf->name = NULL;
 	kfree(stbuf->uid);
+	stbuf->uid = NULL;
 	kfree(stbuf->gid);
+	stbuf->gid = NULL;
 	kfree(stbuf->muid);
+	stbuf->muid = NULL;
 	kfree(stbuf->extension);
+	stbuf->extension = NULL;
 }
 EXPORT_SYMBOL(p9stat_free);
 

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

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

From: Miklos Szeredi <[email protected]>

commit 4c316f2f3ff315cb48efb7435621e5bfb81df96d upstream.

Otherwise fuse_dev_do_write() could come in and finish off the request, and the set_bit(FR_SENT, ...) could trigger the WARN_ON(test_bit(FR_SENT, ...)) in request_end().

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

@@ -1311,8 +1311,8 @@ static ssize_t fuse_dev_do_read(struct f
 	}
 	list_move_tail(&req->list, &fpq->processing);
 	__fuse_get_request(req);
-	spin_unlock(&fpq->lock);
 	set_bit(FR_SENT, &req->flags);
+	spin_unlock(&fpq->lock);
 	/* matches barrier in request_wait_answer() */
 	smp_mb__after_atomic();
 	if (test_bit(FR_INTERRUPTED, &req->flags))

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

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

commit bb177a732c4369bb58a1fe1df8f552b6f0f7db5f upstream.

syzbot has noticed that a specially crafted library can easily hit VM_BUG_ON in __mm_populate

kernel BUG at mm/gup.c:1242!
invalid opcode: 0000 [#1] SMP

  CPU: 2 PID: 9667 Comm: a.out Not tainted 4.18.0-rc3 #644
  Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 05/19/2017
  RIP: 0010:__mm_populate+0x1e2/0x1f0
  Code: 55 d0 65 48 33 14 25 28 00 00 00 89 d8 75 21 48 83 c4 20 5b 41 5c 41 5d 41 5e 41 5f 5d c3 e8 75 18 f1 ff 0f 0b e8 6e 18 f1 ff <0f> 0b 31 db eb c9 e8 93 06 e0 ff 0f 1f 00 55 48 89 e5 53 48 89 fb
  Call Trace:
     vm_brk_flags+0xc3/0x100
     vm_brk+0x1f/0x30
     load_elf_library+0x281/0x2e0
     __ia32_sys_uselib+0x170/0x1e0
     do_fast_syscall_32+0xca/0x420
     entry_SYSENTER_compat+0x70/0x7f

The reason is that the length of the new brk is not page aligned when we try to populate the it. There is no reason to bug on that though. do_brk_flags already aligns the length properly so the mapping is expanded as it should. All we need is to tell mm_populate about it. Besides that there is absolutely no reason to to bug_on in the first place. The worst thing that could happen is that the last page wouldn't get populated and that is far from putting system into an inconsistent state.

Fix the issue by moving the length sanitization code from do_brk_flags up to vm_brk_flags. The only other caller of do_brk_flags is brk syscall entry and it makes sure to provide the proper length so t here is no need for sanitation and so we can use do_brk_flags without it.

Also remove the bogus BUG_ONs.

[bwh: Backported to 4.9:
- There is no do_brk_flags() function; update do_brk()
- Adjust context]

---
 mm/gup.c  |  2 --
 mm/mmap.c | 19 ++++++++++---------
 2 files changed, 10 insertions(+), 11 deletions(-)

index be4ccddac26f..d71da7216c6e 100644
@@ -1122,8 +1122,6 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
 	int locked = 0;
 	long ret = 0;
 
-	VM_BUG_ON(start & ~PAGE_MASK);
-	VM_BUG_ON(len != PAGE_ALIGN(len));
 	end = start + len;
 
 	for (nstart = start; nstart < end; nstart = nend) {

index aa97074a4a99..283755645d17 100644
@@ -2876,21 +2876,15 @@ static inline void verify_mm_writelocked(struct mm_struct *mm)
  *  anonymous maps.  eventually we may be able to do some
  *  brk-specific accounting here.
  */
-static int do_brk(unsigned long addr, unsigned long request)
+static int do_brk(unsigned long addr, unsigned long len)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
-	unsigned long flags, len;
+	unsigned long flags;
 	struct rb_node **rb_link, *rb_parent;
 	pgoff_t pgoff = addr >> PAGE_SHIFT;
 	int error;
 
-	len = PAGE_ALIGN(request);
-	if (len < request)
-		return -ENOMEM;
-	if (!len)
-		return 0;
-
 	flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
 
 	error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED);

@@ -2959,12 +2953,19 @@ static int do_brk(unsigned long addr, unsigned long request)
 	return 0;
 }
 
-int vm_brk(unsigned long addr, unsigned long len)
+int vm_brk(unsigned long addr, unsigned long request)
 {
 	struct mm_struct *mm = current->mm;
+	unsigned long len;
 	int ret;
 	bool populate;
 
+	len = PAGE_ALIGN(request);
+	if (len < request)
+		return -ENOMEM;
+	if (!len)
+		return 0;
+
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;
 

2.17.1

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

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

[ Upstream commit 5983587c8c5ef00d6886477544ad67d495bc5479 ]

Currently if the stat type is invalid then data[i] is being set either by dereferencing a null pointer p, or it is reading from an incorrect previous location if we had a valid stat type previously. Fix this by skipping over the read of p on an invalid stat type.

Detected by CoverityScan, CID#113385 ("Explicit null dereferenced")

---
 drivers/net/ethernet/intel/e1000/e1000_ethtool.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

index e84574b1eae7..2a81f6d72140 100644
@@ -1826,11 +1826,12 @@ static void e1000_get_ethtool_stats(struct net_device *netdev,
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	int i;
-	char *p = NULL;
 	const struct e1000_stats *stat = e1000_gstrings_stats;
 
 	e1000_update_stats(adapter);
-	for (i = 0; i < E1000_GLOBAL_STATS_LEN; i++) {
+	for (i = 0; i < E1000_GLOBAL_STATS_LEN; i++, stat++) {
+		char *p;
+
 		switch (stat->type) {
 		case NETDEV_STATS:
 			p = (char *)netdev + stat->stat_offset;

@@ -1841,15 +1842,13 @@ static void e1000_get_ethtool_stats(struct net_device *netdev,
 		default:
 			WARN_ONCE(1, "Invalid E1000 stat type: %u index %d\n",
 				  stat->type, i);
-			break;
+			continue;
 		}
 
 		if (stat->sizeof_stat == sizeof(u64))
 			data[i] = *(u64 *)p;
 		else
 			data[i] = *(u32 *)p;
-
-		stat++;
 	}
 /* BUG_ON(i != E1000_STATS_LEN); */
 }

2.17.1

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

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

[ Upstream commit 44c445c3d1b4eacff23141fa7977c3b2ec3a45c9 ]

This patch fixes a race condition that can result into the interface being up and carrier on, but with transmits disabled in the hardware. The bug may show up by repeatedly IFF_DOWN+IFF_UP the interface, which allows e1000_watchdog() interleave with e1000_down().

    CPU x                           CPU y
    --------------------------------------------------------------------
    e1000_down():
        netif_carrier_off()
                                    e1000_watchdog():
                                        if (carrier == off) {
                                            netif_carrier_on();
                                            enable_hw_transmit();
                                        }
        disable_hw_transmit();
                                    e1000_watchdog():
                                        /* carrier on, do nothing */

---
 drivers/net/ethernet/intel/e1000/e1000_main.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

index dd112aa5cebb..39a09e18c1b7 100644
@@ -521,8 +521,6 @@ void e1000_down(struct e1000_adapter *adapter)
 	struct net_device *netdev = adapter->netdev;
 	u32 rctl, tctl;
 
-	netif_carrier_off(netdev);
-
 	/* disable receives in the hardware */
 	rctl = er32(RCTL);
 	ew32(RCTL, rctl & ~E1000_RCTL_EN);

@@ -538,6 +536,15 @@ void e1000_down(struct e1000_adapter *adapter)
 	E1000_WRITE_FLUSH();
 	msleep(10);
 
+	/* Set the carrier off after transmits have been disabled in the
+	 * hardware, to avoid race conditions with e1000_watchdog() (which
+	 * may be running concurrently to us, checking for the carrier
+	 * bit to decide whether it should enable transmits again). Such
+	 * a race condition would result into transmission being disabled
+	 * in the hardware until the next IFF_DOWN+IFF_UP cycle.
+	 */
+	netif_carrier_off(netdev);
+
 	napi_disable(&adapter->napi);
 
 	e1000_irq_disable(adapter);

2.17.1

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

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

[ Upstream commit 4dc69c1c1fff2f587f8e737e70b4a4e7565a5c94 ]

Using memcpy() from a string that is shorter than the length copied means the destination buffer is being filled with arbitrary data from the kernel rodata segment. Instead, use strncpy() which will fill the trailing bytes with zeros.

This was found with the future CONFIG_FORTIFY_SOURCE feature.

---
 drivers/net/ethernet/brocade/bna/bnad_ethtool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

index 31f61a744d66..9473d12ce239 100644
@@ -541,8 +541,8 @@ bnad_get_strings(struct net_device *netdev, u32 stringset, u8 *string)
 		for (i = 0; i < BNAD_ETHTOOL_STATS_NUM; i++) {
 			BUG_ON(!(strlen(bnad_net_stats_strings[i]) <
 				   ETH_GSTRING_LEN));
-			memcpy(string, bnad_net_stats_strings[i],
-			       ETH_GSTRING_LEN);
+			strncpy(string, bnad_net_stats_strings[i],
+				ETH_GSTRING_LEN);
 			string += ETH_GSTRING_LEN;
 		}
 		bmap = bna_tx_rid_mask(&bnad->bna);

2.17.1

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

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

[ Upstream commit 0ed9d3de5f8f97e6efd5ca0e3377cab5f0451ead ]

The os_hpmc_size variable sometimes wasn't aligned at word boundary and thus triggered the unaligned fault handler at startup.
Fix it by aligning it properly.

---
 arch/parisc/kernel/hpmc.S | 1 +
 1 file changed, 1 insertion(+)

index 0fbd0a0e1cda..38d461aec46d 100644
@@ -304,6 +304,7 @@ ENDPROC_CFI(os_hpmc)
 
 
 	__INITRODATA
+	.align 4
 	.export os_hpmc_size
 os_hpmc_size:
 	.word .os_hpmc_end-.os_hpmc

2.17.1

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

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

[ Upstream commit d5654e156bc4d68a87bbaa6d7e020baceddf6e68 ]

Make sure that the HPMC (High Priority Machine Check) handler is 16-byte aligned and that it's length in the IVT is a multiple of 16 bytes. Otherwise PDC may decide not to call the HPMC crash handler.

---
 arch/parisc/kernel/hpmc.S | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

index 38d461aec46d..407b3aa5aa07 100644
@@ -83,6 +83,7 @@ END(hpmc_pim_data)
 	.text
 
 	.import intr_save, code
+	.align 16
 ENTRY_CFI(os_hpmc)
 .os_hpmc:
 

@@ -299,12 +300,15 @@ os_hpmc_6:
 
 	b .
 	nop
+	.align 16	/* make function length multiple of 16 bytes */
 ENDPROC_CFI(os_hpmc)
 .os_hpmc_end:
 
 
 	__INITRODATA
+.globl os_hpmc_size
 	.align 4
-	.export os_hpmc_size
+	.type   os_hpmc_size, @object
+	.size   os_hpmc_size, 4
 os_hpmc_size:
 	.word .os_hpmc_end-.os_hpmc

2.17.1

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

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

[ Upstream commit 99a3ae51d557d8e38a7aece65678a31f9db215ee ]

In the C-code we need to put the physical address of the hpmc handler in the interrupt vector table (IVA) in order to get HPMCs working. Since on parisc64 function pointers are indirect (in fact they are function descriptors) we instead export the address as variable and not as function.

This reverts a small part of commit f39cce654f9a ("parisc: Add cfi_startproc and cfi_endproc to assembly code").

---
 arch/parisc/kernel/hpmc.S | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

index 407b3aa5aa07..e88f4e7f39f3 100644
@@ -84,7 +84,7 @@ END(hpmc_pim_data)
 
 	.import intr_save, code
 	.align 16
-ENTRY_CFI(os_hpmc)
+ENTRY(os_hpmc)
 .os_hpmc:
 
 	/*

@@ -301,7 +301,6 @@ os_hpmc_6:
 	b .
 	nop
 	.align 16	/* make function length multiple of 16 bytes */
-ENDPROC_CFI(os_hpmc)
 .os_hpmc_end:
 
 

2.17.1

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

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

[ Upstream commit d06f8a2f1befb5a3d0aa660ab1c05e9b744456ea ]

Masking/unmasking the CPU UART irq in CP0_Status (and redirecting it to other CPUs) may cause interrupts be lost, especially in multi-package machines (Package-0's UART irq cannot be delivered to others). So make mask_loongson_irq() and unmask_loongson_irq() be no-ops.

The original problem (UART IRQ may deliver to any core) is also because of masking/unmasking the CPU UART irq in CP0_Status. So it is safe to remove all of the stuff.

Patchwork: https://patchwork.linux-mips.org/patch/20433/

---
 arch/mips/loongson64/loongson-3/irq.c | 43 ++-------------------------
 1 file changed, 3 insertions(+), 40 deletions(-)

index 8e7649088353..ec5f2b30646c 100644
@@ -50,45 +50,8 @@ static struct irqaction cascade_irqaction = {
 	.name = "cascade",
 };
 
-static inline void mask_loongson_irq(struct irq_data *d)
-{
-	clear_c0_status(0x100 << (d->irq - MIPS_CPU_IRQ_BASE));
-	irq_disable_hazard();
-
-	/* Workaround: UART IRQ may deliver to any core */
-	if (d->irq == LOONGSON_UART_IRQ) {
-		int cpu = smp_processor_id();
-		int node_id = cpu_logical_map(cpu) / loongson_sysconf.cores_per_node;
-		int core_id = cpu_logical_map(cpu) % loongson_sysconf.cores_per_node;
-		u64 intenclr_addr = smp_group[node_id] |
-			(u64)(&LOONGSON_INT_ROUTER_INTENCLR);
-		u64 introuter_lpc_addr = smp_group[node_id] |
-			(u64)(&LOONGSON_INT_ROUTER_LPC);
-
-		*(volatile u32 *)intenclr_addr = 1 << 10;
-		*(volatile u8 *)introuter_lpc_addr = 0x10 + (1<<core_id);
-	}
-}
-
-static inline void unmask_loongson_irq(struct irq_data *d)
-{
-	/* Workaround: UART IRQ may deliver to any core */
-	if (d->irq == LOONGSON_UART_IRQ) {
-		int cpu = smp_processor_id();
-		int node_id = cpu_logical_map(cpu) / loongson_sysconf.cores_per_node;
-		int core_id = cpu_logical_map(cpu) % loongson_sysconf.cores_per_node;
-		u64 intenset_addr = smp_group[node_id] |
-			(u64)(&LOONGSON_INT_ROUTER_INTENSET);
-		u64 introuter_lpc_addr = smp_group[node_id] |
-			(u64)(&LOONGSON_INT_ROUTER_LPC);
-
-		*(volatile u32 *)intenset_addr = 1 << 10;
-		*(volatile u8 *)introuter_lpc_addr = 0x10 + (1<<core_id);
-	}
-
-	set_c0_status(0x100 << (d->irq - MIPS_CPU_IRQ_BASE));
-	irq_enable_hazard();
-}
+static inline void mask_loongson_irq(struct irq_data *d) { }
+static inline void unmask_loongson_irq(struct irq_data *d) { }
 
  /* For MIPS IRQs which shared by all cores */
 static struct irq_chip loongson_irq_chip = {

@@ -126,7 +89,7 @@ void __init mach_init_irq(void)
 	mips_cpu_irq_init();
 	init_i8259_irqs();
 	irq_set_chip_and_handler(LOONGSON_UART_IRQ,
-			&loongson_irq_chip, handle_level_irq);
+			&loongson_irq_chip, handle_percpu_irq);
 
 	/* setup HT1 irq */
 	setup_irq(LOONGSON_HT1_IRQ, &cascade_irqaction);

2.17.1

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

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

[ Upstream commit 360fe725f8849aaddc53475fef5d4a0c439b05ae ]

After commit e509bd7da149dc349160 ("genirq: Allow migration of chained interrupts by installing default action") Loongson-3 fails at here:

setup_irq(LOONGSON_HT1_IRQ, &cascade_irqaction);

This is because both chained_action and cascade_irqaction don't have IRQF_SHARED flag. This will cause Loongson-3 resume fails because HPET timer interrupt can't be delivered during S3. So we set the irqchip of the chained irq to loongson_irq_chip which doesn't disable the chained irq in CP0.Status.

Patchwork: https://patchwork.linux-mips.org/patch/20434/

---
 arch/mips/include/asm/mach-loongson64/irq.h |  2 +-
 arch/mips/loongson64/loongson-3/irq.c       | 13 +++----------
 2 files changed, 4 insertions(+), 11 deletions(-)

index d18c45c7c394..19ff9ce46c02 100644
@@ -9,7 +9,7 @@
 #define MIPS_CPU_IRQ_BASE 56
 
 #define LOONGSON_UART_IRQ   (MIPS_CPU_IRQ_BASE + 2) /* UART */
-#define LOONGSON_HT1_IRQ    (MIPS_CPU_IRQ_BASE + 3) /* HT1 */
+#define LOONGSON_BRIDGE_IRQ (MIPS_CPU_IRQ_BASE + 3) /* CASCADE */
 #define LOONGSON_TIMER_IRQ  (MIPS_CPU_IRQ_BASE + 7) /* CPU Timer */
 
 #define LOONGSON_HT1_CFG_BASE		loongson_sysconf.ht_control_base

index ec5f2b30646c..027f53e3bc81 100644
@@ -44,12 +44,6 @@ void mach_irq_dispatch(unsigned int pending)
 	}
 }
 
-static struct irqaction cascade_irqaction = {
-	.handler = no_action,
-	.flags = IRQF_NO_SUSPEND,
-	.name = "cascade",
-};
-
 static inline void mask_loongson_irq(struct irq_data *d) { }
 static inline void unmask_loongson_irq(struct irq_data *d) { }
 

@@ -90,11 +84,10 @@ void __init mach_init_irq(void)
 	init_i8259_irqs();
 	irq_set_chip_and_handler(LOONGSON_UART_IRQ,
 			&loongson_irq_chip, handle_percpu_irq);
+	irq_set_chip_and_handler(LOONGSON_BRIDGE_IRQ,
+			&loongson_irq_chip, handle_percpu_irq);
 
-	/* setup HT1 irq */
-	setup_irq(LOONGSON_HT1_IRQ, &cascade_irqaction);
-
-	set_c0_status(STATUSF_IP2 | STATUSF_IP6);
+	set_c0_status(STATUSF_IP2 | STATUSF_IP3 | STATUSF_IP6);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU

2.17.1

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

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

From: Enric Balletbo i Serra <[email protected]>

commit 665636b2940d0897c4130253467f5e8c42eea392 upstream.

Fixes the signedness bug returning '(-22)' on the return type by removing the sanity checker in rockchip_ddrclk_get_parent(). The function should return and unsigned value only and it's safe to remove the sanity checker as the core functions that call get_parent like clk_core_get_parent_by_index already ensures the validity of the clk index returned (index >= core->num_parents).

---
 drivers/clk/rockchip/clk-ddr.c |    4 ----
 1 file changed, 4 deletions(-)

@@ -80,16 +80,12 @@ static long rockchip_ddrclk_sip_round_ra
 static u8 rockchip_ddrclk_get_parent(struct clk_hw *hw)
 {
 	struct rockchip_ddrclk *ddrclk = to_rockchip_ddrclk_hw(hw);
-	int num_parents = clk_hw_get_num_parents(hw);
 	u32 val;
 
 	val = clk_readl(ddrclk->reg_base +
 			ddrclk->mux_offset) >> ddrclk->mux_shift;
 	val &= GENMASK(ddrclk->mux_width - 1, 0);
 
-	if (val >= num_parents)
-		return -EINVAL;
-
 	return val;
 }
 

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

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

From: Ilya Dryomov <[email protected]>

commit 94e6992bb560be8bffb47f287194adf070b57695 upstream.

If the read is large enough, we end up spinning in the messenger:

libceph: osd0 192.168.122.1:6801 io error
libceph: osd0 192.168.122.1:6801 io error
libceph: osd0 192.168.122.1:6801 io error

This is a receive side limit, so only reads were affected.

---
 include/linux/ceph/libceph.h |    8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

@@ -77,7 +77,13 @@ struct ceph_options {
 
 #define CEPH_MSG_MAX_FRONT_LEN	(16*1024*1024)
 #define CEPH_MSG_MAX_MIDDLE_LEN	(16*1024*1024)
-#define CEPH_MSG_MAX_DATA_LEN	(16*1024*1024)
+
+/*
+ * Handle the largest possible rbd object in one message.
+ * There is no limit on the size of cephfs objects, but it has to obey
+ * rsize and wsize mount options anyway.
+ */
+#define CEPH_MSG_MAX_DATA_LEN	(32*1024*1024)
 
 #define CEPH_AUTH_NAME_DEFAULT   "guest"
 

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

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

From: Yan, Zheng <[email protected]>

commit efe328230dc01aa0b1269aad0b5fae73eea4677a upstream.

This reverts commit 8b8f53af1ed9df88a4c0fbfdf3db58f62060edf3.

splice_dentry() is used by three places. For two places, req->r_dentry is passed to splice_dentry(). In the case of error, req->r_dentry does not get updated. So splice_dentry() should not drop reference.

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

@@ -1077,8 +1077,12 @@ static struct dentry *splice_dentry(stru
 	if (IS_ERR(realdn)) {
 		pr_err("splice_dentry error %ld %p inode %p ino %llx.%llx\n",
 		       PTR_ERR(realdn), dn, in, ceph_vinop(in));
-		dput(dn);
-		dn = realdn; /* note realdn contains the error */
+		dn = realdn;
+		/*
+		 * Caller should release 'dn' in the case of error.
+		 * If 'req->r_dentry' is passed to this function,
+		 * caller should leave 'req->r_dentry' untouched.
+		 */
 		goto out;
 	} else if (realdn) {
 		dout("dn %p (%d) spliced with %p (%d) "

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

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

From: Arnd Bergmann <[email protected]>

commit be2e1c9dcf76886a83fb1c433a316e26d4ca2550 upstream.

I noticed during the creation of another bugfix that the BCH_CONST_PARAMS option that is set by DOCG3 breaks setting variable parameters for any other users of the BCH library code.

The only other user we have today is the MTD_NAND software BCH implementation (most flash controllers use hardware BCH these days and are not affected). I considered removing BCH_CONST_PARAMS entirely because of the inherent conflict, but according to the description in lib/bch.c there is a significant performance benefit in keeping it.

To avoid the immediate problem of the conflict between MTD_NAND_BCH and DOCG3, this only sets the constant parameters if MTD_NAND_BCH is disabled, which should fix the problem for all cases that are affected. This should also work for all stable kernels.

Note that there is only one machine that actually seems to use the DOCG3 driver (arch/arm/mach-pxa/mioa701.c), so most users should have the driver disabled, but it almost certainly shows up if we wanted to test random kernels on machines that use software BCH in MTD.

---
 drivers/mtd/devices/Kconfig |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -196,7 +196,7 @@ comment "Disk-On-Chip Device Drivers"
 config MTD_DOCG3
 	tristate "M-Systems Disk-On-Chip G3"
 	select BCH
-	select BCH_CONST_PARAMS
+	select BCH_CONST_PARAMS if !MTD_NAND_BCH
 	select BITREVERSE
 	---help---
 	  This provides an MTD device driver for the M-Systems DiskOnChip

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

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

From: John Garry <[email protected]>

commit 89c38422e072bb453e3045b8f1b962a344c3edea upstream.

Currently the NUMA distance map parsing does not validate the distance table for the distance-matrix rules 1-2 in [1].

However the arch NUMA code may enforce some of these rules, but not all. Such is the case for the arm64 port, which does not enforce the rule that the distance between separates nodes cannot equal LOCAL_DISTANCE.

The patch adds the following rules validation:
- distance of node to self equals LOCAL_DISTANCE
- distance of separate nodes > LOCAL_DISTANCE

This change avoids a yet-unresolved crash reported in [2].

A note on dealing with symmetrical distances between nodes:

Validating symmetrical distances between nodes is difficult. If it were mandated in the bindings that every distance must be recorded in the table, then it would be easy. However, it isn't.

In addition to this, it is also possible to record [b, a] distance only (and not [a, b]). So, when processing the table for [b, a], we cannot assert that current distance of [a, b] != [b, a] as invalid, as [a, b] distance may not be present in the table and current distance would be default at REMOTE_DISTANCE.

As such, we maintain the policy that we overwrite distance [a, b] = [b, a] for b > a. This policy is different to kernel ACPI SLIT validation, which allows non-symmetrical distances (ACPI spec SLIT rules allow it). However, the distance debug message is dropped as it may be misleading (for a distance which is later overwritten).

Some final notes on semantics:

- It is implied that it is the responsibility of the arch NUMA code to reset the NUMA distance map for an error in distance map parsing.

- It is the responsibility of the FW NUMA topology parsing (whether OF or ACPI) to enforce NUMA distance rules, and not arch NUMA code.

[1] Documents/devicetree/bindings/numa.txt
[2] https://www.spinics.net/lists/arm-kernel/msg683304.html

---
 drivers/of/of_numa.c |    9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

@@ -126,9 +126,14 @@ static int __init of_numa_parse_distance
 		distance = of_read_number(matrix, 1);
 		matrix++;
 
+		if ((nodea == nodeb && distance != LOCAL_DISTANCE) ||
+		    (nodea != nodeb && distance <= LOCAL_DISTANCE)) {
+			pr_err("Invalid distance[node%d -> node%d] = %d\n",
+			       nodea, nodeb, distance);
+			return -EINVAL;
+		}
+
 		numa_set_distance(nodea, nodeb, distance);
-		pr_debug("distance[node%d -> node%d] = %d\n",
-			 nodea, nodeb, distance);
 
 		/* Set default distance of node B->A same as A->B */
 		if (nodeb > nodea)

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

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

From: H. Peter Anvin (Intel) <[email protected]>

commit d0ffb805b729322626639336986bc83fc2e60871 upstream.

Alpha has had c_ispeed and c_ospeed, but still set speeds in c_cflags using arbitrary flags. Because BOTHER is not defined, the general Linux code doesn't allow setting arbitrary baud rates, and because CBAUDEX == 0, we can have an array overrun of the baud_rate[] table in drivers/tty/tty_baudrate.c if (c_cflags & CBAUD) == 037.

Resolve both problems by #defining BOTHER to 037 on Alpha.

However, userspace still needs to know if setting BOTHER is actually safe given legacy kernels (does anyone actually care about that on Alpha anymore?), so enable the TCGETS2/TCSETS*2 ioctls on Alpha, even though they use the same structure. Define struct termios2 just for compatibility; it is the exact same structure as struct termios. In a future patchset, this will be cleaned up so the uapi headers are usable from libc.

---
 arch/alpha/include/asm/termios.h       |    8 +++++++-
 arch/alpha/include/uapi/asm/ioctls.h   |    5 +++++
 arch/alpha/include/uapi/asm/termbits.h |   17 +++++++++++++++++
 3 files changed, 29 insertions(+), 1 deletion(-)

@@ -72,9 +72,15 @@
 })
 
 #define user_termios_to_kernel_termios(k, u) \
-	copy_from_user(k, u, sizeof(struct termios))
+	copy_from_user(k, u, sizeof(struct termios2))
 
 #define kernel_termios_to_user_termios(u, k) \
+	copy_to_user(u, k, sizeof(struct termios2))
+
+#define user_termios_to_kernel_termios_1(k, u) \
+	copy_from_user(k, u, sizeof(struct termios))
+
+#define kernel_termios_to_user_termios_1(u, k) \
 	copy_to_user(u, k, sizeof(struct termios))
 
 #endif	/* _ALPHA_TERMIOS_H */

@@ -31,6 +31,11 @@
 #define TCXONC		_IO('t', 30)
 #define TCFLSH		_IO('t', 31)
 
+#define TCGETS2		_IOR('T', 42, struct termios2)
+#define TCSETS2		_IOW('T', 43, struct termios2)
+#define TCSETSW2	_IOW('T', 44, struct termios2)
+#define TCSETSF2	_IOW('T', 45, struct termios2)
+
 #define TIOCSWINSZ	_IOW('t', 103, struct winsize)
 #define TIOCGWINSZ	_IOR('t', 104, struct winsize)
 #define	TIOCSTART	_IO('t', 110)		/* start output, like ^Q */

@@ -25,6 +25,19 @@ struct termios {
 	speed_t c_ospeed;		/* output speed */
 };
 
+/* Alpha has identical termios and termios2 */
+
+struct termios2 {
+	tcflag_t c_iflag;		/* input mode flags */
+	tcflag_t c_oflag;		/* output mode flags */
+	tcflag_t c_cflag;		/* control mode flags */
+	tcflag_t c_lflag;		/* local mode flags */
+	cc_t c_cc[NCCS];		/* control characters */
+	cc_t c_line;			/* line discipline (== c_cc[19]) */
+	speed_t c_ispeed;		/* input speed */
+	speed_t c_ospeed;		/* output speed */
+};
+
 /* Alpha has matching termios and ktermios */
 
 struct ktermios {

@@ -147,6 +160,7 @@ struct ktermios {
 #define B3000000  00034
 #define B3500000  00035
 #define B4000000  00036
+#define BOTHER    00037
 
 #define CSIZE	00001400
 #define   CS5	00000000

@@ -164,6 +178,9 @@ struct ktermios {
 #define CMSPAR	  010000000000		/* mark or space (stick) parity */
 #define CRTSCTS	  020000000000		/* flow control */
 
+#define CIBAUD	07600000
+#define IBSHIFT	16
+
 /* c_lflag bits */
 #define ISIG	0x00000080
 #define ICANON	0x00000100

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

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

From: Robbie Ko <[email protected]>

commit 506481b20e818db40b6198815904ecd2d6daee64 upstream.

When the cow_file_range fails, the related resources are unlocked according to the range [start..end), so the unlock cannot be repeated in run_delalloc_nocow.

In some cases (e.g. cur_offset <= end && cow_start != -1), cur_offset is not updated correctly, so move the cur_offset update before cow_file_range.

kernel BUG at mm/page-writeback.c:2663!

  Internal error: Oops - BUG: 0 [#1] SMP
  CPU: 3 PID: 31525 Comm: kworker/u8:7 Tainted: P O
  Hardware name: Realtek_RTD1296 (DT)
  Workqueue: writeback wb_workfn (flush-btrfs-1)
  task: ffffffc076db3380 ti: ffffffc02e9ac000 task.ti: ffffffc02e9ac000
  PC is at clear_page_dirty_for_io+0x1bc/0x1e8
  LR is at clear_page_dirty_for_io+0x14/0x1e8
  pc : [<ffffffc00033c91c>] lr : [<ffffffc00033c774>] pstate: 40000145
  sp : ffffffc02e9af4f0
  Process kworker/u8:7 (pid: 31525, stack limit = 0xffffffc02e9ac020)
  Call trace:
  [<ffffffc00033c91c>] clear_page_dirty_for_io+0x1bc/0x1e8
  [<ffffffbffc514674>] extent_clear_unlock_delalloc+0x1e4/0x210 [btrfs]
  [<ffffffbffc4fb168>] run_delalloc_nocow+0x3b8/0x948 [btrfs]
  [<ffffffbffc4fb948>] run_delalloc_range+0x250/0x3a8 [btrfs]
  [<ffffffbffc514c0c>] writepage_delalloc.isra.21+0xbc/0x1d8 [btrfs]
  [<ffffffbffc516048>] __extent_writepage+0xe8/0x248 [btrfs]
  [<ffffffbffc51630c>] extent_write_cache_pages.isra.17+0x164/0x378 [btrfs]
  [<ffffffbffc5185a8>] extent_writepages+0x48/0x68 [btrfs]
  [<ffffffbffc4f5828>] btrfs_writepages+0x20/0x30 [btrfs]
  [<ffffffc00033d758>] do_writepages+0x30/0x88
  [<ffffffc0003ba0f4>] __writeback_single_inode+0x34/0x198
  [<ffffffc0003ba6c4>] writeback_sb_inodes+0x184/0x3c0
  [<ffffffc0003ba96c>] __writeback_inodes_wb+0x6c/0xc0
  [<ffffffc0003bac20>] wb_writeback+0x1b8/0x1c0
  [<ffffffc0003bb0f0>] wb_workfn+0x150/0x250
  [<ffffffc0002b0014>] process_one_work+0x1dc/0x388
  [<ffffffc0002b02f0>] worker_thread+0x130/0x500
  [<ffffffc0002b6344>] kthread+0x10c/0x110
  [<ffffffc000284590>] ret_from_fork+0x10/0x40
  Code: d503201f a9025bb5 a90363b7 f90023b9 (d4210000)

---
 fs/btrfs/inode.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

@@ -1548,12 +1548,11 @@ out_check:
 	}
 	btrfs_release_path(path);
 
-	if (cur_offset <= end && cow_start == (u64)-1) {
+	if (cur_offset <= end && cow_start == (u64)-1)
 		cow_start = cur_offset;
-		cur_offset = end;
-	}
 
 	if (cow_start != (u64)-1) {
+		cur_offset = end;
 		ret = cow_file_range(inode, locked_page, cow_start, end, end,
 				     page_started, nr_written, 1, NULL);
 		if (ret)

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

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

From: Filipe Manana <[email protected]>

commit ac765f83f1397646c11092a032d4f62c3d478b81 upstream.

We currently allow cloning a range from a file which includes the last block of the file even if the file's size is not aligned to the block size. This is fine and useful when the destination file has the same size, but when it does not and the range ends somewhere in the middle of the destination file, it leads to corruption because the bytes between the EOF and the end of the block have undefined data (when there is support for discard/trimming they have a value of 0x00).

Example:

 $ mkfs.btrfs -f /dev/sdb
 $ mount /dev/sdb /mnt

 $ export foo_size=$((256 * 1024 + 100))
 $ xfs_io -f -c "pwrite -S 0x3c 0 $foo_size" /mnt/foo
 $ xfs_io -f -c "pwrite -S 0xb5 0 1M" /mnt/bar

 $ xfs_io -c "reflink /mnt/foo 0 512K $foo_size" /mnt/bar

 $ od -A d -t x1 /mnt/bar
 0000000 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5
 *
 0524288 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c 3c
 *
 0786528 3c 3c 3c 3c 00 00 00 00 00 00 00 00 00 00 00 00
 0786544 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
 *
 0790528 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5 b5
 *
 1048576

The bytes in the range from 786532 (512Kb + 256Kb + 100 bytes) to 790527 (512Kb + 256Kb + 4Kb - 1) got corrupted, having now a value of 0x00 instead of 0xb5.

This is similar to the problem we had for deduplication that got recently fixed by commit de02b9f6bb65 ("Btrfs: fix data corruption when deduplicating between different files").

Fix this by not allowing such operations to be performed and return the errno -EINVAL to user space. This is what XFS is doing as well at the VFS level. This change however now makes us return -EINVAL instead of -EOPNOTSUPP for cases where the source range maps to an inline extent and the destination range's end is smaller then the destination file's size, since the detection of inline extents is done during the actual process of dropping file extent items (at __btrfs_drop_extents()). Returning the -EINVAL error is done early on and solely based on the input parameters (offsets and length) and destination file's size. This makes us consistent with XFS and anyone else supporting cloning since this case is now checked at a higher level in the VFS and is where the -EINVAL will be returned from starting with kernel 4.20 (the VFS changed was introduced in 4.20-rc1 by commit 07d19dc9fbe9 ("vfs: avoid problematic remapping requests into partial EOF block"). So this change is more geared towards stable kernels, as it's unlikely the new VFS checks get removed intentionally.

A test case for fstests follows soon, as well as an update to filter existing tests that expect -EOPNOTSUPP to accept -EINVAL as well.

---
 fs/btrfs/ioctl.c |   12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

@@ -3911,9 +3911,17 @@ static noinline int btrfs_clone_files(st
 		goto out_unlock;
 	if (len == 0)
 		olen = len = src->i_size - off;
-	/* if we extend to eof, continue to block boundary */
-	if (off + len == src->i_size)
+	/*
+	 * If we extend to eof, continue to block boundary if and only if the
+	 * destination end offset matches the destination file's size, otherwise
+	 * we would be corrupting data by placing the eof block into the middle
+	 * of a file.
+	 */
+	if (off + len == src->i_size) {
+		if (!IS_ALIGNED(len, bs) && destoff + len < inode->i_size)
+			goto out_unlock;
 		len = ALIGN(src->i_size, bs) - off;
+	}
 
 	if (len == 0) {
 		ret = 0;

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

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

From: Michael Kelley <[email protected]>

commit 35b69a420bfb56b7b74cb635ea903db05e357bec upstream.

Add support for platforms where pit_shutdown() doesn't work because of a quirk in the PIT emulation. On these platforms setting the counter register to zero causes the PIT to start running again, negating the shutdown.

Provide a global variable that controls whether the counter register is zero'ed, which platform specific code can override.

---
 drivers/clocksource/i8253.c |   14 ++++++++++++--
 include/linux/i8253.h       |    1 +
 2 files changed, 13 insertions(+), 2 deletions(-)

@@ -19,6 +19,13 @@
 DEFINE_RAW_SPINLOCK(i8253_lock);
 EXPORT_SYMBOL(i8253_lock);
 
+/*
+ * Handle PIT quirk in pit_shutdown() where zeroing the counter register
+ * restarts the PIT, negating the shutdown. On platforms with the quirk,
+ * platform specific code can set this to false.
+ */
+bool i8253_clear_counter_on_shutdown __ro_after_init = true;
+
 #ifdef CONFIG_CLKSRC_I8253
 /*
  * Since the PIT overflows every tick, its not very useful

@@ -108,8 +115,11 @@ static int pit_shutdown(struct clock_eve
 	raw_spin_lock(&i8253_lock);
 
 	outb_p(0x30, PIT_MODE);
-	outb_p(0, PIT_CH0);
-	outb_p(0, PIT_CH0);
+
+	if (i8253_clear_counter_on_shutdown) {
+		outb_p(0, PIT_CH0);
+		outb_p(0, PIT_CH0);
+	}
 
 	raw_spin_unlock(&i8253_lock);
 	return 0;

@@ -21,6 +21,7 @@
 #define PIT_LATCH	((PIT_TICK_RATE + HZ/2) / HZ)
 
 extern raw_spinlock_t i8253_lock;
+extern bool i8253_clear_counter_on_shutdown;
 extern struct clock_event_device i8253_clockevent;
 extern void clockevent_i8253_init(bool oneshot);

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

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

From: Vasily Averin <[email protected]>

commit 9e4028935cca3f9ef9b6a90df9da6f1f94853536 upstream.

Currently bh is set to NULL only during first iteration of for cycle, then this pointer is not cleared after end of using.
Therefore rollback after errors can lead to extra brelse(bh) call, decrements bh counter and later trigger an unexpected warning in __brelse()

Patch moves brelse() calls in body of cycle to exclude requirement of brelse() call in rollback.

---
 fs/ext4/resize.c |    8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

@@ -590,7 +590,6 @@ handle_bb:
 		bh = bclean(handle, sb, block);
 		if (IS_ERR(bh)) {
 			err = PTR_ERR(bh);
-			bh = NULL;
 			goto out;
 		}
 		overhead = ext4_group_overhead_blocks(sb, group);

@@ -602,9 +601,9 @@ handle_bb:
 		ext4_mark_bitmap_end(group_data[i].blocks_count,
 				     sb->s_blocksize * 8, bh->b_data);
 		err = ext4_handle_dirty_metadata(handle, NULL, bh);
+		brelse(bh);
 		if (err)
 			goto out;
-		brelse(bh);
 
 handle_ib:
 		if (bg_flags[i] & EXT4_BG_INODE_UNINIT)

@@ -619,18 +618,16 @@ handle_ib:
 		bh = bclean(handle, sb, block);
 		if (IS_ERR(bh)) {
 			err = PTR_ERR(bh);
-			bh = NULL;
 			goto out;
 		}
 
 		ext4_mark_bitmap_end(EXT4_INODES_PER_GROUP(sb),
 				     sb->s_blocksize * 8, bh->b_data);
 		err = ext4_handle_dirty_metadata(handle, NULL, bh);
+		brelse(bh);
 		if (err)
 			goto out;
-		brelse(bh);
 	}
-	bh = NULL;
 
 	/* Mark group tables in block bitmap */
 	for (j = 0; j < GROUP_TABLE_COUNT; j++) {

@@ -661,7 +658,6 @@ handle_ib:
 	}
 
 out:
-	brelse(bh);
 	err2 = ext4_journal_stop(handle);
 	if (err2 && !err)
 		err = err2;

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

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

From: Vasily Averin <[email protected]>

commit db6aee62406d9fbb53315fcddd81f1dc271d49fa upstream.

---
 fs/ext4/resize.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -2026,6 +2026,10 @@ retry:
 		n_blocks_count_retry = 0;
 		free_flex_gd(flex_gd);
 		flex_gd = NULL;
+		if (resize_inode) {
+			iput(resize_inode);
+			resize_inode = NULL;
+		}
 		goto retry;
 	}
 

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

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

From: Theodore Ts'o <[email protected]>

commit 4f32c38b4662312dd3c5f113d8bdd459887fb773 upstream.

---
 fs/ext4/resize.c |    1 +
 1 file changed, 1 insertion(+)

@@ -844,6 +844,7 @@ static int add_new_gdb(handle_t *handle,
 	err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh);
 	if (unlikely(err)) {
 		ext4_std_error(sb, err);
+		iloc.bh = NULL;
 		goto exit_inode;
 	}
 	brelse(dind);

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

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

From: Vasily Averin <[email protected]>

commit af18e35bfd01e6d65a5e3ef84ffe8b252d1628c5 upstream.

---
 fs/ext4/super.c |    1 +
 1 file changed, 1 insertion(+)

@@ -4305,6 +4305,7 @@ failed_mount6:
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
 	percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+	percpu_free_rwsem(&sbi->s_journal_flag_rwsem);
 failed_mount5:
 	ext4_ext_release(sb);
 	ext4_release_system_zone(sb);

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

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

From: Vasily Averin <[email protected]>

commit 6bdc9977fcdedf47118d2caf7270a19f4b6d8a8f upstream.

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

@@ -1393,6 +1393,8 @@ out:
 	kfree(buffer);
 	if (is)
 		brelse(is->iloc.bh);
+	if (bs)
+		brelse(bs->bh);
 	kfree(is);
 	kfree(bs);
 

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

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

From: Eric W. Biederman <[email protected]>

commit df7342b240185d58d3d9665c0bbf0a0f5570ec29 upstream.

Jonathan Calmels from NVIDIA reported that he's able to bypass the mount visibility security check in place in the Linux kernel by using a combination of the unbindable property along with the private mount propagation option to allow a unprivileged user to see a path which was purposefully hidden by the root user.

Reproducer:
# Hide a path to all users using a tmpfs

  root@castiana:~# mount -t tmpfs tmpfs /sys/devices/
  root@castiana:~#

# As an unprivileged user, unshare user namespace and mount namespace

  stgraber@castiana:~$ unshare -U -m -r

# Confirm the path is still not accessible

  root@castiana:~# ls /sys/devices/

  # Make /sys recursively unbindable and private
  root@castiana:~# mount --make-runbindable /sys
  root@castiana:~# mount --make-private /sys

  # Recursively bind-mount the rest of /sys over to /mnnt
  root@castiana:~# mount --rbind /sys/ /mnt

# Access our hidden /sys/device as an unprivileged user

  root@castiana:~# ls /mnt/devices/
  breakpoint cpu cstate_core cstate_pkg i915 intel_pt isa kprobe
  LNXSYSTM:00 msr pci0000:00 platform pnp0 power software system
  tracepoint uncore_arb uncore_cbox_0 uncore_cbox_1 uprobe virtual

Solve this by teaching copy_tree to fail if a mount turns out to be both unbindable and locked.

---
 fs/namespace.c |   10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

@@ -1788,8 +1788,14 @@ struct mount *copy_tree(struct mount *mn
 		for (s = r; s; s = next_mnt(s, r)) {
 			if (!(flag & CL_COPY_UNBINDABLE) &&
 			    IS_MNT_UNBINDABLE(s)) {
-				s = skip_mnt_tree(s);
-				continue;
+				if (s->mnt.mnt_flags & MNT_LOCKED) {
+					/* Both unbindable and locked. */
+					q = ERR_PTR(-EPERM);
+					goto out;
+				} else {
+					s = skip_mnt_tree(s);
+					continue;
+				}
 			}
 			if (!(flag & CL_COPY_MNT_NS_FILE) &&
 			    is_mnt_ns_file(s->mnt.mnt_root)) {

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

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

From: Eric W. Biederman <[email protected]>

commit 9c8e0a1b683525464a2abe9fb4b54404a50ed2b4 upstream.

I tracked this down to put_mnt_ns running passing UMOUNT_SYNC and disconnecting all of the mounts in a mount namespace. Fix this by factoring drop_mounts out of drop_collected_mounts and passing 0 instead of UMOUNT_SYNC.

There are two possible behavior differences that result from this.
- No longer setting UMOUNT_SYNC will no longer set MNT_SYNC_UMOUNT on the vfsmounts being unmounted. This effects the lazy rcu walk by kicking the walk out of rcu mode and forcing it to be a non-lazy walk.
- No longer disconnecting locked mounts will keep some mounts around longer as they stay because the are locked to other mounts.

There are only two users of drop_collected mounts: audit_tree.c and put_mnt_ns.

In audit_tree.c the mounts are private and there are no rcu lazy walks only calls to iterate_mounts. So the changes should have no effect except for a small timing effect as the connected mounts are disconnected.

In put_mnt_ns there may be references from process outside the mount namespace to the mounts. So the mounts remaining connected will be the bug fix that is needed. That rcu walks are allowed to continue appears not to be a problem especially as the rcu walk change was about an implementation detail not about semantics.

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

@@ -1848,7 +1848,7 @@ void drop_collected_mounts(struct vfsmou
 {
 	namespace_lock();
 	lock_mount_hash();
-	umount_tree(real_mount(mnt), UMOUNT_SYNC);
+	umount_tree(real_mount(mnt), 0);
 	unlock_mount_hash();
 	namespace_unlock();
 }

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

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

From: Frank Sorenson <[email protected]>

commit 5d7a5bcb67c70cbc904057ef52d3fcfeb24420bb upstream.

When truncating the encode buffer, the page_ptr is getting advanced, causing the next page to be skipped while encoding. The page is still included in the response, so the response contains a page of bogus data.

We need to adjust the page_ptr backwards to ensure we encode the next page into the correct place.

We saw this triggered when concurrent directory modifications caused nfsd4_encode_direct_fattr() to return nfserr_noent, and the resulting call to xdr_truncate_encode() corrupted the READDIR reply.

---
 net/sunrpc/xdr.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

@@ -639,11 +639,10 @@ void xdr_truncate_encode(struct xdr_stre
 		WARN_ON_ONCE(xdr->iov);
 		return;
 	}
-	if (fraglen) {
+	if (fraglen)
 		xdr->end = head->iov_base + head->iov_len;
-		xdr->page_ptr--;
-	}
 	/* (otherwise assume xdr->end is already set) */
+	xdr->page_ptr--;
 	head->iov_len = len;
 	buf->len = len;
 	xdr->p = head->iov_base + head->iov_len;

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

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

From: Maciej W. Rozycki <[email protected]>

commit 7ce9a992ffde8ce93d5ae5767362a5c7389ae895 upstream.

Fix an issue with the 32-bit range error path in rtc_hctosys' where no error code is set and consequently the successful preceding call result from rtc_read_time' is propagated to rtc_hctosys_ret'. This in turn makes any subsequent call to hctosys_show' incorrectly report in sysfs that the system time has been set from this RTC while it has not.

Set the error to ERANGE then if we can't express the result due to an overflow.

---
 drivers/rtc/hctosys.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -50,8 +50,10 @@ static int __init rtc_hctosys(void)
 	tv64.tv_sec = rtc_tm_to_time64(&tm);
 
 #if BITS_PER_LONG == 32
-	if (tv64.tv_sec > INT_MAX)
+	if (tv64.tv_sec > INT_MAX) {
+		err = -ERANGE;
 		goto err_read;
+	}
 #endif
 
 	err = do_settimeofday64(&tv64);

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

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

From: Guenter Roeck <[email protected]>

commit 1823342a1f2b47a4e6f5667f67cd28ab6bc4d6cd upstream.

gcc 8.1.0 complains:

fs/configfs/symlink.c:67:3: warning:
'strncpy' output truncated before terminating nul copying as many bytes from a string as its length
fs/configfs/symlink.c: In function 'configfs_get_link':
fs/configfs/symlink.c:63:13: note: length computed here

Using strncpy() is indeed less than perfect since the length of data to be copied has already been determined with strlen(). Replace strncpy() with memcpy() to address the warning and optimize the code a little.

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

@@ -64,7 +64,7 @@ static void fill_item_path(struct config
 
 		/* back up enough to print this bus id with '/' */
 		length -= cur;
-		strncpy(buffer + length,config_item_name(p),cur);
+		memcpy(buffer + length, config_item_name(p), cur);
 		*(buffer + --length) = '/';
 	}
 }

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

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

From: Mike Kravetz <[email protected]>

commit 017b1660df89f5fb4bfe66c34e35f7d2031100c7 upstream.

The page migration code employs try_to_unmap() to try and unmap the source page. This is accomplished by using rmap_walk to find all vmas where the page is mapped. This search stops when page mapcount is zero. For shared PMD huge pages, the page map count is always 1 no matter the number of mappings. Shared mappings are tracked via the reference count of the PMD page. Therefore, try_to_unmap stops prematurely and does not completely unmap all mappings of the source page.

This problem can result is data corruption as writes to the original source page can happen after contents of the page are copied to the target page. Hence, data is lost.

This problem was originally seen as DB corruption of shared global areas after a huge page was soft offlined due to ECC memory errors. DB developers noticed they could reproduce the issue by (hotplug) offlining memory used to back huge pages. A simple testcase can reproduce the problem by creating a shared PMD mapping (note that this must be at least PUD_SIZE in size and PUD_SIZE aligned (1GB on x86)), and using migrate_pages() to migrate process pages between nodes while continually writing to the huge pages being migrated.

To fix, have the try_to_unmap_one routine check for huge PMD sharing by calling huge_pmd_unshare for hugetlbfs huge pages. If it is a shared mapping it will be 'unshared' which removes the page table entry and drops the reference on the PMD page. After this, flush caches and TLB.

mmu notifiers are called before locking page tables, but we can not be sure of PMD sharing until page tables are locked. Therefore, check for the possibility of PMD sharing before locking so that notifiers can prepare for the worst possible case.

---
 include/linux/hugetlb.h |   14 ++++++++++++
 include/linux/mm.h      |    6 +++++
 mm/hugetlb.c            |   37 ++++++++++++++++++++++++++++++-
 mm/rmap.c               |   56 ++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 111 insertions(+), 2 deletions(-)

@@ -109,6 +109,8 @@ pte_t *huge_pte_alloc(struct mm_struct *
 			unsigned long addr, unsigned long sz);
 pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr);
 int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep);
+void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end);
 struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
 			      int write);
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,

@@ -131,6 +133,18 @@ static inline unsigned long hugetlb_tota
 	return 0;
 }
 
+static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr,
+						pte_t *ptep)
+{
+	return 0;
+}
+
+static inline void adjust_range_if_pmd_sharing_possible(
+				struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
+{
+}
+
 #define follow_hugetlb_page(m,v,p,vs,a,b,i,w)	({ BUG(); 0; })
 #define follow_huge_addr(mm, addr, write)	ERR_PTR(-EINVAL)
 #define copy_hugetlb_page_range(src, dst, vma)	({ BUG(); 0; })

@@ -2187,6 +2187,12 @@ static inline struct vm_area_struct *fin
 	return vma;
 }
 
+static inline bool range_in_vma(struct vm_area_struct *vma,
+				unsigned long start, unsigned long end)
+{
+	return (vma && vma->vm_start <= start && end <= vma->vm_end);
+}
+
 #ifdef CONFIG_MMU
 pgprot_t vm_get_page_prot(unsigned long vm_flags);
 void vma_set_page_prot(struct vm_area_struct *vma);

@@ -4333,13 +4333,41 @@ static bool vma_shareable(struct vm_area
 	/*
 	 * check on proper vm_flags and page table alignment
 	 */
-	if (vma->vm_flags & VM_MAYSHARE &&
-	    vma->vm_start <= base && end <= vma->vm_end)
+	if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, base, end))
 		return true;
 	return false;
 }
 
 /*
+ * Determine if start,end range within vma could be mapped by shared pmd.
+ * If yes, adjust start and end to cover range associated with possible
+ * shared pmd mappings.
+ */
+void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
+{
+	unsigned long check_addr = *start;
+
+	if (!(vma->vm_flags & VM_MAYSHARE))
+		return;
+
+	for (check_addr = *start; check_addr < *end; check_addr += PUD_SIZE) {
+		unsigned long a_start = check_addr & PUD_MASK;
+		unsigned long a_end = a_start + PUD_SIZE;
+
+		/*
+		 * If sharing is possible, adjust start/end if necessary.
+		 */
+		if (range_in_vma(vma, a_start, a_end)) {
+			if (a_start < *start)
+				*start = a_start;
+			if (a_end > *end)
+				*end = a_end;
+		}
+	}
+}
+
+/*
  * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
  * and returns the corresponding pte. While this is not necessary for the
  * !shared pmd case because we can allocate the pmd later as well, it makes the

@@ -4435,6 +4463,11 @@ int huge_pmd_unshare(struct mm_struct *m
 {
 	return 0;
 }
+
+void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
+{
+}
 #define want_pmd_share()	(0)
 #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */
 

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

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

From: Stanislav Lisovskiy <[email protected]>

commit 23d8003907d094f77cf959228e2248d6db819fa7 upstream.

Unfortunately drm_dp_get_mst_branch_device which is called from both drm_dp_mst_handle_down_rep and drm_dp_mst_handle_up_rep seem to rely on that mgr->mst_primary is not NULL, which seem to be wrong as it can be cleared with simultaneous mode set, if probing fails or in other case. mgr->lock mutex doesn't protect against that as it might just get assigned to NULL right before, not simultaneously.

There are currently bugs 107738, 108616 bugs which crash in drm_dp_get_mst_branch_device, caused by this issue.

v2: Refactored the code, as it was nicely noticed.
Fixed Bugzilla bug numbers(second was 108616, but not 108816) and added links.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108616
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107738

---
 drivers/gpu/drm/drm_dp_mst_topology.c |    3 +++
 1 file changed, 3 insertions(+)

@@ -1230,6 +1230,9 @@ static struct drm_dp_mst_branch *drm_dp_
 	mutex_lock(&mgr->lock);
 	mstb = mgr->mst_primary;
 
+	if (!mstb)
+		goto out;
+
 	for (i = 0; i < lct - 1; i++) {
 		int shift = (i % 2) ? 0 : 4;
 		int port_num = (rad[i / 2] >> shift) & 0xf;

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

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

From: Young_X <[email protected]>

commit e4f3aa2e1e67bb48dfbaaf1cad59013d5a5bc276 upstream.

There is another cast from unsigned long to int which causes a bounds check to fail with specially crafted input. The value is then used as an index in the slot array in cdrom_slot_status().

This issue is similar to CVE-2018-16658 and CVE-2018-10940.

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

@@ -2435,7 +2435,7 @@ static int cdrom_ioctl_select_disc(struc
 		return -ENOSYS;
 
 	if (arg != CDSL_CURRENT && arg != CDSL_NONE) {
-		if ((int)arg >= cdi->capacity)
+		if (arg >= cdi->capacity)
 			return -EINVAL;
 	}
 

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

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

From: Himanshu Madhani <[email protected]>

commit 4c1458df9635c7e3ced155f594d2e7dfd7254e21 upstream.

---
 drivers/scsi/qla2xxx/qla_mbx.c |    5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

@@ -3580,10 +3580,7 @@ qla2x00_set_idma_speed(scsi_qla_host_t *
 	mcp->mb[0] = MBC_PORT_PARAMS;
 	mcp->mb[1] = loop_id;
 	mcp->mb[2] = BIT_0;
-	if (IS_CNA_CAPABLE(vha->hw))
-		mcp->mb[3] = port_speed & (BIT_5|BIT_4|BIT_3|BIT_2|BIT_1|BIT_0);
-	else
-		mcp->mb[3] = port_speed & (BIT_2|BIT_1|BIT_0);
+	mcp->mb[3] = port_speed & (BIT_5|BIT_4|BIT_3|BIT_2|BIT_1|BIT_0);
 	mcp->mb[9] = vha->vp_idx;
 	mcp->out_mb = MBX_9|MBX_3|MBX_2|MBX_1|MBX_0;
 	mcp->in_mb = MBX_3|MBX_1|MBX_0;

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

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

From: Quinn Tran <[email protected]>

commit 1e4ac5d6fe0a4af17e4b6251b884485832bf75a3 upstream.

If chip unable to fully initialize, use full shutdown sequence to clear out any stale FW state.

---
 drivers/scsi/qla2xxx/qla_init.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -4894,7 +4894,7 @@ qla2x00_abort_isp(scsi_qla_host_t *vha)
 					 * The next call disables the board
 					 * completely.
 					 */
-					ha->isp_ops->reset_adapter(vha);
+					qla2x00_abort_isp_cleanup(vha);
 					vha->flags.online = 0;
 					clear_bit(ISP_ABORT_RETRY,
 					    &vha->dpc_flags);

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

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

From: Kirill Tkhai <[email protected]>

commit bc78abbd55dd28e2287ec6d6502b842321a17c87 upstream.

We may pick freed req in this way:

[cpu0]                                  [cpu1]
fuse_dev_do_read()                      fuse_dev_do_write()
   list_move_tail(&req->list, ...);     ...
   spin_unlock(&fpq->lock);             ...
   ...                                  request_end(fc, req);
   ...                                    fuse_put_request(fc, req);
   if (test_bit(FR_INTERRUPTED, ...))
         queue_interrupt(fiq, req);

Fix that by keeping req alive until we finish all manipulations.

---
 fs/fuse/dev.c |    2 ++
 1 file changed, 2 insertions(+)

@@ -1303,12 +1303,14 @@ static ssize_t fuse_dev_do_read(struct f
 		goto out_end;
 	}
 	list_move_tail(&req->list, &fpq->processing);
+	__fuse_get_request(req);
 	spin_unlock(&fpq->lock);
 	set_bit(FR_SENT, &req->flags);
 	/* matches barrier in request_wait_answer() */
 	smp_mb__after_atomic();
 	if (test_bit(FR_INTERRUPTED, &req->flags))
 		queue_interrupt(fiq, req);
+	fuse_put_request(fc, req);
 
 	return reqsize;
 

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

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

From: Kirill Tkhai <[email protected]>

commit d2d2d4fb1f54eff0f3faa9762d84f6446a4bc5d0 upstream.

After we found req in request_find() and released the lock, everything may happen with the req in parallel:

cpu0                              cpu1
fuse_dev_do_write()               fuse_dev_do_write()
  req = request_find(fpq, ...)    ...
  spin_unlock(&fpq->lock)         ...
  ...                             req = request_find(fpq, oh.unique)
  ...                             spin_unlock(&fpq->lock)
  queue_interrupt(&fc->iq, req);   ...
  ...                              ...
  ...                              ...
  request_end(fc, req);
    fuse_put_request(fc, req);

... queue_interrupt(&fc->iq, req);

---
 fs/fuse/dev.c |    6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

@@ -1868,16 +1868,20 @@ static ssize_t fuse_dev_do_write(struct
 
 	/* Is it an interrupt reply? */
 	if (req->intr_unique == oh.unique) {
+		__fuse_get_request(req);
 		spin_unlock(&fpq->lock);
 
 		err = -EINVAL;
-		if (nbytes != sizeof(struct fuse_out_header))
+		if (nbytes != sizeof(struct fuse_out_header)) {
+			fuse_put_request(fc, req);
 			goto err_finish;
+		}
 
 		if (oh.error == -ENOSYS)
 			fc->no_interrupt = 1;
 		else if (oh.error == -EAGAIN)
 			queue_interrupt(&fc->iq, req);
+		fuse_put_request(fc, req);
 
 		fuse_copy_finish(cs);
 		return nbytes;

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

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

From: Miklos Szeredi <[email protected]>

commit 908a572b80f6e9577b45e81b3dfe2e22111286b8 upstream.

Using waitqueue_active() is racy. Make sure we issue a wake_up() unconditionally after storing into fc->blocked. After that it's okay to optimize with waitqueue_active() since the first wake up provides the necessary barrier for all waiters, not the just the woken one.

---
 fs/fuse/dev.c |   15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

@@ -383,12 +383,19 @@ static void request_end(struct fuse_conn
 	if (test_bit(FR_BACKGROUND, &req->flags)) {
 		spin_lock(&fc->lock);
 		clear_bit(FR_BACKGROUND, &req->flags);
-		if (fc->num_background == fc->max_background)
+		if (fc->num_background == fc->max_background) {
 			fc->blocked = 0;
-
-		/* Wake up next waiter, if any */
-		if (!fc->blocked && waitqueue_active(&fc->blocked_waitq))
 			wake_up(&fc->blocked_waitq);
+		} else if (!fc->blocked) {
+			/*
+			 * Wake up next waiter, if any.  It's okay to use
+			 * waitqueue_active(), as we've already synced up
+			 * fc->blocked with waiters with the wake_up() call
+			 * above.
+			 */
+			if (waitqueue_active(&fc->blocked_waitq))
+				wake_up(&fc->blocked_waitq);
+		}
 
 		if (fc->num_background == fc->congestion_threshold &&
 		    fc->connected && fc->bdi_initialized) {

This is the start of the stable review cycle for the 4.9.138 release. There are 83 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Wed Nov 21 16:25:13 UTC 2018. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	https://www.kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.9.138-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-4.9.y
and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <[email protected]>

    Linux 4.9.138-rc1

Mark Rutland <[email protected]>
KVM: arm64: Fix caching of host MDCR_EL2 value

Chris Wilson <[email protected]>
drm/i915/execlists: Force write serialisation into context image vs execution

Clint Taylor <[email protected]>
drm/i915/hdmi: Add HDMI 2.0 audio clock recovery N values

Stanislav Lisovskiy <[email protected]>
drm/dp_mst: Check if primary mstb is null

Marc Zyngier <[email protected]>
drm/rockchip: Allow driver to be shutdown on reboot/kexec

Mike Kravetz <[email protected]>
mm: migration: fix migration of huge PMD shared pages

Mike Kravetz <[email protected]>
hugetlbfs: fix kernel BUG at fs/hugetlbfs/inode.c:444!

Arnd Bergmann <[email protected]>
lib/ubsan.c: don't mark __ubsan_handle_builtin_unreachable as noreturn

Guenter Roeck <[email protected]>
configfs: replace strncpy with memcpy

Miklos Szeredi <[email protected]>
fuse: fix leaked notify reply

Lukas Czerner <[email protected]>
fuse: fix use-after-free in fuse_direct_IO()

Maciej W. Rozycki <[email protected]>
rtc: hctosys: Add missing range error reporting

Scott Mayhew <[email protected]>
nfsd: COPY and CLONE operations require the saved filehandle to be set

Frank Sorenson <[email protected]>
sunrpc: correct the computation for page_ptr when truncating

Eric W. Biederman <[email protected]>
mount: Prevent MNT_DETACH from disconnecting locked mounts

Eric W. Biederman <[email protected]>
mount: Don't allow copying MNT_UNBINDABLE|MNT_LOCKED mounts

Eric W. Biederman <[email protected]>
mount: Retest MNT_LOCKED in do_umount

Vasily Averin <[email protected]>
ext4: fix buffer leak in __ext4_read_dirblock() on error path

Vasily Averin <[email protected]>
ext4: fix buffer leak in ext4_xattr_move_to_block() on error path

Vasily Averin <[email protected]>
ext4: release bs.bh before re-using in ext4_xattr_block_find()

Vasily Averin <[email protected]>
ext4: fix possible leak of s_journal_flag_rwsem in error path

Theodore Ts'o <[email protected]>

    ext4: fix possible leak of sbi->s_group_desc_leak in error path

Theodore Ts'o <[email protected]>
ext4: avoid possible double brelse() in add_new_gdb() on error path

Vasily Averin <[email protected]>
ext4: fix missing cleanup if ext4_alloc_flex_bg_array() fails while resizing

Vasily Averin <[email protected]>
ext4: avoid buffer leak in ext4_orphan_add() after prior errors

Vasily Averin <[email protected]>
ext4: fix possible inode leak in the retry loop of ext4_resize_fs()

Vasily Averin <[email protected]>
ext4: avoid potential extra brelse in setup_new_flex_group_blocks()

Vasily Averin <[email protected]>
ext4: add missing brelse() add_new_gdb_meta_bg()'s error path

Vasily Averin <[email protected]>
ext4: add missing brelse() in set_flexbg_block_bitmap()'s error path

Vasily Averin <[email protected]>
ext4: add missing brelse() update_backups()'s error path

Michael Kelley <[email protected]>
clockevents/drivers/i8253: Add support for PIT shutdown quirk

Filipe Manana <[email protected]>
Btrfs: fix data corruption due to cloning of eof block

Robbie Ko <[email protected]>
Btrfs: fix cur_offset in the error case for nocow

H. Peter Anvin (Intel) <[email protected]>
arch/alpha, termios: implement BOTHER, IBSHIFT and termios2

H. Peter Anvin <[email protected]>
termios, tty/tty_baudrate.c: fix buffer overrun

John Garry <[email protected]>
of, numa: Validate some distance map rules

Arnd Bergmann <[email protected]>
mtd: docg3: don't set conflicting BCH_CONST_PARAMS option

Vasily Khoruzhick <[email protected]>
netfilter: conntrack: fix calculation of next bucket number in early_drop

Andrea Arcangeli <[email protected]>
mm: thp: relax __GFP_THISNODE for MADV_HUGEPAGE mappings

Changwei Ge <[email protected]>
ocfs2: fix a misuse a of brelse after failing ocfs2_check_dir_entry

Greg Edwards <[email protected]>
vhost/scsi: truncate T10 PI iov_iter to prot_bytes

Gustavo A. R. Silva <[email protected]>
reset: hisilicon: fix potential NULL pointer dereference

Mikulas Patocka <[email protected]>
mach64: fix image corruption due to reading accelerator registers

Mikulas Patocka <[email protected]>
mach64: fix display corruption on big endian machines

Yan, Zheng <[email protected]>
Revert "ceph: fix dentry leak in splice_dentry()"

Ilya Dryomov <[email protected]>
libceph: bump CEPH_MSG_MAX_DATA_LEN

Enric Balletbo i Serra <[email protected]>
clk: rockchip: Fix static checker warning in rockchip_ddrclk_get_parent call

Ronald Wahl <[email protected]>
clk: at91: Fix division by zero in PLL recalc_rate()

Krzysztof Kozlowski <[email protected]>
clk: s2mps11: Fix matching when built as module and DT node contains compatible

Max Filippov <[email protected]>
xtensa: fix boot parameters address translation

Max Filippov <[email protected]>
xtensa: make sure bFLT stack is 16 byte aligned

Max Filippov <[email protected]>
xtensa: add NOTES section to the linker script

Huacai Chen <[email protected]>
MIPS: Loongson-3: Fix BRIDGE irq delivery problem

Huacai Chen <[email protected]>
MIPS: Loongson-3: Fix CPU UART irq delivery problem

Helge Deller <[email protected]>
parisc: Fix exported address of os_hpmc handler

Helge Deller <[email protected]>
parisc: Fix HPMC handler by increasing size to multiple of 16 bytes

Helge Deller <[email protected]>
parisc: Align os_hpmc_size on word boundary

Kees Cook <[email protected]>
bna: ethtool: Avoid reading past end of buffer

Vincenzo Maffione <[email protected]>

    e1000: fix race condition between e1000_down() and e1000_watchdog

Colin Ian King <[email protected]>
e1000: avoid null pointer dereference on invalid stat type

Michal Hocko <[email protected]>
mm: do not bug_on on incorrect length in __mm_populate()

Miklos Szeredi <[email protected]>
fuse: set FR_SENT while locked

Miklos Szeredi <[email protected]>
fuse: fix blocked_waitq wakeup

Kirill Tkhai <[email protected]>
fuse: Fix use-after-free in fuse_dev_do_write()

Kirill Tkhai <[email protected]>
fuse: Fix use-after-free in fuse_dev_do_read()

Quinn Tran <[email protected]>
scsi: qla2xxx: shutdown chip if reset fail

Himanshu Madhani <[email protected]>
scsi: qla2xxx: Fix incorrect port speed being set for FC adapters

Young_X <[email protected]>
cdrom: fix improper type cast, which can leat to information leak.

Dominique Martinet <[email protected]>
9p: clear dangling pointers in p9stat_free

Dominique Martinet <[email protected]>
9p locks: fix glock.client_id leak in do_lock

Breno Leitao <[email protected]>
powerpc/selftests: Wait all threads to join

Marco Felsch <[email protected]>
media: tvp5150: fix width alignment during set_selection()

Phil Elwell <[email protected]>
sc16is7xx: Fix for multi-channel stall

Huacai Chen <[email protected]>
MIPS/PCI: Call pcie_bus_configure_settings() to set MPS/MRRS

Joel Stanley <[email protected]>
powerpc/boot: Ensure _zimage_start is a weak symbol

Dengcheng Zhu <[email protected]>
MIPS: kexec: Mark CPU offline before disabling local IRQ

Nicholas Mc Guire <[email protected]>
media: pci: cx23885: handle adding to list failure

Tomi Valkeinen <[email protected]>
drm/omap: fix memory barrier bug in DMM driver

Daniel Axtens <[email protected]>
powerpc/nohash: fix undefined behaviour when testing page size support

Fabio Estevam <[email protected]>
ARM: imx_v6_v7_defconfig: Select CONFIG_TMPFS_POSIX_ACL

Miles Chen <[email protected]>
tty: check name length in tty_find_polling_driver()

Sam Bobroff <[email protected]>
powerpc/eeh: Fix possible null deref in eeh_dump_dev_log()

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

Diffstat:

 Makefile                                         |  4 +-
 arch/alpha/include/asm/termios.h                 |  8 +++-
 arch/alpha/include/uapi/asm/ioctls.h             |  5 ++
 arch/alpha/include/uapi/asm/termbits.h           | 17 +++++++
 arch/arm/configs/imx_v6_v7_defconfig             |  1 +
 arch/arm/kvm/arm.c                               |  4 +-
 arch/mips/include/asm/mach-loongson64/irq.h      |  2 +-
 arch/mips/kernel/crash.c                         |  3 ++
 arch/mips/kernel/machine_kexec.c                 |  3 ++
 arch/mips/loongson64/loongson-3/irq.c            | 56 +++-------------------
 arch/mips/pci/pci-legacy.c                       |  4 ++
 arch/parisc/kernel/hpmc.S                        | 10 ++--
 arch/powerpc/boot/crt0.S                         |  4 +-
 arch/powerpc/kernel/eeh.c                        |  5 ++
 arch/powerpc/mm/tlb_nohash.c                     |  3 ++
 arch/xtensa/boot/Makefile                        |  2 +-
 arch/xtensa/include/asm/processor.h              |  6 ++-
 arch/xtensa/kernel/head.S                        |  7 ++-
 arch/xtensa/kernel/vmlinux.lds.S                 |  1 +
 drivers/cdrom/cdrom.c                            |  2 +-
 drivers/clk/at91/clk-pll.c                       |  3 ++
 drivers/clk/clk-s2mps11.c                        | 30 ++++++++++++
 drivers/clk/hisilicon/reset.c                    |  5 +-
 drivers/clk/rockchip/clk-ddr.c                   |  4 --
 drivers/clocksource/i8253.c                      | 14 +++++-
 drivers/gpu/drm/drm_dp_mst_topology.c            |  3 ++
 drivers/gpu/drm/i915/intel_audio.c               | 17 +++++++
 drivers/gpu/drm/i915/intel_lrc.c                 | 14 +++++-
 drivers/gpu/drm/omapdrm/omap_dmm_tiler.c         | 11 +++++
 drivers/gpu/drm/rockchip/rockchip_drm_drv.c      |  6 +++
 drivers/media/i2c/tvp5150.c                      | 14 ++++--
 drivers/media/pci/cx23885/altera-ci.c            | 10 ++++
 drivers/mtd/devices/Kconfig                      |  2 +-
 drivers/net/ethernet/brocade/bna/bnad_ethtool.c  |  4 +-
 drivers/net/ethernet/intel/e1000/e1000_ethtool.c |  9 ++--
 drivers/net/ethernet/intel/e1000/e1000_main.c    | 11 ++++-
 drivers/of/of_numa.c                             |  9 +++-
 drivers/rtc/hctosys.c                            |  4 +-
 drivers/scsi/qla2xxx/qla_init.c                  |  2 +-
 drivers/scsi/qla2xxx/qla_mbx.c                   |  5 +-
 drivers/tty/serial/sc16is7xx.c                   | 19 +++++---
 drivers/tty/tty_io.c                             |  2 +-
 drivers/tty/tty_ioctl.c                          |  4 +-
 drivers/vhost/scsi.c                             |  4 +-
 drivers/video/fbdev/aty/mach64_accel.c           | 28 +++++------
 fs/9p/vfs_file.c                                 | 16 ++++++-
 fs/btrfs/inode.c                                 |  5 +-
 fs/btrfs/ioctl.c                                 | 12 ++++-
 fs/ceph/inode.c                                  |  8 +++-
 fs/configfs/symlink.c                            |  2 +-
 fs/ext4/namei.c                                  |  5 +-
 fs/ext4/resize.c                                 | 28 ++++++-----
 fs/ext4/super.c                                  | 17 +++----
 fs/ext4/xattr.c                                  |  4 ++
 fs/fuse/dev.c                                    | 29 +++++++++---
 fs/fuse/file.c                                   |  4 +-
 fs/namespace.c                                   | 22 +++++++--
 fs/nfsd/nfs4proc.c                               |  3 ++
 fs/ocfs2/dir.c                                   |  3 +-
 include/linux/ceph/libceph.h                     |  8 +++-
 include/linux/hugetlb.h                          | 14 ++++++
 include/linux/i8253.h                            |  1 +
 include/linux/mm.h                               |  6 +++
 lib/ubsan.c                                      |  3 +-
 mm/gup.c                                         |  2 -
 mm/hugetlb.c                                     | 60 +++++++++++++++++++++---
 mm/mempolicy.c                                   | 32 ++++++++++++-
 mm/mmap.c                                        | 19 ++++----
 mm/rmap.c                                        | 56 ++++++++++++++++++++++
 net/9p/protocol.c                                |  5 ++
 net/netfilter/nf_conntrack_core.c                | 13 +++--
 net/sunrpc/xdr.c                                 |  5 +-
 tools/testing/selftests/powerpc/tm/tm-tmspr.c    | 27 +++++++----
 73 files changed, 580 insertions(+), 210 deletions(-)

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

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

From: Mikulas Patocka <[email protected]>

commit 3c6c6a7878d00a3ac997a779c5b9861ff25dfcc8 upstream.

The code for manual bit triple is not endian-clean. It builds the variable "hostdword" using byte accesses, therefore we must read the variable with "le32_to_cpu".

The patch also enables (hardware or software) bit triple only if the image is monochrome (image->depth). If we want to blit full-color image, we shouldn't use the triple code.

---
 drivers/video/fbdev/aty/mach64_accel.c |    6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

@@ -344,7 +344,7 @@ void atyfb_imageblit(struct fb_info *inf
 		 * since Rage 3D IIc we have DP_HOST_TRIPLE_EN bit
 		 * this hwaccelerated triple has an issue with not aligned data
 		 */
-		if (M64_HAS(HW_TRIPLE) && image->width % 8 == 0)
+		if (image->depth == 1 && M64_HAS(HW_TRIPLE) && image->width % 8 == 0)
 			pix_width |= DP_HOST_TRIPLE_EN;
 	}
 

@@ -381,7 +381,7 @@ void atyfb_imageblit(struct fb_info *inf
 	src_bytes = (((image->width * image->depth) + 7) / 8) * image->height;
 
 	/* manual triple each pixel */
-	if (info->var.bits_per_pixel == 24 && !(pix_width & DP_HOST_TRIPLE_EN)) {
+	if (image->depth == 1 && info->var.bits_per_pixel == 24 && !(pix_width & DP_HOST_TRIPLE_EN)) {
 		int inbit, outbit, mult24, byte_id_in_dword, width;
 		u8 *pbitmapin = (u8*)image->data, *pbitmapout;
 		u32 hostdword;

@@ -414,7 +414,7 @@ void atyfb_imageblit(struct fb_info *inf
 				}
 			}
 			wait_for_fifo(1, par);
-			aty_st_le32(HOST_DATA0, hostdword, par);
+			aty_st_le32(HOST_DATA0, le32_to_cpu(hostdword), par);
 		}
 	} else {
 		u32 *pbitmap, dwords = (src_bytes + 3) / 4;

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

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

From: Mikulas Patocka <[email protected]>

commit c09bcc91bb94ed91f1391bffcbe294963d605732 upstream.

Reading the registers without waiting for engine idle returns unpredictable values. These unpredictable values result in display corruption - if atyfb_imageblit reads the content of DP_PIX_WIDTH with the bit DP_HOST_TRIPLE_EN set (from previous invocation), the driver would never ever clear the bit, resulting in display corruption.

We don't want to wait for idle because it would degrade performance, so this patch modifies the driver so that it never reads accelerator registers.

HOST_CNTL doesn't have to be read, we can just write it with HOST_BYTE_ALIGN because no other part of the driver cares if HOST_BYTE_ALIGN is set.

DP_PIX_WIDTH is written in the functions atyfb_copyarea and atyfb_fillrect with the default value and in atyfb_imageblit with the value set according to the source image data.

---
 drivers/video/fbdev/aty/mach64_accel.c |   22 +++++++++-------------
 1 file changed, 9 insertions(+), 13 deletions(-)

@@ -126,7 +126,7 @@ void aty_init_engine(struct atyfb_par *p
 
 	/* set host attributes */
 	wait_for_fifo(13, par);
-	aty_st_le32(HOST_CNTL, 0, par);
+	aty_st_le32(HOST_CNTL, HOST_BYTE_ALIGN, par);
 
 	/* set pattern attributes */
 	aty_st_le32(PAT_REG0, 0, par);

@@ -232,7 +232,8 @@ void atyfb_copyarea(struct fb_info *info
 		rotation = rotation24bpp(dx, direction);
 	}
 
-	wait_for_fifo(4, par);
+	wait_for_fifo(5, par);
+	aty_st_le32(DP_PIX_WIDTH, par->crtc.dp_pix_width, par);
 	aty_st_le32(DP_SRC, FRGD_SRC_BLIT, par);
 	aty_st_le32(SRC_Y_X, (sx << 16) | sy, par);
 	aty_st_le32(SRC_HEIGHT1_WIDTH1, (width << 16) | area->height, par);

@@ -268,7 +269,8 @@ void atyfb_fillrect(struct fb_info *info
 		rotation = rotation24bpp(dx, DST_X_LEFT_TO_RIGHT);
 	}
 
-	wait_for_fifo(3, par);
+	wait_for_fifo(4, par);
+	aty_st_le32(DP_PIX_WIDTH, par->crtc.dp_pix_width, par);
 	aty_st_le32(DP_FRGD_CLR, color, par);
 	aty_st_le32(DP_SRC,
 		    BKGD_SRC_BKGD_CLR | FRGD_SRC_FRGD_CLR | MONO_SRC_ONE,

@@ -283,7 +285,7 @@ void atyfb_imageblit(struct fb_info *inf
 {
 	struct atyfb_par *par = (struct atyfb_par *) info->par;
 	u32 src_bytes, dx = image->dx, dy = image->dy, width = image->width;
-	u32 pix_width_save, pix_width, host_cntl, rotation = 0, src, mix;
+	u32 pix_width, rotation = 0, src, mix;
 
 	if (par->asleep)
 		return;

@@ -295,8 +297,7 @@ void atyfb_imageblit(struct fb_info *inf
 		return;
 	}
 
-	pix_width = pix_width_save = aty_ld_le32(DP_PIX_WIDTH, par);
-	host_cntl = aty_ld_le32(HOST_CNTL, par) | HOST_BYTE_ALIGN;
+	pix_width = par->crtc.dp_pix_width;
 
 	switch (image->depth) {
 	case 1:

@@ -369,12 +370,11 @@ void atyfb_imageblit(struct fb_info *inf
 		mix = FRGD_MIX_D_XOR_S | BKGD_MIX_D;
 	}
 
-	wait_for_fifo(6, par);
-	aty_st_le32(DP_WRITE_MASK, 0xFFFFFFFF, par);
+	wait_for_fifo(5, par);
 	aty_st_le32(DP_PIX_WIDTH, pix_width, par);
 	aty_st_le32(DP_MIX, mix, par);
 	aty_st_le32(DP_SRC, src, par);
-	aty_st_le32(HOST_CNTL, host_cntl, par);
+	aty_st_le32(HOST_CNTL, HOST_BYTE_ALIGN, par);
 	aty_st_le32(DST_CNTL, DST_Y_TOP_TO_BOTTOM | DST_X_LEFT_TO_RIGHT | rotation, par);
 
 	draw_rect(dx, dy, width, image->height, par);

@@ -423,8 +423,4 @@ void atyfb_imageblit(struct fb_info *inf
 			aty_st_le32(HOST_DATA0, get_unaligned_le32(pbitmap), par);
 		}
 	}
-
-	/* restore pix_width */
-	wait_for_fifo(1, par);
-	aty_st_le32(DP_PIX_WIDTH, pix_width_save, par);
 }

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

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

From: Gustavo A. R. Silva <[email protected]>

commit e9a2310fb689151166df7fd9971093362d34bd79 upstream.

There is a potential execution path in which function platform_get_resource() returns NULL. If this happens, we will end up having a NULL pointer dereference.

Fix this by replacing devm_ioremap with devm_ioremap_resource, which has the NULL check and the memory region request.

This code was detected with the help of Coccinelle.

---
 drivers/clk/hisilicon/reset.c |    5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

@@ -109,9 +109,8 @@ struct hisi_reset_controller *hisi_reset
 		return NULL;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	rstc->membase = devm_ioremap(&pdev->dev,
-				res->start, resource_size(res));
-	if (!rstc->membase)
+	rstc->membase = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(rstc->membase))
 		return NULL;
 
 	spin_lock_init(&rstc->lock);

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

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

From: Greg Edwards <[email protected]>

commit 4542d623c7134bc1738f8a68ccb6dd546f1c264f upstream.

Commands with protection information included were not truncating the protection iov_iter to the number of protection bytes in the command. This resulted in vhost_scsi mis-calculating the size of the protection SGL in vhost_scsi_calc_sgls(), and including both the protection and data SG entries in the protection SGL.

---
 drivers/vhost/scsi.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -999,7 +999,8 @@ vhost_scsi_handle_vq(struct vhost_scsi *
 				prot_bytes = vhost32_to_cpu(vq, v_req_pi.pi_bytesin);
 			}
 			/*
-			 * Set prot_iter to data_iter, and advance past any
+			 * Set prot_iter to data_iter and truncate it to
+			 * prot_bytes, and advance data_iter past any
 			 * preceeding prot_bytes that may be present.
 			 *
 			 * Also fix up the exp_data_len to reflect only the

@@ -1008,6 +1009,7 @@ vhost_scsi_handle_vq(struct vhost_scsi *
 			if (prot_bytes) {
 				exp_data_len -= prot_bytes;
 				prot_iter = data_iter;
+				iov_iter_truncate(&prot_iter, prot_bytes);
 				iov_iter_advance(&data_iter, prot_bytes);
 			}
 			tag = vhost64_to_cpu(vq, v_req_pi.tag);

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

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

From: Changwei Ge <[email protected]>

commit 29aa30167a0a2e6045a0d6d2e89d8168132333d5 upstream.

Somehow, file system metadata was corrupted, which causes ocfs2_check_dir_entry() to fail in function ocfs2_dir_foreach_blk_el().

According to the original design intention, if above happens we should skip the problematic block and continue to retrieve dir entry. But there is obviouse misuse of brelse around related code.

After failure of ocfs2_check_dir_entry(), current code just moves to next position and uses the problematic buffer head again and again during which the problematic buffer head is released for multiple times. I suppose, this a serious issue which is long-lived in ocfs2. This may cause other file systems which is also used in a the same host insane.

So we should also consider about bakcporting this patch into linux -stable.

---
 fs/ocfs2/dir.c |    3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

@@ -1896,8 +1896,7 @@ static int ocfs2_dir_foreach_blk_el(stru
 				/* On error, skip the f_pos to the
 				   next block. */
 				ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1;
-				brelse(bh);
-				continue;
+				break;
 			}
 			if (le64_to_cpu(de->inode)) {
 				unsigned char d_type = DT_UNKNOWN;

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

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

From: Andrea Arcangeli <[email protected]>

commit ac5b2c18911ffe95c08d69273917f90212cf5659 upstream.

THP allocation might be really disruptive when allocated on NUMA system with the local node full or hard to reclaim. Stefan has posted an allocation stall report on 4.12 based SLES kernel which suggests the same issue:

kvm: page allocation stalls for 194572ms, order:9, mode:0x4740ca(__GFP_HIGHMEM|__GFP_IO|__GFP_FS|__GFP_COMP|__GFP_NOMEMALLOC|__GFP_HARDWALL|__GFP_THISNODE|__GFP_MOVABLE|__GFP_DIRECT_RECLAIM), nodemask=(null) kvm cpuset=/ mems_allowed=0-1

  CPU: 10 PID: 84752 Comm: kvm Tainted: G        W 4.12.0+98-ph <a href="/view.php?id=1" title="[geschlossen] Integration Ramdisk" class="resolved">0000001</a> SLE15 (unreleased)
  Hardware name: Supermicro SYS-1029P-WTRT/X11DDW-NT, BIOS 2.0 12/05/2017
  Call Trace:
   dump_stack+0x5c/0x84
   warn_alloc+0xe0/0x180
   __alloc_pages_slowpath+0x820/0xc90
   __alloc_pages_nodemask+0x1cc/0x210
   alloc_pages_vma+0x1e5/0x280
   do_huge_pmd_wp_page+0x83f/0xf00
   __handle_mm_fault+0x93d/0x1060
   handle_mm_fault+0xc6/0x1b0
   __do_page_fault+0x230/0x430
   do_page_fault+0x2a/0x70
   page_fault+0x7b/0x80
   [...]
  Mem-Info:
  active_anon:126315487 inactive_anon:1612476 isolated_anon:5
   active_file:60183 inactive_file:245285 isolated_file:0
   unevictable:15657 dirty:286 writeback:1 unstable:0
   slab_reclaimable:75543 slab_unreclaimable:2509111
   mapped:81814 shmem:31764 pagetables:370616 bounce:0
   free:32294031 free_pcp:6233 free_cma:0
  Node 0 active_anon:254680388kB inactive_anon:1112760kB active_file:240648kB inactive_file:981168kB unevictable:13368kB isolated(anon):0kB isolated(file):0kB mapped:280240kB dirty:1144kB writeback:0kB shmem:95832kB shmem_thp: 0kB shmem_pmdmapped: 0kB anon_thp: 81225728kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no
  Node 1 active_anon:250583072kB inactive_anon:5337144kB active_file:84kB inactive_file:0kB unevictable:49260kB isolated(anon):20kB isolated(file):0kB mapped:47016kB dirty:0kB writeback:4kB shmem:31224kB shmem_thp: 0kB shmem_pmdmapped: 0kB anon_thp: 31897600kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no

The defrag mode is "madvise" and from the above report it is clear that the THP has been allocated for MADV_HUGEPAGA vma.

Andrea has identified that the main source of the problem is __GFP_THISNODE usage:

: The problem is that direct compaction combined with the NUMA : __GFP_THISNODE logic in mempolicy.c is telling reclaim to swap very : hard the local node, instead of failing the allocation if there's no : THP available in the local node.
:
: Such logic was ok until __GFP_THISNODE was added to the THP allocation : path even with MPOL_DEFAULT.
:
: The idea behind the __GFP_THISNODE addition, is that it is better to : provide local memory in PAGE_SIZE units than to use remote NUMA THP : backed memory. That largely depends on the remote latency though, on : threadrippers for example the overhead is relatively low in my : experience.
:
: The combination of __GFP_THISNODE and __GFP_DIRECT_RECLAIM results in : extremely slow qemu startup with vfio, if the VM is larger than the : size of one host NUMA node. This is because it will try very hard to : unsuccessfully swapout get_user_pages pinned pages as result of the : __GFP_THISNODE being set, instead of falling back to PAGE_SIZE : allocations and instead of trying to allocate THP on other nodes (it : would be even worse without vfio type1 GUP pins of course, except it'd : be swapping heavily instead).

Fix this by removing __GFP_THISNODE for THP requests which are requesting the direct reclaim. This effectivelly reverts 5265047ac301 on the grounds that the zone/node reclaim was known to be disruptive due to premature reclaim when there was memory free. While it made sense at the time for HPC workloads without NUMA awareness on rare machines, it was ultimately harmful in the majority of cases. The existing behaviour is similar, if not as widespare as it applies to a corner case but crucially, it cannot be tuned around like zone_reclaim_mode can. The default behaviour should always be to cause the least harm for the common case.

If there are specialised use cases out there that want zone_reclaim_mode in specific cases, then it can be built on top. Longterm we should consider a memory policy which allows for the node reclaim like behavior for the specific memory ranges which would allow a

[1] http://lkml.kernel.org/r/[email protected]

Mel said:

: Both patches look correct to me but I'm responding to this one because : it's the fix. The change makes sense and moves further away from the : severe stalling behaviour we used to see with both THP and zone reclaim : mode.
:
: I put together a basic experiment with usemem configured to reference a : buffer multiple times that is 80% the size of main memory on a 2-socket : box with symmetric node sizes and defrag set to "always". The defrag : setting is not the default but it would be functionally similar to : accessing a buffer with madvise(MADV_HUGEPAGE). Usemem is configured to : reference the buffer multiple times and while it's not an interesting : workload, it would be expected to complete reasonably quickly as it fits : within memory. The results were;
:
: usemem
: vanilla noreclaim-v1

: Amean     Elapsd-1       42.78 (   0.00%)       26.87 (  37.18%)
: Amean     Elapsd-3       27.55 (   0.00%)        7.44 (  73.00%)
: Amean     Elapsd-4        5.72 (   0.00%)        5.69 (   0.45%)

:
: This shows the elapsed time in seconds for 1 thread, 3 threads and 4 : threads referencing buffers 80% the size of memory. With the patches : applied, it's 37.18% faster for the single thread and 73% faster with two : threads. Note that 4 threads showing little difference does not indicate : the problem is related to thread counts. It's simply the case that 4 : threads gets spread so their workload mostly fits in one node. :
: The overall view from /proc/vmstats is more startling
:
: 4.19.0-rc1 4.19.0-rc1
: vanillanoreclaim-v1r1
: Minor Faults 35593425 708164
: Major Faults 484088 36

: Swap Ins                    3772837           0
: Swap Outs                   3932295           0
:
: Massive amounts of swap in/out without the patch
:
: Direct pages scanned        6013214           0
: Kswapd pages scanned              0           0
: Kswapd pages reclaimed            0           0
: Direct pages reclaimed      4033009           0

:
: Lots of reclaim activity without the patch
:
: Kswapd efficiency 100% 100%
: Kswapd velocity 0.000 0.000
: Direct efficiency 67% 100%
: Direct velocity 11191.956 0.000
:
: Mostly from direct reclaim context as you'd expect without the patch. :
: Page writes by reclaim 3932314.000 0.000

: Page writes file                 19           0
: Page writes anon            3932295           0
: Page reclaim immediate        42336           0

:
: Writes from reclaim context is never good but the patch eliminates it. :
: We should never have default behaviour to thrash the system for such a : basic workload. If zone reclaim mode behaviour is ever desired but on a : single task instead of a global basis then the sensible option is to build : a mempolicy that enforces that behaviour.

This was a severe regression compared to previous kernels that made important workloads unusable and it starts when __GFP_THISNODE was added to THP allocations under MADV_HUGEPAGE. It is not a significant risk to go to the previous behavior before __GFP_THISNODE was added, it worked like that for years.

This was simply an optimization to some lucky workloads that can fit in a single node, but it ended up breaking the VM for others that can't possibly fit in a single node, so going back is safe.

---
 mm/mempolicy.c |   32 ++++++++++++++++++++++++++++++--
 1 file changed, 30 insertions(+), 2 deletions(-)

@@ -2027,8 +2027,36 @@ retry_cpuset:
 		nmask = policy_nodemask(gfp, pol);
 		if (!nmask || node_isset(hpage_node, *nmask)) {
 			mpol_cond_put(pol);
-			page = __alloc_pages_node(hpage_node,
-						gfp | __GFP_THISNODE, order);
+			/*
+			 * We cannot invoke reclaim if __GFP_THISNODE
+			 * is set. Invoking reclaim with
+			 * __GFP_THISNODE set, would cause THP
+			 * allocations to trigger heavy swapping
+			 * despite there may be tons of free memory
+			 * (including potentially plenty of THP
+			 * already available in the buddy) on all the
+			 * other NUMA nodes.
+			 *
+			 * At most we could invoke compaction when
+			 * __GFP_THISNODE is set (but we would need to
+			 * refrain from invoking reclaim even if
+			 * compaction returned COMPACT_SKIPPED because
+			 * there wasn't not enough memory to succeed
+			 * compaction). For now just avoid
+			 * __GFP_THISNODE instead of limiting the
+			 * allocation path to a strict and single
+			 * compaction invocation.
+			 *
+			 * Supposedly if direct reclaim was enabled by
+			 * the caller, the app prefers THP regardless
+			 * of the node it comes from so this would be
+			 * more desiderable behavior than only
+			 * providing THP originated from the local
+			 * node in such case.
+			 */
+			if (!(gfp & __GFP_DIRECT_RECLAIM))
+				gfp |= __GFP_THISNODE;
+			page = __alloc_pages_node(hpage_node, gfp, order);
 			goto out;
 		}
 	}

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

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

From: Vasily Khoruzhick <[email protected]>

commit f393808dc64149ccd0e5a8427505ba2974a59854 upstream.

If there's no entry to drop in bucket that corresponds to the hash, early_drop() should look for it in other buckets. But since it increments hash instead of bucket number, it actually looks in the same bucket 8
times: hsize is 16k by default (14 bits) and hash is 32-bit value, so reciprocal_scale(hash, hsize) returns the same value for hash..hash+7 in most cases.

Fix it by increasing bucket number instead of hash and rename _hash to bucket to avoid future confusion.

---
 net/netfilter/nf_conntrack_core.c |   13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

@@ -918,19 +918,22 @@ static unsigned int early_drop_list(stru
 	return drops;
 }
 
-static noinline int early_drop(struct net *net, unsigned int _hash)
+static noinline int early_drop(struct net *net, unsigned int hash)
 {
-	unsigned int i;
+	unsigned int i, bucket;
 
 	for (i = 0; i < NF_CT_EVICTION_RANGE; i++) {
 		struct hlist_nulls_head *ct_hash;
-		unsigned int hash, hsize, drops;
+		unsigned int hsize, drops;
 
 		rcu_read_lock();
 		nf_conntrack_get_ht(&ct_hash, &hsize);
-		hash = reciprocal_scale(_hash++, hsize);
+		if (!i)
+			bucket = reciprocal_scale(hash, hsize);
+		else
+			bucket = (bucket + 1) % hsize;
 
-		drops = early_drop_list(net, &ct_hash[hash]);
+		drops = early_drop_list(net, &ct_hash[bucket]);
 		rcu_read_unlock();
 
 		if (drops) {

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

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

From: H. Peter Anvin <[email protected]>

commit 991a25194097006ec1e0d2e0814ff920e59e3465 upstream.

On architectures with CBAUDEX == 0 (Alpha and PowerPC), the code in tty_baudrate.c does not do any limit checking on the tty_baudrate[] array, and in fact a buffer overrun is possible on both architectures. Add a limit check to prevent that situation.

This will be followed by a much bigger cleanup/simplification patch.

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

@@ -325,7 +325,7 @@ speed_t tty_termios_baud_rate(struct kte
 		else
 			cbaud += 15;
 	}
-	return baud_table[cbaud];
+	return cbaud >= n_baud_table ? 0 : baud_table[cbaud];
 }
 EXPORT_SYMBOL(tty_termios_baud_rate);
 

@@ -361,7 +361,7 @@ speed_t tty_termios_input_baud_rate(stru
 		else
 			cbaud += 15;
 	}
-	return baud_table[cbaud];
+	return cbaud >= n_baud_table ? 0 : baud_table[cbaud];
 #else
 	return tty_termios_baud_rate(termios);
 #endif

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

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

From: Vasily Averin <[email protected]>

commit ea0abbb648452cdb6e1734b702b6330a7448fcf8 upstream.

---
 fs/ext4/resize.c |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -1095,8 +1095,10 @@ static void update_backups(struct super_
 			   backup_block, backup_block -
 			   ext4_group_first_block_no(sb, group));
 		BUFFER_TRACE(bh, "get_write_access");
-		if ((err = ext4_journal_get_write_access(handle, bh)))
+		if ((err = ext4_journal_get_write_access(handle, bh))) {
+			brelse(bh);
 			break;
+		}
 		lock_buffer(bh);
 		memcpy(bh->b_data, data, size);
 		if (rest)

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

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

From: Vasily Averin <[email protected]>

commit cea5794122125bf67559906a0762186cf417099c upstream.

---
 fs/ext4/resize.c |    6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

@@ -442,16 +442,18 @@ static int set_flexbg_block_bitmap(struc
 
 		BUFFER_TRACE(bh, "get_write_access");
 		err = ext4_journal_get_write_access(handle, bh);
-		if (err)
+		if (err) {
+			brelse(bh);
 			return err;
+		}
 		ext4_debug("mark block bitmap %#04llx (+%llu/%u)\n", block,
 			   block - start, count2);
 		ext4_set_bits(bh->b_data, block - start, count2);
 
 		err = ext4_handle_dirty_metadata(handle, NULL, bh);
+		brelse(bh);
 		if (unlikely(err))
 			return err;
-		brelse(bh);
 	}
 
 	return 0;

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

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

From: Vasily Averin <[email protected]>

commit 61a9c11e5e7a0dab5381afa5d9d4dd5ebf18f7a0 upstream.

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

@@ -899,6 +899,7 @@ static int add_new_gdb_meta_bg(struct su
 				     sizeof(struct buffer_head *),
 				     GFP_NOFS);
 	if (!n_group_desc) {
+		brelse(gdb_bh);
 		err = -ENOMEM;
 		ext4_warning(sb, "not enough memory for %lu groups",
 			     gdb_num + 1);

@@ -914,8 +915,6 @@ static int add_new_gdb_meta_bg(struct su
 	kvfree(o_group_desc);
 	BUFFER_TRACE(gdb_bh, "get_write_access");
 	err = ext4_journal_get_write_access(handle, gdb_bh);
-	if (unlikely(err))
-		brelse(gdb_bh);
 	return err;
 }
 

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

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

From: Max Filippov <[email protected]>

commit 4119ba211bc4f1bf638f41e50b7a0f329f58aa16 upstream.

This section collects all source .note.* sections together in the vmlinux image. Without it .note.Linux section may be placed at address 0, while the rest of the kernel is at its normal address, resulting in a huge vmlinux.bin image that may not be linked into the xtensa Image.elf.

---
 arch/xtensa/boot/Makefile        |    2 +-
 arch/xtensa/kernel/vmlinux.lds.S |    1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

@@ -31,7 +31,7 @@ $(bootdir-y): $(addprefix $(obj)/,$(subd
 	      $(addprefix $(obj)/,$(host-progs))
 	$(Q)$(MAKE) $(build)=$(obj)/$@ $(MAKECMDGOALS)
 
-OBJCOPYFLAGS = --strip-all -R .comment -R .note.gnu.build-id -O binary
+OBJCOPYFLAGS = --strip-all -R .comment -R .notes -O binary
 
 vmlinux.bin: vmlinux FORCE
 	$(call if_changed,objcopy)

@@ -109,6 +109,7 @@ SECTIONS
   .fixup   : { *(.fixup) }
 
   EXCEPTION_TABLE(16)
+  NOTES
   /* Data section */
 
   _sdata = .;