This is the 4.19.45 stable release

-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAlzk4CsACgkQONu9yGCS
 aT5Xaw//UWopx4Yqbiv+4HBgW+2ijP4utxI4lBNYITD44jvkyVJnztUtVkWepu5r
 Tkl/7zytXOpxbpuhS0xqpWwG7lL5eT4NCG08KSX4lYQVjIWX4YzVkw9gLe9V2AaK
 IqTzaWtbuagARbnR3UC65TI4kjRGsr9ldY0AbbGGVTM6IwPquHN9Qd9TAzRwRohn
 CxY94Bwp1RcN2sSPkD3nUCUGOSNh97BXyypeM7FyceOzOpyAdQCXoUPc84cPqdNC
 4GBkd5Z1IL/7zX3HDjQeGS0KK6e1enslSmsbSSUVuHI90LCr3CZPJkFF8RFnPnff
 2RA7bdhp8C1JPeLDimr+SNSLEl9yywoH6d4UQAnBwoLDjiFCEITVgjDtYzzd81+1
 ES6lbUAs8v/LXkaCaExq6pNNd1prg6Mj9Fe6cz+G9V/YV1tLUsoAJHdFucu8Sp7w
 rwz/PZ6waCf8VRO4aYFF9b+u7PQ/RFZWQYsz22P7PhAYg0CTajV1FWGk1AYi0+wQ
 5YCmthbWhDo9U5lAFyQ0pVTXv/UNgEu6MfV1/jKtCk5AzsbE77orj1xusKckHq2e
 QojgmELmHMlFFajI0h/ddDo7iwz/5OrPVs9D03RysiOciMzdTKPucPyC0Ah4yEBA
 sJ0cQkaVtqO2Nu3E42lfQTpVIqBgi8NGav+kRwryB1YyKeaXLsM=
 =HJ7O
 -----END PGP SIGNATURE-----

Merge 4.19.45 into android-4.19

Changes in 4.19.45
	locking/rwsem: Prevent decrement of reader count before increment
	x86/speculation/mds: Revert CPU buffer clear on double fault exit
	x86/speculation/mds: Improve CPU buffer clear documentation
	objtool: Fix function fallthrough detection
	arm64: dts: rockchip: Disable DCMDs on RK3399's eMMC controller.
	ARM: dts: exynos: Fix interrupt for shared EINTs on Exynos5260
	ARM: dts: exynos: Fix audio (microphone) routing on Odroid XU3
	mmc: sdhci-of-arasan: Add DTS property to disable DCMDs.
	ARM: exynos: Fix a leaked reference by adding missing of_node_put
	power: supply: axp288_charger: Fix unchecked return value
	power: supply: axp288_fuel_gauge: Add ACEPC T8 and T11 mini PCs to the blacklist
	arm64: mmap: Ensure file offset is treated as unsigned
	arm64: arch_timer: Ensure counter register reads occur with seqlock held
	arm64: compat: Reduce address limit
	arm64: Clear OSDLR_EL1 on CPU boot
	arm64: Save and restore OSDLR_EL1 across suspend/resume
	sched/x86: Save [ER]FLAGS on context switch
	crypto: crypto4xx - fix ctr-aes missing output IV
	crypto: crypto4xx - fix cfb and ofb "overran dst buffer" issues
	crypto: salsa20 - don't access already-freed walk.iv
	crypto: chacha20poly1305 - set cra_name correctly
	crypto: ccp - Do not free psp_master when PLATFORM_INIT fails
	crypto: vmx - fix copy-paste error in CTR mode
	crypto: skcipher - don't WARN on unprocessed data after slow walk step
	crypto: crct10dif-generic - fix use via crypto_shash_digest()
	crypto: x86/crct10dif-pcl - fix use via crypto_shash_digest()
	crypto: arm64/gcm-aes-ce - fix no-NEON fallback code
	crypto: gcm - fix incompatibility between "gcm" and "gcm_base"
	crypto: rockchip - update IV buffer to contain the next IV
	crypto: arm/aes-neonbs - don't access already-freed walk.iv
	crypto: arm64/aes-neonbs - don't access already-freed walk.iv
	mmc: core: Fix tag set memory leak
	ALSA: line6: toneport: Fix broken usage of timer for delayed execution
	ALSA: usb-audio: Fix a memory leak bug
	ALSA: hda/hdmi - Read the pin sense from register when repolling
	ALSA: hda/hdmi - Consider eld_valid when reporting jack event
	ALSA: hda/realtek - EAPD turn on later
	ALSA: hdea/realtek - Headset fixup for System76 Gazelle (gaze14)
	ASoC: max98090: Fix restore of DAPM Muxes
	ASoC: RT5677-SPI: Disable 16Bit SPI Transfers
	ASoC: fsl_esai: Fix missing break in switch statement
	ASoC: codec: hdac_hdmi add device_link to card device
	bpf, arm64: remove prefetch insn in xadd mapping
	crypto: ccree - remove special handling of chained sg
	crypto: ccree - fix mem leak on error path
	crypto: ccree - don't map MAC key on stack
	crypto: ccree - use correct internal state sizes for export
	crypto: ccree - don't map AEAD key and IV on stack
	crypto: ccree - pm resume first enable the source clk
	crypto: ccree - HOST_POWER_DOWN_EN should be the last CC access during suspend
	crypto: ccree - add function to handle cryptocell tee fips error
	crypto: ccree - handle tee fips error during power management resume
	mm/mincore.c: make mincore() more conservative
	mm/huge_memory: fix vmf_insert_pfn_{pmd, pud}() crash, handle unaligned addresses
	mm/hugetlb.c: don't put_page in lock of hugetlb_lock
	hugetlb: use same fault hash key for shared and private mappings
	ocfs2: fix ocfs2 read inode data panic in ocfs2_iget
	userfaultfd: use RCU to free the task struct when fork fails
	ACPI: PM: Set enable_for_wake for wakeup GPEs during suspend-to-idle
	mfd: da9063: Fix OTP control register names to match datasheets for DA9063/63L
	mfd: max77620: Fix swapped FPS_PERIOD_MAX_US values
	mtd: spi-nor: intel-spi: Avoid crossing 4K address boundary on read/write
	tty: vt.c: Fix TIOCL_BLANKSCREEN console blanking if blankinterval == 0
	tty/vt: fix write/write race in ioctl(KDSKBSENT) handler
	jbd2: check superblock mapped prior to committing
	ext4: make sanity check in mballoc more strict
	ext4: ignore e_value_offs for xattrs with value-in-ea-inode
	ext4: avoid drop reference to iloc.bh twice
	ext4: fix use-after-free race with debug_want_extra_isize
	ext4: actually request zeroing of inode table after grow
	ext4: fix ext4_show_options for file systems w/o journal
	btrfs: Check the first key and level for cached extent buffer
	btrfs: Correctly free extent buffer in case btree_read_extent_buffer_pages fails
	btrfs: Honour FITRIM range constraints during free space trim
	Btrfs: send, flush dellaloc in order to avoid data loss
	Btrfs: do not start a transaction during fiemap
	Btrfs: do not start a transaction at iterate_extent_inodes()
	bcache: fix a race between cache register and cacheset unregister
	bcache: never set KEY_PTRS of journal key to 0 in journal_reclaim()
	ipmi:ssif: compare block number correctly for multi-part return messages
	crypto: ccm - fix incompatibility between "ccm" and "ccm_base"
	fs/writeback.c: use rcu_barrier() to wait for inflight wb switches going into workqueue when umount
	tty: Don't force RISCV SBI console as preferred console
	ext4: zero out the unused memory region in the extent tree block
	ext4: fix data corruption caused by overlapping unaligned and aligned IO
	ext4: fix use-after-free in dx_release()
	ext4: avoid panic during forced reboot due to aborted journal
	ALSA: hda/realtek - Corrected fixup for System76 Gazelle (gaze14)
	ALSA: hda/realtek - Fixup headphone noise via runtime suspend
	ALSA: hda/realtek - Fix for Lenovo B50-70 inverted internal microphone bug
	jbd2: fix potential double free
	KVM: x86: Skip EFER vs. guest CPUID checks for host-initiated writes
	KVM: lapic: Busy wait for timer to expire when using hv_timer
	kbuild: turn auto.conf.cmd into a mandatory include file
	xen/pvh: set xen_domain_type to HVM in xen_pvh_init
	libnvdimm/namespace: Fix label tracking error
	iov_iter: optimize page_copy_sane()
	pstore: Centralize init/exit routines
	pstore: Allocate compression during late_initcall()
	pstore: Refactor compression initialization
	ext4: fix compile error when using BUFFER_TRACE
	ext4: don't update s_rev_level if not required
	Linux 4.19.45

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>

Documentation/x86/mds.rst

@@ -142,45 +142,13 @@ Mitigation points
    mds_user_clear.
 
    The mitigation is invoked in prepare_exit_to_usermode() which covers
-   most of the kernel to user space transitions. There are a few exceptions
+   all but one of the kernel to user space transitions.  The exception
-   which are not invoking prepare_exit_to_usermode() on return to user
+   is when we return from a Non Maskable Interrupt (NMI), which is
-   space. These exceptions use the paranoid exit code.
+   handled directly in do_nmi().
 
-   - Non Maskable Interrupt (NMI):
+   (The reason that NMI is special is that prepare_exit_to_usermode() can
-
+    enable IRQs.  In NMI context, NMIs are blocked, and we don't want to
-     Access to sensible data like keys, credentials in the NMI context is
+    enable IRQs with NMIs blocked.)
-     mostly theoretical: The CPU can do prefetching or execute a
-     misspeculated code path and thereby fetching data which might end up
-     leaking through a buffer.
-
-     But for mounting other attacks the kernel stack address of the task is
-     already valuable information. So in full mitigation mode, the NMI is
-     mitigated on the return from do_nmi() to provide almost complete
-     coverage.
-
-   - Double fault (#DF):
-
-     A double fault is usually fatal, but the ESPFIX workaround, which can
-     be triggered from user space through modify_ldt(2) is a recoverable
-     double fault. #DF uses the paranoid exit path, so explicit mitigation
-     in the double fault handler is required.
-
-   - Machine Check Exception (#MC):
-
-     Another corner case is a #MC which hits between the CPU buffer clear
-     invocation and the actual return to user. As this still is in kernel
-     space it takes the paranoid exit path which does not clear the CPU
-     buffers. So the #MC handler repopulates the buffers to some
-     extent. Machine checks are not reliably controllable and the window is
-     extremly small so mitigation would just tick a checkbox that this
-     theoretical corner case is covered. To keep the amount of special
-     cases small, ignore #MC.
-
-   - Debug Exception (#DB):
-
-     This takes the paranoid exit path only when the INT1 breakpoint is in
-     kernel space. #DB on a user space address takes the regular exit path,
-     so no extra mitigation required.
 
 
 2. C-State transition

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 4
 PATCHLEVEL = 19
-SUBLEVEL = 44
+SUBLEVEL = 45
 EXTRAVERSION =
 NAME = "People's Front"
 
@@ -630,7 +630,7 @@ ifeq ($(may-sync-config),1)
 # Read in dependencies to all Kconfig* files, make sure to run syncconfig if
 # changes are detected. This should be included after arch/$(SRCARCH)/Makefile
 # because some architectures define CROSS_COMPILE there.
--include include/config/auto.conf.cmd
+include include/config/auto.conf.cmd
 
 # To avoid any implicit rule to kick in, define an empty command
 $(KCONFIG_CONFIG): ;

arch/arm/boot/dts/exynos5260.dtsi

@@ -223,7 +223,7 @@
 			wakeup-interrupt-controller {
 				compatible = "samsung,exynos4210-wakeup-eint";
 				interrupt-parent = <&gic>;
-				interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+				interrupts = <GIC_SPI 48 IRQ_TYPE_LEVEL_HIGH>;
 			};
 		};
 

arch/arm/boot/dts/exynos5422-odroidxu3-audio.dtsi

@@ -22,7 +22,7 @@
 			"Headphone Jack", "HPL",
 			"Headphone Jack", "HPR",
 			"Headphone Jack", "MICBIAS",
-			"IN1", "Headphone Jack",
+			"IN12", "Headphone Jack",
 			"Speakers", "SPKL",
 			"Speakers", "SPKR";
 

arch/arm/crypto/aes-neonbs-glue.c

@@ -278,6 +278,8 @@ static int __xts_crypt(struct skcipher_request *req,
 	int err;
 
 	err = skcipher_walk_virt(&walk, req, true);
+	if (err)
+		return err;
 
 	crypto_cipher_encrypt_one(ctx->tweak_tfm, walk.iv, walk.iv);
 

arch/arm/mach-exynos/firmware.c

@@ -196,6 +196,7 @@ void __init exynos_firmware_init(void)
 		return;
 
 	addr = of_get_address(nd, 0, NULL, NULL);
+	of_node_put(nd);
 	if (!addr) {
 		pr_err("%s: No address specified.\n", __func__);
 		return;

arch/arm/mach-exynos/suspend.c

@@ -639,8 +639,10 @@ void __init exynos_pm_init(void)
 
 	if (WARN_ON(!of_find_property(np, "interrupt-controller", NULL))) {
 		pr_warn("Outdated DT detected, suspend/resume will NOT work\n");
+		of_node_put(np);
 		return;
 	}
+	of_node_put(np);
 
 	pm_data = (const struct exynos_pm_data *) match->data;
 

arch/arm64/boot/dts/rockchip/rk3399.dtsi

@@ -305,6 +305,7 @@
 		phys = <&emmc_phy>;
 		phy-names = "phy_arasan";
 		power-domains = <&power RK3399_PD_EMMC>;
+		disable-cqe-dcmd;
 		status = "disabled";
 	};
 

arch/arm64/crypto/aes-neonbs-glue.c

@@ -304,6 +304,8 @@ static int __xts_crypt(struct skcipher_request *req,
 	int err;
 
 	err = skcipher_walk_virt(&walk, req, false);
+	if (err)
+		return err;
 
 	kernel_neon_begin();
 	neon_aes_ecb_encrypt(walk.iv, walk.iv, ctx->twkey, ctx->key.rounds, 1);

arch/arm64/crypto/ghash-ce-glue.c

@@ -434,9 +434,11 @@ static int gcm_encrypt(struct aead_request *req)
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
 		while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) {
-			int blocks = walk.nbytes / AES_BLOCK_SIZE;
+			const int blocks =
+				walk.nbytes / (2 * AES_BLOCK_SIZE) * 2;
 			u8 *dst = walk.dst.virt.addr;
 			u8 *src = walk.src.virt.addr;
+			int remaining = blocks;
 
 			do {
 				__aes_arm64_encrypt(ctx->aes_key.key_enc,
@@ -446,9 +448,9 @@ static int gcm_encrypt(struct aead_request *req)
 
 				dst += AES_BLOCK_SIZE;
 				src += AES_BLOCK_SIZE;
-			} while (--blocks > 0);
+			} while (--remaining > 0);
 
-			ghash_do_update(walk.nbytes / AES_BLOCK_SIZE, dg,
+			ghash_do_update(blocks, dg,
 					walk.dst.virt.addr, &ctx->ghash_key,
 					NULL);
 
@@ -569,7 +571,7 @@ static int gcm_decrypt(struct aead_request *req)
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
 		while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) {
-			int blocks = walk.nbytes / AES_BLOCK_SIZE;
+			int blocks = walk.nbytes / (2 * AES_BLOCK_SIZE) * 2;
 			u8 *dst = walk.dst.virt.addr;
 			u8 *src = walk.src.virt.addr;
 

arch/arm64/include/asm/arch_timer.h

@@ -148,18 +148,47 @@ static inline void arch_timer_set_cntkctl(u32 cntkctl)
 	isb();
 }
 
+/*
+ * Ensure that reads of the counter are treated the same as memory reads
+ * for the purposes of ordering by subsequent memory barriers.
+ *
+ * This insanity brought to you by speculative system register reads,
+ * out-of-order memory accesses, sequence locks and Thomas Gleixner.
+ *
+ * http://lists.infradead.org/pipermail/linux-arm-kernel/2019-February/631195.html
+ */
+#define arch_counter_enforce_ordering(val) do {				\
+	u64 tmp, _val = (val);						\
+									\
+	asm volatile(							\
+	"	eor	%0, %1, %1\n"					\
+	"	add	%0, sp, %0\n"					\
+	"	ldr	xzr, [%0]"					\
+	: "=r" (tmp) : "r" (_val));					\
+} while (0)
+
 static inline u64 arch_counter_get_cntpct(void)
 {
+	u64 cnt;
+
 	isb();
-	return arch_timer_reg_read_stable(cntpct_el0);
+	cnt = arch_timer_reg_read_stable(cntpct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
 }
 
 static inline u64 arch_counter_get_cntvct(void)
 {
+	u64 cnt;
+
 	isb();
-	return arch_timer_reg_read_stable(cntvct_el0);
+	cnt = arch_timer_reg_read_stable(cntvct_el0);
+	arch_counter_enforce_ordering(cnt);
+	return cnt;
 }
 
+#undef arch_counter_enforce_ordering
+
 static inline int arch_timer_arch_init(void)
 {
 	return 0;

arch/arm64/include/asm/processor.h

@@ -53,7 +53,15 @@
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area.
  */
 #ifdef CONFIG_COMPAT
+#ifdef CONFIG_ARM64_64K_PAGES
+/*
+ * With CONFIG_ARM64_64K_PAGES enabled, the last page is occupied
+ * by the compat vectors page.
+ */
 #define TASK_SIZE_32		UL(0x100000000)
+#else
+#define TASK_SIZE_32		(UL(0x100000000) - PAGE_SIZE)
+#endif /* CONFIG_ARM64_64K_PAGES */
 #define TASK_SIZE		(test_thread_flag(TIF_32BIT) ? \
 				TASK_SIZE_32 : TASK_SIZE_64)
 #define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_32BIT) ? \

arch/arm64/kernel/debug-monitors.c

@@ -135,6 +135,7 @@ NOKPROBE_SYMBOL(disable_debug_monitors);
  */
 static int clear_os_lock(unsigned int cpu)
 {
+	write_sysreg(0, osdlr_el1);
 	write_sysreg(0, oslar_el1);
 	isb();
 	return 0;

arch/arm64/kernel/sys.c

@@ -31,7 +31,7 @@
 
 SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
 		unsigned long, prot, unsigned long, flags,
-		unsigned long, fd, off_t, off)
+		unsigned long, fd, unsigned long, off)
 {
 	if (offset_in_page(off) != 0)
 		return -EINVAL;

arch/arm64/kernel/vdso/gettimeofday.S

@@ -73,6 +73,13 @@ x_tmp		.req	x8
 	movn	x_tmp, #0xff00, lsl #48
 	and	\res, x_tmp, \res
 	mul	\res, \res, \mult
+	/*
+	 * Fake address dependency from the value computed from the counter
+	 * register to subsequent data page accesses so that the sequence
+	 * locking also orders the read of the counter.
+	 */
+	and	x_tmp, \res, xzr
+	add	vdso_data, vdso_data, x_tmp
 	.endm
 
 	/*
@@ -147,12 +154,12 @@ ENTRY(__kernel_gettimeofday)
 	/* w11 = cs_mono_mult, w12 = cs_shift */
 	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
 	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
-	seqcnt_check fail=1b
 
 	get_nsec_per_sec res=x9
 	lsl	x9, x9, x12
 
 	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+	seqcnt_check fail=1b
 	get_ts_realtime res_sec=x10, res_nsec=x11, \
 		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
 
@@ -211,13 +218,13 @@ realtime:
 	/* w11 = cs_mono_mult, w12 = cs_shift */
 	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
 	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
-	seqcnt_check fail=realtime
 
 	/* All computations are done with left-shifted nsecs. */
 	get_nsec_per_sec res=x9
 	lsl	x9, x9, x12
 
 	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+	seqcnt_check fail=realtime
 	get_ts_realtime res_sec=x10, res_nsec=x11, \
 		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
 	clock_gettime_return, shift=1
@@ -231,7 +238,6 @@ monotonic:
 	ldp	w11, w12, [vdso_data, #VDSO_CS_MONO_MULT]
 	ldp	x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC]
 	ldp	x3, x4, [vdso_data, #VDSO_WTM_CLK_SEC]
-	seqcnt_check fail=monotonic
 
 	/* All computations are done with left-shifted nsecs. */
 	lsl	x4, x4, x12
@@ -239,6 +245,7 @@ monotonic:
 	lsl	x9, x9, x12
 
 	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+	seqcnt_check fail=monotonic
 	get_ts_realtime res_sec=x10, res_nsec=x11, \
 		clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9
 
@@ -253,13 +260,13 @@ monotonic_raw:
 	/* w11 = cs_raw_mult, w12 = cs_shift */
 	ldp	w12, w11, [vdso_data, #VDSO_CS_SHIFT]
 	ldp	x13, x14, [vdso_data, #VDSO_RAW_TIME_SEC]
-	seqcnt_check fail=monotonic_raw
 
 	/* All computations are done with left-shifted nsecs. */
 	get_nsec_per_sec res=x9
 	lsl	x9, x9, x12
 
 	get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11
+	seqcnt_check fail=monotonic_raw
 	get_ts_clock_raw res_sec=x10, res_nsec=x11, \
 		clock_nsec=x15, nsec_to_sec=x9
 

arch/arm64/mm/proc.S

@@ -70,24 +70,25 @@ ENTRY(cpu_do_suspend)
 	mrs	x2, tpidr_el0
 	mrs	x3, tpidrro_el0
 	mrs	x4, contextidr_el1
-	mrs	x5, cpacr_el1
+	mrs	x5, osdlr_el1
-	mrs	x6, tcr_el1
+	mrs	x6, cpacr_el1
-	mrs	x7, vbar_el1
+	mrs	x7, tcr_el1
-	mrs	x8, mdscr_el1
+	mrs	x8, vbar_el1
-	mrs	x9, oslsr_el1
+	mrs	x9, mdscr_el1
-	mrs	x10, sctlr_el1
+	mrs	x10, oslsr_el1
+	mrs	x11, sctlr_el1
 alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
-	mrs	x11, tpidr_el1
+	mrs	x12, tpidr_el1
 alternative_else
-	mrs	x11, tpidr_el2
+	mrs	x12, tpidr_el2
 alternative_endif
-	mrs	x12, sp_el0
+	mrs	x13, sp_el0
 	stp	x2, x3, [x0]
-	stp	x4, xzr, [x0, #16]
+	stp	x4, x5, [x0, #16]
-	stp	x5, x6, [x0, #32]
+	stp	x6, x7, [x0, #32]
-	stp	x7, x8, [x0, #48]
+	stp	x8, x9, [x0, #48]
-	stp	x9, x10, [x0, #64]
+	stp	x10, x11, [x0, #64]
-	stp	x11, x12, [x0, #80]
+	stp	x12, x13, [x0, #80]
 	ret
 ENDPROC(cpu_do_suspend)
 
@@ -110,8 +111,8 @@ ENTRY(cpu_do_resume)
 	msr	cpacr_el1, x6
 
 	/* Don't change t0sz here, mask those bits when restoring */
-	mrs	x5, tcr_el1
+	mrs	x7, tcr_el1
-	bfi	x8, x5, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
+	bfi	x8, x7, TCR_T0SZ_OFFSET, TCR_TxSZ_WIDTH
 
 	msr	tcr_el1, x8
 	msr	vbar_el1, x9
@@ -135,6 +136,7 @@ alternative_endif
 	/*
 	 * Restore oslsr_el1 by writing oslar_el1
 	 */
+	msr	osdlr_el1, x5
 	ubfx	x11, x11, #1, #1
 	msr	oslar_el1, x11
 	reset_pmuserenr_el0 x0			// Disable PMU access from EL0

arch/arm64/net/bpf_jit.h

@@ -100,12 +100,6 @@
 #define A64_STXR(sf, Rt, Rn, Rs) \
 	A64_LSX(sf, Rt, Rn, Rs, STORE_EX)
 
-/* Prefetch */
-#define A64_PRFM(Rn, type, target, policy) \
-	aarch64_insn_gen_prefetch(Rn, AARCH64_INSN_PRFM_TYPE_##type, \
-				  AARCH64_INSN_PRFM_TARGET_##target, \
-				  AARCH64_INSN_PRFM_POLICY_##policy)
-
 /* Add/subtract (immediate) */
 #define A64_ADDSUB_IMM(sf, Rd, Rn, imm12, type) \
 	aarch64_insn_gen_add_sub_imm(Rd, Rn, imm12, \

arch/arm64/net/bpf_jit_comp.c

@@ -736,7 +736,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_STX | BPF_XADD | BPF_DW:
 		emit_a64_mov_i(1, tmp, off, ctx);
 		emit(A64_ADD(1, tmp, tmp, dst), ctx);
-		emit(A64_PRFM(tmp, PST, L1, STRM), ctx);
 		emit(A64_LDXR(isdw, tmp2, tmp), ctx);
 		emit(A64_ADD(isdw, tmp2, tmp2, src), ctx);
 		emit(A64_STXR(isdw, tmp2, tmp, tmp3), ctx);

arch/x86/crypto/crct10dif-pclmul_glue.c

@@ -76,15 +76,14 @@ static int chksum_final(struct shash_desc *desc, u8 *out)
 	return 0;
 }
 
-static int __chksum_finup(__u16 *crcp, const u8 *data, unsigned int len,
+static int __chksum_finup(__u16 crc, const u8 *data, unsigned int len, u8 *out)
-			u8 *out)
 {
 	if (irq_fpu_usable()) {
 		kernel_fpu_begin();
-		*(__u16 *)out = crc_t10dif_pcl(*crcp, data, len);
+		*(__u16 *)out = crc_t10dif_pcl(crc, data, len);
 		kernel_fpu_end();
 	} else
-		*(__u16 *)out = crc_t10dif_generic(*crcp, data, len);
+		*(__u16 *)out = crc_t10dif_generic(crc, data, len);
 	return 0;
 }
 
@@ -93,15 +92,13 @@ static int chksum_finup(struct shash_desc *desc, const u8 *data,
 {
 	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
 
-	return __chksum_finup(&ctx->crc, data, len, out);
+	return __chksum_finup(ctx->crc, data, len, out);
 }
 
 static int chksum_digest(struct shash_desc *desc, const u8 *data,
 			 unsigned int length, u8 *out)
 {
-	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+	return __chksum_finup(0, data, length, out);
-
-	return __chksum_finup(&ctx->crc, data, length, out);
 }
 
 static struct shash_alg alg = {

arch/x86/entry/entry_32.S

@@ -648,6 +648,7 @@ ENTRY(__switch_to_asm)
 	pushl	%ebx
 	pushl	%edi
 	pushl	%esi
+	pushfl
 
 	/* switch stack */
 	movl	%esp, TASK_threadsp(%eax)
@@ -670,6 +671,7 @@ ENTRY(__switch_to_asm)
 #endif
 
 	/* restore callee-saved registers */
+	popfl
 	popl	%esi
 	popl	%edi
 	popl	%ebx

arch/x86/entry/entry_64.S

@@ -352,6 +352,7 @@ ENTRY(__switch_to_asm)
 	pushq	%r13
 	pushq	%r14
 	pushq	%r15
+	pushfq
 
 	/* switch stack */
 	movq	%rsp, TASK_threadsp(%rdi)
@@ -374,6 +375,7 @@ ENTRY(__switch_to_asm)
 #endif
 
 	/* restore callee-saved registers */
+	popfq
 	popq	%r15
 	popq	%r14
 	popq	%r13

arch/x86/include/asm/switch_to.h

@@ -40,6 +40,7 @@ asmlinkage void ret_from_fork(void);
  * order of the fields must match the code in __switch_to_asm().
  */
 struct inactive_task_frame {
+	unsigned long flags;
 #ifdef CONFIG_X86_64
 	unsigned long r15;
 	unsigned long r14;

arch/x86/kernel/process_32.c

@@ -130,6 +130,13 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	struct task_struct *tsk;
 	int err;
 
+	/*
+	 * For a new task use the RESET flags value since there is no before.
+	 * All the status flags are zero; DF and all the system flags must also
+	 * be 0, specifically IF must be 0 because we context switch to the new
+	 * task with interrupts disabled.
+	 */
+	frame->flags = X86_EFLAGS_FIXED;
 	frame->bp = 0;
 	frame->ret_addr = (unsigned long) ret_from_fork;
 	p->thread.sp = (unsigned long) fork_frame;

arch/x86/kernel/process_64.c

@@ -300,6 +300,14 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	childregs = task_pt_regs(p);
 	fork_frame = container_of(childregs, struct fork_frame, regs);
 	frame = &fork_frame->frame;
+
+	/*
+	 * For a new task use the RESET flags value since there is no before.
+	 * All the status flags are zero; DF and all the system flags must also
+	 * be 0, specifically IF must be 0 because we context switch to the new
+	 * task with interrupts disabled.
+	 */
+	frame->flags = X86_EFLAGS_FIXED;
 	frame->bp = 0;
 	frame->ret_addr = (unsigned long) ret_from_fork;
 	p->thread.sp = (unsigned long) fork_frame;

arch/x86/kernel/traps.c

@@ -58,7 +58,6 @@
 #include <asm/alternative.h>
 #include <asm/fpu/xstate.h>
 #include <asm/trace/mpx.h>
-#include <asm/nospec-branch.h>
 #include <asm/mpx.h>
 #include <asm/vm86.h>
 #include <asm/umip.h>
@@ -388,13 +387,6 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 		regs->ip = (unsigned long)general_protection;
 		regs->sp = (unsigned long)&gpregs->orig_ax;
 
-		/*
-		 * This situation can be triggered by userspace via
-		 * modify_ldt(2) and the return does not take the regular
-		 * user space exit, so a CPU buffer clear is required when
-		 * MDS mitigation is enabled.
-		 */
-		mds_user_clear_cpu_buffers();
 		return;
 	}
 #endif

arch/x86/kvm/lapic.c

@@ -1449,7 +1449,7 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 	if (swait_active(q))
 		swake_up_one(q);
 
-	if (apic_lvtt_tscdeadline(apic))
+	if (apic_lvtt_tscdeadline(apic) || ktimer->hv_timer_in_use)
 		ktimer->expired_tscdeadline = ktimer->tscdeadline;
 }
 

arch/x86/kvm/x86.c

@@ -1162,31 +1162,42 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 	return 0;
 }
 
+static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
+{
+	if (efer & EFER_FFXSR && !guest_cpuid_has(vcpu, X86_FEATURE_FXSR_OPT))
+		return false;
+
+	if (efer & EFER_SVME && !guest_cpuid_has(vcpu, X86_FEATURE_SVM))
+		return false;
+
+	return true;
+
+}
 bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
 	if (efer & efer_reserved_bits)
 		return false;
 
-	if (efer & EFER_FFXSR && !guest_cpuid_has(vcpu, X86_FEATURE_FXSR_OPT))
+	return __kvm_valid_efer(vcpu, efer);
-			return false;
-
-	if (efer & EFER_SVME && !guest_cpuid_has(vcpu, X86_FEATURE_SVM))
-			return false;
-
-	return true;
 }
 EXPORT_SYMBOL_GPL(kvm_valid_efer);
 
-static int set_efer(struct kvm_vcpu *vcpu, u64 efer)
+static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	u64 old_efer = vcpu->arch.efer;
+	u64 efer = msr_info->data;
 
-	if (!kvm_valid_efer(vcpu, efer))
+	if (efer & efer_reserved_bits)
-		return 1;
+		return false;
 
-	if (is_paging(vcpu)
+	if (!msr_info->host_initiated) {
-	    && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
+		if (!__kvm_valid_efer(vcpu, efer))
-		return 1;
+			return 1;
+
+		if (is_paging(vcpu) &&
+		    (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
+			return 1;
+	}
 
 	efer &= ~EFER_LMA;
 	efer |= vcpu->arch.efer & EFER_LMA;
@@ -2356,7 +2367,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vcpu->arch.arch_capabilities = data;
 		break;
 	case MSR_EFER:
-		return set_efer(vcpu, data);
+		return set_efer(vcpu, msr_info);
 	case MSR_K7_HWCR:
 		data &= ~(u64)0x40;	/* ignore flush filter disable */
 		data &= ~(u64)0x100;	/* ignore ignne emulation enable */

arch/x86/xen/enlighten_pvh.c

@@ -97,6 +97,7 @@ void __init xen_prepare_pvh(void)
 	}
 
 	xen_pvh = 1;
+	xen_domain_type = XEN_HVM_DOMAIN;
 	xen_start_flags = pvh_start_info.flags;
 
 	msr = cpuid_ebx(xen_cpuid_base() + 2);

crypto/ccm.c

@@ -455,7 +455,6 @@ static void crypto_ccm_free(struct aead_instance *inst)
 
 static int crypto_ccm_create_common(struct crypto_template *tmpl,
 				    struct rtattr **tb,
-				    const char *full_name,
 				    const char *ctr_name,
 				    const char *mac_name)
 {
@@ -483,7 +482,8 @@ static int crypto_ccm_create_common(struct crypto_template *tmpl,
 
 	mac = __crypto_hash_alg_common(mac_alg);
 	err = -EINVAL;
-	if (mac->digestsize != 16)
+	if (strncmp(mac->base.cra_name, "cbcmac(", 7) != 0 ||
+	    mac->digestsize != 16)
 		goto out_put_mac;
 
 	inst = kzalloc(sizeof(*inst) + sizeof(*ictx), GFP_KERNEL);
@@ -506,23 +506,27 @@ static int crypto_ccm_create_common(struct crypto_template *tmpl,
 
 	ctr = crypto_spawn_skcipher_alg(&ictx->ctr);
 
-	/* Not a stream cipher? */
+	/* The skcipher algorithm must be CTR mode, using 16-byte blocks. */
 	err = -EINVAL;
-	if (ctr->base.cra_blocksize != 1)
+	if (strncmp(ctr->base.cra_name, "ctr(", 4) != 0 ||
+	    crypto_skcipher_alg_ivsize(ctr) != 16 ||
+	    ctr->base.cra_blocksize != 1)
 		goto err_drop_ctr;
 
-	/* We want the real thing! */
+	/* ctr and cbcmac must use the same underlying block cipher. */
-	if (crypto_skcipher_alg_ivsize(ctr) != 16)
+	if (strcmp(ctr->base.cra_name + 4, mac->base.cra_name + 7) != 0)
 		goto err_drop_ctr;
 
 	err = -ENAMETOOLONG;
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "ccm(%s", ctr->base.cra_name + 4) >= CRYPTO_MAX_ALG_NAME)
+		goto err_drop_ctr;
+
 	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "ccm_base(%s,%s)", ctr->base.cra_driver_name,
 		     mac->base.cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
 		goto err_drop_ctr;
 
-	memcpy(inst->alg.base.cra_name, full_name, CRYPTO_MAX_ALG_NAME);
-
 	inst->alg.base.cra_flags = ctr->base.cra_flags & CRYPTO_ALG_ASYNC;
 	inst->alg.base.cra_priority = (mac->base.cra_priority +
 				       ctr->base.cra_priority) / 2;
@@ -564,7 +568,6 @@ static int crypto_ccm_create(struct crypto_template *tmpl, struct rtattr **tb)
 	const char *cipher_name;
 	char ctr_name[CRYPTO_MAX_ALG_NAME];
 	char mac_name[CRYPTO_MAX_ALG_NAME];
-	char full_name[CRYPTO_MAX_ALG_NAME];
 
 	cipher_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(cipher_name))
@@ -578,12 +581,7 @@ static int crypto_ccm_create(struct crypto_template *tmpl, struct rtattr **tb)
 		     cipher_name) >= CRYPTO_MAX_ALG_NAME)
 		return -ENAMETOOLONG;
 
-	if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "ccm(%s)", cipher_name) >=
+	return crypto_ccm_create_common(tmpl, tb, ctr_name, mac_name);
-	    CRYPTO_MAX_ALG_NAME)
-		return -ENAMETOOLONG;
-
-	return crypto_ccm_create_common(tmpl, tb, full_name, ctr_name,
-					mac_name);
 }
 
 static struct crypto_template crypto_ccm_tmpl = {
@@ -596,23 +594,17 @@ static int crypto_ccm_base_create(struct crypto_template *tmpl,
 				  struct rtattr **tb)
 {
 	const char *ctr_name;
-	const char *cipher_name;
+	const char *mac_name;
-	char full_name[CRYPTO_MAX_ALG_NAME];
 
 	ctr_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(ctr_name))
 		return PTR_ERR(ctr_name);
 
-	cipher_name = crypto_attr_alg_name(tb[2]);
+	mac_name = crypto_attr_alg_name(tb[2]);
-	if (IS_ERR(cipher_name))
+	if (IS_ERR(mac_name))
-		return PTR_ERR(cipher_name);
+		return PTR_ERR(mac_name);
 
-	if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "ccm_base(%s,%s)",
+	return crypto_ccm_create_common(tmpl, tb, ctr_name, mac_name);
-		     ctr_name, cipher_name) >= CRYPTO_MAX_ALG_NAME)
-		return -ENAMETOOLONG;
-
-	return crypto_ccm_create_common(tmpl, tb, full_name, ctr_name,
-					cipher_name);
 }
 
 static struct crypto_template crypto_ccm_base_tmpl = {

crypto/chacha20poly1305.c

@@ -647,8 +647,8 @@ static int chachapoly_create(struct crypto_template *tmpl, struct rtattr **tb,
 
 	err = -ENAMETOOLONG;
 	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
-		     "%s(%s,%s)", name, chacha_name,
+		     "%s(%s,%s)", name, chacha->base.cra_name,
-		     poly_name) >= CRYPTO_MAX_ALG_NAME)
+		     poly->cra_name) >= CRYPTO_MAX_ALG_NAME)
 		goto out_drop_chacha;
 	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "%s(%s,%s)", name, chacha->base.cra_driver_name,

crypto/crct10dif_generic.c

@@ -65,10 +65,9 @@ static int chksum_final(struct shash_desc *desc, u8 *out)
 	return 0;
 }
 
-static int __chksum_finup(__u16 *crcp, const u8 *data, unsigned int len,
+static int __chksum_finup(__u16 crc, const u8 *data, unsigned int len, u8 *out)
-			u8 *out)
 {
-	*(__u16 *)out = crc_t10dif_generic(*crcp, data, len);
+	*(__u16 *)out = crc_t10dif_generic(crc, data, len);
 	return 0;
 }
 
@@ -77,15 +76,13 @@ static int chksum_finup(struct shash_desc *desc, const u8 *data,
 {
 	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
 
-	return __chksum_finup(&ctx->crc, data, len, out);
+	return __chksum_finup(ctx->crc, data, len, out);
 }
 
 static int chksum_digest(struct shash_desc *desc, const u8 *data,
 			 unsigned int length, u8 *out)
 {
-	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+	return __chksum_finup(0, data, length, out);
-
-	return __chksum_finup(&ctx->crc, data, length, out);
 }
 
 static struct shash_alg alg = {

crypto/gcm.c

@@ -597,7 +597,6 @@ static void crypto_gcm_free(struct aead_instance *inst)
 
 static int crypto_gcm_create_common(struct crypto_template *tmpl,
 				    struct rtattr **tb,
-				    const char *full_name,
 				    const char *ctr_name,
 				    const char *ghash_name)
 {
@@ -638,7 +637,8 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl,
 		goto err_free_inst;
 
 	err = -EINVAL;
-	if (ghash->digestsize != 16)
+	if (strcmp(ghash->base.cra_name, "ghash") != 0 ||
+	    ghash->digestsize != 16)
 		goto err_drop_ghash;
 
 	crypto_set_skcipher_spawn(&ctx->ctr, aead_crypto_instance(inst));
@@ -650,24 +650,24 @@ static int crypto_gcm_create_common(struct crypto_template *tmpl,
 
 	ctr = crypto_spawn_skcipher_alg(&ctx->ctr);
 
-	/* We only support 16-byte blocks. */
+	/* The skcipher algorithm must be CTR mode, using 16-byte blocks. */
 	err = -EINVAL;
-	if (crypto_skcipher_alg_ivsize(ctr) != 16)
+	if (strncmp(ctr->base.cra_name, "ctr(", 4) != 0 ||
-		goto out_put_ctr;
+	    crypto_skcipher_alg_ivsize(ctr) != 16 ||
-
+	    ctr->base.cra_blocksize != 1)
-	/* Not a stream cipher? */
-	if (ctr->base.cra_blocksize != 1)
 		goto out_put_ctr;
 
 	err = -ENAMETOOLONG;
+	if (snprintf(inst->alg.base.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "gcm(%s", ctr->base.cra_name + 4) >= CRYPTO_MAX_ALG_NAME)
+		goto out_put_ctr;
+
 	if (snprintf(inst->alg.base.cra_driver_name, CRYPTO_MAX_ALG_NAME,
 		     "gcm_base(%s,%s)", ctr->base.cra_driver_name,
 		     ghash_alg->cra_driver_name) >=
 	    CRYPTO_MAX_ALG_NAME)
 		goto out_put_ctr;
 
-	memcpy(inst->alg.base.cra_name, full_name, CRYPTO_MAX_ALG_NAME);
-
 	inst->alg.base.cra_flags = (ghash->base.cra_flags |
 				    ctr->base.cra_flags) & CRYPTO_ALG_ASYNC;
 	inst->alg.base.cra_priority = (ghash->base.cra_priority +
@@ -709,7 +709,6 @@ static int crypto_gcm_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	const char *cipher_name;
 	char ctr_name[CRYPTO_MAX_ALG_NAME];
-	char full_name[CRYPTO_MAX_ALG_NAME];
 
 	cipher_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(cipher_name))
@@ -719,12 +718,7 @@ static int crypto_gcm_create(struct crypto_template *tmpl, struct rtattr **tb)
 	    CRYPTO_MAX_ALG_NAME)
 		return -ENAMETOOLONG;
 
-	if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "gcm(%s)", cipher_name) >=
+	return crypto_gcm_create_common(tmpl, tb, ctr_name, "ghash");
-	    CRYPTO_MAX_ALG_NAME)
-		return -ENAMETOOLONG;
-
-	return crypto_gcm_create_common(tmpl, tb, full_name,
-					ctr_name, "ghash");
 }
 
 static struct crypto_template crypto_gcm_tmpl = {
@@ -738,7 +732,6 @@ static int crypto_gcm_base_create(struct crypto_template *tmpl,
 {
 	const char *ctr_name;
 	const char *ghash_name;
-	char full_name[CRYPTO_MAX_ALG_NAME];
 
 	ctr_name = crypto_attr_alg_name(tb[1]);
 	if (IS_ERR(ctr_name))
@@ -748,12 +741,7 @@ static int crypto_gcm_base_create(struct crypto_template *tmpl,
 	if (IS_ERR(ghash_name))
 		return PTR_ERR(ghash_name);
 
-	if (snprintf(full_name, CRYPTO_MAX_ALG_NAME, "gcm_base(%s,%s)",
+	return crypto_gcm_create_common(tmpl, tb, ctr_name, ghash_name);
-		     ctr_name, ghash_name) >= CRYPTO_MAX_ALG_NAME)
-		return -ENAMETOOLONG;
-
-	return crypto_gcm_create_common(tmpl, tb, full_name,
-					ctr_name, ghash_name);
 }
 
 static struct crypto_template crypto_gcm_base_tmpl = {

crypto/salsa20_generic.c

@@ -161,7 +161,7 @@ static int salsa20_crypt(struct skcipher_request *req)
 
 	err = skcipher_walk_virt(&walk, req, true);
 
-	salsa20_init(state, ctx, walk.iv);
+	salsa20_init(state, ctx, req->iv);
 
 	while (walk.nbytes > 0) {
 		unsigned int nbytes = walk.nbytes;

crypto/skcipher.c

@@ -131,8 +131,13 @@ int skcipher_walk_done(struct skcipher_walk *walk, int err)
 		memcpy(walk->dst.virt.addr, walk->page, n);
 		skcipher_unmap_dst(walk);
 	} else if (unlikely(walk->flags & SKCIPHER_WALK_SLOW)) {
-		if (WARN_ON(err)) {
+		if (err) {
-			/* unexpected case; didn't process all bytes */
+			/*
+			 * Didn't process all bytes.  Either the algorithm is
+			 * broken, or this was the last step and it turned out
+			 * the message wasn't evenly divisible into blocks but
+			 * the algorithm requires it.
+			 */
 			err = -EINVAL;
 			goto finish;
 		}

drivers/acpi/sleep.c

@@ -977,6 +977,8 @@ static int acpi_s2idle_prepare(void)
 	if (acpi_sci_irq_valid())
 		enable_irq_wake(acpi_sci_irq);
 
+	acpi_enable_wakeup_devices(ACPI_STATE_S0);
+
 	/* Change the configuration of GPEs to avoid spurious wakeup. */
 	acpi_enable_all_wakeup_gpes();
 	acpi_os_wait_events_complete();
@@ -1026,6 +1028,8 @@ static void acpi_s2idle_restore(void)
 {
 	acpi_enable_all_runtime_gpes();
 
+	acpi_disable_wakeup_devices(ACPI_STATE_S0);
+
 	if (acpi_sci_irq_valid())
 		disable_irq_wake(acpi_sci_irq);
 

drivers/char/ipmi/ipmi_ssif.c

@@ -688,12 +688,16 @@ static void msg_done_handler(struct ssif_info *ssif_info, int result,
 			/* End of read */
 			len = ssif_info->multi_len;
 			data = ssif_info->data;
-		} else if (blocknum != ssif_info->multi_pos) {
+		} else if (blocknum + 1 != ssif_info->multi_pos) {
 			/*
 			 * Out of sequence block, just abort.  Block
 			 * numbers start at zero for the second block,
 			 * but multi_pos starts at one, so the +1.
 			 */
+			if (ssif_info->ssif_debug & SSIF_DEBUG_MSG)
+				dev_dbg(&ssif_info->client->dev,
+					"Received message out of sequence, expected %u, got %u\n",
+					ssif_info->multi_pos - 1, blocknum);
 			result = -EIO;
 		} else {
 			ssif_inc_stat(ssif_info, received_message_parts);

drivers/crypto/amcc/crypto4xx_alg.c

@@ -141,9 +141,10 @@ static int crypto4xx_setkey_aes(struct crypto_skcipher *cipher,
 	/* Setup SA */
 	sa = ctx->sa_in;
 
-	set_dynamic_sa_command_0(sa, SA_NOT_SAVE_HASH, (cm == CRYPTO_MODE_CBC ?
+	set_dynamic_sa_command_0(sa, SA_NOT_SAVE_HASH, (cm == CRYPTO_MODE_ECB ?
-				 SA_SAVE_IV : SA_NOT_SAVE_IV),
+				 SA_NOT_SAVE_IV : SA_SAVE_IV),
-				 SA_LOAD_HASH_FROM_SA, SA_LOAD_IV_FROM_STATE,
+				 SA_NOT_LOAD_HASH, (cm == CRYPTO_MODE_ECB ?
+				 SA_LOAD_IV_FROM_SA : SA_LOAD_IV_FROM_STATE),
 				 SA_NO_HEADER_PROC, SA_HASH_ALG_NULL,
 				 SA_CIPHER_ALG_AES, SA_PAD_TYPE_ZERO,
 				 SA_OP_GROUP_BASIC, SA_OPCODE_DECRYPT,
@@ -162,6 +163,11 @@ static int crypto4xx_setkey_aes(struct crypto_skcipher *cipher,
 	memcpy(ctx->sa_out, ctx->sa_in, ctx->sa_len * 4);
 	sa = ctx->sa_out;
 	sa->sa_command_0.bf.dir = DIR_OUTBOUND;
+	/*
+	 * SA_OPCODE_ENCRYPT is the same value as SA_OPCODE_DECRYPT.
+	 * it's the DIR_(IN|OUT)BOUND that matters
+	 */
+	sa->sa_command_0.bf.opcode = SA_OPCODE_ENCRYPT;
 
 	return 0;
 }

drivers/crypto/amcc/crypto4xx_core.c

@@ -712,7 +712,23 @@ int crypto4xx_build_pd(struct crypto_async_request *req,
 	size_t offset_to_sr_ptr;
 	u32 gd_idx = 0;
 	int tmp;
-	bool is_busy;
+	bool is_busy, force_sd;
+
+	/*
+	 * There's a very subtile/disguised "bug" in the hardware that
+	 * gets indirectly mentioned in 18.1.3.5 Encryption/Decryption
+	 * of the hardware spec:
+	 * *drum roll* the AES/(T)DES OFB and CFB modes are listed as
+	 * operation modes for >>> "Block ciphers" <<<.
+	 *
+	 * To workaround this issue and stop the hardware from causing
+	 * "overran dst buffer" on crypttexts that are not a multiple
+	 * of 16 (AES_BLOCK_SIZE), we force the driver to use the
+	 * scatter buffers.
+	 */
+	force_sd = (req_sa->sa_command_1.bf.crypto_mode9_8 == CRYPTO_MODE_CFB
+		|| req_sa->sa_command_1.bf.crypto_mode9_8 == CRYPTO_MODE_OFB)
+		&& (datalen % AES_BLOCK_SIZE);
 
 	/* figure how many gd are needed */
 	tmp = sg_nents_for_len(src, assoclen + datalen);
@@ -730,7 +746,7 @@ int crypto4xx_build_pd(struct crypto_async_request *req,
 	}
 
 	/* figure how many sd are needed */
-	if (sg_is_last(dst)) {
+	if (sg_is_last(dst) && force_sd == false) {
 		num_sd = 0;
 	} else {
 		if (datalen > PPC4XX_SD_BUFFER_SIZE) {
@@ -805,9 +821,10 @@ int crypto4xx_build_pd(struct crypto_async_request *req,
 	pd->sa_len = sa_len;
 
 	pd_uinfo = &dev->pdr_uinfo[pd_entry];
-	pd_uinfo->async_req = req;
 	pd_uinfo->num_gd = num_gd;
 	pd_uinfo->num_sd = num_sd;
+	pd_uinfo->dest_va = dst;
+	pd_uinfo->async_req = req;
 
 	if (iv_len)
 		memcpy(pd_uinfo->sr_va->save_iv, iv, iv_len);
@@ -826,7 +843,6 @@ int crypto4xx_build_pd(struct crypto_async_request *req,
 		/* get first gd we are going to use */
 		gd_idx = fst_gd;
 		pd_uinfo->first_gd = fst_gd;
-		pd_uinfo->num_gd = num_gd;
 		gd = crypto4xx_get_gdp(dev, &gd_dma, gd_idx);
 		pd->src = gd_dma;
 		/* enable gather */
@@ -863,17 +879,14 @@ int crypto4xx_build_pd(struct crypto_async_request *req,
 		 * Indicate gather array is not used
 		 */
 		pd_uinfo->first_gd = 0xffffffff;
-		pd_uinfo->num_gd = 0;
 	}
-	if (sg_is_last(dst)) {
+	if (!num_sd) {
 		/*
 		 * we know application give us dst a whole piece of memory
 		 * no need to use scatter ring.
 		 */
 		pd_uinfo->using_sd = 0;
 		pd_uinfo->first_sd = 0xffffffff;
-		pd_uinfo->num_sd = 0;
-		pd_uinfo->dest_va = dst;
 		sa->sa_command_0.bf.scatter = 0;
 		pd->dest = (u32)dma_map_page(dev->core_dev->device,
 					     sg_page(dst), dst->offset,
@@ -887,9 +900,7 @@ int crypto4xx_build_pd(struct crypto_async_request *req,
 		nbytes = datalen;
 		sa->sa_command_0.bf.scatter = 1;
 		pd_uinfo->using_sd = 1;
-		pd_uinfo->dest_va = dst;
 		pd_uinfo->first_sd = fst_sd;
-		pd_uinfo->num_sd = num_sd;
 		sd = crypto4xx_get_sdp(dev, &sd_dma, sd_idx);
 		pd->dest = sd_dma;
 		/* setup scatter descriptor */

drivers/crypto/ccp/psp-dev.c

@@ -935,7 +935,7 @@ void psp_pci_init(void)
 	rc = sev_platform_init(&error);
 	if (rc) {
 		dev_err(sp->dev, "SEV: failed to INIT error %#x\n", error);
-		goto err;
+		return;
 	}
 
 	dev_info(sp->dev, "SEV API:%d.%d build:%d\n", psp_master->api_major,

drivers/crypto/ccree/cc_aead.c

@@ -415,7 +415,7 @@ static int validate_keys_sizes(struct cc_aead_ctx *ctx)
 /* This function prepers the user key so it can pass to the hmac processing
  * (copy to intenral buffer or hash in case of key longer than block
  */
-static int cc_get_plain_hmac_key(struct crypto_aead *tfm, const u8 *key,
+static int cc_get_plain_hmac_key(struct crypto_aead *tfm, const u8 *authkey,
 				 unsigned int keylen)
 {
 	dma_addr_t key_dma_addr = 0;
@@ -428,6 +428,7 @@ static int cc_get_plain_hmac_key(struct crypto_aead *tfm, const u8 *key,
 	unsigned int hashmode;
 	unsigned int idx = 0;
 	int rc = 0;
+	u8 *key = NULL;
 	struct cc_hw_desc desc[MAX_AEAD_SETKEY_SEQ];
 	dma_addr_t padded_authkey_dma_addr =
 		ctx->auth_state.hmac.padded_authkey_dma_addr;
@@ -446,11 +447,17 @@ static int cc_get_plain_hmac_key(struct crypto_aead *tfm, const u8 *key,
 	}
 
 	if (keylen != 0) {
+
+		key = kmemdup(authkey, keylen, GFP_KERNEL);
+		if (!key)
+			return -ENOMEM;
+
 		key_dma_addr = dma_map_single(dev, (void *)key, keylen,
 					      DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, key_dma_addr)) {
 			dev_err(dev, "Mapping key va=0x%p len=%u for DMA failed\n",
 				key, keylen);
+			kzfree(key);
 			return -ENOMEM;
 		}
 		if (keylen > blocksize) {
@@ -533,6 +540,8 @@ static int cc_get_plain_hmac_key(struct crypto_aead *tfm, const u8 *key,
 	if (key_dma_addr)
 		dma_unmap_single(dev, key_dma_addr, keylen, DMA_TO_DEVICE);
 
+	kzfree(key);
+
 	return rc;
 }
 

drivers/crypto/ccree/cc_buffer_mgr.c

@@ -83,24 +83,17 @@ static void cc_copy_mac(struct device *dev, struct aead_request *req,
  */
 static unsigned int cc_get_sgl_nents(struct device *dev,
 				     struct scatterlist *sg_list,
-				     unsigned int nbytes, u32 *lbytes,
+				     unsigned int nbytes, u32 *lbytes)
-				     bool *is_chained)
 {
 	unsigned int nents = 0;
 
 	while (nbytes && sg_list) {
-		if (sg_list->length) {
+		nents++;
-			nents++;
+		/* get the number of bytes in the last entry */
-			/* get the number of bytes in the last entry */
+		*lbytes = nbytes;
-			*lbytes = nbytes;
+		nbytes -= (sg_list->length > nbytes) ?
-			nbytes -= (sg_list->length > nbytes) ?
+				nbytes : sg_list->length;
-					nbytes : sg_list->length;
+		sg_list = sg_next(sg_list);
-			sg_list = sg_next(sg_list);
-		} else {
-			sg_list = (struct scatterlist *)sg_page(sg_list);
-			if (is_chained)
-				*is_chained = true;
-		}
 	}
 	dev_dbg(dev, "nents %d last bytes %d\n", nents, *lbytes);
 	return nents;
@@ -142,7 +135,7 @@ void cc_copy_sg_portion(struct device *dev, u8 *dest, struct scatterlist *sg,
 {
 	u32 nents, lbytes;
 
-	nents = cc_get_sgl_nents(dev, sg, end, &lbytes, NULL);
+	nents = cc_get_sgl_nents(dev, sg, end, &lbytes);
 	sg_copy_buffer(sg, nents, (void *)dest, (end - to_skip + 1), to_skip,
 		       (direct == CC_SG_TO_BUF));
 }
@@ -311,40 +304,10 @@ static void cc_add_sg_entry(struct device *dev, struct buffer_array *sgl_data,
 	sgl_data->num_of_buffers++;
 }
 
-static int cc_dma_map_sg(struct device *dev, struct scatterlist *sg, u32 nents,
-			 enum dma_data_direction direction)
-{
-	u32 i, j;
-	struct scatterlist *l_sg = sg;
-
-	for (i = 0; i < nents; i++) {
-		if (!l_sg)
-			break;
-		if (dma_map_sg(dev, l_sg, 1, direction) != 1) {
-			dev_err(dev, "dma_map_page() sg buffer failed\n");
-			goto err;
-		}
-		l_sg = sg_next(l_sg);
-	}
-	return nents;
-
-err:
-	/* Restore mapped parts */
-	for (j = 0; j < i; j++) {
-		if (!sg)
-			break;
-		dma_unmap_sg(dev, sg, 1, direction);
-		sg = sg_next(sg);
-	}
-	return 0;
-}
-
 static int cc_map_sg(struct device *dev, struct scatterlist *sg,
 		     unsigned int nbytes, int direction, u32 *nents,
 		     u32 max_sg_nents, u32 *lbytes, u32 *mapped_nents)
 {
-	bool is_chained = false;
-
 	if (sg_is_last(sg)) {
 		/* One entry only case -set to DLLI */
 		if (dma_map_sg(dev, sg, 1, direction) != 1) {
@@ -358,35 +321,21 @@ static int cc_map_sg(struct device *dev, struct scatterlist *sg,
 		*nents = 1;
 		*mapped_nents = 1;
 	} else {  /*sg_is_last*/
-		*nents = cc_get_sgl_nents(dev, sg, nbytes, lbytes,
+		*nents = cc_get_sgl_nents(dev, sg, nbytes, lbytes);
-					  &is_chained);
 		if (*nents > max_sg_nents) {
 			*nents = 0;
 			dev_err(dev, "Too many fragments. current %d max %d\n",
 				*nents, max_sg_nents);
 			return -ENOMEM;
 		}
-		if (!is_chained) {
+		/* In case of mmu the number of mapped nents might
-			/* In case of mmu the number of mapped nents might
+		 * be changed from the original sgl nents
-			 * be changed from the original sgl nents
+		 */
-			 */
+		*mapped_nents = dma_map_sg(dev, sg, *nents, direction);
-			*mapped_nents = dma_map_sg(dev, sg, *nents, direction);
+		if (*mapped_nents == 0) {
-			if (*mapped_nents == 0) {
+			*nents = 0;
-				*nents = 0;
+			dev_err(dev, "dma_map_sg() sg buffer failed\n");
-				dev_err(dev, "dma_map_sg() sg buffer failed\n");
+			return -ENOMEM;
-				return -ENOMEM;
-			}
-		} else {
-			/*In this case the driver maps entry by entry so it
-			 * must have the same nents before and after map
-			 */
-			*mapped_nents = cc_dma_map_sg(dev, sg, *nents,
-						      direction);
-			if (*mapped_nents != *nents) {
-				*nents = *mapped_nents;
-				dev_err(dev, "dma_map_sg() sg buffer failed\n");
-				return -ENOMEM;
-			}
 		}
 	}
 
@@ -571,7 +520,6 @@ void cc_unmap_aead_request(struct device *dev, struct aead_request *req)
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	struct cc_drvdata *drvdata = dev_get_drvdata(dev);
 	u32 dummy;
-	bool chained;
 	u32 size_to_unmap = 0;
 
 	if (areq_ctx->mac_buf_dma_addr) {
@@ -612,6 +560,7 @@ void cc_unmap_aead_request(struct device *dev, struct aead_request *req)
 	if (areq_ctx->gen_ctx.iv_dma_addr) {
 		dma_unmap_single(dev, areq_ctx->gen_ctx.iv_dma_addr,
 				 hw_iv_size, DMA_BIDIRECTIONAL);
+		kzfree(areq_ctx->gen_ctx.iv);
 	}
 
 	/* Release pool */
@@ -636,15 +585,14 @@ void cc_unmap_aead_request(struct device *dev, struct aead_request *req)
 		size_to_unmap += crypto_aead_ivsize(tfm);
 
 	dma_unmap_sg(dev, req->src,
-		     cc_get_sgl_nents(dev, req->src, size_to_unmap,
+		     cc_get_sgl_nents(dev, req->src, size_to_unmap, &dummy),
-				      &dummy, &chained),
 		     DMA_BIDIRECTIONAL);
 	if (req->src != req->dst) {
 		dev_dbg(dev, "Unmapping dst sgl: req->dst=%pK\n",
 			sg_virt(req->dst));
 		dma_unmap_sg(dev, req->dst,
 			     cc_get_sgl_nents(dev, req->dst, size_to_unmap,
-					      &dummy, &chained),
+					      &dummy),
 			     DMA_BIDIRECTIONAL);
 	}
 	if (drvdata->coherent &&
@@ -717,19 +665,27 @@ static int cc_aead_chain_iv(struct cc_drvdata *drvdata,
 	struct aead_req_ctx *areq_ctx = aead_request_ctx(req);
 	unsigned int hw_iv_size = areq_ctx->hw_iv_size;
 	struct device *dev = drvdata_to_dev(drvdata);
+	gfp_t flags = cc_gfp_flags(&req->base);
 	int rc = 0;
 
 	if (!req->iv) {
 		areq_ctx->gen_ctx.iv_dma_addr = 0;
+		areq_ctx->gen_ctx.iv = NULL;
 		goto chain_iv_exit;
 	}
 
-	areq_ctx->gen_ctx.iv_dma_addr = dma_map_single(dev, req->iv,
+	areq_ctx->gen_ctx.iv = kmemdup(req->iv, hw_iv_size, flags);
-						       hw_iv_size,
+	if (!areq_ctx->gen_ctx.iv)
-						       DMA_BIDIRECTIONAL);
+		return -ENOMEM;
+
+	areq_ctx->gen_ctx.iv_dma_addr =
+		dma_map_single(dev, areq_ctx->gen_ctx.iv, hw_iv_size,
+			       DMA_BIDIRECTIONAL);
 	if (dma_mapping_error(dev, areq_ctx->gen_ctx.iv_dma_addr)) {
 		dev_err(dev, "Mapping iv %u B at va=%pK for DMA failed\n",
 			hw_iv_size, req->iv);
+		kzfree(areq_ctx->gen_ctx.iv);
+		areq_ctx->gen_ctx.iv = NULL;
 		rc = -ENOMEM;
 		goto chain_iv_exit;
 	}
@@ -1022,7 +978,6 @@ static int cc_aead_chain_data(struct cc_drvdata *drvdata,
 	unsigned int size_for_map = req->assoclen + req->cryptlen;
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
 	u32 sg_index = 0;
-	bool chained = false;
 	bool is_gcm4543 = areq_ctx->is_gcm4543;
 	u32 size_to_skip = req->assoclen;
 
@@ -1043,7 +998,7 @@ static int cc_aead_chain_data(struct cc_drvdata *drvdata,
 	size_for_map += (direct == DRV_CRYPTO_DIRECTION_ENCRYPT) ?
 			authsize : 0;
 	src_mapped_nents = cc_get_sgl_nents(dev, req->src, size_for_map,
-					    &src_last_bytes, &chained);
+					    &src_last_bytes);
 	sg_index = areq_ctx->src_sgl->length;
 	//check where the data starts
 	while (sg_index <= size_to_skip) {
@@ -1085,7 +1040,7 @@ static int cc_aead_chain_data(struct cc_drvdata *drvdata,
 	}
 
 	dst_mapped_nents = cc_get_sgl_nents(dev, req->dst, size_for_map,
-					    &dst_last_bytes, &chained);
+					    &dst_last_bytes);
 	sg_index = areq_ctx->dst_sgl->length;
 	offset = size_to_skip;
 
@@ -1486,7 +1441,7 @@ int cc_map_hash_request_update(struct cc_drvdata *drvdata, void *ctx,
 		dev_dbg(dev, " less than one block: curr_buff=%pK *curr_buff_cnt=0x%X copy_to=%pK\n",
 			curr_buff, *curr_buff_cnt, &curr_buff[*curr_buff_cnt]);
 		areq_ctx->in_nents =
-			cc_get_sgl_nents(dev, src, nbytes, &dummy, NULL);
+			cc_get_sgl_nents(dev, src, nbytes, &dummy);
 		sg_copy_to_buffer(src, areq_ctx->in_nents,
 				  &curr_buff[*curr_buff_cnt], nbytes);
 		*curr_buff_cnt += nbytes;

drivers/crypto/ccree/cc_driver.h

@@ -162,6 +162,7 @@ struct cc_alg_template {
 
 struct async_gen_req_ctx {
 	dma_addr_t iv_dma_addr;
+	u8 *iv;
 	enum drv_crypto_direction op_type;
 };
 

drivers/crypto/ccree/cc_fips.c

@@ -72,20 +72,28 @@ static inline void tee_fips_error(struct device *dev)
 		dev_err(dev, "TEE reported error!\n");
 }
 
+/*
+ * This function check if cryptocell tee fips error occurred
+ * and in such case triggers system error
+ */
+void cc_tee_handle_fips_error(struct cc_drvdata *p_drvdata)
+{
+	struct device *dev = drvdata_to_dev(p_drvdata);
+
+	if (!cc_get_tee_fips_status(p_drvdata))
+		tee_fips_error(dev);
+}
+
 /* Deferred service handler, run as interrupt-fired tasklet */
 static void fips_dsr(unsigned long devarg)
 {
 	struct cc_drvdata *drvdata = (struct cc_drvdata *)devarg;
-	struct device *dev = drvdata_to_dev(drvdata);
+	u32 irq, val;
-	u32 irq, state, val;
 
 	irq = (drvdata->irq & (CC_GPR0_IRQ_MASK));
 
 	if (irq) {
-		state = cc_ioread(drvdata, CC_REG(GPR_HOST));
+		cc_tee_handle_fips_error(drvdata);
-
-		if (state != (CC_FIPS_SYNC_TEE_STATUS | CC_FIPS_SYNC_MODULE_OK))
-			tee_fips_error(dev);
 	}
 
 	/* after verifing that there is nothing to do,
@@ -113,8 +121,7 @@ int cc_fips_init(struct cc_drvdata *p_drvdata)
 	dev_dbg(dev, "Initializing fips tasklet\n");
 	tasklet_init(&fips_h->tasklet, fips_dsr, (unsigned long)p_drvdata);
 
-	if (!cc_get_tee_fips_status(p_drvdata))
+	cc_tee_handle_fips_error(p_drvdata);
-		tee_fips_error(dev);
 
 	return 0;
 }

drivers/crypto/ccree/cc_fips.h

@@ -18,6 +18,7 @@ int cc_fips_init(struct cc_drvdata *p_drvdata);
 void cc_fips_fini(struct cc_drvdata *drvdata);
 void fips_handler(struct cc_drvdata *drvdata);
 void cc_set_ree_fips_status(struct cc_drvdata *drvdata, bool ok);
+void cc_tee_handle_fips_error(struct cc_drvdata *p_drvdata);
 
 #else  /* CONFIG_CRYPTO_FIPS */
 
@@ -30,6 +31,7 @@ static inline void cc_fips_fini(struct cc_drvdata *drvdata) {}
 static inline void cc_set_ree_fips_status(struct cc_drvdata *drvdata,
 					  bool ok) {}
 static inline void fips_handler(struct cc_drvdata *drvdata) {}
+static inline void cc_tee_handle_fips_error(struct cc_drvdata *p_drvdata) {}
 
 #endif /* CONFIG_CRYPTO_FIPS */
 

drivers/crypto/ccree/cc_hash.c

@@ -64,6 +64,7 @@ struct cc_hash_alg {
 struct hash_key_req_ctx {
 	u32 keylen;
 	dma_addr_t key_dma_addr;
+	u8 *key;
 };
 
 /* hash per-session context */
@@ -724,13 +725,20 @@ static int cc_hash_setkey(struct crypto_ahash *ahash, const u8 *key,
 	ctx->key_params.keylen = keylen;
 	ctx->key_params.key_dma_addr = 0;
 	ctx->is_hmac = true;
+	ctx->key_params.key = NULL;
 
 	if (keylen) {
+		ctx->key_params.key = kmemdup(key, keylen, GFP_KERNEL);
+		if (!ctx->key_params.key)
+			return -ENOMEM;
+
 		ctx->key_params.key_dma_addr =
-			dma_map_single(dev, (void *)key, keylen, DMA_TO_DEVICE);
+			dma_map_single(dev, (void *)ctx->key_params.key, keylen,
+				       DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, ctx->key_params.key_dma_addr)) {
 			dev_err(dev, "Mapping key va=0x%p len=%u for DMA failed\n",
-				key, keylen);
+				ctx->key_params.key, keylen);
+			kzfree(ctx->key_params.key);
 			return -ENOMEM;
 		}
 		dev_dbg(dev, "mapping key-buffer: key_dma_addr=%pad keylen=%u\n",
@@ -881,6 +889,9 @@ static int cc_hash_setkey(struct crypto_ahash *ahash, const u8 *key,
 		dev_dbg(dev, "Unmapped key-buffer: key_dma_addr=%pad keylen=%u\n",
 			&ctx->key_params.key_dma_addr, ctx->key_params.keylen);
 	}
+
+	kzfree(ctx->key_params.key);
+
 	return rc;
 }
 
@@ -907,11 +918,16 @@ static int cc_xcbc_setkey(struct crypto_ahash *ahash,
 
 	ctx->key_params.keylen = keylen;
 
+	ctx->key_params.key = kmemdup(key, keylen, GFP_KERNEL);
+	if (!ctx->key_params.key)
+		return -ENOMEM;
+
 	ctx->key_params.key_dma_addr =
-		dma_map_single(dev, (void *)key, keylen, DMA_TO_DEVICE);
+		dma_map_single(dev, ctx->key_params.key, keylen, DMA_TO_DEVICE);
 	if (dma_mapping_error(dev, ctx->key_params.key_dma_addr)) {
 		dev_err(dev, "Mapping key va=0x%p len=%u for DMA failed\n",
 			key, keylen);
+		kzfree(ctx->key_params.key);
 		return -ENOMEM;
 	}
 	dev_dbg(dev, "mapping key-buffer: key_dma_addr=%pad keylen=%u\n",
@@ -963,6 +979,8 @@ static int cc_xcbc_setkey(struct crypto_ahash *ahash,
 	dev_dbg(dev, "Unmapped key-buffer: key_dma_addr=%pad keylen=%u\n",
 		&ctx->key_params.key_dma_addr, ctx->key_params.keylen);
 
+	kzfree(ctx->key_params.key);
+
 	return rc;
 }
 
@@ -1598,7 +1616,7 @@ static struct cc_hash_template driver_hash[] = {
 			.setkey = cc_hash_setkey,
 			.halg = {
 				.digestsize = SHA224_DIGEST_SIZE,
-				.statesize = CC_STATE_SIZE(SHA224_DIGEST_SIZE),
+				.statesize = CC_STATE_SIZE(SHA256_DIGEST_SIZE),
 			},
 		},
 		.hash_mode = DRV_HASH_SHA224,
@@ -1623,7 +1641,7 @@ static struct cc_hash_template driver_hash[] = {
 			.setkey = cc_hash_setkey,
 			.halg = {
 				.digestsize = SHA384_DIGEST_SIZE,
-				.statesize = CC_STATE_SIZE(SHA384_DIGEST_SIZE),
+				.statesize = CC_STATE_SIZE(SHA512_DIGEST_SIZE),
 			},
 		},
 		.hash_mode = DRV_HASH_SHA384,

drivers/crypto/ccree/cc_ivgen.c

@@ -154,9 +154,6 @@ void cc_ivgen_fini(struct cc_drvdata *drvdata)
 	}
 
 	ivgen_ctx->pool = NULL_SRAM_ADDR;
-
-	/* release "this" context */
-	kfree(ivgen_ctx);
 }
 
 /*!
@@ -174,10 +171,12 @@ int cc_ivgen_init(struct cc_drvdata *drvdata)
 	int rc;
 
 	/* Allocate "this" context */
-	ivgen_ctx = kzalloc(sizeof(*ivgen_ctx), GFP_KERNEL);
+	ivgen_ctx = devm_kzalloc(device, sizeof(*ivgen_ctx), GFP_KERNEL);
 	if (!ivgen_ctx)
 		return -ENOMEM;
 
+	drvdata->ivgen_handle = ivgen_ctx;
+
 	/* Allocate pool's header for initial enc. key/IV */
 	ivgen_ctx->pool_meta = dma_alloc_coherent(device, CC_IVPOOL_META_SIZE,
 						  &ivgen_ctx->pool_meta_dma,
@@ -196,8 +195,6 @@ int cc_ivgen_init(struct cc_drvdata *drvdata)
 		goto out;
 	}
 
-	drvdata->ivgen_handle = ivgen_ctx;
-
 	return cc_init_iv_sram(drvdata);
 
 out:

drivers/crypto/ccree/cc_pm.c

@@ -11,6 +11,7 @@
 #include "cc_ivgen.h"
 #include "cc_hash.h"
 #include "cc_pm.h"
+#include "cc_fips.h"
 
 #define POWER_DOWN_ENABLE 0x01
 #define POWER_DOWN_DISABLE 0x00
@@ -25,13 +26,13 @@ int cc_pm_suspend(struct device *dev)
 	int rc;
 
 	dev_dbg(dev, "set HOST_POWER_DOWN_EN\n");
-	cc_iowrite(drvdata, CC_REG(HOST_POWER_DOWN_EN), POWER_DOWN_ENABLE);
 	rc = cc_suspend_req_queue(drvdata);
 	if (rc) {
 		dev_err(dev, "cc_suspend_req_queue (%x)\n", rc);
 		return rc;
 	}
 	fini_cc_regs(drvdata);
+	cc_iowrite(drvdata, CC_REG(HOST_POWER_DOWN_EN), POWER_DOWN_ENABLE);
 	cc_clk_off(drvdata);
 	return 0;
 }
@@ -42,19 +43,21 @@ int cc_pm_resume(struct device *dev)
 	struct cc_drvdata *drvdata = dev_get_drvdata(dev);
 
 	dev_dbg(dev, "unset HOST_POWER_DOWN_EN\n");
-	cc_iowrite(drvdata, CC_REG(HOST_POWER_DOWN_EN), POWER_DOWN_DISABLE);
+	/* Enables the device source clk */
-
 	rc = cc_clk_on(drvdata);
 	if (rc) {
 		dev_err(dev, "failed getting clock back on. We're toast.\n");
 		return rc;
 	}
 
+	cc_iowrite(drvdata, CC_REG(HOST_POWER_DOWN_EN), POWER_DOWN_DISABLE);
 	rc = init_cc_regs(drvdata, false);
 	if (rc) {
 		dev_err(dev, "init_cc_regs (%x)\n", rc);
 		return rc;
 	}
+	/* check if tee fips error occurred during power down */
+	cc_tee_handle_fips_error(drvdata);
 
 	rc = cc_resume_req_queue(drvdata);
 	if (rc) {

drivers/crypto/rockchip/rk3288_crypto_ablkcipher.c

@@ -250,9 +250,14 @@ static int rk_set_data_start(struct rk_crypto_info *dev)
 	u8 *src_last_blk = page_address(sg_page(dev->sg_src)) +
 		dev->sg_src->offset + dev->sg_src->length - ivsize;
 
-	/* store the iv that need to be updated in chain mode */
+	/* Store the iv that need to be updated in chain mode.
-	if (ctx->mode & RK_CRYPTO_DEC)
+	 * And update the IV buffer to contain the next IV for decryption mode.
+	 */
+	if (ctx->mode & RK_CRYPTO_DEC) {
 		memcpy(ctx->iv, src_last_blk, ivsize);
+		sg_pcopy_to_buffer(dev->first, dev->src_nents, req->info,
+				   ivsize, dev->total - ivsize);
+	}
 
 	err = dev->load_data(dev, dev->sg_src, dev->sg_dst);
 	if (!err)
@@ -288,13 +293,19 @@ static void rk_iv_copyback(struct rk_crypto_info *dev)
 	struct ablkcipher_request *req =
 		ablkcipher_request_cast(dev->async_req);
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct rk_cipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
 	u32 ivsize = crypto_ablkcipher_ivsize(tfm);
 
-	if (ivsize == DES_BLOCK_SIZE)
+	/* Update the IV buffer to contain the next IV for encryption mode. */
-		memcpy_fromio(req->info, dev->reg + RK_CRYPTO_TDES_IV_0,
+	if (!(ctx->mode & RK_CRYPTO_DEC)) {
-			      ivsize);
+		if (dev->aligned) {
-	else if (ivsize == AES_BLOCK_SIZE)
+			memcpy(req->info, sg_virt(dev->sg_dst) +
-		memcpy_fromio(req->info, dev->reg + RK_CRYPTO_AES_IV_0, ivsize);
+				dev->sg_dst->length - ivsize, ivsize);
+		} else {
+			memcpy(req->info, dev->addr_vir +
+				dev->count - ivsize, ivsize);
+		}
+	}
 }
 
 static void rk_update_iv(struct rk_crypto_info *dev)

drivers/crypto/vmx/aesp8-ppc.pl

@@ -1854,7 +1854,7 @@ Lctr32_enc8x_three:
 	stvx_u		$out1,$x10,$out
 	stvx_u		$out2,$x20,$out
 	addi		$out,$out,0x30
-	b		Lcbc_dec8x_done
+	b		Lctr32_enc8x_done
 
 .align	5
 Lctr32_enc8x_two:
@@ -1866,7 +1866,7 @@ Lctr32_enc8x_two:
 	stvx_u		$out0,$x00,$out
 	stvx_u		$out1,$x10,$out
 	addi		$out,$out,0x20
-	b		Lcbc_dec8x_done
+	b		Lctr32_enc8x_done
 
 .align	5
 Lctr32_enc8x_one:

drivers/dax/device.c

@@ -325,8 +325,7 @@ static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax,
 
 	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
 
-	return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, *pfn,
+	return vmf_insert_pfn_pmd(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE);
-			vmf->flags & FAULT_FLAG_WRITE);
 }
 
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
@@ -376,8 +375,7 @@ static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
 
 	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
 
-	return vmf_insert_pfn_pud(vmf->vma, vmf->address, vmf->pud, *pfn,
+	return vmf_insert_pfn_pud(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE);
-			vmf->flags & FAULT_FLAG_WRITE);
 }
 #else
 static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,

drivers/md/bcache/journal.c

@@ -540,11 +540,11 @@ static void journal_reclaim(struct cache_set *c)
 				  ca->sb.nr_this_dev);
 	}
 
-	bkey_init(k);
+	if (n) {
-	SET_KEY_PTRS(k, n);
+		bkey_init(k);
-
+		SET_KEY_PTRS(k, n);
-	if (n)
 		c->journal.blocks_free = c->sb.bucket_size >> c->block_bits;
+	}
 out:
 	if (!journal_full(&c->journal))
 		__closure_wake_up(&c->journal.wait);
@@ -671,6 +671,9 @@ static void journal_write_unlocked(struct closure *cl)
 		ca->journal.seq[ca->journal.cur_idx] = w->data->seq;
 	}
 
+	/* If KEY_PTRS(k) == 0, this jset gets lost in air */
+	BUG_ON(i == 0);
+
 	atomic_dec_bug(&fifo_back(&c->journal.pin));
 	bch_journal_next(&c->journal);
 	journal_reclaim(c);

drivers/md/bcache/super.c

@@ -1511,6 +1511,7 @@ static void cache_set_free(struct closure *cl)
 	bch_btree_cache_free(c);
 	bch_journal_free(c);
 
+	mutex_lock(&bch_register_lock);
 	for_each_cache(ca, c, i)
 		if (ca) {
 			ca->set = NULL;
@@ -1529,7 +1530,6 @@ static void cache_set_free(struct closure *cl)
 	mempool_exit(&c->search);
 	kfree(c->devices);
 
-	mutex_lock(&bch_register_lock);
 	list_del(&c->list);
 	mutex_unlock(&bch_register_lock);
 

drivers/mmc/core/queue.c

@@ -494,6 +494,7 @@ void mmc_cleanup_queue(struct mmc_queue *mq)
 		blk_mq_unquiesce_queue(q);
 
 	blk_cleanup_queue(q);
+	blk_mq_free_tag_set(&mq->tag_set);
 
 	/*
 	 * A request can be completed before the next request, potentially

drivers/mmc/host/sdhci-of-arasan.c

@@ -814,7 +814,10 @@ static int sdhci_arasan_probe(struct platform_device *pdev)
 		host->mmc_host_ops.start_signal_voltage_switch =
 					sdhci_arasan_voltage_switch;
 		sdhci_arasan->has_cqe = true;
-		host->mmc->caps2 |= MMC_CAP2_CQE | MMC_CAP2_CQE_DCMD;
+		host->mmc->caps2 |= MMC_CAP2_CQE;
+
+		if (!of_property_read_bool(np, "disable-cqe-dcmd"))
+			host->mmc->caps2 |= MMC_CAP2_CQE_DCMD;
 	}
 
 	ret = sdhci_arasan_add_host(sdhci_arasan);

drivers/mtd/spi-nor/intel-spi.c

@@ -632,6 +632,10 @@ static ssize_t intel_spi_read(struct spi_nor *nor, loff_t from, size_t len,
 	while (len > 0) {
 		block_size = min_t(size_t, len, INTEL_SPI_FIFO_SZ);
 
+		/* Read cannot cross 4K boundary */
+		block_size = min_t(loff_t, from + block_size,
+				   round_up(from + 1, SZ_4K)) - from;
+
 		writel(from, ispi->base + FADDR);
 
 		val = readl(ispi->base + HSFSTS_CTL);
@@ -685,6 +689,10 @@ static ssize_t intel_spi_write(struct spi_nor *nor, loff_t to, size_t len,
 	while (len > 0) {
 		block_size = min_t(size_t, len, INTEL_SPI_FIFO_SZ);
 
+		/* Write cannot cross 4K boundary */
+		block_size = min_t(loff_t, to + block_size,
+				   round_up(to + 1, SZ_4K)) - to;
+
 		writel(to, ispi->base + FADDR);
 
 		val = readl(ispi->base + HSFSTS_CTL);

drivers/nvdimm/label.c

@@ -623,6 +623,17 @@ static const guid_t *to_abstraction_guid(enum nvdimm_claim_class claim_class,
 		return &guid_null;
 }
 
+static void reap_victim(struct nd_mapping *nd_mapping,
+		struct nd_label_ent *victim)
+{
+	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+	u32 slot = to_slot(ndd, victim->label);
+
+	dev_dbg(ndd->dev, "free: %d\n", slot);
+	nd_label_free_slot(ndd, slot);
+	victim->label = NULL;
+}
+
 static int __pmem_label_update(struct nd_region *nd_region,
 		struct nd_mapping *nd_mapping, struct nd_namespace_pmem *nspm,
 		int pos, unsigned long flags)
@@ -630,9 +641,9 @@ static int __pmem_label_update(struct nd_region *nd_region,
 	struct nd_namespace_common *ndns = &nspm->nsio.common;
 	struct nd_interleave_set *nd_set = nd_region->nd_set;
 	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
-	struct nd_label_ent *label_ent, *victim = NULL;
 	struct nd_namespace_label *nd_label;
 	struct nd_namespace_index *nsindex;
+	struct nd_label_ent *label_ent;
 	struct nd_label_id label_id;
 	struct resource *res;
 	unsigned long *free;
@@ -701,18 +712,10 @@ static int __pmem_label_update(struct nd_region *nd_region,
 	list_for_each_entry(label_ent, &nd_mapping->labels, list) {
 		if (!label_ent->label)
 			continue;
-		if (memcmp(nspm->uuid, label_ent->label->uuid,
+		if (test_and_clear_bit(ND_LABEL_REAP, &label_ent->flags)
-					NSLABEL_UUID_LEN) != 0)
+				|| memcmp(nspm->uuid, label_ent->label->uuid,
-			continue;
+					NSLABEL_UUID_LEN) == 0)
-		victim = label_ent;
+			reap_victim(nd_mapping, label_ent);
-		list_move_tail(&victim->list, &nd_mapping->labels);
-		break;
-	}
-	if (victim) {
-		dev_dbg(ndd->dev, "free: %d\n", slot);
-		slot = to_slot(ndd, victim->label);
-		nd_label_free_slot(ndd, slot);
-		victim->label = NULL;
 	}
 
 	/* update index */

drivers/nvdimm/namespace_devs.c

@@ -1248,12 +1248,27 @@ static int namespace_update_uuid(struct nd_region *nd_region,
 	for (i = 0; i < nd_region->ndr_mappings; i++) {
 		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
 		struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+		struct nd_label_ent *label_ent;
 		struct resource *res;
 
 		for_each_dpa_resource(ndd, res)
 			if (strcmp(res->name, old_label_id.id) == 0)
 				sprintf((void *) res->name, "%s",
 						new_label_id.id);
+
+		mutex_lock(&nd_mapping->lock);
+		list_for_each_entry(label_ent, &nd_mapping->labels, list) {
+			struct nd_namespace_label *nd_label = label_ent->label;
+			struct nd_label_id label_id;
+
+			if (!nd_label)
+				continue;
+			nd_label_gen_id(&label_id, nd_label->uuid,
+					__le32_to_cpu(nd_label->flags));
+			if (strcmp(old_label_id.id, label_id.id) == 0)
+				set_bit(ND_LABEL_REAP, &label_ent->flags);
+		}
+		mutex_unlock(&nd_mapping->lock);
 	}
 	kfree(*old_uuid);
  out:

drivers/nvdimm/nd.h

@@ -113,8 +113,12 @@ struct nd_percpu_lane {
 	spinlock_t lock;
 };
 
+enum nd_label_flags {
+	ND_LABEL_REAP,
+};
 struct nd_label_ent {
 	struct list_head list;
+	unsigned long flags;
 	struct nd_namespace_label *label;
 };
 

drivers/power/supply/axp288_charger.c

@@ -832,6 +832,10 @@ static int axp288_charger_probe(struct platform_device *pdev)
 	/* Register charger interrupts */
 	for (i = 0; i < CHRG_INTR_END; i++) {
 		pirq = platform_get_irq(info->pdev, i);
+		if (pirq < 0) {
+			dev_err(&pdev->dev, "Failed to get IRQ: %d\n", pirq);
+			return pirq;
+		}
 		info->irq[i] = regmap_irq_get_virq(info->regmap_irqc, pirq);
 		if (info->irq[i] < 0) {
 			dev_warn(&info->pdev->dev,

drivers/power/supply/axp288_fuel_gauge.c

@@ -695,6 +695,26 @@ static void fuel_gauge_init_irq(struct axp288_fg_info *info)
  * detection reports one despite it not being there.
  */
 static const struct dmi_system_id axp288_fuel_gauge_blacklist[] = {
+	{
+		/* ACEPC T8 Cherry Trail Z8350 mini PC */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "To be filled by O.E.M."),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "Cherry Trail CR"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "T8"),
+			/* also match on somewhat unique bios-version */
+			DMI_EXACT_MATCH(DMI_BIOS_VERSION, "1.000"),
+		},
+	},
+	{
+		/* ACEPC T11 Cherry Trail Z8350 mini PC */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "To be filled by O.E.M."),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "Cherry Trail CR"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_SKU, "T11"),
+			/* also match on somewhat unique bios-version */
+			DMI_EXACT_MATCH(DMI_BIOS_VERSION, "1.000"),
+		},
+	},
 	{
 		/* Intel Cherry Trail Compute Stick, Windows version */
 		.matches = {

drivers/tty/hvc/hvc_riscv_sbi.c

@@ -53,7 +53,6 @@ device_initcall(hvc_sbi_init);
 static int __init hvc_sbi_console_init(void)
 {
 	hvc_instantiate(0, 0, &hvc_sbi_ops);
-	add_preferred_console("hvc", 0, NULL);
 
 	return 0;
 }

drivers/tty/vt/keyboard.c

@@ -123,6 +123,7 @@ static const int NR_TYPES = ARRAY_SIZE(max_vals);
 static struct input_handler kbd_handler;
 static DEFINE_SPINLOCK(kbd_event_lock);
 static DEFINE_SPINLOCK(led_lock);
+static DEFINE_SPINLOCK(func_buf_lock); /* guard 'func_buf'  and friends */
 static unsigned long key_down[BITS_TO_LONGS(KEY_CNT)];	/* keyboard key bitmap */
 static unsigned char shift_down[NR_SHIFT];		/* shift state counters.. */
 static bool dead_key_next;
@@ -1990,11 +1991,12 @@ int vt_do_kdgkb_ioctl(int cmd, struct kbsentry __user *user_kdgkb, int perm)
 	char *p;
 	u_char *q;
 	u_char __user *up;
-	int sz;
+	int sz, fnw_sz;
 	int delta;
 	char *first_free, *fj, *fnw;
 	int i, j, k;
 	int ret;
+	unsigned long flags;
 
 	if (!capable(CAP_SYS_TTY_CONFIG))
 		perm = 0;
@@ -2037,7 +2039,14 @@ int vt_do_kdgkb_ioctl(int cmd, struct kbsentry __user *user_kdgkb, int perm)
 			goto reterr;
 		}
 
+		fnw = NULL;
+		fnw_sz = 0;
+		/* race aginst other writers */
+		again:
+		spin_lock_irqsave(&func_buf_lock, flags);
 		q = func_table[i];
+
+		/* fj pointer to next entry after 'q' */
 		first_free = funcbufptr + (funcbufsize - funcbufleft);
 		for (j = i+1; j < MAX_NR_FUNC && !func_table[j]; j++)
 			;
@@ -2045,10 +2054,12 @@ int vt_do_kdgkb_ioctl(int cmd, struct kbsentry __user *user_kdgkb, int perm)
 			fj = func_table[j];
 		else
 			fj = first_free;
-
+		/* buffer usage increase by new entry */
 		delta = (q ? -strlen(q) : 1) + strlen(kbs->kb_string);
+
 		if (delta <= funcbufleft) { 	/* it fits in current buf */
 		    if (j < MAX_NR_FUNC) {
+			/* make enough space for new entry at 'fj' */
 			memmove(fj + delta, fj, first_free - fj);
 			for (k = j; k < MAX_NR_FUNC; k++)
 			    if (func_table[k])
@@ -2061,20 +2072,28 @@ int vt_do_kdgkb_ioctl(int cmd, struct kbsentry __user *user_kdgkb, int perm)
 		    sz = 256;
 		    while (sz < funcbufsize - funcbufleft + delta)
 		      sz <<= 1;
-		    fnw = kmalloc(sz, GFP_KERNEL);
+		    if (fnw_sz != sz) {
-		    if(!fnw) {
+		      spin_unlock_irqrestore(&func_buf_lock, flags);
-		      ret = -ENOMEM;
+		      kfree(fnw);
-		      goto reterr;
+		      fnw = kmalloc(sz, GFP_KERNEL);
+		      fnw_sz = sz;
+		      if (!fnw) {
+			ret = -ENOMEM;
+			goto reterr;
+		      }
+		      goto again;
 		    }
 
 		    if (!q)
 		      func_table[i] = fj;
+		    /* copy data before insertion point to new location */
 		    if (fj > funcbufptr)
 			memmove(fnw, funcbufptr, fj - funcbufptr);
 		    for (k = 0; k < j; k++)
 		      if (func_table[k])
 			func_table[k] = fnw + (func_table[k] - funcbufptr);
 
+		    /* copy data after insertion point to new location */
 		    if (first_free > fj) {
 			memmove(fnw + (fj - funcbufptr) + delta, fj, first_free - fj);
 			for (k = j; k < MAX_NR_FUNC; k++)
@@ -2087,7 +2106,9 @@ int vt_do_kdgkb_ioctl(int cmd, struct kbsentry __user *user_kdgkb, int perm)
 		    funcbufleft = funcbufleft - delta + sz - funcbufsize;
 		    funcbufsize = sz;
 		}
+		/* finally insert item itself */
 		strcpy(func_table[i], kbs->kb_string);
+		spin_unlock_irqrestore(&func_buf_lock, flags);
 		break;
 	}
 	ret = 0;

drivers/tty/vt/vt.c

@@ -4155,8 +4155,6 @@ void do_blank_screen(int entering_gfx)
 		return;
 	}
 
-	if (blank_state != blank_normal_wait)
-		return;
 	blank_state = blank_off;
 
 	/* don't blank graphics */

fs/btrfs/backref.c

@@ -1452,8 +1452,8 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans,
  * callers (such as fiemap) which want to know whether the extent is
  * shared but do not need a ref count.
  *
- * This attempts to allocate a transaction in order to account for
+ * This attempts to attach to the running transaction in order to account for
- * delayed refs, but continues on even when the alloc fails.
+ * delayed refs, but continues on even when no running transaction exists.
  *
  * Return: 0 if extent is not shared, 1 if it is shared, < 0 on error.
  */
@@ -1476,13 +1476,16 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr)
 	tmp = ulist_alloc(GFP_NOFS);
 	roots = ulist_alloc(GFP_NOFS);
 	if (!tmp || !roots) {
-		ulist_free(tmp);
+		ret = -ENOMEM;
-		ulist_free(roots);
+		goto out;
-		return -ENOMEM;
 	}
 
-	trans = btrfs_join_transaction(root);
+	trans = btrfs_attach_transaction(root);
 	if (IS_ERR(trans)) {
+		if (PTR_ERR(trans) != -ENOENT && PTR_ERR(trans) != -EROFS) {
+			ret = PTR_ERR(trans);
+			goto out;
+		}
 		trans = NULL;
 		down_read(&fs_info->commit_root_sem);
 	} else {
@@ -1515,6 +1518,7 @@ int btrfs_check_shared(struct btrfs_root *root, u64 inum, u64 bytenr)
 	} else {
 		up_read(&fs_info->commit_root_sem);
 	}
+out:
 	ulist_free(tmp);
 	ulist_free(roots);
 	return ret;
@@ -1904,14 +1908,20 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
 			extent_item_objectid);
 
 	if (!search_commit_root) {
-		trans = btrfs_join_transaction(fs_info->extent_root);
+		trans = btrfs_attach_transaction(fs_info->extent_root);
-		if (IS_ERR(trans))
+		if (IS_ERR(trans)) {
-			return PTR_ERR(trans);
+			if (PTR_ERR(trans) != -ENOENT &&
-		btrfs_get_tree_mod_seq(fs_info, &tree_mod_seq_elem);
+			    PTR_ERR(trans) != -EROFS)
-	} else {
+				return PTR_ERR(trans);
-		down_read(&fs_info->commit_root_sem);
+			trans = NULL;
+		}
 	}
 
+	if (trans)
+		btrfs_get_tree_mod_seq(fs_info, &tree_mod_seq_elem);
+	else
+		down_read(&fs_info->commit_root_sem);
+
 	ret = btrfs_find_all_leafs(trans, fs_info, extent_item_objectid,
 				   tree_mod_seq_elem.seq, &refs,
 				   &extent_item_pos, ignore_offset);
@@ -1943,7 +1953,7 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info,
 
 	free_leaf_list(refs);
 out:
-	if (!search_commit_root) {
+	if (trans) {
 		btrfs_put_tree_mod_seq(fs_info, &tree_mod_seq_elem);
 		btrfs_end_transaction(trans);
 	} else {

fs/btrfs/ctree.c

@@ -2436,6 +2436,16 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
 	if (tmp) {
 		/* first we do an atomic uptodate check */
 		if (btrfs_buffer_uptodate(tmp, gen, 1) > 0) {
+			/*
+			 * Do extra check for first_key, eb can be stale due to
+			 * being cached, read from scrub, or have multiple
+			 * parents (shared tree blocks).
+			 */
+			if (btrfs_verify_level_key(fs_info, tmp,
+					parent_level - 1, &first_key, gen)) {
+				free_extent_buffer(tmp);
+				return -EUCLEAN;
+			}
 			*eb_ret = tmp;
 			return 0;
 		}

fs/btrfs/disk-io.c

@@ -408,9 +408,9 @@ static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info,
 	return ret;
 }
 
-static int verify_level_key(struct btrfs_fs_info *fs_info,
+int btrfs_verify_level_key(struct btrfs_fs_info *fs_info,
-			    struct extent_buffer *eb, int level,
+			   struct extent_buffer *eb, int level,
-			    struct btrfs_key *first_key, u64 parent_transid)
+			   struct btrfs_key *first_key, u64 parent_transid)
 {
 	int found_level;
 	struct btrfs_key found_key;
@@ -487,8 +487,8 @@ static int btree_read_extent_buffer_pages(struct btrfs_fs_info *fs_info,
 			if (verify_parent_transid(io_tree, eb,
 						   parent_transid, 0))
 				ret = -EIO;
-			else if (verify_level_key(fs_info, eb, level,
+			else if (btrfs_verify_level_key(fs_info, eb, level,
-						  first_key, parent_transid))
+						first_key, parent_transid))
 				ret = -EUCLEAN;
 			else
 				break;
@@ -995,13 +995,18 @@ void readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr)
 {
 	struct extent_buffer *buf = NULL;
 	struct inode *btree_inode = fs_info->btree_inode;
+	int ret;
 
 	buf = btrfs_find_create_tree_block(fs_info, bytenr);
 	if (IS_ERR(buf))
 		return;
-	read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
+
-				 buf, WAIT_NONE, 0);
+	ret = read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree, buf,
-	free_extent_buffer(buf);
+			WAIT_NONE, 0);
+	if (ret < 0)
+		free_extent_buffer_stale(buf);
+	else
+		free_extent_buffer(buf);
 }
 
 int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr,
@@ -1021,12 +1026,12 @@ int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr,
 	ret = read_extent_buffer_pages(io_tree, buf, WAIT_PAGE_LOCK,
 				       mirror_num);
 	if (ret) {
-		free_extent_buffer(buf);
+		free_extent_buffer_stale(buf);
 		return ret;
 	}
 
 	if (test_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags)) {
-		free_extent_buffer(buf);
+		free_extent_buffer_stale(buf);
 		return -EIO;
 	} else if (extent_buffer_uptodate(buf)) {
 		*eb = buf;
@@ -1080,7 +1085,7 @@ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
 	ret = btree_read_extent_buffer_pages(fs_info, buf, parent_transid,
 					     level, first_key);
 	if (ret) {
-		free_extent_buffer(buf);
+		free_extent_buffer_stale(buf);
 		return ERR_PTR(ret);
 	}
 	return buf;

fs/btrfs/disk-io.h

@@ -39,6 +39,9 @@ static inline u64 btrfs_sb_offset(int mirror)
 struct btrfs_device;
 struct btrfs_fs_devices;
 
+int btrfs_verify_level_key(struct btrfs_fs_info *fs_info,
+			   struct extent_buffer *eb, int level,
+			   struct btrfs_key *first_key, u64 parent_transid);
 struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
 				      u64 parent_transid, int level,
 				      struct btrfs_key *first_key);

fs/btrfs/extent-tree.c

@@ -10789,9 +10789,9 @@ int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info,
  * held back allocations.
  */
 static int btrfs_trim_free_extents(struct btrfs_device *device,
-				   u64 minlen, u64 *trimmed)
+				   struct fstrim_range *range, u64 *trimmed)
 {
-	u64 start = 0, len = 0;
+	u64 start = range->start, len = 0;
 	int ret;
 
 	*trimmed = 0;
@@ -10834,8 +10834,8 @@ static int btrfs_trim_free_extents(struct btrfs_device *device,
 		if (!trans)
 			up_read(&fs_info->commit_root_sem);
 
-		ret = find_free_dev_extent_start(trans, device, minlen, start,
+		ret = find_free_dev_extent_start(trans, device, range->minlen,
-						 &start, &len);
+						 start, &start, &len);
 		if (trans) {
 			up_read(&fs_info->commit_root_sem);
 			btrfs_put_transaction(trans);
@@ -10848,6 +10848,16 @@ static int btrfs_trim_free_extents(struct btrfs_device *device,
 			break;
 		}
 
+		/* If we are out of the passed range break */
+		if (start > range->start + range->len - 1) {
+			mutex_unlock(&fs_info->chunk_mutex);
+			ret = 0;
+			break;
+		}
+
+		start = max(range->start, start);
+		len = min(range->len, len);
+
 		ret = btrfs_issue_discard(device->bdev, start, len, &bytes);
 		mutex_unlock(&fs_info->chunk_mutex);
 
@@ -10857,6 +10867,10 @@ static int btrfs_trim_free_extents(struct btrfs_device *device,
 		start += len;
 		*trimmed += bytes;
 
+		/* We've trimmed enough */
+		if (*trimmed >= range->len)
+			break;
+
 		if (fatal_signal_pending(current)) {
 			ret = -ERESTARTSYS;
 			break;
@@ -10940,8 +10954,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
 	mutex_lock(&fs_info->fs_devices->device_list_mutex);
 	devices = &fs_info->fs_devices->devices;
 	list_for_each_entry(device, devices, dev_list) {
-		ret = btrfs_trim_free_extents(device, range->minlen,
+		ret = btrfs_trim_free_extents(device, range, &group_trimmed);
-					      &group_trimmed);
 		if (ret) {
 			dev_failed++;
 			dev_ret = ret;

fs/btrfs/send.c

@@ -6583,6 +6583,38 @@ static int ensure_commit_roots_uptodate(struct send_ctx *sctx)
 	return btrfs_commit_transaction(trans);
 }
 
+/*
+ * Make sure any existing dellaloc is flushed for any root used by a send
+ * operation so that we do not miss any data and we do not race with writeback
+ * finishing and changing a tree while send is using the tree. This could
+ * happen if a subvolume is in RW mode, has delalloc, is turned to RO mode and
+ * a send operation then uses the subvolume.
+ * After flushing delalloc ensure_commit_roots_uptodate() must be called.
+ */
+static int flush_delalloc_roots(struct send_ctx *sctx)
+{
+	struct btrfs_root *root = sctx->parent_root;
+	int ret;
+	int i;
+
+	if (root) {
+		ret = btrfs_start_delalloc_snapshot(root);
+		if (ret)
+			return ret;
+		btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX);
+	}
+
+	for (i = 0; i < sctx->clone_roots_cnt; i++) {
+		root = sctx->clone_roots[i].root;
+		ret = btrfs_start_delalloc_snapshot(root);
+		if (ret)
+			return ret;
+		btrfs_wait_ordered_extents(root, U64_MAX, 0, U64_MAX);
+	}
+
+	return 0;
+}
+
 static void btrfs_root_dec_send_in_progress(struct btrfs_root* root)
 {
 	spin_lock(&root->root_item_lock);
@@ -6807,6 +6839,10 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg)
 			NULL);
 	sort_clone_roots = 1;
 
+	ret = flush_delalloc_roots(sctx);
+	if (ret)
+		goto out;
+
 	ret = ensure_commit_roots_uptodate(sctx);
 	if (ret)
 		goto out;

fs/dax.c

@@ -1660,8 +1660,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 		}
 
 		trace_dax_pmd_insert_mapping(inode, vmf, PMD_SIZE, pfn, entry);
-		result = vmf_insert_pfn_pmd(vma, vmf->address, vmf->pmd, pfn,
+		result = vmf_insert_pfn_pmd(vmf, pfn, write);
-					    write);
 		break;
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
@@ -1775,8 +1774,7 @@ static vm_fault_t dax_insert_pfn_mkwrite(struct vm_fault *vmf,
 		break;
 #ifdef CONFIG_FS_DAX_PMD
 	case PE_SIZE_PMD:
-		ret = vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd,
+		ret = vmf_insert_pfn_pmd(vmf, pfn, FAULT_FLAG_WRITE);
-			pfn, true);
 		break;
 #endif
 	default:

fs/ext4/ext4.h

@@ -1669,6 +1669,8 @@ static inline void ext4_clear_state_flags(struct ext4_inode_info *ei)
 #define EXT4_FEATURE_INCOMPAT_INLINE_DATA	0x8000 /* data in inode */
 #define EXT4_FEATURE_INCOMPAT_ENCRYPT		0x10000
 
+extern void ext4_update_dynamic_rev(struct super_block *sb);
+
 #define EXT4_FEATURE_COMPAT_FUNCS(name, flagname) \
 static inline bool ext4_has_feature_##name(struct super_block *sb) \
 { \
@@ -1677,6 +1679,7 @@ static inline bool ext4_has_feature_##name(struct super_block *sb) \
 } \
 static inline void ext4_set_feature_##name(struct super_block *sb) \
 { \
+	ext4_update_dynamic_rev(sb); \
 	EXT4_SB(sb)->s_es->s_feature_compat |= \
 		cpu_to_le32(EXT4_FEATURE_COMPAT_##flagname); \
 } \
@@ -1694,6 +1697,7 @@ static inline bool ext4_has_feature_##name(struct super_block *sb) \
 } \
 static inline void ext4_set_feature_##name(struct super_block *sb) \
 { \
+	ext4_update_dynamic_rev(sb); \
 	EXT4_SB(sb)->s_es->s_feature_ro_compat |= \
 		cpu_to_le32(EXT4_FEATURE_RO_COMPAT_##flagname); \
 } \
@@ -1711,6 +1715,7 @@ static inline bool ext4_has_feature_##name(struct super_block *sb) \
 } \
 static inline void ext4_set_feature_##name(struct super_block *sb) \
 { \
+	ext4_update_dynamic_rev(sb); \
 	EXT4_SB(sb)->s_es->s_feature_incompat |= \
 		cpu_to_le32(EXT4_FEATURE_INCOMPAT_##flagname); \
 } \
@@ -2673,7 +2678,6 @@ do {									\
 
 #endif
 
-extern void ext4_update_dynamic_rev(struct super_block *sb);
 extern int ext4_update_compat_feature(handle_t *handle, struct super_block *sb,
 					__u32 compat);
 extern int ext4_update_rocompat_feature(handle_t *handle,

fs/ext4/extents.c

@@ -1035,6 +1035,7 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
 	__le32 border;
 	ext4_fsblk_t *ablocks = NULL; /* array of allocated blocks */
 	int err = 0;
+	size_t ext_size = 0;
 
 	/* make decision: where to split? */
 	/* FIXME: now decision is simplest: at current extent */
@@ -1126,6 +1127,10 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
 		le16_add_cpu(&neh->eh_entries, m);
 	}
 
+	/* zero out unused area in the extent block */
+	ext_size = sizeof(struct ext4_extent_header) +
+		sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries);
+	memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size);
 	ext4_extent_block_csum_set(inode, neh);
 	set_buffer_uptodate(bh);
 	unlock_buffer(bh);
@@ -1205,6 +1210,11 @@ static int ext4_ext_split(handle_t *handle, struct inode *inode,
 				sizeof(struct ext4_extent_idx) * m);
 			le16_add_cpu(&neh->eh_entries, m);
 		}
+		/* zero out unused area in the extent block */
+		ext_size = sizeof(struct ext4_extent_header) +
+		   (sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries));
+		memset(bh->b_data + ext_size, 0,
+			inode->i_sb->s_blocksize - ext_size);
 		ext4_extent_block_csum_set(inode, neh);
 		set_buffer_uptodate(bh);
 		unlock_buffer(bh);
@@ -1270,6 +1280,7 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
 	ext4_fsblk_t newblock, goal = 0;
 	struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
 	int err = 0;
+	size_t ext_size = 0;
 
 	/* Try to prepend new index to old one */
 	if (ext_depth(inode))
@@ -1295,9 +1306,11 @@ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode,
 		goto out;
 	}
 
+	ext_size = sizeof(EXT4_I(inode)->i_data);
 	/* move top-level index/leaf into new block */
-	memmove(bh->b_data, EXT4_I(inode)->i_data,
+	memmove(bh->b_data, EXT4_I(inode)->i_data, ext_size);
-		sizeof(EXT4_I(inode)->i_data));
+	/* zero out unused area in the extent block */
+	memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size);
 
 	/* set size of new block */
 	neh = ext_block_hdr(bh);

fs/ext4/file.c

@@ -264,6 +264,13 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	}
 
 	ret = __generic_file_write_iter(iocb, from);
+	/*
+	 * Unaligned direct AIO must be the only IO in flight. Otherwise
+	 * overlapping aligned IO after unaligned might result in data
+	 * corruption.
+	 */
+	if (ret == -EIOCBQUEUED && unaligned_aio)
+		ext4_unwritten_wait(inode);
 	inode_unlock(inode);
 
 	if (ret > 0)

fs/ext4/inode.c

@@ -5373,7 +5373,6 @@ static int ext4_do_update_inode(handle_t *handle,
 		err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
 		if (err)
 			goto out_brelse;
-		ext4_update_dynamic_rev(sb);
 		ext4_set_feature_large_file(sb);
 		ext4_handle_sync(handle);
 		err = ext4_handle_dirty_super(handle, sb);
@@ -6024,7 +6023,7 @@ int ext4_expand_extra_isize(struct inode *inode,
 
 	ext4_write_lock_xattr(inode, &no_expand);
 
-	BUFFER_TRACE(iloc.bh, "get_write_access");
+	BUFFER_TRACE(iloc->bh, "get_write_access");
 	error = ext4_journal_get_write_access(handle, iloc->bh);
 	if (error) {
 		brelse(iloc->bh);

fs/ext4/ioctl.c

@@ -977,7 +977,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (err == 0)
 			err = err2;
 		mnt_drop_write_file(filp);
-		if (!err && (o_group > EXT4_SB(sb)->s_groups_count) &&
+		if (!err && (o_group < EXT4_SB(sb)->s_groups_count) &&
 		    ext4_has_group_desc_csum(sb) &&
 		    test_opt(sb, INIT_INODE_TABLE))
 			err = ext4_register_li_request(sb, o_group);

fs/ext4/mballoc.c

@@ -1539,7 +1539,7 @@ static int mb_find_extent(struct ext4_buddy *e4b, int block,
 		ex->fe_len += 1 << order;
 	}
 
-	if (ex->fe_start + ex->fe_len > (1 << (e4b->bd_blkbits + 3))) {
+	if (ex->fe_start + ex->fe_len > EXT4_CLUSTERS_PER_GROUP(e4b->bd_sb)) {
 		/* Should never happen! (but apparently sometimes does?!?) */
 		WARN_ON(1);
 		ext4_error(e4b->bd_sb, "corruption or bug in mb_find_extent "

fs/ext4/namei.c

@@ -871,12 +871,15 @@ static void dx_release(struct dx_frame *frames)
 {
 	struct dx_root_info *info;
 	int i;
+	unsigned int indirect_levels;
 
 	if (frames[0].bh == NULL)
 		return;
 
 	info = &((struct dx_root *)frames[0].bh->b_data)->info;
-	for (i = 0; i <= info->indirect_levels; i++) {
+	/* save local copy, "info" may be freed after brelse() */
+	indirect_levels = info->indirect_levels;
+	for (i = 0; i <= indirect_levels; i++) {
 		if (frames[i].bh == NULL)
 			break;
 		brelse(frames[i].bh);

fs/ext4/resize.c

@@ -874,6 +874,7 @@ static int add_new_gdb(handle_t *handle, struct inode *inode,
 	err = ext4_handle_dirty_metadata(handle, NULL, gdb_bh);
 	if (unlikely(err)) {
 		ext4_std_error(sb, err);
+		iloc.bh = NULL;
 		goto errout;
 	}
 	brelse(dind);

fs/ext4/super.c

@@ -698,7 +698,7 @@ void __ext4_abort(struct super_block *sb, const char *function,
 			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
 		save_error_info(sb, function, line);
 	}
-	if (test_opt(sb, ERRORS_PANIC)) {
+	if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) {
 		if (EXT4_SB(sb)->s_journal &&
 		  !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
 			return;
@@ -2259,7 +2259,6 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 		es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
 	le16_add_cpu(&es->s_mnt_count, 1);
 	ext4_update_tstamp(es, s_mtime);
-	ext4_update_dynamic_rev(sb);
 	if (sbi->s_journal)
 		ext4_set_feature_journal_needs_recovery(sb);
 
@@ -3514,6 +3513,37 @@ int ext4_calculate_overhead(struct super_block *sb)
 	return 0;
 }
 
+static void ext4_clamp_want_extra_isize(struct super_block *sb)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_super_block *es = sbi->s_es;
+
+	/* determine the minimum size of new large inodes, if present */
+	if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE &&
+	    sbi->s_want_extra_isize == 0) {
+		sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
+						     EXT4_GOOD_OLD_INODE_SIZE;
+		if (ext4_has_feature_extra_isize(sb)) {
+			if (sbi->s_want_extra_isize <
+			    le16_to_cpu(es->s_want_extra_isize))
+				sbi->s_want_extra_isize =
+					le16_to_cpu(es->s_want_extra_isize);
+			if (sbi->s_want_extra_isize <
+			    le16_to_cpu(es->s_min_extra_isize))
+				sbi->s_want_extra_isize =
+					le16_to_cpu(es->s_min_extra_isize);
+		}
+	}
+	/* Check if enough inode space is available */
+	if (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize >
+							sbi->s_inode_size) {
+		sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
+						       EXT4_GOOD_OLD_INODE_SIZE;
+		ext4_msg(sb, KERN_INFO,
+			 "required extra inode space not available");
+	}
+}
+
 static void ext4_set_resv_clusters(struct super_block *sb)
 {
 	ext4_fsblk_t resv_clusters;
@@ -4239,7 +4269,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				 "data=, fs mounted w/o journal");
 			goto failed_mount_wq;
 		}
-		sbi->s_def_mount_opt &= EXT4_MOUNT_JOURNAL_CHECKSUM;
+		sbi->s_def_mount_opt &= ~EXT4_MOUNT_JOURNAL_CHECKSUM;
 		clear_opt(sb, JOURNAL_CHECKSUM);
 		clear_opt(sb, DATA_FLAGS);
 		sbi->s_journal = NULL;
@@ -4388,30 +4418,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	} else if (ret)
 		goto failed_mount4a;
 
-	/* determine the minimum size of new large inodes, if present */
+	ext4_clamp_want_extra_isize(sb);
-	if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE &&
-	    sbi->s_want_extra_isize == 0) {
-		sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
-						     EXT4_GOOD_OLD_INODE_SIZE;
-		if (ext4_has_feature_extra_isize(sb)) {
-			if (sbi->s_want_extra_isize <
-			    le16_to_cpu(es->s_want_extra_isize))
-				sbi->s_want_extra_isize =
-					le16_to_cpu(es->s_want_extra_isize);
-			if (sbi->s_want_extra_isize <
-			    le16_to_cpu(es->s_min_extra_isize))
-				sbi->s_want_extra_isize =
-					le16_to_cpu(es->s_min_extra_isize);
-		}
-	}
-	/* Check if enough inode space is available */
-	if (EXT4_GOOD_OLD_INODE_SIZE + sbi->s_want_extra_isize >
-							sbi->s_inode_size) {
-		sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
-						       EXT4_GOOD_OLD_INODE_SIZE;
-		ext4_msg(sb, KERN_INFO, "required extra inode space not"
-			 "available");
-	}
 
 	ext4_set_resv_clusters(sb);
 
@@ -5197,6 +5204,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		goto restore_opts;
 	}
 
+	ext4_clamp_want_extra_isize(sb);
+
 	if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^
 	    test_opt(sb, JOURNAL_CHECKSUM)) {
 		ext4_msg(sb, KERN_ERR, "changing journal_checksum "

fs/ext4/xattr.c

@@ -1700,7 +1700,7 @@ static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
 
 	/* No failures allowed past this point. */
 
-	if (!s->not_found && here->e_value_size && here->e_value_offs) {
+	if (!s->not_found && here->e_value_size && !here->e_value_inum) {
 		/* Remove the old value. */
 		void *first_val = s->base + min_offs;
 		size_t offs = le16_to_cpu(here->e_value_offs);

fs/fs-writeback.c

@@ -530,8 +530,6 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 
 	isw->inode = inode;
 
-	atomic_inc(&isw_nr_in_flight);
-
 	/*
 	 * In addition to synchronizing among switchers, I_WB_SWITCH tells
 	 * the RCU protected stat update paths to grab the i_page
@@ -539,6 +537,9 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id)
 	 * Let's continue after I_WB_SWITCH is guaranteed to be visible.
 	 */
 	call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn);
+
+	atomic_inc(&isw_nr_in_flight);
+
 	goto out_unlock;
 
 out_free:
@@ -908,7 +909,11 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
 void cgroup_writeback_umount(void)
 {
 	if (atomic_read(&isw_nr_in_flight)) {
-		synchronize_rcu();
+		/*
+		 * Use rcu_barrier() to wait for all pending callbacks to
+		 * ensure that all in-flight wb switches are in the workqueue.
+		 */
+		rcu_barrier();
 		flush_workqueue(isw_wq);
 	}
 }

fs/hugetlbfs/inode.c

@@ -426,9 +426,7 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 			u32 hash;
 
 			index = page->index;
-			hash = hugetlb_fault_mutex_hash(h, current->mm,
+			hash = hugetlb_fault_mutex_hash(h, mapping, index, 0);
-							&pseudo_vma,
-							mapping, index, 0);
 			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 			/*
@@ -625,8 +623,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 		addr = index * hpage_size;
 
 		/* mutex taken here, fault path and hole punch */
-		hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping,
+		hash = hugetlb_fault_mutex_hash(h, mapping, index, addr);
-						index, addr);
 		mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 		/* See if already present in mapping to avoid alloc/free */

fs/jbd2/journal.c

@@ -1366,6 +1366,10 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags)
 	journal_superblock_t *sb = journal->j_superblock;
 	int ret;
 
+	/* Buffer got discarded which means block device got invalidated */
+	if (!buffer_mapped(bh))
+		return -EIO;
+
 	trace_jbd2_write_superblock(journal, write_flags);
 	if (!(journal->j_flags & JBD2_BARRIER))
 		write_flags &= ~(REQ_FUA | REQ_PREFLUSH);
@@ -2385,22 +2389,19 @@ static struct kmem_cache *jbd2_journal_head_cache;
 static atomic_t nr_journal_heads = ATOMIC_INIT(0);
 #endif
 
-static int jbd2_journal_init_journal_head_cache(void)
+static int __init jbd2_journal_init_journal_head_cache(void)
 {
-	int retval;
+	J_ASSERT(!jbd2_journal_head_cache);
-
-	J_ASSERT(jbd2_journal_head_cache == NULL);
 	jbd2_journal_head_cache = kmem_cache_create("jbd2_journal_head",
 				sizeof(struct journal_head),
 				0,		/* offset */
 				SLAB_TEMPORARY | SLAB_TYPESAFE_BY_RCU,
 				NULL);		/* ctor */
-	retval = 0;
 	if (!jbd2_journal_head_cache) {
-		retval = -ENOMEM;
 		printk(KERN_EMERG "JBD2: no memory for journal_head cache\n");
+		return -ENOMEM;
 	}
-	return retval;
+	return 0;
 }
 
 static void jbd2_journal_destroy_journal_head_cache(void)
@@ -2646,28 +2647,38 @@ static void __exit jbd2_remove_jbd_stats_proc_entry(void)
 
 struct kmem_cache *jbd2_handle_cache, *jbd2_inode_cache;
 
-static int __init jbd2_journal_init_handle_cache(void)
+static int __init jbd2_journal_init_inode_cache(void)
 {
-	jbd2_handle_cache = KMEM_CACHE(jbd2_journal_handle, SLAB_TEMPORARY);
+	J_ASSERT(!jbd2_inode_cache);
-	if (jbd2_handle_cache == NULL) {
-		printk(KERN_EMERG "JBD2: failed to create handle cache\n");
-		return -ENOMEM;
-	}
 	jbd2_inode_cache = KMEM_CACHE(jbd2_inode, 0);
-	if (jbd2_inode_cache == NULL) {
+	if (!jbd2_inode_cache) {
-		printk(KERN_EMERG "JBD2: failed to create inode cache\n");
+		pr_emerg("JBD2: failed to create inode cache\n");
-		kmem_cache_destroy(jbd2_handle_cache);
 		return -ENOMEM;
 	}
 	return 0;
 }
 
+static int __init jbd2_journal_init_handle_cache(void)
+{
+	J_ASSERT(!jbd2_handle_cache);
+	jbd2_handle_cache = KMEM_CACHE(jbd2_journal_handle, SLAB_TEMPORARY);
+	if (!jbd2_handle_cache) {
+		printk(KERN_EMERG "JBD2: failed to create handle cache\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static void jbd2_journal_destroy_inode_cache(void)
+{
+	kmem_cache_destroy(jbd2_inode_cache);
+	jbd2_inode_cache = NULL;
+}
+
 static void jbd2_journal_destroy_handle_cache(void)
 {
 	kmem_cache_destroy(jbd2_handle_cache);
 	jbd2_handle_cache = NULL;
-	kmem_cache_destroy(jbd2_inode_cache);
-	jbd2_inode_cache = NULL;
 }
 
 /*
@@ -2678,11 +2689,15 @@ static int __init journal_init_caches(void)
 {
 	int ret;
 
-	ret = jbd2_journal_init_revoke_caches();
+	ret = jbd2_journal_init_revoke_record_cache();
+	if (ret == 0)
+		ret = jbd2_journal_init_revoke_table_cache();
 	if (ret == 0)
 		ret = jbd2_journal_init_journal_head_cache();
 	if (ret == 0)
 		ret = jbd2_journal_init_handle_cache();
+	if (ret == 0)
+		ret = jbd2_journal_init_inode_cache();
 	if (ret == 0)
 		ret = jbd2_journal_init_transaction_cache();
 	return ret;
@@ -2690,9 +2705,11 @@ static int __init journal_init_caches(void)
 
 static void jbd2_journal_destroy_caches(void)
 {
-	jbd2_journal_destroy_revoke_caches();
+	jbd2_journal_destroy_revoke_record_cache();
+	jbd2_journal_destroy_revoke_table_cache();
 	jbd2_journal_destroy_journal_head_cache();
 	jbd2_journal_destroy_handle_cache();
+	jbd2_journal_destroy_inode_cache();
 	jbd2_journal_destroy_transaction_cache();
 	jbd2_journal_destroy_slabs();
 }

fs/jbd2/revoke.c

@@ -178,33 +178,41 @@ static struct jbd2_revoke_record_s *find_revoke_record(journal_t *journal,
 	return NULL;
 }
 
-void jbd2_journal_destroy_revoke_caches(void)
+void jbd2_journal_destroy_revoke_record_cache(void)
 {
 	kmem_cache_destroy(jbd2_revoke_record_cache);
 	jbd2_revoke_record_cache = NULL;
+}
+
+void jbd2_journal_destroy_revoke_table_cache(void)
+{
 	kmem_cache_destroy(jbd2_revoke_table_cache);
 	jbd2_revoke_table_cache = NULL;
 }
 
-int __init jbd2_journal_init_revoke_caches(void)
+int __init jbd2_journal_init_revoke_record_cache(void)
 {
 	J_ASSERT(!jbd2_revoke_record_cache);
-	J_ASSERT(!jbd2_revoke_table_cache);
-
 	jbd2_revoke_record_cache = KMEM_CACHE(jbd2_revoke_record_s,
 					SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY);
-	if (!jbd2_revoke_record_cache)
-		goto record_cache_failure;
 
+	if (!jbd2_revoke_record_cache) {
+		pr_emerg("JBD2: failed to create revoke_record cache\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+int __init jbd2_journal_init_revoke_table_cache(void)
+{
+	J_ASSERT(!jbd2_revoke_table_cache);
 	jbd2_revoke_table_cache = KMEM_CACHE(jbd2_revoke_table_s,
 					     SLAB_TEMPORARY);
-	if (!jbd2_revoke_table_cache)
+	if (!jbd2_revoke_table_cache) {
-		goto table_cache_failure;
+		pr_emerg("JBD2: failed to create revoke_table cache\n");
-	return 0;
-table_cache_failure:
-	jbd2_journal_destroy_revoke_caches();
-record_cache_failure:
 		return -ENOMEM;
+	}
+	return 0;
 }
 
 static struct jbd2_revoke_table_s *jbd2_journal_init_revoke_table(int hash_size)

fs/jbd2/transaction.c

@@ -42,9 +42,11 @@ int __init jbd2_journal_init_transaction_cache(void)
 					0,
 					SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY,
 					NULL);
-	if (transaction_cache)
+	if (!transaction_cache) {
-		return 0;
+		pr_emerg("JBD2: failed to create transaction cache\n");
-	return -ENOMEM;
+		return -ENOMEM;
+	}
+	return 0;
 }
 
 void jbd2_journal_destroy_transaction_cache(void)

fs/ocfs2/export.c

@@ -148,16 +148,24 @@ static struct dentry *ocfs2_get_parent(struct dentry *child)
 	u64 blkno;
 	struct dentry *parent;
 	struct inode *dir = d_inode(child);
+	int set;
 
 	trace_ocfs2_get_parent(child, child->d_name.len, child->d_name.name,
 			       (unsigned long long)OCFS2_I(dir)->ip_blkno);
 
+	status = ocfs2_nfs_sync_lock(OCFS2_SB(dir->i_sb), 1);
+	if (status < 0) {
+		mlog(ML_ERROR, "getting nfs sync lock(EX) failed %d\n", status);
+		parent = ERR_PTR(status);
+		goto bail;
+	}
+
 	status = ocfs2_inode_lock(dir, NULL, 0);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
 		parent = ERR_PTR(status);
-		goto bail;
+		goto unlock_nfs_sync;
 	}
 
 	status = ocfs2_lookup_ino_from_name(dir, "..", 2, &blkno);
@@ -166,11 +174,31 @@ static struct dentry *ocfs2_get_parent(struct dentry *child)
 		goto bail_unlock;
 	}
 
+	status = ocfs2_test_inode_bit(OCFS2_SB(dir->i_sb), blkno, &set);
+	if (status < 0) {
+		if (status == -EINVAL) {
+			status = -ESTALE;
+		} else
+			mlog(ML_ERROR, "test inode bit failed %d\n", status);
+		parent = ERR_PTR(status);
+		goto bail_unlock;
+	}
+
+	trace_ocfs2_get_dentry_test_bit(status, set);
+	if (!set) {
+		status = -ESTALE;
+		parent = ERR_PTR(status);
+		goto bail_unlock;
+	}
+
 	parent = d_obtain_alias(ocfs2_iget(OCFS2_SB(dir->i_sb), blkno, 0, 0));
 
 bail_unlock:
 	ocfs2_inode_unlock(dir, 0);
 
+unlock_nfs_sync:
+	ocfs2_nfs_sync_unlock(OCFS2_SB(dir->i_sb), 1);
+
 bail:
 	trace_ocfs2_get_parent_end(parent);
 

fs/pstore/inode.c

@@ -482,12 +482,10 @@ static struct file_system_type pstore_fs_type = {
 	.kill_sb	= pstore_kill_sb,
 };
 
-static int __init init_pstore_fs(void)
+int __init pstore_init_fs(void)
 {
 	int err;
 
-	pstore_choose_compression();
-
 	/* Create a convenient mount point for people to access pstore */
 	err = sysfs_create_mount_point(fs_kobj, "pstore");
 	if (err)
@@ -500,14 +498,9 @@ static int __init init_pstore_fs(void)
 out:
 	return err;
 }
-module_init(init_pstore_fs)
 
-static void __exit exit_pstore_fs(void)
+void __exit pstore_exit_fs(void)
 {
 	unregister_filesystem(&pstore_fs_type);
 	sysfs_remove_mount_point(fs_kobj, "pstore");
 }
-module_exit(exit_pstore_fs)
-
-MODULE_AUTHOR("Tony Luck <tony.luck@intel.com>");
-MODULE_LICENSE("GPL");

fs/pstore/internal.h

@@ -37,7 +37,8 @@ extern bool	pstore_is_mounted(void);
 extern void	pstore_record_init(struct pstore_record *record,
 				   struct pstore_info *psi);
 
-/* Called during module_init() */
+/* Called during pstore init/exit. */
-extern void __init pstore_choose_compression(void);
+int __init	pstore_init_fs(void);
+void __exit	pstore_exit_fs(void);
 
 #endif

fs/pstore/platform.c

@@ -274,36 +274,56 @@ static int pstore_decompress(void *in, void *out,
 
 static void allocate_buf_for_compression(void)
 {
+	struct crypto_comp *ctx;
+	int size;
+	char *buf;
+
+	/* Skip if not built-in or compression backend not selected yet. */
 	if (!IS_ENABLED(CONFIG_PSTORE_COMPRESS) || !zbackend)
 		return;
 
+	/* Skip if no pstore backend yet or compression init already done. */
+	if (!psinfo || tfm)
+		return;
+
 	if (!crypto_has_comp(zbackend->name, 0, 0)) {
-		pr_err("No %s compression\n", zbackend->name);
+		pr_err("Unknown compression: %s\n", zbackend->name);
 		return;
 	}
 
-	big_oops_buf_sz = zbackend->zbufsize(psinfo->bufsize);
+	size = zbackend->zbufsize(psinfo->bufsize);
-	if (big_oops_buf_sz <= 0)
+	if (size <= 0) {
-		return;
+		pr_err("Invalid compression size for %s: %d\n",
-
+		       zbackend->name, size);
-	big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
-	if (!big_oops_buf) {
-		pr_err("allocate compression buffer error!\n");
 		return;
 	}
 
-	tfm = crypto_alloc_comp(zbackend->name, 0, 0);
+	buf = kmalloc(size, GFP_KERNEL);
-	if (IS_ERR_OR_NULL(tfm)) {
+	if (!buf) {
-		kfree(big_oops_buf);
+		pr_err("Failed %d byte compression buffer allocation for: %s\n",
-		big_oops_buf = NULL;
+		       size, zbackend->name);
-		pr_err("crypto_alloc_comp() failed!\n");
 		return;
 	}
+
+	ctx = crypto_alloc_comp(zbackend->name, 0, 0);
+	if (IS_ERR_OR_NULL(ctx)) {
+		kfree(buf);
+		pr_err("crypto_alloc_comp('%s') failed: %ld\n", zbackend->name,
+		       PTR_ERR(ctx));
+		return;
+	}
+
+	/* A non-NULL big_oops_buf indicates compression is available. */
+	tfm = ctx;
+	big_oops_buf_sz = size;
+	big_oops_buf = buf;
+
+	pr_info("Using compression: %s\n", zbackend->name);
 }
 
 static void free_buf_for_compression(void)
 {
-	if (IS_ENABLED(CONFIG_PSTORE_COMPRESS) && !IS_ERR_OR_NULL(tfm))
+	if (IS_ENABLED(CONFIG_PSTORE_COMPRESS) && tfm)
 		crypto_free_comp(tfm);
 	kfree(big_oops_buf);
 	big_oops_buf = NULL;
@@ -774,14 +794,43 @@ void __init pstore_choose_compression(void)
 	for (step = zbackends; step->name; step++) {
 		if (!strcmp(compress, step->name)) {
 			zbackend = step;
-			pr_info("using %s compression\n", zbackend->name);
 			return;
 		}
 	}
 }
 
+static int __init pstore_init(void)
+{
+	int ret;
+
+	pstore_choose_compression();
+
+	/*
+	 * Check if any pstore backends registered earlier but did not
+	 * initialize compression because crypto was not ready. If so,
+	 * initialize compression now.
+	 */
+	allocate_buf_for_compression();
+
+	ret = pstore_init_fs();
+	if (ret)
+		return ret;
+
+	return 0;
+}
+late_initcall(pstore_init);
+
+static void __exit pstore_exit(void)
+{
+	pstore_exit_fs();
+}
+module_exit(pstore_exit)
+
 module_param(compress, charp, 0444);
 MODULE_PARM_DESC(compress, "Pstore compression to use");
 
 module_param(backend, charp, 0444);
 MODULE_PARM_DESC(backend, "Pstore backend to use");
+
+MODULE_AUTHOR("Tony Luck <tony.luck@intel.com>");
+MODULE_LICENSE("GPL");

fs/pstore/ram.c

@@ -956,7 +956,7 @@ static int __init ramoops_init(void)
 
 	return ret;
 }
-late_initcall(ramoops_init);
+postcore_initcall(ramoops_init);
 
 static void __exit ramoops_exit(void)
 {

include/linux/huge_mm.h

@@ -47,10 +47,8 @@ extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			unsigned long addr, pgprot_t newprot,
 			int prot_numa);
-vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
+vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write);
-			pmd_t *pmd, pfn_t pfn, bool write);
+vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write);
-vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
-			pud_t *pud, pfn_t pfn, bool write);
 enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_FLAG,
 	TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,

include/linux/hugetlb.h

@@ -123,9 +123,7 @@ void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason);
 void free_huge_page(struct page *page);
 void hugetlb_fix_reserve_counts(struct inode *inode);
 extern struct mutex *hugetlb_fault_mutex_table;
-u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
+u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
-				struct vm_area_struct *vma,
-				struct address_space *mapping,
 				pgoff_t idx, unsigned long address);
 
 pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);

include/linux/jbd2.h

@@ -1317,7 +1317,7 @@ extern void		__wait_on_journal (journal_t *);
 
 /* Transaction cache support */
 extern void jbd2_journal_destroy_transaction_cache(void);
-extern int  jbd2_journal_init_transaction_cache(void);
+extern int __init jbd2_journal_init_transaction_cache(void);
 extern void jbd2_journal_free_transaction(transaction_t *);
 
 /*
@@ -1445,8 +1445,10 @@ static inline void jbd2_free_inode(struct jbd2_inode *jinode)
 /* Primary revoke support */
 #define JOURNAL_REVOKE_DEFAULT_HASH 256
 extern int	   jbd2_journal_init_revoke(journal_t *, int);
-extern void	   jbd2_journal_destroy_revoke_caches(void);
+extern void	   jbd2_journal_destroy_revoke_record_cache(void);
-extern int	   jbd2_journal_init_revoke_caches(void);
+extern void	   jbd2_journal_destroy_revoke_table_cache(void);
+extern int __init jbd2_journal_init_revoke_record_cache(void);
+extern int __init jbd2_journal_init_revoke_table_cache(void);
 
 extern void	   jbd2_journal_destroy_revoke(journal_t *);
 extern int	   jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *);

include/linux/mfd/da9063/registers.h

@@ -215,9 +215,9 @@
 
 /* DA9063 Configuration registers */
 /* OTP */
-#define	DA9063_REG_OPT_COUNT		0x101
+#define	DA9063_REG_OTP_CONT		0x101
-#define	DA9063_REG_OPT_ADDR		0x102
+#define	DA9063_REG_OTP_ADDR		0x102
-#define	DA9063_REG_OPT_DATA		0x103
+#define	DA9063_REG_OTP_DATA		0x103
 
 /* Customer Trim and Configuration */
 #define	DA9063_REG_T_OFFSET		0x104

include/linux/mfd/max77620.h

@@ -136,8 +136,8 @@
 #define MAX77620_FPS_PERIOD_MIN_US		40
 #define MAX20024_FPS_PERIOD_MIN_US		20
 
-#define MAX77620_FPS_PERIOD_MAX_US		2560
+#define MAX20024_FPS_PERIOD_MAX_US		2560
-#define MAX20024_FPS_PERIOD_MAX_US		5120
+#define MAX77620_FPS_PERIOD_MAX_US		5120
 
 #define MAX77620_REG_FPS_GPIO1			0x54
 #define MAX77620_REG_FPS_GPIO2			0x55

kernel/fork.c

@@ -910,6 +910,15 @@ static void mm_init_aio(struct mm_struct *mm)
 #endif
 }
 
+static __always_inline void mm_clear_owner(struct mm_struct *mm,
+					   struct task_struct *p)
+{
+#ifdef CONFIG_MEMCG
+	if (mm->owner == p)
+		WRITE_ONCE(mm->owner, NULL);
+#endif
+}
+
 static void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
 {
 #ifdef CONFIG_MEMCG
@@ -1289,6 +1298,7 @@ static struct mm_struct *dup_mm(struct task_struct *tsk)
 free_pt:
 	/* don't put binfmt in mmput, we haven't got module yet */
 	mm->binfmt = NULL;
+	mm_init_owner(mm, NULL);
 	mmput(mm);
 
 fail_nomem:
@@ -1620,6 +1630,21 @@ static inline void rcu_copy_process(struct task_struct *p)
 #endif /* #ifdef CONFIG_TASKS_RCU */
 }
 
+static void __delayed_free_task(struct rcu_head *rhp)
+{
+	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
+
+	free_task(tsk);
+}
+
+static __always_inline void delayed_free_task(struct task_struct *tsk)
+{
+	if (IS_ENABLED(CONFIG_MEMCG))
+		call_rcu(&tsk->rcu, __delayed_free_task);
+	else
+		free_task(tsk);
+}
+
 /*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
@@ -2081,8 +2106,10 @@ static __latent_entropy struct task_struct *copy_process(
 bad_fork_cleanup_namespaces:
 	exit_task_namespaces(p);
 bad_fork_cleanup_mm:
-	if (p->mm)
+	if (p->mm) {
+		mm_clear_owner(p->mm, p);
 		mmput(p->mm);
+	}
 bad_fork_cleanup_signal:
 	if (!(clone_flags & CLONE_THREAD))
 		free_signal_struct(p->signal);
@@ -2113,7 +2140,7 @@ static __latent_entropy struct task_struct *copy_process(
 bad_fork_free:
 	p->state = TASK_DEAD;
 	put_task_stack(p);
-	free_task(p);
+	delayed_free_task(p);
 fork_out:
 	spin_lock_irq(&current->sighand->siglock);
 	hlist_del_init(&delayed.node);

kernel/locking/rwsem-xadd.c

@@ -130,6 +130,7 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 {
 	struct rwsem_waiter *waiter, *tmp;
 	long oldcount, woken = 0, adjustment = 0;
+	struct list_head wlist;
 
 	/*
 	 * Take a peek at the queue head waiter such that we can determine
@@ -188,18 +189,42 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 	 * of the queue. We know that woken will be at least 1 as we accounted
 	 * for above. Note we increment the 'active part' of the count by the
 	 * number of readers before waking any processes up.
+	 *
+	 * We have to do wakeup in 2 passes to prevent the possibility that
+	 * the reader count may be decremented before it is incremented. It
+	 * is because the to-be-woken waiter may not have slept yet. So it
+	 * may see waiter->task got cleared, finish its critical section and
+	 * do an unlock before the reader count increment.
+	 *
+	 * 1) Collect the read-waiters in a separate list, count them and
+	 *    fully increment the reader count in rwsem.
+	 * 2) For each waiters in the new list, clear waiter->task and
+	 *    put them into wake_q to be woken up later.
 	 */
-	list_for_each_entry_safe(waiter, tmp, &sem->wait_list, list) {
+	list_for_each_entry(waiter, &sem->wait_list, list) {
-		struct task_struct *tsk;
-
 		if (waiter->type == RWSEM_WAITING_FOR_WRITE)
 			break;
 
 		woken++;
-		tsk = waiter->task;
+	}
+	list_cut_before(&wlist, &sem->wait_list, &waiter->list);
 
+	adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;
+	if (list_empty(&sem->wait_list)) {
+		/* hit end of list above */
+		adjustment -= RWSEM_WAITING_BIAS;
+	}
+
+	if (adjustment)
+		atomic_long_add(adjustment, &sem->count);
+
+	/* 2nd pass */
+	list_for_each_entry_safe(waiter, tmp, &wlist, list) {
+		struct task_struct *tsk;
+
+		tsk = waiter->task;
 		get_task_struct(tsk);
-		list_del(&waiter->list);
+
 		/*
 		 * Ensure calling get_task_struct() before setting the reader
 		 * waiter to nil such that rwsem_down_read_failed() cannot
@@ -215,15 +240,6 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 		/* wake_q_add() already take the task ref */
 		put_task_struct(tsk);
 	}
-
-	adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;
-	if (list_empty(&sem->wait_list)) {
-		/* hit end of list above */
-		adjustment -= RWSEM_WAITING_BIAS;
-	}
-
-	if (adjustment)
-		atomic_long_add(adjustment, &sem->count);
 }
 
 /*

lib/iov_iter.c

@@ -817,8 +817,21 @@ EXPORT_SYMBOL(_copy_from_iter_full_nocache);
 
 static inline bool page_copy_sane(struct page *page, size_t offset, size_t n)
 {
-	struct page *head = compound_head(page);
+	struct page *head;
-	size_t v = n + offset + page_address(page) - page_address(head);
+	size_t v = n + offset;
+
+	/*
+	 * The general case needs to access the page order in order
+	 * to compute the page size.
+	 * However, we mostly deal with order-0 pages and thus can
+	 * avoid a possible cache line miss for requests that fit all
+	 * page orders.
+	 */
+	if (n <= v && v <= PAGE_SIZE)
+		return true;
+
+	head = compound_head(page);
+	v += (page - head) << PAGE_SHIFT;
 
 	if (likely(n <= v && v <= (PAGE_SIZE << compound_order(head))))
 		return true;

mm/huge_memory.c

@@ -772,11 +772,13 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 		pte_free(mm, pgtable);
 }
 
-vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
+vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
-			pmd_t *pmd, pfn_t pfn, bool write)
 {
+	unsigned long addr = vmf->address & PMD_MASK;
+	struct vm_area_struct *vma = vmf->vma;
 	pgprot_t pgprot = vma->vm_page_prot;
 	pgtable_t pgtable = NULL;
+
 	/*
 	 * If we had pmd_special, we could avoid all these restrictions,
 	 * but we need to be consistent with PTEs and architectures that
@@ -799,7 +801,7 @@ vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
 
 	track_pfn_insert(vma, &pgprot, pfn);
 
-	insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write, pgtable);
+	insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, pgtable);
 	return VM_FAULT_NOPAGE;
 }
 EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
@@ -848,10 +850,12 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
 	spin_unlock(ptl);
 }
 
-vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
+vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
-			pud_t *pud, pfn_t pfn, bool write)
 {
+	unsigned long addr = vmf->address & PUD_MASK;
+	struct vm_area_struct *vma = vmf->vma;
 	pgprot_t pgprot = vma->vm_page_prot;
+
 	/*
 	 * If we had pud_special, we could avoid all these restrictions,
 	 * but we need to be consistent with PTEs and architectures that
@@ -868,7 +872,7 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
 
 	track_pfn_insert(vma, &pgprot, pfn);
 
-	insert_pfn_pud(vma, addr, pud, pfn, pgprot, write);
+	insert_pfn_pud(vma, addr, vmf->pud, pfn, pgprot, write);
 	return VM_FAULT_NOPAGE;
 }
 EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud);

mm/hugetlb.c

@@ -1572,8 +1572,9 @@ static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
 	 */
 	if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) {
 		SetPageHugeTemporary(page);
+		spin_unlock(&hugetlb_lock);
 		put_page(page);
-		page = NULL;
+		return NULL;
 	} else {
 		h->surplus_huge_pages++;
 		h->surplus_huge_pages_node[page_to_nid(page)]++;
@@ -3777,8 +3778,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 			 * handling userfault.  Reacquire after handling
 			 * fault to make calling code simpler.
 			 */
-			hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping,
+			hash = hugetlb_fault_mutex_hash(h, mapping, idx, haddr);
-							idx, haddr);
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			ret = handle_userfault(&vmf, VM_UFFD_MISSING);
 			mutex_lock(&hugetlb_fault_mutex_table[hash]);
@@ -3886,21 +3886,14 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 }
 
 #ifdef CONFIG_SMP
-u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
+u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
-			    struct vm_area_struct *vma,
-			    struct address_space *mapping,
 			    pgoff_t idx, unsigned long address)
 {
 	unsigned long key[2];
 	u32 hash;
 
-	if (vma->vm_flags & VM_SHARED) {
+	key[0] = (unsigned long) mapping;
-		key[0] = (unsigned long) mapping;
+	key[1] = idx;
-		key[1] = idx;
-	} else {
-		key[0] = (unsigned long) mm;
-		key[1] = address >> huge_page_shift(h);
-	}
 
 	hash = jhash2((u32 *)&key, sizeof(key)/sizeof(u32), 0);
 
@@ -3911,9 +3904,7 @@ u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
  * For uniprocesor systems we always use a single mutex, so just
  * return 0 and avoid the hashing overhead.
  */
-u32 hugetlb_fault_mutex_hash(struct hstate *h, struct mm_struct *mm,
+u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
-			    struct vm_area_struct *vma,
-			    struct address_space *mapping,
 			    pgoff_t idx, unsigned long address)
 {
 	return 0;
@@ -3958,7 +3949,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * get spurious allocation failures if two CPUs race to instantiate
 	 * the same page in the page cache.
 	 */
-	hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping, idx, haddr);
+	hash = hugetlb_fault_mutex_hash(h, mapping, idx, haddr);
 	mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 	entry = huge_ptep_get(ptep);