Merge 4.15.0-rc6 into usb-next

We want the USB fixes in here, and this resolves a merge issue with the
vhci_rx.c file.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Documentation/admin-guide/kernel-parameters.rst

@@ -109,6 +109,7 @@ parameter is applicable::
 	IPV6	IPv6 support is enabled.
 	ISAPNP	ISA PnP code is enabled.
 	ISDN	Appropriate ISDN support is enabled.
+	ISOL	CPU Isolation is enabled.
 	JOY	Appropriate joystick support is enabled.
 	KGDB	Kernel debugger support is enabled.
 	KVM	Kernel Virtual Machine support is enabled.

Documentation/admin-guide/kernel-parameters.txt

@@ -328,11 +328,15 @@
 			not play well with APC CPU idle - disable it if you have
 			APC and your system crashes randomly.
 
-	apic=		[APIC,X86-32] Advanced Programmable Interrupt Controller
+	apic=		[APIC,X86] Advanced Programmable Interrupt Controller
 			Change the output verbosity whilst booting
 			Format: { quiet (default) | verbose | debug }
 			Change the amount of debugging information output
 			when initialising the APIC and IO-APIC components.
+			For X86-32, this can also be used to specify an APIC
+			driver name.
+			Format: apic=driver_name
+			Examples: apic=bigsmp
 
 	apic_extnmi=	[APIC,X86] External NMI delivery setting
 			Format: { bsp (default) | all | none }
@@ -1737,7 +1741,7 @@
 	isapnp=		[ISAPNP]
 			Format: <RDP>,<reset>,<pci_scan>,<verbosity>
 
-	isolcpus=	[KNL,SMP] Isolate a given set of CPUs from disturbance.
+	isolcpus=	[KNL,SMP,ISOL] Isolate a given set of CPUs from disturbance.
 			[Deprecated - use cpusets instead]
 			Format: [flag-list,]<cpu-list>
 
@@ -2662,7 +2666,7 @@
 			Valid arguments: on, off
 			Default: on
 
-	nohz_full=	[KNL,BOOT]
+	nohz_full=	[KNL,BOOT,SMP,ISOL]
 			The argument is a cpu list, as described above.
 			In kernels built with CONFIG_NO_HZ_FULL=y, set
 			the specified list of CPUs whose tick will be stopped
@@ -2708,6 +2712,8 @@
 			steal time is computed, but won't influence scheduler
 			behaviour
 
+	nopti		[X86-64] Disable kernel page table isolation
+
 	nolapic		[X86-32,APIC] Do not enable or use the local APIC.
 
 	nolapic_timer	[X86-32,APIC] Do not use the local APIC timer.
@@ -3282,6 +3288,12 @@
 	pt.		[PARIDE]
 			See Documentation/blockdev/paride.txt.
 
+	pti=		[X86_64]
+			Control user/kernel address space isolation:
+			on - enable
+			off - disable
+			auto - default setting
+
 	pty.legacy_count=
 			[KNL] Number of legacy pty's. Overwrites compiled-in
 			default number.

Documentation/admin-guide/thunderbolt.rst

@@ -230,7 +230,7 @@ If supported by your machine this will be exposed by the WMI bus with
 a sysfs attribute called "force_power".
 
 For example the intel-wmi-thunderbolt driver exposes this attribute in:
-  /sys/devices/platform/PNP0C14:00/wmi_bus/wmi_bus-PNP0C14:00/86CCFD48-205E-4A77-9C48-2021CBEDE341/force_power
+  /sys/bus/wmi/devices/86CCFD48-205E-4A77-9C48-2021CBEDE341/force_power
 
   To force the power to on, write 1 to this attribute file.
   To disable force power, write 0 to this attribute file.

Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt

@@ -13,7 +13,6 @@ Required properties:
                  at25df321a
                  at25df641
                  at26df081a
-                 en25s64
                  mr25h128
                  mr25h256
                  mr25h10
@@ -33,7 +32,6 @@ Required properties:
                  s25fl008k
                  s25fl064k
                  sst25vf040b
-                 sst25wf040b
                  m25p40
                  m25p80
                  m25p16

Documentation/devicetree/bindings/sound/da7218.txt

@@ -73,7 +73,7 @@ Example:
 		compatible = "dlg,da7218";
 		reg = <0x1a>;
 		interrupt-parent = <&gpio6>;
-		interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
 		wakeup-source;
 
 		VDD-supply = <&reg_audio>;

Documentation/devicetree/bindings/sound/da7219.txt

@@ -77,7 +77,7 @@ Example:
 		reg = <0x1a>;
 
 		interrupt-parent = <&gpio6>;
-		interrupts = <11 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <11 IRQ_TYPE_LEVEL_LOW>;
 
 		VDD-supply = <&reg_audio>;
 		VDDMIC-supply = <&reg_audio>;

Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt

@@ -12,24 +12,30 @@ Required properties:
   - "fsl,imx53-ecspi" for SPI compatible with the one integrated on i.MX53 and later Soc
 - reg : Offset and length of the register set for the device
 - interrupts : Should contain CSPI/eCSPI interrupt
-- cs-gpios : Specifies the gpio pins to be used for chipselects.
 - clocks : Clock specifiers for both ipg and per clocks.
 - clock-names : Clock names should include both "ipg" and "per"
 See the clock consumer binding,
 	Documentation/devicetree/bindings/clock/clock-bindings.txt
-- dmas: DMA specifiers for tx and rx dma. See the DMA client binding,
-		Documentation/devicetree/bindings/dma/dma.txt
-- dma-names: DMA request names should include "tx" and "rx" if present.
 
-Obsolete properties:
-- fsl,spi-num-chipselects : Contains the number of the chipselect
+Recommended properties:
+- cs-gpios : GPIOs to use as chip selects, see spi-bus.txt.  While the native chip
+select lines can be used, they appear to always generate a pulse between each
+word of a transfer.  Most use cases will require GPIO based chip selects to
+generate a valid transaction.
 
 Optional properties:
+- num-cs :  Number of total chip selects, see spi-bus.txt.
+- dmas: DMA specifiers for tx and rx dma. See the DMA client binding,
+Documentation/devicetree/bindings/dma/dma.txt.
+- dma-names: DMA request names, if present, should include "tx" and "rx".
 - fsl,spi-rdy-drctl: Integer, representing the value of DRCTL, the register
 controlling the SPI_READY handling. Note that to enable the DRCTL consideration,
 the SPI_READY mode-flag needs to be set too.
 Valid values are: 0 (disabled), 1 (edge-triggered burst) and 2 (level-triggered burst).
 
+Obsolete properties:
+- fsl,spi-num-chipselects : Contains the number of the chipselect
+
 Example:
 
 ecspi@70010000 {

Documentation/x86/x86_64/mm.txt

@@ -1,6 +1,4 @@
 
-<previous description obsolete, deleted>
-
 Virtual memory map with 4 level page tables:
 
 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
@@ -14,13 +12,16 @@ ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
 ffffec0000000000 - fffffbffffffffff (=44 bits) kasan shadow memory (16TB)
 ... unused hole ...
+fffffe0000000000 - fffffe7fffffffff (=39 bits) LDT remap for PTI
+fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping
 ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
 ... unused hole ...
 ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
 ... unused hole ...
 ffffffff80000000 - ffffffff9fffffff (=512 MB)  kernel text mapping, from phys 0
-ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space (variable)
-ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
+ffffffffa0000000 - [fixmap start]   (~1526 MB) module mapping space (variable)
+[fixmap start]   - ffffffffff5fffff kernel-internal fixmap range
+ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI
 ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
 
 Virtual memory map with 5 level page tables:
@@ -29,26 +30,29 @@ Virtual memory map with 5 level page tables:
 hole caused by [56:63] sign extension
 ff00000000000000 - ff0fffffffffffff (=52 bits) guard hole, reserved for hypervisor
 ff10000000000000 - ff8fffffffffffff (=55 bits) direct mapping of all phys. memory
-ff90000000000000 - ff91ffffffffffff (=49 bits) hole
-ff92000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space
+ff90000000000000 - ff9fffffffffffff (=52 bits) LDT remap for PTI
+ffa0000000000000 - ffd1ffffffffffff (=54 bits) vmalloc/ioremap space (12800 TB)
 ffd2000000000000 - ffd3ffffffffffff (=49 bits) hole
 ffd4000000000000 - ffd5ffffffffffff (=49 bits) virtual memory map (512TB)
 ... unused hole ...
 ffdf000000000000 - fffffc0000000000 (=53 bits) kasan shadow memory (8PB)
 ... unused hole ...
+fffffe8000000000 - fffffeffffffffff (=39 bits) cpu_entry_area mapping
 ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
 ... unused hole ...
 ffffffef00000000 - fffffffeffffffff (=64 GB) EFI region mapping space
 ... unused hole ...
 ffffffff80000000 - ffffffff9fffffff (=512 MB)  kernel text mapping, from phys 0
-ffffffffa0000000 - ffffffffff5fffff (=1526 MB) module mapping space
-ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls
+ffffffffa0000000 - [fixmap start]   (~1526 MB) module mapping space
+[fixmap start]   - ffffffffff5fffff kernel-internal fixmap range
+ffffffffff600000 - ffffffffff600fff (=4 kB) legacy vsyscall ABI
 ffffffffffe00000 - ffffffffffffffff (=2 MB) unused hole
 
 Architecture defines a 64-bit virtual address. Implementations can support
 less. Currently supported are 48- and 57-bit virtual addresses. Bits 63
-through to the most-significant implemented bit are set to either all ones
-or all zero. This causes hole between user space and kernel addresses.
+through to the most-significant implemented bit are sign extended.
+This causes hole between user space and kernel addresses if you interpret them
+as unsigned.
 
 The direct mapping covers all memory in the system up to the highest
 memory address (this means in some cases it can also include PCI memory
@@ -58,9 +62,6 @@ vmalloc space is lazily synchronized into the different PML4/PML5 pages of
 the processes using the page fault handler, with init_top_pgt as
 reference.
 
-Current X86-64 implementations support up to 46 bits of address space (64 TB),
-which is our current limit. This expands into MBZ space in the page tables.
-
 We map EFI runtime services in the 'efi_pgd' PGD in a 64Gb large virtual
 memory window (this size is arbitrary, it can be raised later if needed).
 The mappings are not part of any other kernel PGD and are only available
@@ -72,5 +73,3 @@ following fixmap section.
 Note that if CONFIG_RANDOMIZE_MEMORY is enabled, the direct mapping of all
 physical memory, vmalloc/ioremap space and virtual memory map are randomized.
 Their order is preserved but their base will be offset early at boot time.
-
--Andi Kleen, Jul 2004

MAINTAINERS

@@ -2621,24 +2621,22 @@ F:	fs/bfs/
 F:	include/uapi/linux/bfs_fs.h
 
 BLACKFIN ARCHITECTURE
-M:	Steven Miao <realmz6@gmail.com>
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 T:	git git://git.code.sf.net/p/adi-linux/code
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	arch/blackfin/
 
 BLACKFIN EMAC DRIVER
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	drivers/net/ethernet/adi/
 
 BLACKFIN MEDIA DRIVER
-M:	Scott Jiang <scott.jiang.linux@gmail.com>
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org/
-S:	Supported
+S:	Orphan
 F:	drivers/media/platform/blackfin/
 F:	drivers/media/i2c/adv7183*
 F:	drivers/media/i2c/vs6624*
@@ -2646,25 +2644,25 @@ F:	drivers/media/i2c/vs6624*
 BLACKFIN RTC DRIVER
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	drivers/rtc/rtc-bfin.c
 
 BLACKFIN SDH DRIVER
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	drivers/mmc/host/bfin_sdh.c
 
 BLACKFIN SERIAL DRIVER
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	drivers/tty/serial/bfin_uart.c
 
 BLACKFIN WATCHDOG DRIVER
 L:	adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers)
 W:	http://blackfin.uclinux.org
-S:	Supported
+S:	Orphan
 F:	drivers/watchdog/bfin_wdt.c
 
 BLINKM RGB LED DRIVER
@@ -13493,6 +13491,7 @@ M:	Mika Westerberg <mika.westerberg@linux.intel.com>
 M:	Yehezkel Bernat <yehezkel.bernat@intel.com>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/westeri/thunderbolt.git
 S:	Maintained
+F:	Documentation/admin-guide/thunderbolt.rst
 F:	drivers/thunderbolt/
 F:	include/linux/thunderbolt.h
 

Makefile

@@ -2,7 +2,7 @@
 VERSION = 4
 PATCHLEVEL = 15
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc6
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*
@@ -789,6 +789,9 @@ KBUILD_CFLAGS += $(call cc-disable-warning, pointer-sign)
 # disable invalid "can't wrap" optimizations for signed / pointers
 KBUILD_CFLAGS	+= $(call cc-option,-fno-strict-overflow)
 
+# Make sure -fstack-check isn't enabled (like gentoo apparently did)
+KBUILD_CFLAGS  += $(call cc-option,-fno-stack-check,)
+
 # conserve stack if available
 KBUILD_CFLAGS   += $(call cc-option,-fconserve-stack)
 

arch/arm/lib/csumpartialcopyuser.S

@@ -85,7 +85,11 @@
 		.pushsection .text.fixup,"ax"
 		.align	4
 9001:		mov	r4, #-EFAULT
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+		ldr	r5, [sp, #9*4]		@ *err_ptr
+#else
 		ldr	r5, [sp, #8*4]		@ *err_ptr
+#endif
 		str	r4, [r5]
 		ldmia	sp, {r1, r2}		@ retrieve dst, len
 		add	r2, r2, r1

arch/arm64/kvm/hyp/debug-sr.c

@@ -74,6 +74,9 @@ static void __hyp_text __debug_save_spe_nvhe(u64 *pmscr_el1)
 {
 	u64 reg;
 
+	/* Clear pmscr in case of early return */
+	*pmscr_el1 = 0;
+
 	/* SPE present on this CPU? */
 	if (!cpuid_feature_extract_unsigned_field(read_sysreg(id_aa64dfr0_el1),
 						  ID_AA64DFR0_PMSVER_SHIFT))

arch/parisc/boot/compressed/misc.c

@@ -123,8 +123,8 @@ int puts(const char *s)
 	while ((nuline = strchr(s, '\n')) != NULL) {
 		if (nuline != s)
 			pdc_iodc_print(s, nuline - s);
-			pdc_iodc_print("\r\n", 2);
-			s = nuline + 1;
+		pdc_iodc_print("\r\n", 2);
+		s = nuline + 1;
 	}
 	if (*s != '\0')
 		pdc_iodc_print(s, strlen(s));

arch/parisc/include/asm/thread_info.h

@@ -35,7 +35,12 @@ struct thread_info {
 
 /* thread information allocation */
 
+#ifdef CONFIG_IRQSTACKS
+#define THREAD_SIZE_ORDER	2 /* PA-RISC requires at least 16k stack */
+#else
 #define THREAD_SIZE_ORDER	3 /* PA-RISC requires at least 32k stack */
+#endif
+
 /* Be sure to hunt all references to this down when you change the size of
  * the kernel stack */
 #define THREAD_SIZE             (PAGE_SIZE << THREAD_SIZE_ORDER)

arch/parisc/kernel/entry.S

@@ -878,9 +878,6 @@ ENTRY_CFI(syscall_exit_rfi)
 	STREG   %r19,PT_SR7(%r16)
 
 intr_return:
-	/* NOTE: Need to enable interrupts incase we schedule. */
-	ssm     PSW_SM_I, %r0
-
 	/* check for reschedule */
 	mfctl   %cr30,%r1
 	LDREG   TI_FLAGS(%r1),%r19	/* sched.h: TIF_NEED_RESCHED */
@@ -907,6 +904,11 @@ intr_check_sig:
 	LDREG	PT_IASQ1(%r16), %r20
 	cmpib,COND(=),n 0,%r20,intr_restore /* backward */
 
+	/* NOTE: We need to enable interrupts if we have to deliver
+	 * signals. We used to do this earlier but it caused kernel
+	 * stack overflows. */
+	ssm     PSW_SM_I, %r0
+
 	copy	%r0, %r25			/* long in_syscall = 0 */
 #ifdef CONFIG_64BIT
 	ldo	-16(%r30),%r29			/* Reference param save area */
@@ -958,6 +960,10 @@ intr_do_resched:
 	cmpib,COND(=)	0, %r20, intr_do_preempt
 	nop
 
+	/* NOTE: We need to enable interrupts if we schedule.  We used
+	 * to do this earlier but it caused kernel stack overflows. */
+	ssm     PSW_SM_I, %r0
+
 #ifdef CONFIG_64BIT
 	ldo	-16(%r30),%r29		/* Reference param save area */
 #endif

arch/parisc/kernel/hpmc.S

@@ -305,6 +305,7 @@ ENDPROC_CFI(os_hpmc)
 
 
 	__INITRODATA
+	.align 4
 	.export os_hpmc_size
 os_hpmc_size:
 	.word .os_hpmc_end-.os_hpmc

arch/parisc/kernel/unwind.c

@@ -15,7 +15,6 @@
 #include <linux/slab.h>
 #include <linux/kallsyms.h>
 #include <linux/sort.h>
-#include <linux/sched.h>
 
 #include <linux/uaccess.h>
 #include <asm/assembly.h>

arch/parisc/lib/delay.c

@@ -16,9 +16,7 @@
 #include <linux/preempt.h>
 #include <linux/init.h>
 
-#include <asm/processor.h>
 #include <asm/delay.h>
-
 #include <asm/special_insns.h>    /* for mfctl() */
 #include <asm/processor.h> /* for boot_cpu_data */
 

arch/powerpc/include/asm/mmu_context.h

@@ -160,9 +160,10 @@ static inline void enter_lazy_tlb(struct mm_struct *mm,
 #endif
 }
 
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm,
+				struct mm_struct *mm)
 {
+	return 0;
 }
 
 #ifndef CONFIG_PPC_BOOK3S_64

arch/powerpc/kernel/process.c

@@ -1403,7 +1403,7 @@ void show_regs(struct pt_regs * regs)
 
 	printk("NIP:  "REG" LR: "REG" CTR: "REG"\n",
 	       regs->nip, regs->link, regs->ctr);
-	printk("REGS: %p TRAP: %04lx   %s  (%s)\n",
+	printk("REGS: %px TRAP: %04lx   %s  (%s)\n",
 	       regs, regs->trap, print_tainted(), init_utsname()->release);
 	printk("MSR:  "REG" ", regs->msr);
 	print_msr_bits(regs->msr);

arch/powerpc/kvm/book3s_xive.c

@@ -725,7 +725,8 @@ u64 kvmppc_xive_get_icp(struct kvm_vcpu *vcpu)
 
 	/* Return the per-cpu state for state saving/migration */
 	return (u64)xc->cppr << KVM_REG_PPC_ICP_CPPR_SHIFT |
-	       (u64)xc->mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT;
+	       (u64)xc->mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT |
+	       (u64)0xff << KVM_REG_PPC_ICP_PPRI_SHIFT;
 }
 
 int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval)
@@ -1558,7 +1559,7 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
 
 	/*
 	 * Restore P and Q. If the interrupt was pending, we
-	 * force both P and Q, which will trigger a resend.
+	 * force Q and !P, which will trigger a resend.
 	 *
 	 * That means that a guest that had both an interrupt
 	 * pending (queued) and Q set will restore with only
@@ -1566,7 +1567,7 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
 	 * is perfectly fine as coalescing interrupts that haven't
 	 * been presented yet is always allowed.
 	 */
-	if (val & KVM_XICS_PRESENTED || val & KVM_XICS_PENDING)
+	if (val & KVM_XICS_PRESENTED && !(val & KVM_XICS_PENDING))
 		state->old_p = true;
 	if (val & KVM_XICS_QUEUED || val & KVM_XICS_PENDING)
 		state->old_q = true;

arch/powerpc/net/bpf_jit_comp64.c

@@ -763,7 +763,8 @@ emit_clear:
 			func = (u8 *) __bpf_call_base + imm;
 
 			/* Save skb pointer if we need to re-cache skb data */
-			if (bpf_helper_changes_pkt_data(func))
+			if ((ctx->seen & SEEN_SKB) &&
+			    bpf_helper_changes_pkt_data(func))
 				PPC_BPF_STL(3, 1, bpf_jit_stack_local(ctx));
 
 			bpf_jit_emit_func_call(image, ctx, (u64)func);
@@ -772,7 +773,8 @@ emit_clear:
 			PPC_MR(b2p[BPF_REG_0], 3);
 
 			/* refresh skb cache */
-			if (bpf_helper_changes_pkt_data(func)) {
+			if ((ctx->seen & SEEN_SKB) &&
+			    bpf_helper_changes_pkt_data(func)) {
 				/* reload skb pointer to r3 */
 				PPC_BPF_LL(3, 1, bpf_jit_stack_local(ctx));
 				bpf_jit_emit_skb_loads(image, ctx);

arch/powerpc/perf/core-book3s.c

@@ -410,8 +410,12 @@ static __u64 power_pmu_bhrb_to(u64 addr)
 	int ret;
 	__u64 target;
 
-	if (is_kernel_addr(addr))
-		return branch_target((unsigned int *)addr);
+	if (is_kernel_addr(addr)) {
+		if (probe_kernel_read(&instr, (void *)addr, sizeof(instr)))
+			return 0;
+
+		return branch_target(&instr);
+	}
 
 	/* Userspace: need copy instruction here then translate it */
 	pagefault_disable();

arch/powerpc/perf/imc-pmu.c

@@ -309,6 +309,19 @@ static int ppc_nest_imc_cpu_offline(unsigned int cpu)
 	if (!cpumask_test_and_clear_cpu(cpu, &nest_imc_cpumask))
 		return 0;
 
+	/*
+	 * Check whether nest_imc is registered. We could end up here if the
+	 * cpuhotplug callback registration fails. i.e, callback invokes the
+	 * offline path for all successfully registered nodes. At this stage,
+	 * nest_imc pmu will not be registered and we should return here.
+	 *
+	 * We return with a zero since this is not an offline failure. And
+	 * cpuhp_setup_state() returns the actual failure reason to the caller,
+	 * which in turn will call the cleanup routine.
+	 */
+	if (!nest_pmus)
+		return 0;
+
 	/*
 	 * Now that this cpu is one of the designated,
 	 * find a next cpu a) which is online and b) in same chip.
@@ -1171,6 +1184,7 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
 		if (nest_pmus == 1) {
 			cpuhp_remove_state(CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE);
 			kfree(nest_imc_refc);
+			kfree(per_nest_pmu_arr);
 		}
 
 		if (nest_pmus > 0)
@@ -1195,7 +1209,6 @@ static void imc_common_cpuhp_mem_free(struct imc_pmu *pmu_ptr)
 		kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]->attrs);
 	kfree(pmu_ptr->attr_groups[IMC_EVENT_ATTR]);
 	kfree(pmu_ptr);
-	kfree(per_nest_pmu_arr);
 	return;
 }
 
@@ -1309,6 +1322,8 @@ int init_imc_pmu(struct device_node *parent, struct imc_pmu *pmu_ptr, int pmu_id
 			ret = nest_pmu_cpumask_init();
 			if (ret) {
 				mutex_unlock(&nest_init_lock);
+				kfree(nest_imc_refc);
+				kfree(per_nest_pmu_arr);
 				goto err_free;
 			}
 		}

arch/powerpc/sysdev/fsl_msi.c

@@ -354,6 +354,7 @@ static int fsl_of_msi_remove(struct platform_device *ofdev)
 }
 
 static struct lock_class_key fsl_msi_irq_class;
+static struct lock_class_key fsl_msi_irq_request_class;
 
 static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev,
 			       int offset, int irq_index)
@@ -373,7 +374,8 @@ static int fsl_msi_setup_hwirq(struct fsl_msi *msi, struct platform_device *dev,
 		dev_err(&dev->dev, "No memory for MSI cascade data\n");
 		return -ENOMEM;
 	}
-	irq_set_lockdep_class(virt_msir, &fsl_msi_irq_class);
+	irq_set_lockdep_class(virt_msir, &fsl_msi_irq_class,
+			      &fsl_msi_irq_request_class);
 	cascade_data->index = offset;
 	cascade_data->msi_data = msi;
 	cascade_data->virq = virt_msir;

arch/s390/net/bpf_jit_comp.c

@@ -55,8 +55,7 @@ struct bpf_jit {
 #define SEEN_LITERAL	8	/* code uses literals */
 #define SEEN_FUNC	16	/* calls C functions */
 #define SEEN_TAIL_CALL	32	/* code uses tail calls */
-#define SEEN_SKB_CHANGE	64	/* code changes skb data */
-#define SEEN_REG_AX	128	/* code uses constant blinding */
+#define SEEN_REG_AX	64	/* code uses constant blinding */
 #define SEEN_STACK	(SEEN_FUNC | SEEN_MEM | SEEN_SKB)
 
 /*
@@ -448,12 +447,12 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth)
 			EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0,
 				      REG_15, 152);
 	}
-	if (jit->seen & SEEN_SKB)
+	if (jit->seen & SEEN_SKB) {
 		emit_load_skb_data_hlen(jit);
-	if (jit->seen & SEEN_SKB_CHANGE)
 		/* stg %b1,ST_OFF_SKBP(%r0,%r15) */
 		EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15,
 			      STK_OFF_SKBP);
+	}
 }
 
 /*
@@ -983,8 +982,8 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i
 		EMIT2(0x0d00, REG_14, REG_W1);
 		/* lgr %b0,%r2: load return value into %b0 */
 		EMIT4(0xb9040000, BPF_REG_0, REG_2);
-		if (bpf_helper_changes_pkt_data((void *)func)) {
-			jit->seen |= SEEN_SKB_CHANGE;
+		if ((jit->seen & SEEN_SKB) &&
+		    bpf_helper_changes_pkt_data((void *)func)) {
 			/* lg %b1,ST_OFF_SKBP(%r15) */
 			EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0,
 				      REG_15, STK_OFF_SKBP);

arch/sparc/lib/hweight.S

@@ -44,8 +44,8 @@ EXPORT_SYMBOL(__arch_hweight32)
 	.previous
 
 ENTRY(__arch_hweight64)
-	sethi	%hi(__sw_hweight16), %g1
-	jmpl	%g1 + %lo(__sw_hweight16), %g0
+	sethi	%hi(__sw_hweight64), %g1
+	jmpl	%g1 + %lo(__sw_hweight64), %g0
 	 nop
 ENDPROC(__arch_hweight64)
 EXPORT_SYMBOL(__arch_hweight64)

arch/sparc/mm/fault_32.c

@@ -113,7 +113,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code,
 	if (!printk_ratelimit())
 		return;
 
-	printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x",
+	printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x",
 	       task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
 	       tsk->comm, task_pid_nr(tsk), address,
 	       (void *)regs->pc, (void *)regs->u_regs[UREG_I7],

arch/sparc/mm/fault_64.c

@@ -154,7 +154,7 @@ show_signal_msg(struct pt_regs *regs, int sig, int code,
 	if (!printk_ratelimit())
 		return;
 
-	printk("%s%s[%d]: segfault at %lx ip %p (rpc %p) sp %p error %x",
+	printk("%s%s[%d]: segfault at %lx ip %px (rpc %px) sp %px error %x",
 	       task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
 	       tsk->comm, task_pid_nr(tsk), address,
 	       (void *)regs->tpc, (void *)regs->u_regs[UREG_I7],

arch/sparc/net/bpf_jit_comp_64.c

@@ -1245,14 +1245,16 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		u8 *func = ((u8 *)__bpf_call_base) + imm;
 
 		ctx->saw_call = true;
+		if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func))
+			emit_reg_move(bpf2sparc[BPF_REG_1], L7, ctx);
 
 		emit_call((u32 *)func, ctx);
 		emit_nop(ctx);
 
 		emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx);
 
-		if (bpf_helper_changes_pkt_data(func) && ctx->saw_ld_abs_ind)
-			load_skb_regs(ctx, bpf2sparc[BPF_REG_6]);
+		if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func))
+			load_skb_regs(ctx, L7);
 		break;
 	}
 

arch/um/include/asm/mmu_context.h

@@ -15,9 +15,10 @@ extern void uml_setup_stubs(struct mm_struct *mm);
 /*
  * Needed since we do not use the asm-generic/mm_hooks.h:
  */
-static inline void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 {
 	uml_setup_stubs(mm);
+	return 0;
 }
 extern void arch_exit_mmap(struct mm_struct *mm);
 static inline void arch_unmap(struct mm_struct *mm,

arch/um/kernel/trap.c

@@ -150,7 +150,7 @@ static void show_segv_info(struct uml_pt_regs *regs)
 	if (!printk_ratelimit())
 		return;
 
-	printk("%s%s[%d]: segfault at %lx ip %p sp %p error %x",
+	printk("%s%s[%d]: segfault at %lx ip %px sp %px error %x",
 		task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
 		tsk->comm, task_pid_nr(tsk), FAULT_ADDRESS(*fi),
 		(void *)UPT_IP(regs), (void *)UPT_SP(regs),

arch/unicore32/include/asm/mmu_context.h

@@ -81,9 +81,10 @@ do { \
 	} \
 } while (0)
 
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm,
+				struct mm_struct *mm)
 {
+	return 0;
 }
 
 static inline void arch_unmap(struct mm_struct *mm,

arch/x86/Kconfig

@@ -926,7 +926,8 @@ config MAXSMP
 config NR_CPUS
 	int "Maximum number of CPUs" if SMP && !MAXSMP
 	range 2 8 if SMP && X86_32 && !X86_BIGSMP
-	range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK
+	range 2 64 if SMP && X86_32 && X86_BIGSMP
+	range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK && X86_64
 	range 2 8192 if SMP && !MAXSMP && CPUMASK_OFFSTACK && X86_64
 	default "1" if !SMP
 	default "8192" if MAXSMP

arch/x86/boot/compressed/pagetable.c

@@ -23,6 +23,9 @@
  */
 #undef CONFIG_AMD_MEM_ENCRYPT
 
+/* No PAGE_TABLE_ISOLATION support needed either: */
+#undef CONFIG_PAGE_TABLE_ISOLATION
+
 #include "misc.h"
 
 /* These actually do the work of building the kernel identity maps. */

arch/x86/boot/genimage.sh

@@ -80,39 +80,43 @@ genfdimage288() {
 	mcopy $FBZIMAGE w:linux
 }
 
-genisoimage() {
+geniso() {
 	tmp_dir=`dirname $FIMAGE`/isoimage
 	rm -rf $tmp_dir
 	mkdir $tmp_dir
-	for i in lib lib64 share end ; do
+	for i in lib lib64 share ; do
 		for j in syslinux ISOLINUX ; do
 			if [ -f /usr/$i/$j/isolinux.bin ] ; then
 				isolinux=/usr/$i/$j/isolinux.bin
-				cp $isolinux $tmp_dir
 			fi
 		done
 		for j in syslinux syslinux/modules/bios ; do
 			if [ -f /usr/$i/$j/ldlinux.c32 ]; then
 				ldlinux=/usr/$i/$j/ldlinux.c32
-				cp $ldlinux $tmp_dir
 			fi
 		done
 		if [ -n "$isolinux" -a -n "$ldlinux" ] ; then
 			break
 		fi
-		if [ $i = end -a -z "$isolinux" ] ; then
-			echo 'Need an isolinux.bin file, please install syslinux/isolinux.'
-			exit 1
-		fi
 	done
+	if [ -z "$isolinux" ] ; then
+		echo 'Need an isolinux.bin file, please install syslinux/isolinux.'
+		exit 1
+	fi
+	if [ -z "$ldlinux" ] ; then
+		echo 'Need an ldlinux.c32 file, please install syslinux/isolinux.'
+		exit 1
+	fi
+	cp $isolinux $tmp_dir
+	cp $ldlinux $tmp_dir
 	cp $FBZIMAGE $tmp_dir/linux
 	echo "$KCMDLINE" > $tmp_dir/isolinux.cfg
 	if [ -f "$FDINITRD" ] ; then
 		cp "$FDINITRD" $tmp_dir/initrd.img
 	fi
-	mkisofs -J -r -input-charset=utf-8 -quiet -o $FIMAGE -b isolinux.bin \
-		-c boot.cat -no-emul-boot -boot-load-size 4 -boot-info-table \
-		$tmp_dir
+	genisoimage -J -r -input-charset=utf-8 -quiet -o $FIMAGE \
+		-b isolinux.bin -c boot.cat -no-emul-boot -boot-load-size 4 \
+		-boot-info-table $tmp_dir
 	isohybrid $FIMAGE 2>/dev/null || true
 	rm -rf $tmp_dir
 }
@@ -121,6 +125,6 @@ case $1 in
 	bzdisk)     genbzdisk;;
 	fdimage144) genfdimage144;;
 	fdimage288) genfdimage288;;
-	isoimage)   genisoimage;;
+	isoimage)   geniso;;
 	*)          echo 'Unknown image format'; exit 1;
 esac

arch/x86/entry/calling.h

@@ -1,6 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/jump_label.h>
 #include <asm/unwind_hints.h>
+#include <asm/cpufeatures.h>
+#include <asm/page_types.h>
+#include <asm/percpu.h>
+#include <asm/asm-offsets.h>
+#include <asm/processor-flags.h>
 
 /*
 
@@ -187,6 +192,146 @@ For 32-bit we have the following conventions - kernel is built with
 #endif
 .endm
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+
+/*
+ * PAGE_TABLE_ISOLATION PGDs are 8k.  Flip bit 12 to switch between the two
+ * halves:
+ */
+#define PTI_SWITCH_PGTABLES_MASK	(1<<PAGE_SHIFT)
+#define PTI_SWITCH_MASK		(PTI_SWITCH_PGTABLES_MASK|(1<<X86_CR3_PTI_SWITCH_BIT))
+
+.macro SET_NOFLUSH_BIT	reg:req
+	bts	$X86_CR3_PCID_NOFLUSH_BIT, \reg
+.endm
+
+.macro ADJUST_KERNEL_CR3 reg:req
+	ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID
+	/* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */
+	andq    $(~PTI_SWITCH_MASK), \reg
+.endm
+
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+	mov	%cr3, \scratch_reg
+	ADJUST_KERNEL_CR3 \scratch_reg
+	mov	\scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+#define THIS_CPU_user_pcid_flush_mask   \
+	PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask
+
+.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+	mov	%cr3, \scratch_reg
+
+	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
+
+	/*
+	 * Test if the ASID needs a flush.
+	 */
+	movq	\scratch_reg, \scratch_reg2
+	andq	$(0x7FF), \scratch_reg		/* mask ASID */
+	bt	\scratch_reg, THIS_CPU_user_pcid_flush_mask
+	jnc	.Lnoflush_\@
+
+	/* Flush needed, clear the bit */
+	btr	\scratch_reg, THIS_CPU_user_pcid_flush_mask
+	movq	\scratch_reg2, \scratch_reg
+	jmp	.Lwrcr3_\@
+
+.Lnoflush_\@:
+	movq	\scratch_reg2, \scratch_reg
+	SET_NOFLUSH_BIT \scratch_reg
+
+.Lwrcr3_\@:
+	/* Flip the PGD and ASID to the user version */
+	orq     $(PTI_SWITCH_MASK), \scratch_reg
+	mov	\scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+.macro SWITCH_TO_USER_CR3_STACK	scratch_reg:req
+	pushq	%rax
+	SWITCH_TO_USER_CR3_NOSTACK scratch_reg=\scratch_reg scratch_reg2=%rax
+	popq	%rax
+.endm
+
+.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
+	ALTERNATIVE "jmp .Ldone_\@", "", X86_FEATURE_PTI
+	movq	%cr3, \scratch_reg
+	movq	\scratch_reg, \save_reg
+	/*
+	 * Is the "switch mask" all zero?  That means that both of
+	 * these are zero:
+	 *
+	 *	1. The user/kernel PCID bit, and
+	 *	2. The user/kernel "bit" that points CR3 to the
+	 *	   bottom half of the 8k PGD
+	 *
+	 * That indicates a kernel CR3 value, not a user CR3.
+	 */
+	testq	$(PTI_SWITCH_MASK), \scratch_reg
+	jz	.Ldone_\@
+
+	ADJUST_KERNEL_CR3 \scratch_reg
+	movq	\scratch_reg, %cr3
+
+.Ldone_\@:
+.endm
+
+.macro RESTORE_CR3 scratch_reg:req save_reg:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+
+	ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID
+
+	/*
+	 * KERNEL pages can always resume with NOFLUSH as we do
+	 * explicit flushes.
+	 */
+	bt	$X86_CR3_PTI_SWITCH_BIT, \save_reg
+	jnc	.Lnoflush_\@
+
+	/*
+	 * Check if there's a pending flush for the user ASID we're
+	 * about to set.
+	 */
+	movq	\save_reg, \scratch_reg
+	andq	$(0x7FF), \scratch_reg
+	bt	\scratch_reg, THIS_CPU_user_pcid_flush_mask
+	jnc	.Lnoflush_\@
+
+	btr	\scratch_reg, THIS_CPU_user_pcid_flush_mask
+	jmp	.Lwrcr3_\@
+
+.Lnoflush_\@:
+	SET_NOFLUSH_BIT \save_reg
+
+.Lwrcr3_\@:
+	/*
+	 * The CR3 write could be avoided when not changing its value,
+	 * but would require a CR3 read *and* a scratch register.
+	 */
+	movq	\save_reg, %cr3
+.Lend_\@:
+.endm
+
+#else /* CONFIG_PAGE_TABLE_ISOLATION=n: */
+
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+.endm
+.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req
+.endm
+.macro SWITCH_TO_USER_CR3_STACK scratch_reg:req
+.endm
+.macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req
+.endm
+.macro RESTORE_CR3 scratch_reg:req save_reg:req
+.endm
+
+#endif
+
 #endif /* CONFIG_X86_64 */
 
 /*

arch/x86/entry/entry_32.S

@@ -941,9 +941,10 @@ ENTRY(debug)
 	movl	%esp, %eax			# pt_regs pointer
 
 	/* Are we currently on the SYSENTER stack? */
-	PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx)
-	subl	%eax, %ecx	/* ecx = (end of SYSENTER_stack) - esp */
-	cmpl	$SIZEOF_SYSENTER_stack, %ecx
+	movl	PER_CPU_VAR(cpu_entry_area), %ecx
+	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+	subl	%eax, %ecx	/* ecx = (end of entry_stack) - esp */
+	cmpl	$SIZEOF_entry_stack, %ecx
 	jb	.Ldebug_from_sysenter_stack
 
 	TRACE_IRQS_OFF
@@ -984,9 +985,10 @@ ENTRY(nmi)
 	movl	%esp, %eax			# pt_regs pointer
 
 	/* Are we currently on the SYSENTER stack? */
-	PER_CPU(cpu_tss + CPU_TSS_SYSENTER_stack + SIZEOF_SYSENTER_stack, %ecx)
-	subl	%eax, %ecx	/* ecx = (end of SYSENTER_stack) - esp */
-	cmpl	$SIZEOF_SYSENTER_stack, %ecx
+	movl	PER_CPU_VAR(cpu_entry_area), %ecx
+	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+	subl	%eax, %ecx	/* ecx = (end of entry_stack) - esp */
+	cmpl	$SIZEOF_entry_stack, %ecx
 	jb	.Lnmi_from_sysenter_stack
 
 	/* Not on SYSENTER stack. */

arch/x86/entry/entry_64.S

@@ -23,7 +23,6 @@
 #include <asm/segment.h>
 #include <asm/cache.h>
 #include <asm/errno.h>
-#include "calling.h"
 #include <asm/asm-offsets.h>
 #include <asm/msr.h>
 #include <asm/unistd.h>
@@ -40,6 +39,8 @@
 #include <asm/frame.h>
 #include <linux/err.h>
 
+#include "calling.h"
+
 .code64
 .section .entry.text, "ax"
 
@@ -140,6 +141,67 @@ END(native_usergs_sysret64)
  * with them due to bugs in both AMD and Intel CPUs.
  */
 
+	.pushsection .entry_trampoline, "ax"
+
+/*
+ * The code in here gets remapped into cpu_entry_area's trampoline.  This means
+ * that the assembler and linker have the wrong idea as to where this code
+ * lives (and, in fact, it's mapped more than once, so it's not even at a
+ * fixed address).  So we can't reference any symbols outside the entry
+ * trampoline and expect it to work.
+ *
+ * Instead, we carefully abuse %rip-relative addressing.
+ * _entry_trampoline(%rip) refers to the start of the remapped) entry
+ * trampoline.  We can thus find cpu_entry_area with this macro:
+ */
+
+#define CPU_ENTRY_AREA \
+	_entry_trampoline - CPU_ENTRY_AREA_entry_trampoline(%rip)
+
+/* The top word of the SYSENTER stack is hot and is usable as scratch space. */
+#define RSP_SCRATCH	CPU_ENTRY_AREA_entry_stack + \
+			SIZEOF_entry_stack - 8 + CPU_ENTRY_AREA
+
+ENTRY(entry_SYSCALL_64_trampoline)
+	UNWIND_HINT_EMPTY
+	swapgs
+
+	/* Stash the user RSP. */
+	movq	%rsp, RSP_SCRATCH
+
+	/* Note: using %rsp as a scratch reg. */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
+	/* Load the top of the task stack into RSP */
+	movq	CPU_ENTRY_AREA_tss + TSS_sp1 + CPU_ENTRY_AREA, %rsp
+
+	/* Start building the simulated IRET frame. */
+	pushq	$__USER_DS			/* pt_regs->ss */
+	pushq	RSP_SCRATCH			/* pt_regs->sp */
+	pushq	%r11				/* pt_regs->flags */
+	pushq	$__USER_CS			/* pt_regs->cs */
+	pushq	%rcx				/* pt_regs->ip */
+
+	/*
+	 * x86 lacks a near absolute jump, and we can't jump to the real
+	 * entry text with a relative jump.  We could push the target
+	 * address and then use retq, but this destroys the pipeline on
+	 * many CPUs (wasting over 20 cycles on Sandy Bridge).  Instead,
+	 * spill RDI and restore it in a second-stage trampoline.
+	 */
+	pushq	%rdi
+	movq	$entry_SYSCALL_64_stage2, %rdi
+	jmp	*%rdi
+END(entry_SYSCALL_64_trampoline)
+
+	.popsection
+
+ENTRY(entry_SYSCALL_64_stage2)
+	UNWIND_HINT_EMPTY
+	popq	%rdi
+	jmp	entry_SYSCALL_64_after_hwframe
+END(entry_SYSCALL_64_stage2)
+
 ENTRY(entry_SYSCALL_64)
 	UNWIND_HINT_EMPTY
 	/*
@@ -149,6 +211,10 @@ ENTRY(entry_SYSCALL_64)
 	 */
 
 	swapgs
+	/*
+	 * This path is not taken when PAGE_TABLE_ISOLATION is disabled so it
+	 * is not required to switch CR3.
+	 */
 	movq	%rsp, PER_CPU_VAR(rsp_scratch)
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
@@ -330,8 +396,25 @@ syscall_return_via_sysret:
 	popq	%rsi	/* skip rcx */
 	popq	%rdx
 	popq	%rsi
+
+	/*
+	 * Now all regs are restored except RSP and RDI.
+	 * Save old stack pointer and switch to trampoline stack.
+	 */
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+
+	pushq	RSP-RDI(%rdi)	/* RSP */
+	pushq	(%rdi)		/* RDI */
+
+	/*
+	 * We are on the trampoline stack.  All regs except RDI are live.
+	 * We can do future final exit work right here.
+	 */
+	SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+
 	popq	%rdi
-	movq	RSP-ORIG_RAX(%rsp), %rsp
+	popq	%rsp
 	USERGS_SYSRET64
 END(entry_SYSCALL_64)
 
@@ -466,12 +549,13 @@ END(irq_entries_start)
 
 .macro DEBUG_ENTRY_ASSERT_IRQS_OFF
 #ifdef CONFIG_DEBUG_ENTRY
-	pushfq
-	testl $X86_EFLAGS_IF, (%rsp)
+	pushq %rax
+	SAVE_FLAGS(CLBR_RAX)
+	testl $X86_EFLAGS_IF, %eax
 	jz .Lokay_\@
 	ud2
 .Lokay_\@:
-	addq $8, %rsp
+	popq %rax
 #endif
 .endm
 
@@ -563,6 +647,13 @@ END(irq_entries_start)
 /* 0(%rsp): ~(interrupt number) */
 	.macro interrupt func
 	cld
+
+	testb	$3, CS-ORIG_RAX(%rsp)
+	jz	1f
+	SWAPGS
+	call	switch_to_thread_stack
+1:
+
 	ALLOC_PT_GPREGS_ON_STACK
 	SAVE_C_REGS
 	SAVE_EXTRA_REGS
@@ -572,12 +663,8 @@ END(irq_entries_start)
 	jz	1f
 
 	/*
-	 * IRQ from user mode.  Switch to kernel gsbase and inform context
-	 * tracking that we're in kernel mode.
-	 */
-	SWAPGS
-
-	/*
+	 * IRQ from user mode.
+	 *
 	 * We need to tell lockdep that IRQs are off.  We can't do this until
 	 * we fix gsbase, and we should do it before enter_from_user_mode
 	 * (which can take locks).  Since TRACE_IRQS_OFF idempotent,
@@ -630,10 +717,43 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode)
 	ud2
 1:
 #endif
-	SWAPGS
 	POP_EXTRA_REGS
-	POP_C_REGS
-	addq	$8, %rsp	/* skip regs->orig_ax */
+	popq	%r11
+	popq	%r10
+	popq	%r9
+	popq	%r8
+	popq	%rax
+	popq	%rcx
+	popq	%rdx
+	popq	%rsi
+
+	/*
+	 * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS.
+	 * Save old stack pointer and switch to trampoline stack.
+	 */
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
+
+	/* Copy the IRET frame to the trampoline stack. */
+	pushq	6*8(%rdi)	/* SS */
+	pushq	5*8(%rdi)	/* RSP */
+	pushq	4*8(%rdi)	/* EFLAGS */
+	pushq	3*8(%rdi)	/* CS */
+	pushq	2*8(%rdi)	/* RIP */
+
+	/* Push user RDI on the trampoline stack. */
+	pushq	(%rdi)
+
+	/*
+	 * We are on the trampoline stack.  All regs except RDI are live.
+	 * We can do future final exit work right here.
+	 */
+
+	SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+
+	/* Restore RDI. */
+	popq	%rdi
+	SWAPGS
 	INTERRUPT_RETURN
 
 
@@ -713,7 +833,9 @@ native_irq_return_ldt:
 	 */
 
 	pushq	%rdi				/* Stash user RDI */
-	SWAPGS
+	SWAPGS					/* to kernel GS */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi	/* to kernel CR3 */
+
 	movq	PER_CPU_VAR(espfix_waddr), %rdi
 	movq	%rax, (0*8)(%rdi)		/* user RAX */
 	movq	(1*8)(%rsp), %rax		/* user RIP */
@@ -729,7 +851,6 @@ native_irq_return_ldt:
 	/* Now RAX == RSP. */
 
 	andl	$0xffff0000, %eax		/* RAX = (RSP & 0xffff0000) */
-	popq	%rdi				/* Restore user RDI */
 
 	/*
 	 * espfix_stack[31:16] == 0.  The page tables are set up such that
@@ -740,7 +861,11 @@ native_irq_return_ldt:
 	 * still points to an RO alias of the ESPFIX stack.
 	 */
 	orq	PER_CPU_VAR(espfix_stack), %rax
-	SWAPGS
+
+	SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi
+	SWAPGS					/* to user GS */
+	popq	%rdi				/* Restore user RDI */
+
 	movq	%rax, %rsp
 	UNWIND_HINT_IRET_REGS offset=8
 
@@ -829,7 +954,35 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
 /*
  * Exception entry points.
  */
-#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss) + (TSS_ist + ((x) - 1) * 8)
+#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8)
+
+/*
+ * Switch to the thread stack.  This is called with the IRET frame and
+ * orig_ax on the stack.  (That is, RDI..R12 are not on the stack and
+ * space has not been allocated for them.)
+ */
+ENTRY(switch_to_thread_stack)
+	UNWIND_HINT_FUNC
+
+	pushq	%rdi
+	/* Need to switch before accessing the thread stack. */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+	UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI
+
+	pushq	7*8(%rdi)		/* regs->ss */
+	pushq	6*8(%rdi)		/* regs->rsp */
+	pushq	5*8(%rdi)		/* regs->eflags */
+	pushq	4*8(%rdi)		/* regs->cs */
+	pushq	3*8(%rdi)		/* regs->ip */
+	pushq	2*8(%rdi)		/* regs->orig_ax */
+	pushq	8(%rdi)			/* return address */
+	UNWIND_HINT_FUNC
+
+	movq	(%rdi), %rdi
+	ret
+END(switch_to_thread_stack)
 
 .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
 ENTRY(\sym)
@@ -848,11 +1001,12 @@ ENTRY(\sym)
 
 	ALLOC_PT_GPREGS_ON_STACK
 
-	.if \paranoid
-	.if \paranoid == 1
+	.if \paranoid < 2
 	testb	$3, CS(%rsp)			/* If coming from userspace, switch stacks */
-	jnz	1f
+	jnz	.Lfrom_usermode_switch_stack_\@
 	.endif
+
+	.if \paranoid
 	call	paranoid_entry
 	.else
 	call	error_entry
@@ -894,20 +1048,15 @@ ENTRY(\sym)
 	jmp	error_exit
 	.endif
 
-	.if \paranoid == 1
+	.if \paranoid < 2
 	/*
-	 * Paranoid entry from userspace.  Switch stacks and treat it
+	 * Entry from userspace.  Switch stacks and treat it
 	 * as a normal entry.  This means that paranoid handlers
 	 * run in real process context if user_mode(regs).
 	 */
-1:
+.Lfrom_usermode_switch_stack_\@:
 	call	error_entry
 
-
-	movq	%rsp, %rdi			/* pt_regs pointer */
-	call	sync_regs
-	movq	%rax, %rsp			/* switch stack */
-
 	movq	%rsp, %rdi			/* pt_regs pointer */
 
 	.if \has_error_code
@@ -1119,7 +1268,11 @@ ENTRY(paranoid_entry)
 	js	1f				/* negative -> in kernel */
 	SWAPGS
 	xorl	%ebx, %ebx
-1:	ret
+
+1:
+	SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14
+
+	ret
 END(paranoid_entry)
 
 /*
@@ -1141,6 +1294,7 @@ ENTRY(paranoid_exit)
 	testl	%ebx, %ebx			/* swapgs needed? */
 	jnz	.Lparanoid_exit_no_swapgs
 	TRACE_IRQS_IRETQ
+	RESTORE_CR3	scratch_reg=%rbx save_reg=%r14
 	SWAPGS_UNSAFE_STACK
 	jmp	.Lparanoid_exit_restore
 .Lparanoid_exit_no_swapgs:
@@ -1168,8 +1322,18 @@ ENTRY(error_entry)
 	 * from user mode due to an IRET fault.
 	 */
 	SWAPGS
+	/* We have user CR3.  Change to kernel CR3. */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 
 .Lerror_entry_from_usermode_after_swapgs:
+	/* Put us onto the real thread stack. */
+	popq	%r12				/* save return addr in %12 */
+	movq	%rsp, %rdi			/* arg0 = pt_regs pointer */
+	call	sync_regs
+	movq	%rax, %rsp			/* switch stack */
+	ENCODE_FRAME_POINTER
+	pushq	%r12
+
 	/*
 	 * We need to tell lockdep that IRQs are off.  We can't do this until
 	 * we fix gsbase, and we should do it before enter_from_user_mode
@@ -1206,6 +1370,7 @@ ENTRY(error_entry)
 	 * .Lgs_change's error handler with kernel gsbase.
 	 */
 	SWAPGS
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 	jmp .Lerror_entry_done
 
 .Lbstep_iret:
@@ -1215,10 +1380,11 @@ ENTRY(error_entry)
 
 .Lerror_bad_iret:
 	/*
-	 * We came from an IRET to user mode, so we have user gsbase.
-	 * Switch to kernel gsbase:
+	 * We came from an IRET to user mode, so we have user
+	 * gsbase and CR3.  Switch to kernel gsbase and CR3:
 	 */
 	SWAPGS
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rax
 
 	/*
 	 * Pretend that the exception came from user mode: set up pt_regs
@@ -1250,6 +1416,10 @@ END(error_exit)
 /*
  * Runs on exception stack.  Xen PV does not go through this path at all,
  * so we can use real assembly here.
+ *
+ * Registers:
+ *	%r14: Used to save/restore the CR3 of the interrupted context
+ *	      when PAGE_TABLE_ISOLATION is in use.  Do not clobber.
  */
 ENTRY(nmi)
 	UNWIND_HINT_IRET_REGS
@@ -1313,6 +1483,7 @@ ENTRY(nmi)
 
 	swapgs
 	cld
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx
 	movq	%rsp, %rdx
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 	UNWIND_HINT_IRET_REGS base=%rdx offset=8
@@ -1565,6 +1736,8 @@ end_repeat_nmi:
 	movq	$-1, %rsi
 	call	do_nmi
 
+	RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
+
 	testl	%ebx, %ebx			/* swapgs needed? */
 	jnz	nmi_restore
 nmi_swapgs:

arch/x86/entry/entry_64_compat.S

@@ -48,7 +48,11 @@
  */
 ENTRY(entry_SYSENTER_compat)
 	/* Interrupts are off on entry. */
-	SWAPGS_UNSAFE_STACK
+	SWAPGS
+
+	/* We are about to clobber %rsp anyway, clobbering here is OK */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
+
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	/*
@@ -215,6 +219,12 @@ GLOBAL(entry_SYSCALL_compat_after_hwframe)
 	pushq   $0			/* pt_regs->r14 = 0 */
 	pushq   $0			/* pt_regs->r15 = 0 */
 
+	/*
+	 * We just saved %rdi so it is safe to clobber.  It is not
+	 * preserved during the C calls inside TRACE_IRQS_OFF anyway.
+	 */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+
 	/*
 	 * User mode is traced as though IRQs are on, and SYSENTER
 	 * turned them off.
@@ -256,10 +266,22 @@ sysret32_from_system_call:
 	 * when the system call started, which is already known to user
 	 * code.  We zero R8-R10 to avoid info leaks.
          */
+	movq	RSP-ORIG_RAX(%rsp), %rsp
+
+	/*
+	 * The original userspace %rsp (RSP-ORIG_RAX(%rsp)) is stored
+	 * on the process stack which is not mapped to userspace and
+	 * not readable after we SWITCH_TO_USER_CR3.  Delay the CR3
+	 * switch until after after the last reference to the process
+	 * stack.
+	 *
+	 * %r8/%r9 are zeroed before the sysret, thus safe to clobber.
+	 */
+	SWITCH_TO_USER_CR3_NOSTACK scratch_reg=%r8 scratch_reg2=%r9
+
 	xorq	%r8, %r8
 	xorq	%r9, %r9
 	xorq	%r10, %r10
-	movq	RSP-ORIG_RAX(%rsp), %rsp
 	swapgs
 	sysretl
 END(entry_SYSCALL_compat)
@@ -306,8 +328,11 @@ ENTRY(entry_INT80_compat)
 	 */
 	movl	%eax, %eax
 
-	/* Construct struct pt_regs on stack (iret frame is already on stack) */
 	pushq	%rax			/* pt_regs->orig_ax */
+
+	/* switch to thread stack expects orig_ax to be pushed */
+	call	switch_to_thread_stack
+
 	pushq	%rdi			/* pt_regs->di */
 	pushq	%rsi			/* pt_regs->si */
 	pushq	%rdx			/* pt_regs->dx */

arch/x86/entry/vsyscall/vsyscall_64.c

@@ -37,6 +37,7 @@
 #include <asm/unistd.h>
 #include <asm/fixmap.h>
 #include <asm/traps.h>
+#include <asm/paravirt.h>
 
 #define CREATE_TRACE_POINTS
 #include "vsyscall_trace.h"
@@ -138,6 +139,10 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 
 	WARN_ON_ONCE(address != regs->ip);
 
+	/* This should be unreachable in NATIVE mode. */
+	if (WARN_ON(vsyscall_mode == NATIVE))
+		return false;
+
 	if (vsyscall_mode == NONE) {
 		warn_bad_vsyscall(KERN_INFO, regs,
 				  "vsyscall attempted with vsyscall=none");
@@ -329,16 +334,47 @@ int in_gate_area_no_mm(unsigned long addr)
 	return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR;
 }
 
+/*
+ * The VSYSCALL page is the only user-accessible page in the kernel address
+ * range.  Normally, the kernel page tables can have _PAGE_USER clear, but
+ * the tables covering VSYSCALL_ADDR need _PAGE_USER set if vsyscalls
+ * are enabled.
+ *
+ * Some day we may create a "minimal" vsyscall mode in which we emulate
+ * vsyscalls but leave the page not present.  If so, we skip calling
+ * this.
+ */
+void __init set_vsyscall_pgtable_user_bits(pgd_t *root)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset_pgd(root, VSYSCALL_ADDR);
+	set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
+	p4d = p4d_offset(pgd, VSYSCALL_ADDR);
+#if CONFIG_PGTABLE_LEVELS >= 5
+	p4d->p4d |= _PAGE_USER;
+#endif
+	pud = pud_offset(p4d, VSYSCALL_ADDR);
+	set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER));
+	pmd = pmd_offset(pud, VSYSCALL_ADDR);
+	set_pmd(pmd, __pmd(pmd_val(*pmd) | _PAGE_USER));
+}
+
 void __init map_vsyscall(void)
 {
 	extern char __vsyscall_page;
 	unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
 
-	if (vsyscall_mode != NONE)
+	if (vsyscall_mode != NONE) {
 		__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
 			     vsyscall_mode == NATIVE
 			     ? PAGE_KERNEL_VSYSCALL
 			     : PAGE_KERNEL_VVAR);
+		set_vsyscall_pgtable_user_bits(swapper_pg_dir);
+	}
 
 	BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
 		     (unsigned long)VSYSCALL_ADDR);

arch/x86/events/intel/core.c

@@ -3847,6 +3847,8 @@ static struct attribute *intel_pmu_attrs[] = {
 
 __init int intel_pmu_init(void)
 {
+	struct attribute **extra_attr = NULL;
+	struct attribute **to_free = NULL;
 	union cpuid10_edx edx;
 	union cpuid10_eax eax;
 	union cpuid10_ebx ebx;
@@ -3854,7 +3856,6 @@ __init int intel_pmu_init(void)
 	unsigned int unused;
 	struct extra_reg *er;
 	int version, i;
-	struct attribute **extra_attr = NULL;
 	char *name;
 
 	if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
@@ -4294,6 +4295,7 @@ __init int intel_pmu_init(void)
 		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
 			hsw_format_attr : nhm_format_attr;
 		extra_attr = merge_attr(extra_attr, skl_format_attr);
+		to_free = extra_attr;
 		x86_pmu.cpu_events = get_hsw_events_attrs();
 		intel_pmu_pebs_data_source_skl(
 			boot_cpu_data.x86_model == INTEL_FAM6_SKYLAKE_X);
@@ -4401,6 +4403,7 @@ __init int intel_pmu_init(void)
 		pr_cont("full-width counters, ");
 	}
 
+	kfree(to_free);
 	return 0;
 }
 

arch/x86/events/intel/ds.c

@@ -3,16 +3,18 @@
 #include <linux/types.h>
 #include <linux/slab.h>
 
+#include <asm/cpu_entry_area.h>
 #include <asm/perf_event.h>
 #include <asm/insn.h>
 
 #include "../perf_event.h"
 
+/* Waste a full page so it can be mapped into the cpu_entry_area */
+DEFINE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
+
 /* The size of a BTS record in bytes: */
 #define BTS_RECORD_SIZE		24
 
-#define BTS_BUFFER_SIZE		(PAGE_SIZE << 4)
-#define PEBS_BUFFER_SIZE	(PAGE_SIZE << 4)
 #define PEBS_FIXUP_SIZE		PAGE_SIZE
 
 /*
@@ -279,17 +281,52 @@ void fini_debug_store_on_cpu(int cpu)
 
 static DEFINE_PER_CPU(void *, insn_buffer);
 
-static int alloc_pebs_buffer(int cpu)
+static void ds_update_cea(void *cea, void *addr, size_t size, pgprot_t prot)
 {
-	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+	phys_addr_t pa;
+	size_t msz = 0;
+
+	pa = virt_to_phys(addr);
+	for (; msz < size; msz += PAGE_SIZE, pa += PAGE_SIZE, cea += PAGE_SIZE)
+		cea_set_pte(cea, pa, prot);
+}
+
+static void ds_clear_cea(void *cea, size_t size)
+{
+	size_t msz = 0;
+
+	for (; msz < size; msz += PAGE_SIZE, cea += PAGE_SIZE)
+		cea_set_pte(cea, 0, PAGE_NONE);
+}
+
+static void *dsalloc_pages(size_t size, gfp_t flags, int cpu)
+{
+	unsigned int order = get_order(size);
 	int node = cpu_to_node(cpu);
-	int max;
-	void *buffer, *ibuffer;
+	struct page *page;
+
+	page = __alloc_pages_node(node, flags | __GFP_ZERO, order);
+	return page ? page_address(page) : NULL;
+}
+
+static void dsfree_pages(const void *buffer, size_t size)
+{
+	if (buffer)
+		free_pages((unsigned long)buffer, get_order(size));
+}
+
+static int alloc_pebs_buffer(int cpu)
+{
+	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+	struct debug_store *ds = hwev->ds;
+	size_t bsiz = x86_pmu.pebs_buffer_size;
+	int max, node = cpu_to_node(cpu);
+	void *buffer, *ibuffer, *cea;
 
 	if (!x86_pmu.pebs)
 		return 0;
 
-	buffer = kzalloc_node(x86_pmu.pebs_buffer_size, GFP_KERNEL, node);
+	buffer = dsalloc_pages(bsiz, GFP_KERNEL, cpu);
 	if (unlikely(!buffer))
 		return -ENOMEM;
 
@@ -300,25 +337,27 @@ static int alloc_pebs_buffer(int cpu)
 	if (x86_pmu.intel_cap.pebs_format < 2) {
 		ibuffer = kzalloc_node(PEBS_FIXUP_SIZE, GFP_KERNEL, node);
 		if (!ibuffer) {
-			kfree(buffer);
+			dsfree_pages(buffer, bsiz);
 			return -ENOMEM;
 		}
 		per_cpu(insn_buffer, cpu) = ibuffer;
 	}
-
-	max = x86_pmu.pebs_buffer_size / x86_pmu.pebs_record_size;
-
-	ds->pebs_buffer_base = (u64)(unsigned long)buffer;
+	hwev->ds_pebs_vaddr = buffer;
+	/* Update the cpu entry area mapping */
+	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
+	ds->pebs_buffer_base = (unsigned long) cea;
+	ds_update_cea(cea, buffer, bsiz, PAGE_KERNEL);
 	ds->pebs_index = ds->pebs_buffer_base;
-	ds->pebs_absolute_maximum = ds->pebs_buffer_base +
-		max * x86_pmu.pebs_record_size;
-
+	max = x86_pmu.pebs_record_size * (bsiz / x86_pmu.pebs_record_size);
+	ds->pebs_absolute_maximum = ds->pebs_buffer_base + max;
 	return 0;
 }
 
 static void release_pebs_buffer(int cpu)
 {
-	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+	struct debug_store *ds = hwev->ds;
+	void *cea;
 
 	if (!ds || !x86_pmu.pebs)
 		return;
@@ -326,73 +365,70 @@ static void release_pebs_buffer(int cpu)
 	kfree(per_cpu(insn_buffer, cpu));
 	per_cpu(insn_buffer, cpu) = NULL;
 
-	kfree((void *)(unsigned long)ds->pebs_buffer_base);
+	/* Clear the fixmap */
+	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
+	ds_clear_cea(cea, x86_pmu.pebs_buffer_size);
 	ds->pebs_buffer_base = 0;
+	dsfree_pages(hwev->ds_pebs_vaddr, x86_pmu.pebs_buffer_size);
+	hwev->ds_pebs_vaddr = NULL;
 }
 
 static int alloc_bts_buffer(int cpu)
 {
-	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-	int node = cpu_to_node(cpu);
-	int max, thresh;
-	void *buffer;
+	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+	struct debug_store *ds = hwev->ds;
+	void *buffer, *cea;
+	int max;
 
 	if (!x86_pmu.bts)
 		return 0;
 
-	buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
+	buffer = dsalloc_pages(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, cpu);
 	if (unlikely(!buffer)) {
 		WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__);
 		return -ENOMEM;
 	}
-
-	max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
-	thresh = max / 16;
-
-	ds->bts_buffer_base = (u64)(unsigned long)buffer;
+	hwev->ds_bts_vaddr = buffer;
+	/* Update the fixmap */
+	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer;
+	ds->bts_buffer_base = (unsigned long) cea;
+	ds_update_cea(cea, buffer, BTS_BUFFER_SIZE, PAGE_KERNEL);
 	ds->bts_index = ds->bts_buffer_base;
-	ds->bts_absolute_maximum = ds->bts_buffer_base +
-		max * BTS_RECORD_SIZE;
-	ds->bts_interrupt_threshold = ds->bts_absolute_maximum -
-		thresh * BTS_RECORD_SIZE;
-
+	max = BTS_RECORD_SIZE * (BTS_BUFFER_SIZE / BTS_RECORD_SIZE);
+	ds->bts_absolute_maximum = ds->bts_buffer_base + max;
+	ds->bts_interrupt_threshold = ds->bts_absolute_maximum - (max / 16);
 	return 0;
 }
 
 static void release_bts_buffer(int cpu)
 {
-	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
+	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
+	struct debug_store *ds = hwev->ds;
+	void *cea;
 
 	if (!ds || !x86_pmu.bts)
 		return;
 
-	kfree((void *)(unsigned long)ds->bts_buffer_base);
+	/* Clear the fixmap */
+	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.bts_buffer;
+	ds_clear_cea(cea, BTS_BUFFER_SIZE);
 	ds->bts_buffer_base = 0;
+	dsfree_pages(hwev->ds_bts_vaddr, BTS_BUFFER_SIZE);
+	hwev->ds_bts_vaddr = NULL;
 }
 
 static int alloc_ds_buffer(int cpu)
 {
-	int node = cpu_to_node(cpu);
-	struct debug_store *ds;
-
-	ds = kzalloc_node(sizeof(*ds), GFP_KERNEL, node);
-	if (unlikely(!ds))
-		return -ENOMEM;
+	struct debug_store *ds = &get_cpu_entry_area(cpu)->cpu_debug_store;
 
+	memset(ds, 0, sizeof(*ds));
 	per_cpu(cpu_hw_events, cpu).ds = ds;
-
 	return 0;
 }
 
 static void release_ds_buffer(int cpu)
 {
-	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-
-	if (!ds)
-		return;
-
 	per_cpu(cpu_hw_events, cpu).ds = NULL;
-	kfree(ds);
 }
 
 void release_ds_buffers(void)

arch/x86/events/perf_event.h

@@ -14,6 +14,8 @@
 
 #include <linux/perf_event.h>
 
+#include <asm/intel_ds.h>
+
 /* To enable MSR tracing please use the generic trace points. */
 
 /*
@@ -77,8 +79,6 @@ struct amd_nb {
 	struct event_constraint event_constraints[X86_PMC_IDX_MAX];
 };
 
-/* The maximal number of PEBS events: */
-#define MAX_PEBS_EVENTS		8
 #define PEBS_COUNTER_MASK	((1ULL << MAX_PEBS_EVENTS) - 1)
 
 /*
@@ -95,23 +95,6 @@ struct amd_nb {
 	PERF_SAMPLE_TRANSACTION | PERF_SAMPLE_PHYS_ADDR | \
 	PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)
 
-/*
- * A debug store configuration.
- *
- * We only support architectures that use 64bit fields.
- */
-struct debug_store {
-	u64	bts_buffer_base;
-	u64	bts_index;
-	u64	bts_absolute_maximum;
-	u64	bts_interrupt_threshold;
-	u64	pebs_buffer_base;
-	u64	pebs_index;
-	u64	pebs_absolute_maximum;
-	u64	pebs_interrupt_threshold;
-	u64	pebs_event_reset[MAX_PEBS_EVENTS];
-};
-
 #define PEBS_REGS \
 	(PERF_REG_X86_AX | \
 	 PERF_REG_X86_BX | \
@@ -216,6 +199,8 @@ struct cpu_hw_events {
 	 * Intel DebugStore bits
 	 */
 	struct debug_store	*ds;
+	void			*ds_pebs_vaddr;
+	void			*ds_bts_vaddr;
 	u64			pebs_enabled;
 	int			n_pebs;
 	int			n_large_pebs;

arch/x86/include/asm/asm.h

@@ -136,6 +136,7 @@
 #endif
 
 #ifndef __ASSEMBLY__
+#ifndef __BPF__
 /*
  * This output constraint should be used for any inline asm which has a "call"
  * instruction.  Otherwise the asm may be inserted before the frame pointer
@@ -145,5 +146,6 @@
 register unsigned long current_stack_pointer asm(_ASM_SP);
 #define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
 #endif
+#endif
 
 #endif /* _ASM_X86_ASM_H */

arch/x86/include/asm/cpu_entry_area.h

@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _ASM_X86_CPU_ENTRY_AREA_H
+#define _ASM_X86_CPU_ENTRY_AREA_H
+
+#include <linux/percpu-defs.h>
+#include <asm/processor.h>
+#include <asm/intel_ds.h>
+
+/*
+ * cpu_entry_area is a percpu region that contains things needed by the CPU
+ * and early entry/exit code.  Real types aren't used for all fields here
+ * to avoid circular header dependencies.
+ *
+ * Every field is a virtual alias of some other allocated backing store.
+ * There is no direct allocation of a struct cpu_entry_area.
+ */
+struct cpu_entry_area {
+	char gdt[PAGE_SIZE];
+
+	/*
+	 * The GDT is just below entry_stack and thus serves (on x86_64) as
+	 * a a read-only guard page.
+	 */
+	struct entry_stack_page entry_stack_page;
+
+	/*
+	 * On x86_64, the TSS is mapped RO.  On x86_32, it's mapped RW because
+	 * we need task switches to work, and task switches write to the TSS.
+	 */
+	struct tss_struct tss;
+
+	char entry_trampoline[PAGE_SIZE];
+
+#ifdef CONFIG_X86_64
+	/*
+	 * Exception stacks used for IST entries.
+	 *
+	 * In the future, this should have a separate slot for each stack
+	 * with guard pages between them.
+	 */
+	char exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ];
+#endif
+#ifdef CONFIG_CPU_SUP_INTEL
+	/*
+	 * Per CPU debug store for Intel performance monitoring. Wastes a
+	 * full page at the moment.
+	 */
+	struct debug_store cpu_debug_store;
+	/*
+	 * The actual PEBS/BTS buffers must be mapped to user space
+	 * Reserve enough fixmap PTEs.
+	 */
+	struct debug_store_buffers cpu_debug_buffers;
+#endif
+};
+
+#define CPU_ENTRY_AREA_SIZE	(sizeof(struct cpu_entry_area))
+#define CPU_ENTRY_AREA_TOT_SIZE	(CPU_ENTRY_AREA_SIZE * NR_CPUS)
+
+DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
+
+extern void setup_cpu_entry_areas(void);
+extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
+
+#define	CPU_ENTRY_AREA_RO_IDT		CPU_ENTRY_AREA_BASE
+#define CPU_ENTRY_AREA_PER_CPU		(CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE)
+
+#define CPU_ENTRY_AREA_RO_IDT_VADDR	((void *)CPU_ENTRY_AREA_RO_IDT)
+
+#define CPU_ENTRY_AREA_MAP_SIZE			\
+	(CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_TOT_SIZE - CPU_ENTRY_AREA_BASE)
+
+extern struct cpu_entry_area *get_cpu_entry_area(int cpu);
+
+static inline struct entry_stack *cpu_entry_stack(int cpu)
+{
+	return &get_cpu_entry_area(cpu)->entry_stack_page.stack;
+}
+
+#endif

arch/x86/include/asm/cpufeature.h

@@ -135,6 +135,8 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
 	set_bit(bit, (unsigned long *)cpu_caps_set);	\
 } while (0)
 
+#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit)
+
 #if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_X86_FAST_FEATURE_TESTS)
 /*
  * Static testing of CPU features.  Used the same as boot_cpu_has().

arch/x86/include/asm/cpufeatures.h

@@ -197,11 +197,12 @@
 #define X86_FEATURE_CAT_L3		( 7*32+ 4) /* Cache Allocation Technology L3 */
 #define X86_FEATURE_CAT_L2		( 7*32+ 5) /* Cache Allocation Technology L2 */
 #define X86_FEATURE_CDP_L3		( 7*32+ 6) /* Code and Data Prioritization L3 */
+#define X86_FEATURE_INVPCID_SINGLE	( 7*32+ 7) /* Effectively INVPCID && CR4.PCIDE=1 */
 
 #define X86_FEATURE_HW_PSTATE		( 7*32+ 8) /* AMD HW-PState */
 #define X86_FEATURE_PROC_FEEDBACK	( 7*32+ 9) /* AMD ProcFeedbackInterface */
 #define X86_FEATURE_SME			( 7*32+10) /* AMD Secure Memory Encryption */
-
+#define X86_FEATURE_PTI			( 7*32+11) /* Kernel Page Table Isolation enabled */
 #define X86_FEATURE_INTEL_PPIN		( 7*32+14) /* Intel Processor Inventory Number */
 #define X86_FEATURE_INTEL_PT		( 7*32+15) /* Intel Processor Trace */
 #define X86_FEATURE_AVX512_4VNNIW	( 7*32+16) /* AVX-512 Neural Network Instructions */
@@ -340,5 +341,6 @@
 #define X86_BUG_SWAPGS_FENCE		X86_BUG(11) /* SWAPGS without input dep on GS */
 #define X86_BUG_MONITOR			X86_BUG(12) /* IPI required to wake up remote CPU */
 #define X86_BUG_AMD_E400		X86_BUG(13) /* CPU is among the affected by Erratum 400 */
+#define X86_BUG_CPU_INSECURE		X86_BUG(14) /* CPU is insecure and needs kernel page table isolation */
 
 #endif /* _ASM_X86_CPUFEATURES_H */

arch/x86/include/asm/desc.h

@@ -7,6 +7,7 @@
 #include <asm/mmu.h>
 #include <asm/fixmap.h>
 #include <asm/irq_vectors.h>
+#include <asm/cpu_entry_area.h>
 
 #include <linux/smp.h>
 #include <linux/percpu.h>
@@ -20,6 +21,8 @@ static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *in
 
 	desc->type		= (info->read_exec_only ^ 1) << 1;
 	desc->type	       |= info->contents << 2;
+	/* Set the ACCESS bit so it can be mapped RO */
+	desc->type	       |= 1;
 
 	desc->s			= 1;
 	desc->dpl		= 0x3;
@@ -60,17 +63,10 @@ static inline struct desc_struct *get_current_gdt_rw(void)
 	return this_cpu_ptr(&gdt_page)->gdt;
 }
 
-/* Get the fixmap index for a specific processor */
-static inline unsigned int get_cpu_gdt_ro_index(int cpu)
-{
-	return FIX_GDT_REMAP_BEGIN + cpu;
-}
-
 /* Provide the fixmap address of the remapped GDT */
 static inline struct desc_struct *get_cpu_gdt_ro(int cpu)
 {
-	unsigned int idx = get_cpu_gdt_ro_index(cpu);
-	return (struct desc_struct *)__fix_to_virt(idx);
+	return (struct desc_struct *)&get_cpu_entry_area(cpu)->gdt;
 }
 
 /* Provide the current read-only GDT */
@@ -185,7 +181,7 @@ static inline void set_tssldt_descriptor(void *d, unsigned long addr,
 #endif
 }
 
-static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr)
+static inline void __set_tss_desc(unsigned cpu, unsigned int entry, struct x86_hw_tss *addr)
 {
 	struct desc_struct *d = get_cpu_gdt_rw(cpu);
 	tss_desc tss;

arch/x86/include/asm/disabled-features.h

@@ -50,6 +50,12 @@
 # define DISABLE_LA57	(1<<(X86_FEATURE_LA57 & 31))
 #endif
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define DISABLE_PTI		0
+#else
+# define DISABLE_PTI		(1 << (X86_FEATURE_PTI & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -60,7 +66,7 @@
 #define DISABLED_MASK4	(DISABLE_PCID)
 #define DISABLED_MASK5	0
 #define DISABLED_MASK6	0
-#define DISABLED_MASK7	0
+#define DISABLED_MASK7	(DISABLE_PTI)
 #define DISABLED_MASK8	0
 #define DISABLED_MASK9	(DISABLE_MPX)
 #define DISABLED_MASK10	0

arch/x86/include/asm/espfix.h

@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_ESPFIX_H
 #define _ASM_X86_ESPFIX_H
 
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_X86_ESPFIX64
 
 #include <asm/percpu.h>
 
@@ -11,7 +11,8 @@ DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
 
 extern void init_espfix_bsp(void);
 extern void init_espfix_ap(int cpu);
-
-#endif /* CONFIG_X86_64 */
+#else
+static inline void init_espfix_ap(int cpu) { }
+#endif
 
 #endif /* _ASM_X86_ESPFIX_H */

arch/x86/include/asm/fixmap.h

@@ -44,7 +44,6 @@ extern unsigned long __FIXADDR_TOP;
 			 PAGE_SIZE)
 #endif
 
-
 /*
  * Here we define all the compile-time 'special' virtual
  * addresses. The point is to have a constant address at
@@ -84,7 +83,6 @@ enum fixed_addresses {
 	FIX_IO_APIC_BASE_0,
 	FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
 #endif
-	FIX_RO_IDT,	/* Virtual mapping for read-only IDT */
 #ifdef CONFIG_X86_32
 	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
 	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
@@ -100,9 +98,6 @@ enum fixed_addresses {
 #ifdef	CONFIG_X86_INTEL_MID
 	FIX_LNW_VRTC,
 #endif
-	/* Fixmap entries to remap the GDTs, one per processor. */
-	FIX_GDT_REMAP_BEGIN,
-	FIX_GDT_REMAP_END = FIX_GDT_REMAP_BEGIN + NR_CPUS - 1,
 
 #ifdef CONFIG_ACPI_APEI_GHES
 	/* Used for GHES mapping from assorted contexts */
@@ -143,7 +138,7 @@ enum fixed_addresses {
 extern void reserve_top_address(unsigned long reserve);
 
 #define FIXADDR_SIZE	(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_START		(FIXADDR_TOP - FIXADDR_SIZE)
+#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
 
 extern int fixmaps_set;
 

arch/x86/include/asm/hypervisor.h

@@ -20,16 +20,7 @@
 #ifndef _ASM_X86_HYPERVISOR_H
 #define _ASM_X86_HYPERVISOR_H
 
-#ifdef CONFIG_HYPERVISOR_GUEST
-
-#include <asm/kvm_para.h>
-#include <asm/x86_init.h>
-#include <asm/xen/hypervisor.h>
-
-/*
- * x86 hypervisor information
- */
-
+/* x86 hypervisor types  */
 enum x86_hypervisor_type {
 	X86_HYPER_NATIVE = 0,
 	X86_HYPER_VMWARE,
@@ -39,6 +30,12 @@ enum x86_hypervisor_type {
 	X86_HYPER_KVM,
 };
 
+#ifdef CONFIG_HYPERVISOR_GUEST
+
+#include <asm/kvm_para.h>
+#include <asm/x86_init.h>
+#include <asm/xen/hypervisor.h>
+
 struct hypervisor_x86 {
 	/* Hypervisor name */
 	const char	*name;
@@ -58,7 +55,15 @@ struct hypervisor_x86 {
 
 extern enum x86_hypervisor_type x86_hyper_type;
 extern void init_hypervisor_platform(void);
+static inline bool hypervisor_is_type(enum x86_hypervisor_type type)
+{
+	return x86_hyper_type == type;
+}
 #else
 static inline void init_hypervisor_platform(void) { }
+static inline bool hypervisor_is_type(enum x86_hypervisor_type type)
+{
+	return type == X86_HYPER_NATIVE;
+}
 #endif /* CONFIG_HYPERVISOR_GUEST */
 #endif /* _ASM_X86_HYPERVISOR_H */

arch/x86/include/asm/intel_ds.h

@@ -0,0 +1,36 @@
+#ifndef _ASM_INTEL_DS_H
+#define _ASM_INTEL_DS_H
+
+#include <linux/percpu-defs.h>
+
+#define BTS_BUFFER_SIZE		(PAGE_SIZE << 4)
+#define PEBS_BUFFER_SIZE	(PAGE_SIZE << 4)
+
+/* The maximal number of PEBS events: */
+#define MAX_PEBS_EVENTS		8
+
+/*
+ * A debug store configuration.
+ *
+ * We only support architectures that use 64bit fields.
+ */
+struct debug_store {
+	u64	bts_buffer_base;
+	u64	bts_index;
+	u64	bts_absolute_maximum;
+	u64	bts_interrupt_threshold;
+	u64	pebs_buffer_base;
+	u64	pebs_index;
+	u64	pebs_absolute_maximum;
+	u64	pebs_interrupt_threshold;
+	u64	pebs_event_reset[MAX_PEBS_EVENTS];
+} __aligned(PAGE_SIZE);
+
+DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
+
+struct debug_store_buffers {
+	char	bts_buffer[BTS_BUFFER_SIZE];
+	char	pebs_buffer[PEBS_BUFFER_SIZE];
+};
+
+#endif

arch/x86/include/asm/invpcid.h

@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_INVPCID
+#define _ASM_X86_INVPCID
+
+static inline void __invpcid(unsigned long pcid, unsigned long addr,
+			     unsigned long type)
+{
+	struct { u64 d[2]; } desc = { { pcid, addr } };
+
+	/*
+	 * The memory clobber is because the whole point is to invalidate
+	 * stale TLB entries and, especially if we're flushing global
+	 * mappings, we don't want the compiler to reorder any subsequent
+	 * memory accesses before the TLB flush.
+	 *
+	 * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
+	 * invpcid (%rcx), %rax in long mode.
+	 */
+	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
+		      : : "m" (desc), "a" (type), "c" (&desc) : "memory");
+}
+
+#define INVPCID_TYPE_INDIV_ADDR		0
+#define INVPCID_TYPE_SINGLE_CTXT	1
+#define INVPCID_TYPE_ALL_INCL_GLOBAL	2
+#define INVPCID_TYPE_ALL_NON_GLOBAL	3
+
+/* Flush all mappings for a given pcid and addr, not including globals. */
+static inline void invpcid_flush_one(unsigned long pcid,
+				     unsigned long addr)
+{
+	__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
+}
+
+/* Flush all mappings for a given PCID, not including globals. */
+static inline void invpcid_flush_single_context(unsigned long pcid)
+{
+	__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+}
+
+/* Flush all mappings, including globals, for all PCIDs. */
+static inline void invpcid_flush_all(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+}
+
+/* Flush all mappings for all PCIDs except globals. */
+static inline void invpcid_flush_all_nonglobals(void)
+{
+	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+}
+
+#endif /* _ASM_X86_INVPCID */

arch/x86/include/asm/irqdomain.h

@@ -44,7 +44,7 @@ extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
 extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
 			      unsigned int nr_irqs);
 extern int mp_irqdomain_activate(struct irq_domain *domain,
-				 struct irq_data *irq_data, bool early);
+				 struct irq_data *irq_data, bool reserve);
 extern void mp_irqdomain_deactivate(struct irq_domain *domain,
 				    struct irq_data *irq_data);
 extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain);

arch/x86/include/asm/irqflags.h

@@ -142,6 +142,9 @@ static inline notrace unsigned long arch_local_irq_save(void)
 	swapgs;					\
 	sysretl
 
+#ifdef CONFIG_DEBUG_ENTRY
+#define SAVE_FLAGS(x)		pushfq; popq %rax
+#endif
 #else
 #define INTERRUPT_RETURN		iret
 #define ENABLE_INTERRUPTS_SYSEXIT	sti; sysexit

arch/x86/include/asm/kdebug.h

@@ -26,6 +26,7 @@ extern void die(const char *, struct pt_regs *,long);
 extern int __must_check __die(const char *, struct pt_regs *, long);
 extern void show_stack_regs(struct pt_regs *regs);
 extern void __show_regs(struct pt_regs *regs, int all);
+extern void show_iret_regs(struct pt_regs *regs);
 extern unsigned long oops_begin(void);
 extern void oops_end(unsigned long, struct pt_regs *, int signr);
 

arch/x86/include/asm/mmu.h

@@ -3,6 +3,7 @@
 #define _ASM_X86_MMU_H
 
 #include <linux/spinlock.h>
+#include <linux/rwsem.h>
 #include <linux/mutex.h>
 #include <linux/atomic.h>
 
@@ -27,7 +28,8 @@ typedef struct {
 	atomic64_t tlb_gen;
 
 #ifdef CONFIG_MODIFY_LDT_SYSCALL
-	struct ldt_struct *ldt;
+	struct rw_semaphore	ldt_usr_sem;
+	struct ldt_struct	*ldt;
 #endif
 
 #ifdef CONFIG_X86_64

arch/x86/include/asm/mmu_context.h

@@ -50,22 +50,53 @@ struct ldt_struct {
 	 * call gates.  On native, we could merge the ldt_struct and LDT
 	 * allocations, but it's not worth trying to optimize.
 	 */
-	struct desc_struct *entries;
-	unsigned int nr_entries;
+	struct desc_struct	*entries;
+	unsigned int		nr_entries;
+
+	/*
+	 * If PTI is in use, then the entries array is not mapped while we're
+	 * in user mode.  The whole array will be aliased at the addressed
+	 * given by ldt_slot_va(slot).  We use two slots so that we can allocate
+	 * and map, and enable a new LDT without invalidating the mapping
+	 * of an older, still-in-use LDT.
+	 *
+	 * slot will be -1 if this LDT doesn't have an alias mapping.
+	 */
+	int			slot;
 };
 
+/* This is a multiple of PAGE_SIZE. */
+#define LDT_SLOT_STRIDE (LDT_ENTRIES * LDT_ENTRY_SIZE)
+
+static inline void *ldt_slot_va(int slot)
+{
+#ifdef CONFIG_X86_64
+	return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot);
+#else
+	BUG();
+#endif
+}
+
 /*
  * Used for LDT copy/destruction.
  */
-int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm);
+static inline void init_new_context_ldt(struct mm_struct *mm)
+{
+	mm->context.ldt = NULL;
+	init_rwsem(&mm->context.ldt_usr_sem);
+}
+int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm);
 void destroy_context_ldt(struct mm_struct *mm);
+void ldt_arch_exit_mmap(struct mm_struct *mm);
 #else	/* CONFIG_MODIFY_LDT_SYSCALL */
-static inline int init_new_context_ldt(struct task_struct *tsk,
-				       struct mm_struct *mm)
+static inline void init_new_context_ldt(struct mm_struct *mm) { }
+static inline int ldt_dup_context(struct mm_struct *oldmm,
+				  struct mm_struct *mm)
 {
 	return 0;
 }
-static inline void destroy_context_ldt(struct mm_struct *mm) {}
+static inline void destroy_context_ldt(struct mm_struct *mm) { }
+static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { }
 #endif
 
 static inline void load_mm_ldt(struct mm_struct *mm)
@@ -90,10 +121,31 @@ static inline void load_mm_ldt(struct mm_struct *mm)
 	 * that we can see.
 	 */
 
-	if (unlikely(ldt))
-		set_ldt(ldt->entries, ldt->nr_entries);
-	else
+	if (unlikely(ldt)) {
+		if (static_cpu_has(X86_FEATURE_PTI)) {
+			if (WARN_ON_ONCE((unsigned long)ldt->slot > 1)) {
+				/*
+				 * Whoops -- either the new LDT isn't mapped
+				 * (if slot == -1) or is mapped into a bogus
+				 * slot (if slot > 1).
+				 */
+				clear_LDT();
+				return;
+			}
+
+			/*
+			 * If page table isolation is enabled, ldt->entries
+			 * will not be mapped in the userspace pagetables.
+			 * Tell the CPU to access the LDT through the alias
+			 * at ldt_slot_va(ldt->slot).
+			 */
+			set_ldt(ldt_slot_va(ldt->slot), ldt->nr_entries);
+		} else {
+			set_ldt(ldt->entries, ldt->nr_entries);
+		}
+	} else {
 		clear_LDT();
+	}
 #else
 	clear_LDT();
 #endif
@@ -132,18 +184,21 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
+	mutex_init(&mm->context.lock);
+
 	mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id);
 	atomic64_set(&mm->context.tlb_gen, 0);
 
-	#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 	if (cpu_feature_enabled(X86_FEATURE_OSPKE)) {
 		/* pkey 0 is the default and always allocated */
 		mm->context.pkey_allocation_map = 0x1;
 		/* -1 means unallocated or invalid */
 		mm->context.execute_only_pkey = -1;
 	}
-	#endif
-	return init_new_context_ldt(tsk, mm);
+#endif
+	init_new_context_ldt(mm);
+	return 0;
 }
 static inline void destroy_context(struct mm_struct *mm)
 {
@@ -176,15 +231,16 @@ do {						\
 } while (0)
 #endif
 
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
+static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 {
 	paravirt_arch_dup_mmap(oldmm, mm);
+	return ldt_dup_context(oldmm, mm);
 }
 
 static inline void arch_exit_mmap(struct mm_struct *mm)
 {
 	paravirt_arch_exit_mmap(mm);
+	ldt_arch_exit_mmap(mm);
 }
 
 #ifdef CONFIG_X86_64
@@ -281,33 +337,6 @@ static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 	return __pkru_allows_pkey(vma_pkey(vma), write);
 }
 
-/*
- * If PCID is on, ASID-aware code paths put the ASID+1 into the PCID
- * bits.  This serves two purposes.  It prevents a nasty situation in
- * which PCID-unaware code saves CR3, loads some other value (with PCID
- * == 0), and then restores CR3, thus corrupting the TLB for ASID 0 if
- * the saved ASID was nonzero.  It also means that any bugs involving
- * loading a PCID-enabled CR3 with CR4.PCIDE off will trigger
- * deterministically.
- */
-
-static inline unsigned long build_cr3(struct mm_struct *mm, u16 asid)
-{
-	if (static_cpu_has(X86_FEATURE_PCID)) {
-		VM_WARN_ON_ONCE(asid > 4094);
-		return __sme_pa(mm->pgd) | (asid + 1);
-	} else {
-		VM_WARN_ON_ONCE(asid != 0);
-		return __sme_pa(mm->pgd);
-	}
-}
-
-static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
-{
-	VM_WARN_ON_ONCE(asid > 4094);
-	return __sme_pa(mm->pgd) | (asid + 1) | CR3_NOFLUSH;
-}
-
 /*
  * This can be used from process context to figure out what the value of
  * CR3 is without needing to do a (slow) __read_cr3().
@@ -317,7 +346,7 @@ static inline unsigned long build_cr3_noflush(struct mm_struct *mm, u16 asid)
  */
 static inline unsigned long __get_current_cr3_fast(void)
 {
-	unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm),
+	unsigned long cr3 = build_cr3(this_cpu_read(cpu_tlbstate.loaded_mm)->pgd,
 		this_cpu_read(cpu_tlbstate.loaded_mm_asid));
 
 	/* For now, be very restrictive about when this can be called. */

arch/x86/include/asm/paravirt.h

@@ -927,6 +927,15 @@ extern void default_banner(void);
 	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64),	\
 		  CLBR_NONE,						\
 		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64))
+
+#ifdef CONFIG_DEBUG_ENTRY
+#define SAVE_FLAGS(clobbers)                                        \
+	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \
+		  PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE);        \
+		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl);    \
+		  PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
+#endif
+
 #endif	/* CONFIG_X86_32 */
 
 #endif /* __ASSEMBLY__ */

arch/x86/include/asm/pgalloc.h

@@ -30,6 +30,17 @@ static inline void paravirt_release_p4d(unsigned long pfn) {}
  */
 extern gfp_t __userpte_alloc_gfp;
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Instead of one PGD, we acquire two PGDs.  Being order-1, it is
+ * both 8k in size and 8k-aligned.  That lets us just flip bit 12
+ * in a pointer to swap between the two 4k halves.
+ */
+#define PGD_ALLOCATION_ORDER 1
+#else
+#define PGD_ALLOCATION_ORDER 0
+#endif
+
 /*
  * Allocate and free page tables.
  */

arch/x86/include/asm/pgtable.h

@@ -28,6 +28,7 @@ extern pgd_t early_top_pgt[PTRS_PER_PGD];
 int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
 
 void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
+void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user);
 void ptdump_walk_pgd_level_checkwx(void);
 
 #ifdef CONFIG_DEBUG_WX
@@ -841,7 +842,12 @@ static inline pud_t *pud_offset(p4d_t *p4d, unsigned long address)
 
 static inline int p4d_bad(p4d_t p4d)
 {
-	return (p4d_flags(p4d) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
+	unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER;
+
+	if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+		ignore_flags |= _PAGE_NX;
+
+	return (p4d_flags(p4d) & ~ignore_flags) != 0;
 }
 #endif  /* CONFIG_PGTABLE_LEVELS > 3 */
 
@@ -875,7 +881,12 @@ static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
 
 static inline int pgd_bad(pgd_t pgd)
 {
-	return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
+	unsigned long ignore_flags = _PAGE_USER;
+
+	if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+		ignore_flags |= _PAGE_NX;
+
+	return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE;
 }
 
 static inline int pgd_none(pgd_t pgd)
@@ -904,7 +915,11 @@ static inline int pgd_none(pgd_t pgd)
  * pgd_offset() returns a (pgd_t *)
  * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
  */
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
+#define pgd_offset_pgd(pgd, address) (pgd + pgd_index((address)))
+/*
+ * a shortcut to get a pgd_t in a given mm
+ */
+#define pgd_offset(mm, address) pgd_offset_pgd((mm)->pgd, (address))
 /*
  * a shortcut which implies the use of the kernel's pgd, instead
  * of a process's
@@ -1106,7 +1121,14 @@ static inline int pud_write(pud_t pud)
  */
 static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
 {
-       memcpy(dst, src, count * sizeof(pgd_t));
+	memcpy(dst, src, count * sizeof(pgd_t));
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+	/* Clone the user space pgd as well */
+	memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src),
+	       count * sizeof(pgd_t));
+#endif
 }
 
 #define PTE_SHIFT ilog2(PTRS_PER_PTE)

arch/x86/include/asm/pgtable_32_types.h

@@ -38,13 +38,22 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
 #define LAST_PKMAP 1024
 #endif
 
-#define PKMAP_BASE ((FIXADDR_START - PAGE_SIZE * (LAST_PKMAP + 1))	\
-		    & PMD_MASK)
+/*
+ * Define this here and validate with BUILD_BUG_ON() in pgtable_32.c
+ * to avoid include recursion hell
+ */
+#define CPU_ENTRY_AREA_PAGES	(NR_CPUS * 40)
+
+#define CPU_ENTRY_AREA_BASE				\
+	((FIXADDR_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1)) & PMD_MASK)
+
+#define PKMAP_BASE		\
+	((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
 
 #ifdef CONFIG_HIGHMEM
 # define VMALLOC_END	(PKMAP_BASE - 2 * PAGE_SIZE)
 #else
-# define VMALLOC_END	(FIXADDR_START - 2 * PAGE_SIZE)
+# define VMALLOC_END	(CPU_ENTRY_AREA_BASE - 2 * PAGE_SIZE)
 #endif
 
 #define MODULES_VADDR	VMALLOC_START

arch/x86/include/asm/pgtable_64.h

@@ -131,9 +131,97 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp)
 #endif
 }
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
+ * (8k-aligned and 8k in size).  The kernel one is at the beginning 4k and
+ * the user one is in the last 4k.  To switch between them, you
+ * just need to flip the 12th bit in their addresses.
+ */
+#define PTI_PGTABLE_SWITCH_BIT	PAGE_SHIFT
+
+/*
+ * This generates better code than the inline assembly in
+ * __set_bit().
+ */
+static inline void *ptr_set_bit(void *ptr, int bit)
+{
+	unsigned long __ptr = (unsigned long)ptr;
+
+	__ptr |= BIT(bit);
+	return (void *)__ptr;
+}
+static inline void *ptr_clear_bit(void *ptr, int bit)
+{
+	unsigned long __ptr = (unsigned long)ptr;
+
+	__ptr &= ~BIT(bit);
+	return (void *)__ptr;
+}
+
+static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
+{
+	return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
+{
+	return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
+{
+	return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
+{
+	return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
+/*
+ * Page table pages are page-aligned.  The lower half of the top
+ * level is used for userspace and the top half for the kernel.
+ *
+ * Returns true for parts of the PGD that map userspace and
+ * false for the parts that map the kernel.
+ */
+static inline bool pgdp_maps_userspace(void *__ptr)
+{
+	unsigned long ptr = (unsigned long)__ptr;
+
+	return (ptr & ~PAGE_MASK) < (PAGE_SIZE / 2);
+}
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd);
+
+/*
+ * Take a PGD location (pgdp) and a pgd value that needs to be set there.
+ * Populates the user and returns the resulting PGD that must be set in
+ * the kernel copy of the page tables.
+ */
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return pgd;
+	return __pti_set_user_pgd(pgdp, pgd);
+}
+#else
+static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	return pgd;
+}
+#endif
+
 static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
 {
+#if defined(CONFIG_PAGE_TABLE_ISOLATION) && !defined(CONFIG_X86_5LEVEL)
+	p4dp->pgd = pti_set_user_pgd(&p4dp->pgd, p4d.pgd);
+#else
 	*p4dp = p4d;
+#endif
 }
 
 static inline void native_p4d_clear(p4d_t *p4d)
@@ -147,7 +235,11 @@ static inline void native_p4d_clear(p4d_t *p4d)
 
 static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	*pgdp = pti_set_user_pgd(pgdp, pgd);
+#else
 	*pgdp = pgd;
+#endif
 }
 
 static inline void native_pgd_clear(pgd_t *pgd)

arch/x86/include/asm/pgtable_64_types.h

@@ -76,32 +76,45 @@ typedef struct { pteval_t pte; } pte_t;
 #define PGDIR_MASK	(~(PGDIR_SIZE - 1))
 
 /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
-#define MAXMEM		_AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+#define MAXMEM			_AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+
 #ifdef CONFIG_X86_5LEVEL
-#define VMALLOC_SIZE_TB _AC(16384, UL)
-#define __VMALLOC_BASE	_AC(0xff92000000000000, UL)
-#define __VMEMMAP_BASE	_AC(0xffd4000000000000, UL)
+# define VMALLOC_SIZE_TB	_AC(12800, UL)
+# define __VMALLOC_BASE		_AC(0xffa0000000000000, UL)
+# define __VMEMMAP_BASE		_AC(0xffd4000000000000, UL)
+# define LDT_PGD_ENTRY		_AC(-112, UL)
+# define LDT_BASE_ADDR		(LDT_PGD_ENTRY << PGDIR_SHIFT)
 #else
-#define VMALLOC_SIZE_TB	_AC(32, UL)
-#define __VMALLOC_BASE	_AC(0xffffc90000000000, UL)
-#define __VMEMMAP_BASE	_AC(0xffffea0000000000, UL)
+# define VMALLOC_SIZE_TB	_AC(32, UL)
+# define __VMALLOC_BASE		_AC(0xffffc90000000000, UL)
+# define __VMEMMAP_BASE		_AC(0xffffea0000000000, UL)
+# define LDT_PGD_ENTRY		_AC(-4, UL)
+# define LDT_BASE_ADDR		(LDT_PGD_ENTRY << PGDIR_SHIFT)
 #endif
+
 #ifdef CONFIG_RANDOMIZE_MEMORY
-#define VMALLOC_START	vmalloc_base
-#define VMEMMAP_START	vmemmap_base
+# define VMALLOC_START		vmalloc_base
+# define VMEMMAP_START		vmemmap_base
 #else
-#define VMALLOC_START	__VMALLOC_BASE
-#define VMEMMAP_START	__VMEMMAP_BASE
+# define VMALLOC_START		__VMALLOC_BASE
+# define VMEMMAP_START		__VMEMMAP_BASE
 #endif /* CONFIG_RANDOMIZE_MEMORY */
-#define VMALLOC_END	(VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
-#define MODULES_VADDR    (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
+
+#define VMALLOC_END		(VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
+
+#define MODULES_VADDR		(__START_KERNEL_map + KERNEL_IMAGE_SIZE)
 /* The module sections ends with the start of the fixmap */
-#define MODULES_END   __fix_to_virt(__end_of_fixed_addresses + 1)
-#define MODULES_LEN   (MODULES_END - MODULES_VADDR)
-#define ESPFIX_PGD_ENTRY _AC(-2, UL)
-#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT)
-#define EFI_VA_START	 ( -4 * (_AC(1, UL) << 30))
-#define EFI_VA_END	 (-68 * (_AC(1, UL) << 30))
+#define MODULES_END		__fix_to_virt(__end_of_fixed_addresses + 1)
+#define MODULES_LEN		(MODULES_END - MODULES_VADDR)
+
+#define ESPFIX_PGD_ENTRY	_AC(-2, UL)
+#define ESPFIX_BASE_ADDR	(ESPFIX_PGD_ENTRY << P4D_SHIFT)
+
+#define CPU_ENTRY_AREA_PGD	_AC(-3, UL)
+#define CPU_ENTRY_AREA_BASE	(CPU_ENTRY_AREA_PGD << P4D_SHIFT)
+
+#define EFI_VA_START		( -4 * (_AC(1, UL) << 30))
+#define EFI_VA_END		(-68 * (_AC(1, UL) << 30))
 
 #define EARLY_DYNAMIC_PAGE_TABLES	64
 

arch/x86/include/asm/processor-flags.h

@@ -38,6 +38,11 @@
 #define CR3_ADDR_MASK	__sme_clr(0x7FFFFFFFFFFFF000ull)
 #define CR3_PCID_MASK	0xFFFull
 #define CR3_NOFLUSH	BIT_ULL(63)
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define X86_CR3_PTI_SWITCH_BIT	11
+#endif
+
 #else
 /*
  * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save

arch/x86/include/asm/processor.h

@@ -163,9 +163,9 @@ enum cpuid_regs_idx {
 extern struct cpuinfo_x86	boot_cpu_data;
 extern struct cpuinfo_x86	new_cpu_data;
 
-extern struct tss_struct	doublefault_tss;
-extern __u32			cpu_caps_cleared[NCAPINTS];
-extern __u32			cpu_caps_set[NCAPINTS];
+extern struct x86_hw_tss	doublefault_tss;
+extern __u32			cpu_caps_cleared[NCAPINTS + NBUGINTS];
+extern __u32			cpu_caps_set[NCAPINTS + NBUGINTS];
 
 #ifdef CONFIG_SMP
 DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
@@ -253,6 +253,11 @@ static inline void load_cr3(pgd_t *pgdir)
 	write_cr3(__sme_pa(pgdir));
 }
 
+/*
+ * Note that while the legacy 'TSS' name comes from 'Task State Segment',
+ * on modern x86 CPUs the TSS also holds information important to 64-bit mode,
+ * unrelated to the task-switch mechanism:
+ */
 #ifdef CONFIG_X86_32
 /* This is the TSS defined by the hardware. */
 struct x86_hw_tss {
@@ -305,7 +310,13 @@ struct x86_hw_tss {
 struct x86_hw_tss {
 	u32			reserved1;
 	u64			sp0;
+
+	/*
+	 * We store cpu_current_top_of_stack in sp1 so it's always accessible.
+	 * Linux does not use ring 1, so sp1 is not otherwise needed.
+	 */
 	u64			sp1;
+
 	u64			sp2;
 	u64			reserved2;
 	u64			ist[7];
@@ -323,12 +334,22 @@ struct x86_hw_tss {
 #define IO_BITMAP_BITS			65536
 #define IO_BITMAP_BYTES			(IO_BITMAP_BITS/8)
 #define IO_BITMAP_LONGS			(IO_BITMAP_BYTES/sizeof(long))
-#define IO_BITMAP_OFFSET		offsetof(struct tss_struct, io_bitmap)
+#define IO_BITMAP_OFFSET		(offsetof(struct tss_struct, io_bitmap) - offsetof(struct tss_struct, x86_tss))
 #define INVALID_IO_BITMAP_OFFSET	0x8000
 
+struct entry_stack {
+	unsigned long		words[64];
+};
+
+struct entry_stack_page {
+	struct entry_stack stack;
+} __aligned(PAGE_SIZE);
+
 struct tss_struct {
 	/*
-	 * The hardware state:
+	 * The fixed hardware portion.  This must not cross a page boundary
+	 * at risk of violating the SDM's advice and potentially triggering
+	 * errata.
 	 */
 	struct x86_hw_tss	x86_tss;
 
@@ -339,18 +360,9 @@ struct tss_struct {
 	 * be within the limit.
 	 */
 	unsigned long		io_bitmap[IO_BITMAP_LONGS + 1];
+} __aligned(PAGE_SIZE);
 
-#ifdef CONFIG_X86_32
-	/*
-	 * Space for the temporary SYSENTER stack.
-	 */
-	unsigned long		SYSENTER_stack_canary;
-	unsigned long		SYSENTER_stack[64];
-#endif
-
-} ____cacheline_aligned;
-
-DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
+DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw);
 
 /*
  * sizeof(unsigned long) coming from an extra "long" at the end
@@ -364,6 +376,9 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss);
 
 #ifdef CONFIG_X86_32
 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
+#else
+/* The RO copy can't be accessed with this_cpu_xyz(), so use the RW copy. */
+#define cpu_current_top_of_stack cpu_tss_rw.x86_tss.sp1
 #endif
 
 /*
@@ -523,7 +538,7 @@ static inline void native_set_iopl_mask(unsigned mask)
 static inline void
 native_load_sp0(unsigned long sp0)
 {
-	this_cpu_write(cpu_tss.x86_tss.sp0, sp0);
+	this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0);
 }
 
 static inline void native_swapgs(void)
@@ -535,12 +550,12 @@ static inline void native_swapgs(void)
 
 static inline unsigned long current_top_of_stack(void)
 {
-#ifdef CONFIG_X86_64
-	return this_cpu_read_stable(cpu_tss.x86_tss.sp0);
-#else
-	/* sp0 on x86_32 is special in and around vm86 mode. */
+	/*
+	 *  We can't read directly from tss.sp0: sp0 on x86_32 is special in
+	 *  and around vm86 mode and sp0 on x86_64 is special because of the
+	 *  entry trampoline.
+	 */
 	return this_cpu_read_stable(cpu_current_top_of_stack);
-#endif
 }
 
 static inline bool on_thread_stack(void)
@@ -837,13 +852,22 @@ static inline void spin_lock_prefetch(const void *x)
 
 #else
 /*
- * User space process size. 47bits minus one guard page.  The guard
- * page is necessary on Intel CPUs: if a SYSCALL instruction is at
- * the highest possible canonical userspace address, then that
- * syscall will enter the kernel with a non-canonical return
- * address, and SYSRET will explode dangerously.  We avoid this
- * particular problem by preventing anything from being mapped
- * at the maximum canonical address.
+ * User space process size.  This is the first address outside the user range.
+ * There are a few constraints that determine this:
+ *
+ * On Intel CPUs, if a SYSCALL instruction is at the highest canonical
+ * address, then that syscall will enter the kernel with a
+ * non-canonical return address, and SYSRET will explode dangerously.
+ * We avoid this particular problem by preventing anything executable
+ * from being mapped at the maximum canonical address.
+ *
+ * On AMD CPUs in the Ryzen family, there's a nasty bug in which the
+ * CPUs malfunction if they execute code from the highest canonical page.
+ * They'll speculate right off the end of the canonical space, and
+ * bad things happen.  This is worked around in the same way as the
+ * Intel problem.
+ *
+ * With page table isolation enabled, we map the LDT in ... [stay tuned]
  */
 #define TASK_SIZE_MAX	((1UL << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE)
 

arch/x86/include/asm/pti.h

@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef _ASM_X86_PTI_H
+#define _ASM_X86_PTI_H
+#ifndef __ASSEMBLY__
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+extern void pti_init(void);
+extern void pti_check_boottime_disable(void);
+#else
+static inline void pti_check_boottime_disable(void) { }
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_PTI_H */

arch/x86/include/asm/stacktrace.h

@@ -16,6 +16,7 @@ enum stack_type {
 	STACK_TYPE_TASK,
 	STACK_TYPE_IRQ,
 	STACK_TYPE_SOFTIRQ,
+	STACK_TYPE_ENTRY,
 	STACK_TYPE_EXCEPTION,
 	STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1,
 };
@@ -28,6 +29,8 @@ struct stack_info {
 bool in_task_stack(unsigned long *stack, struct task_struct *task,
 		   struct stack_info *info);
 
+bool in_entry_stack(unsigned long *stack, struct stack_info *info);
+
 int get_stack_info(unsigned long *stack, struct task_struct *task,
 		   struct stack_info *info, unsigned long *visit_mask);
 

arch/x86/include/asm/switch_to.h

@@ -16,8 +16,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 		      struct tss_struct *tss);
 
 /* This runs runs on the previous thread's stack. */
-static inline void prepare_switch_to(struct task_struct *prev,
-				     struct task_struct *next)
+static inline void prepare_switch_to(struct task_struct *next)
 {
 #ifdef CONFIG_VMAP_STACK
 	/*
@@ -70,7 +69,7 @@ struct fork_frame {
 
 #define switch_to(prev, next, last)					\
 do {									\
-	prepare_switch_to(prev, next);					\
+	prepare_switch_to(next);					\
 									\
 	((last) = __switch_to_asm((prev), (next)));			\
 } while (0)
@@ -79,10 +78,10 @@ do {									\
 static inline void refresh_sysenter_cs(struct thread_struct *thread)
 {
 	/* Only happens when SEP is enabled, no need to test "SEP"arately: */
-	if (unlikely(this_cpu_read(cpu_tss.x86_tss.ss1) == thread->sysenter_cs))
+	if (unlikely(this_cpu_read(cpu_tss_rw.x86_tss.ss1) == thread->sysenter_cs))
 		return;
 
-	this_cpu_write(cpu_tss.x86_tss.ss1, thread->sysenter_cs);
+	this_cpu_write(cpu_tss_rw.x86_tss.ss1, thread->sysenter_cs);
 	wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
 }
 #endif
@@ -90,10 +89,12 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread)
 /* This is used when switching tasks or entering/exiting vm86 mode. */
 static inline void update_sp0(struct task_struct *task)
 {
+	/* On x86_64, sp0 always points to the entry trampoline stack, which is constant: */
 #ifdef CONFIG_X86_32
 	load_sp0(task->thread.sp0);
 #else
-	load_sp0(task_top_of_stack(task));
+	if (static_cpu_has(X86_FEATURE_XENPV))
+		load_sp0(task_top_of_stack(task));
 #endif
 }
 

arch/x86/include/asm/thread_info.h

@@ -207,7 +207,7 @@ static inline int arch_within_stack_frames(const void * const stack,
 #else /* !__ASSEMBLY__ */
 
 #ifdef CONFIG_X86_64
-# define cpu_current_top_of_stack (cpu_tss + TSS_sp0)
+# define cpu_current_top_of_stack (cpu_tss_rw + TSS_sp1)
 #endif
 
 #endif

arch/x86/include/asm/tlbflush.h

@@ -9,70 +9,130 @@
 #include <asm/cpufeature.h>
 #include <asm/special_insns.h>
 #include <asm/smp.h>
+#include <asm/invpcid.h>
+#include <asm/pti.h>
+#include <asm/processor-flags.h>
 
-static inline void __invpcid(unsigned long pcid, unsigned long addr,
-			     unsigned long type)
-{
-	struct { u64 d[2]; } desc = { { pcid, addr } };
+/*
+ * The x86 feature is called PCID (Process Context IDentifier). It is similar
+ * to what is traditionally called ASID on the RISC processors.
+ *
+ * We don't use the traditional ASID implementation, where each process/mm gets
+ * its own ASID and flush/restart when we run out of ASID space.
+ *
+ * Instead we have a small per-cpu array of ASIDs and cache the last few mm's
+ * that came by on this CPU, allowing cheaper switch_mm between processes on
+ * this CPU.
+ *
+ * We end up with different spaces for different things. To avoid confusion we
+ * use different names for each of them:
+ *
+ * ASID  - [0, TLB_NR_DYN_ASIDS-1]
+ *         the canonical identifier for an mm
+ *
+ * kPCID - [1, TLB_NR_DYN_ASIDS]
+ *         the value we write into the PCID part of CR3; corresponds to the
+ *         ASID+1, because PCID 0 is special.
+ *
+ * uPCID - [2048 + 1, 2048 + TLB_NR_DYN_ASIDS]
+ *         for KPTI each mm has two address spaces and thus needs two
+ *         PCID values, but we can still do with a single ASID denomination
+ *         for each mm. Corresponds to kPCID + 2048.
+ *
+ */
 
-	/*
-	 * The memory clobber is because the whole point is to invalidate
-	 * stale TLB entries and, especially if we're flushing global
-	 * mappings, we don't want the compiler to reorder any subsequent
-	 * memory accesses before the TLB flush.
-	 *
-	 * The hex opcode is invpcid (%ecx), %eax in 32-bit mode and
-	 * invpcid (%rcx), %rax in long mode.
-	 */
-	asm volatile (".byte 0x66, 0x0f, 0x38, 0x82, 0x01"
-		      : : "m" (desc), "a" (type), "c" (&desc) : "memory");
-}
+/* There are 12 bits of space for ASIDS in CR3 */
+#define CR3_HW_ASID_BITS		12
 
-#define INVPCID_TYPE_INDIV_ADDR		0
-#define INVPCID_TYPE_SINGLE_CTXT	1
-#define INVPCID_TYPE_ALL_INCL_GLOBAL	2
-#define INVPCID_TYPE_ALL_NON_GLOBAL	3
+/*
+ * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for
+ * user/kernel switches
+ */
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define PTI_CONSUMED_PCID_BITS	1
+#else
+# define PTI_CONSUMED_PCID_BITS	0
+#endif
 
-/* Flush all mappings for a given pcid and addr, not including globals. */
-static inline void invpcid_flush_one(unsigned long pcid,
-				     unsigned long addr)
-{
-	__invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR);
-}
+#define CR3_AVAIL_PCID_BITS (X86_CR3_PCID_BITS - PTI_CONSUMED_PCID_BITS)
+
+/*
+ * ASIDs are zero-based: 0->MAX_AVAIL_ASID are valid.  -1 below to account
+ * for them being zero-based.  Another -1 is because PCID 0 is reserved for
+ * use by non-PCID-aware users.
+ */
+#define MAX_ASID_AVAILABLE ((1 << CR3_AVAIL_PCID_BITS) - 2)
+
+/*
+ * 6 because 6 should be plenty and struct tlb_state will fit in two cache
+ * lines.
+ */
+#define TLB_NR_DYN_ASIDS	6
 
-/* Flush all mappings for a given PCID, not including globals. */
-static inline void invpcid_flush_single_context(unsigned long pcid)
+/*
+ * Given @asid, compute kPCID
+ */
+static inline u16 kern_pcid(u16 asid)
 {
-	__invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT);
+	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	/*
+	 * Make sure that the dynamic ASID space does not confict with the
+	 * bit we are using to switch between user and kernel ASIDs.
+	 */
+	BUILD_BUG_ON(TLB_NR_DYN_ASIDS >= (1 << X86_CR3_PTI_SWITCH_BIT));
+
+	/*
+	 * The ASID being passed in here should have respected the
+	 * MAX_ASID_AVAILABLE and thus never have the switch bit set.
+	 */
+	VM_WARN_ON_ONCE(asid & (1 << X86_CR3_PTI_SWITCH_BIT));
+#endif
+	/*
+	 * The dynamically-assigned ASIDs that get passed in are small
+	 * (<TLB_NR_DYN_ASIDS).  They never have the high switch bit set,
+	 * so do not bother to clear it.
+	 *
+	 * If PCID is on, ASID-aware code paths put the ASID+1 into the
+	 * PCID bits.  This serves two purposes.  It prevents a nasty
+	 * situation in which PCID-unaware code saves CR3, loads some other
+	 * value (with PCID == 0), and then restores CR3, thus corrupting
+	 * the TLB for ASID 0 if the saved ASID was nonzero.  It also means
+	 * that any bugs involving loading a PCID-enabled CR3 with
+	 * CR4.PCIDE off will trigger deterministically.
+	 */
+	return asid + 1;
 }
 
-/* Flush all mappings, including globals, for all PCIDs. */
-static inline void invpcid_flush_all(void)
+/*
+ * Given @asid, compute uPCID
+ */
+static inline u16 user_pcid(u16 asid)
 {
-	__invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL);
+	u16 ret = kern_pcid(asid);
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	ret |= 1 << X86_CR3_PTI_SWITCH_BIT;
+#endif
+	return ret;
 }
 
-/* Flush all mappings for all PCIDs except globals. */
-static inline void invpcid_flush_all_nonglobals(void)
+struct pgd_t;
+static inline unsigned long build_cr3(pgd_t *pgd, u16 asid)
 {
-	__invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL);
+	if (static_cpu_has(X86_FEATURE_PCID)) {
+		return __sme_pa(pgd) | kern_pcid(asid);
+	} else {
+		VM_WARN_ON_ONCE(asid != 0);
+		return __sme_pa(pgd);
+	}
 }
 
-static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
+static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
 {
-	u64 new_tlb_gen;
-
-	/*
-	 * Bump the generation count.  This also serves as a full barrier
-	 * that synchronizes with switch_mm(): callers are required to order
-	 * their read of mm_cpumask after their writes to the paging
-	 * structures.
-	 */
-	smp_mb__before_atomic();
-	new_tlb_gen = atomic64_inc_return(&mm->context.tlb_gen);
-	smp_mb__after_atomic();
-
-	return new_tlb_gen;
+	VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE);
+	VM_WARN_ON_ONCE(!this_cpu_has(X86_FEATURE_PCID));
+	return __sme_pa(pgd) | kern_pcid(asid) | CR3_NOFLUSH;
 }
 
 #ifdef CONFIG_PARAVIRT
@@ -99,12 +159,6 @@ static inline bool tlb_defer_switch_to_init_mm(void)
 	return !static_cpu_has(X86_FEATURE_PCID);
 }
 
-/*
- * 6 because 6 should be plenty and struct tlb_state will fit in
- * two cache lines.
- */
-#define TLB_NR_DYN_ASIDS 6
-
 struct tlb_context {
 	u64 ctx_id;
 	u64 tlb_gen;
@@ -138,6 +192,24 @@ struct tlb_state {
 	 */
 	bool is_lazy;
 
+	/*
+	 * If set we changed the page tables in such a way that we
+	 * needed an invalidation of all contexts (aka. PCIDs / ASIDs).
+	 * This tells us to go invalidate all the non-loaded ctxs[]
+	 * on the next context switch.
+	 *
+	 * The current ctx was kept up-to-date as it ran and does not
+	 * need to be invalidated.
+	 */
+	bool invalidate_other;
+
+	/*
+	 * Mask that contains TLB_NR_DYN_ASIDS+1 bits to indicate
+	 * the corresponding user PCID needs a flush next time we
+	 * switch to it; see SWITCH_TO_USER_CR3.
+	 */
+	unsigned short user_pcid_flush_mask;
+
 	/*
 	 * Access to this CR4 shadow and to H/W CR4 is protected by
 	 * disabling interrupts when modifying either one.
@@ -218,6 +290,14 @@ static inline unsigned long cr4_read_shadow(void)
 	return this_cpu_read(cpu_tlbstate.cr4);
 }
 
+/*
+ * Mark all other ASIDs as invalid, preserves the current.
+ */
+static inline void invalidate_other_asid(void)
+{
+	this_cpu_write(cpu_tlbstate.invalidate_other, true);
+}
+
 /*
  * Save some of cr4 feature set we're using (e.g.  Pentium 4MB
  * enable and PPro Global page enable), so that any CPU's that boot
@@ -237,37 +317,63 @@ static inline void cr4_set_bits_and_update_boot(unsigned long mask)
 
 extern void initialize_tlbstate_and_flush(void);
 
-static inline void __native_flush_tlb(void)
+/*
+ * Given an ASID, flush the corresponding user ASID.  We can delay this
+ * until the next time we switch to it.
+ *
+ * See SWITCH_TO_USER_CR3.
+ */
+static inline void invalidate_user_asid(u16 asid)
 {
+	/* There is no user ASID if address space separation is off */
+	if (!IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
+		return;
+
 	/*
-	 * If current->mm == NULL then we borrow a mm which may change during a
-	 * task switch and therefore we must not be preempted while we write CR3
-	 * back:
+	 * We only have a single ASID if PCID is off and the CR3
+	 * write will have flushed it.
 	 */
-	preempt_disable();
-	native_write_cr3(__native_read_cr3());
-	preempt_enable();
+	if (!cpu_feature_enabled(X86_FEATURE_PCID))
+		return;
+
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	__set_bit(kern_pcid(asid),
+		  (unsigned long *)this_cpu_ptr(&cpu_tlbstate.user_pcid_flush_mask));
 }
 
-static inline void __native_flush_tlb_global_irq_disabled(void)
+/*
+ * flush the entire current user mapping
+ */
+static inline void __native_flush_tlb(void)
 {
-	unsigned long cr4;
+	/*
+	 * Preemption or interrupts must be disabled to protect the access
+	 * to the per CPU variable and to prevent being preempted between
+	 * read_cr3() and write_cr3().
+	 */
+	WARN_ON_ONCE(preemptible());
 
-	cr4 = this_cpu_read(cpu_tlbstate.cr4);
-	/* clear PGE */
-	native_write_cr4(cr4 & ~X86_CR4_PGE);
-	/* write old PGE again and flush TLBs */
-	native_write_cr4(cr4);
+	invalidate_user_asid(this_cpu_read(cpu_tlbstate.loaded_mm_asid));
+
+	/* If current->mm == NULL then the read_cr3() "borrows" an mm */
+	native_write_cr3(__native_read_cr3());
 }
 
+/*
+ * flush everything
+ */
 static inline void __native_flush_tlb_global(void)
 {
-	unsigned long flags;
+	unsigned long cr4, flags;
 
 	if (static_cpu_has(X86_FEATURE_INVPCID)) {
 		/*
 		 * Using INVPCID is considerably faster than a pair of writes
 		 * to CR4 sandwiched inside an IRQ flag save/restore.
+		 *
+		 * Note, this works with CR4.PCIDE=0 or 1.
 		 */
 		invpcid_flush_all();
 		return;
@@ -280,36 +386,69 @@ static inline void __native_flush_tlb_global(void)
 	 */
 	raw_local_irq_save(flags);
 
-	__native_flush_tlb_global_irq_disabled();
+	cr4 = this_cpu_read(cpu_tlbstate.cr4);
+	/* toggle PGE */
+	native_write_cr4(cr4 ^ X86_CR4_PGE);
+	/* write old PGE again and flush TLBs */
+	native_write_cr4(cr4);
 
 	raw_local_irq_restore(flags);
 }
 
+/*
+ * flush one page in the user mapping
+ */
 static inline void __native_flush_tlb_single(unsigned long addr)
 {
+	u32 loaded_mm_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+
 	asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
+
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	/*
+	 * Some platforms #GP if we call invpcid(type=1/2) before CR4.PCIDE=1.
+	 * Just use invalidate_user_asid() in case we are called early.
+	 */
+	if (!this_cpu_has(X86_FEATURE_INVPCID_SINGLE))
+		invalidate_user_asid(loaded_mm_asid);
+	else
+		invpcid_flush_one(user_pcid(loaded_mm_asid), addr);
 }
 
+/*
+ * flush everything
+ */
 static inline void __flush_tlb_all(void)
 {
-	if (boot_cpu_has(X86_FEATURE_PGE))
+	if (boot_cpu_has(X86_FEATURE_PGE)) {
 		__flush_tlb_global();
-	else
+	} else {
+		/*
+		 * !PGE -> !PCID (setup_pcid()), thus every flush is total.
+		 */
 		__flush_tlb();
-
-	/*
-	 * Note: if we somehow had PCID but not PGE, then this wouldn't work --
-	 * we'd end up flushing kernel translations for the current ASID but
-	 * we might fail to flush kernel translations for other cached ASIDs.
-	 *
-	 * To avoid this issue, we force PCID off if PGE is off.
-	 */
+	}
 }
 
+/*
+ * flush one page in the kernel mapping
+ */
 static inline void __flush_tlb_one(unsigned long addr)
 {
 	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ONE);
 	__flush_tlb_single(addr);
+
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	/*
+	 * __flush_tlb_single() will have cleared the TLB entry for this ASID,
+	 * but since kernel space is replicated across all, we must also
+	 * invalidate all others.
+	 */
+	invalidate_other_asid();
 }
 
 #define TLB_FLUSH_ALL	-1UL
@@ -370,6 +509,17 @@ static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a)
 void native_flush_tlb_others(const struct cpumask *cpumask,
 			     const struct flush_tlb_info *info);
 
+static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
+{
+	/*
+	 * Bump the generation count.  This also serves as a full barrier
+	 * that synchronizes with switch_mm(): callers are required to order
+	 * their read of mm_cpumask after their writes to the paging
+	 * structures.
+	 */
+	return atomic64_inc_return(&mm->context.tlb_gen);
+}
+
 static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
 					struct mm_struct *mm)
 {

arch/x86/include/asm/trace/irq_vectors.h

@@ -283,34 +283,34 @@ TRACE_EVENT(vector_alloc_managed,
 DECLARE_EVENT_CLASS(vector_activate,
 
 	TP_PROTO(unsigned int irq, bool is_managed, bool can_reserve,
-		 bool early),
+		 bool reserve),
 
-	TP_ARGS(irq, is_managed, can_reserve, early),
+	TP_ARGS(irq, is_managed, can_reserve, reserve),
 
 	TP_STRUCT__entry(
 		__field(	unsigned int,	irq		)
 		__field(	bool,		is_managed	)
 		__field(	bool,		can_reserve	)
-		__field(	bool,		early		)
+		__field(	bool,		reserve		)
 	),
 
 	TP_fast_assign(
 		__entry->irq		= irq;
 		__entry->is_managed	= is_managed;
 		__entry->can_reserve	= can_reserve;
-		__entry->early		= early;
+		__entry->reserve	= reserve;
 	),
 
-	TP_printk("irq=%u is_managed=%d can_reserve=%d early=%d",
+	TP_printk("irq=%u is_managed=%d can_reserve=%d reserve=%d",
 		  __entry->irq, __entry->is_managed, __entry->can_reserve,
-		  __entry->early)
+		  __entry->reserve)
 );
 
 #define DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(name)				\
 DEFINE_EVENT_FN(vector_activate, name,					\
 	TP_PROTO(unsigned int irq, bool is_managed,			\
-		 bool can_reserve, bool early),				\
-	TP_ARGS(irq, is_managed, can_reserve, early), NULL, NULL);	\
+		 bool can_reserve, bool reserve),			\
+	TP_ARGS(irq, is_managed, can_reserve, reserve), NULL, NULL);	\
 
 DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(vector_activate);
 DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(vector_deactivate);

arch/x86/include/asm/traps.h

@@ -75,7 +75,6 @@ dotraplinkage void do_segment_not_present(struct pt_regs *, long);
 dotraplinkage void do_stack_segment(struct pt_regs *, long);
 #ifdef CONFIG_X86_64
 dotraplinkage void do_double_fault(struct pt_regs *, long);
-asmlinkage struct pt_regs *sync_regs(struct pt_regs *);
 #endif
 dotraplinkage void do_general_protection(struct pt_regs *, long);
 dotraplinkage void do_page_fault(struct pt_regs *, unsigned long);

arch/x86/include/asm/unwind.h

@@ -7,6 +7,9 @@
 #include <asm/ptrace.h>
 #include <asm/stacktrace.h>
 
+#define IRET_FRAME_OFFSET (offsetof(struct pt_regs, ip))
+#define IRET_FRAME_SIZE   (sizeof(struct pt_regs) - IRET_FRAME_OFFSET)
+
 struct unwind_state {
 	struct stack_info stack_info;
 	unsigned long stack_mask;
@@ -52,6 +55,10 @@ void unwind_start(struct unwind_state *state, struct task_struct *task,
 }
 
 #if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER)
+/*
+ * WARNING: The entire pt_regs may not be safe to dereference.  In some cases,
+ * only the iret frame registers are accessible.  Use with caution!
+ */
 static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
 {
 	if (unwind_done(state))

arch/x86/include/asm/vsyscall.h

@@ -7,6 +7,7 @@
 
 #ifdef CONFIG_X86_VSYSCALL_EMULATION
 extern void map_vsyscall(void);
+extern void set_vsyscall_pgtable_user_bits(pgd_t *root);
 
 /*
  * Called on instruction fetch fault in vsyscall page.

arch/x86/include/uapi/asm/processor-flags.h

@@ -78,7 +78,12 @@
 #define X86_CR3_PWT		_BITUL(X86_CR3_PWT_BIT)
 #define X86_CR3_PCD_BIT		4 /* Page Cache Disable */
 #define X86_CR3_PCD		_BITUL(X86_CR3_PCD_BIT)
-#define X86_CR3_PCID_MASK	_AC(0x00000fff,UL) /* PCID Mask */
+
+#define X86_CR3_PCID_BITS	12
+#define X86_CR3_PCID_MASK	(_AC((1UL << X86_CR3_PCID_BITS) - 1, UL))
+
+#define X86_CR3_PCID_NOFLUSH_BIT 63 /* Preserve old PCID */
+#define X86_CR3_PCID_NOFLUSH    _BITULL(X86_CR3_PCID_NOFLUSH_BIT)
 
 /*
  * Intel CPU features in CR4

arch/x86/kernel/apic/apic.c

@@ -2626,11 +2626,13 @@ static int __init apic_set_verbosity(char *arg)
 		apic_verbosity = APIC_DEBUG;
 	else if (strcmp("verbose", arg) == 0)
 		apic_verbosity = APIC_VERBOSE;
+#ifdef CONFIG_X86_64
 	else {
 		pr_warning("APIC Verbosity level %s not recognised"
 			" use apic=verbose or apic=debug\n", arg);
 		return -EINVAL;
 	}
+#endif
 
 	return 0;
 }

arch/x86/kernel/apic/apic_flat_64.c

@@ -151,7 +151,7 @@ static struct apic apic_flat __ro_after_init = {
 	.apic_id_valid			= default_apic_id_valid,
 	.apic_id_registered		= flat_apic_id_registered,
 
-	.irq_delivery_mode		= dest_LowestPrio,
+	.irq_delivery_mode		= dest_Fixed,
 	.irq_dest_mode			= 1, /* logical */
 
 	.disable_esr			= 0,

arch/x86/kernel/apic/apic_noop.c

@@ -110,7 +110,7 @@ struct apic apic_noop __ro_after_init = {
 	.apic_id_valid			= default_apic_id_valid,
 	.apic_id_registered		= noop_apic_id_registered,
 
-	.irq_delivery_mode		= dest_LowestPrio,
+	.irq_delivery_mode		= dest_Fixed,
 	/* logical delivery broadcast to all CPUs: */
 	.irq_dest_mode			= 1,
 

arch/x86/kernel/apic/io_apic.c

@@ -2988,7 +2988,7 @@ void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq,
 }
 
 int mp_irqdomain_activate(struct irq_domain *domain,
-			  struct irq_data *irq_data, bool early)
+			  struct irq_data *irq_data, bool reserve)
 {
 	unsigned long flags;
 

arch/x86/kernel/apic/msi.c

@@ -39,17 +39,13 @@ static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
 		((apic->irq_dest_mode == 0) ?
 			MSI_ADDR_DEST_MODE_PHYSICAL :
 			MSI_ADDR_DEST_MODE_LOGICAL) |
-		((apic->irq_delivery_mode != dest_LowestPrio) ?
-			MSI_ADDR_REDIRECTION_CPU :
-			MSI_ADDR_REDIRECTION_LOWPRI) |
+		MSI_ADDR_REDIRECTION_CPU |
 		MSI_ADDR_DEST_ID(cfg->dest_apicid);
 
 	msg->data =
 		MSI_DATA_TRIGGER_EDGE |
 		MSI_DATA_LEVEL_ASSERT |
-		((apic->irq_delivery_mode != dest_LowestPrio) ?
-			MSI_DATA_DELIVERY_FIXED :
-			MSI_DATA_DELIVERY_LOWPRI) |
+		MSI_DATA_DELIVERY_FIXED |
 		MSI_DATA_VECTOR(cfg->vector);
 }
 

arch/x86/kernel/apic/probe_32.c

@@ -105,7 +105,7 @@ static struct apic apic_default __ro_after_init = {
 	.apic_id_valid			= default_apic_id_valid,
 	.apic_id_registered		= default_apic_id_registered,
 
-	.irq_delivery_mode		= dest_LowestPrio,
+	.irq_delivery_mode		= dest_Fixed,
 	/* logical delivery broadcast to all CPUs: */
 	.irq_dest_mode			= 1,
 

arch/x86/kernel/apic/vector.c

@@ -184,6 +184,7 @@ static void reserve_irq_vector_locked(struct irq_data *irqd)
 	irq_matrix_reserve(vector_matrix);
 	apicd->can_reserve = true;
 	apicd->has_reserved = true;
+	irqd_set_can_reserve(irqd);
 	trace_vector_reserve(irqd->irq, 0);
 	vector_assign_managed_shutdown(irqd);
 }
@@ -368,8 +369,18 @@ static int activate_reserved(struct irq_data *irqd)
 	int ret;
 
 	ret = assign_irq_vector_any_locked(irqd);
-	if (!ret)
+	if (!ret) {
 		apicd->has_reserved = false;
+		/*
+		 * Core might have disabled reservation mode after
+		 * allocating the irq descriptor. Ideally this should
+		 * happen before allocation time, but that would require
+		 * completely convoluted ways of transporting that
+		 * information.
+		 */
+		if (!irqd_can_reserve(irqd))
+			apicd->can_reserve = false;
+	}
 	return ret;
 }
 
@@ -398,21 +409,21 @@ static int activate_managed(struct irq_data *irqd)
 }
 
 static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd,
-			       bool early)
+			       bool reserve)
 {
 	struct apic_chip_data *apicd = apic_chip_data(irqd);
 	unsigned long flags;
 	int ret = 0;
 
 	trace_vector_activate(irqd->irq, apicd->is_managed,
-			      apicd->can_reserve, early);
+			      apicd->can_reserve, reserve);
 
 	/* Nothing to do for fixed assigned vectors */
 	if (!apicd->can_reserve && !apicd->is_managed)
 		return 0;
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	if (early || irqd_is_managed_and_shutdown(irqd))
+	if (reserve || irqd_is_managed_and_shutdown(irqd))
 		vector_assign_managed_shutdown(irqd);
 	else if (apicd->is_managed)
 		ret = activate_managed(irqd);
@@ -478,6 +489,7 @@ static bool vector_configure_legacy(unsigned int virq, struct irq_data *irqd,
 	} else {
 		/* Release the vector */
 		apicd->can_reserve = true;
+		irqd_set_can_reserve(irqd);
 		clear_irq_vector(irqd);
 		realloc = true;
 	}

arch/x86/kernel/apic/x2apic_cluster.c

@@ -184,7 +184,7 @@ static struct apic apic_x2apic_cluster __ro_after_init = {
 	.apic_id_valid			= x2apic_apic_id_valid,
 	.apic_id_registered		= x2apic_apic_id_registered,
 
-	.irq_delivery_mode		= dest_LowestPrio,
+	.irq_delivery_mode		= dest_Fixed,
 	.irq_dest_mode			= 1, /* logical */
 
 	.disable_esr			= 0,

arch/x86/kernel/asm-offsets.c

@@ -17,6 +17,7 @@
 #include <asm/sigframe.h>
 #include <asm/bootparam.h>
 #include <asm/suspend.h>
+#include <asm/tlbflush.h>
 
 #ifdef CONFIG_XEN
 #include <xen/interface/xen.h>
@@ -93,4 +94,13 @@ void common(void) {
 
 	BLANK();
 	DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));
+
+	/* TLB state for the entry code */
+	OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask);
+
+	/* Layout info for cpu_entry_area */
+	OFFSET(CPU_ENTRY_AREA_tss, cpu_entry_area, tss);
+	OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline);
+	OFFSET(CPU_ENTRY_AREA_entry_stack, cpu_entry_area, entry_stack_page);
+	DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack));
 }

arch/x86/kernel/asm-offsets_32.c

@@ -47,13 +47,8 @@ void foo(void)
 	BLANK();
 
 	/* Offset from the sysenter stack to tss.sp0 */
-	DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) -
-	       offsetofend(struct tss_struct, SYSENTER_stack));
-
-	/* Offset from cpu_tss to SYSENTER_stack */
-	OFFSET(CPU_TSS_SYSENTER_stack, tss_struct, SYSENTER_stack);
-	/* Size of SYSENTER_stack */
-	DEFINE(SIZEOF_SYSENTER_stack, sizeof(((struct tss_struct *)0)->SYSENTER_stack));
+	DEFINE(TSS_sysenter_sp0, offsetof(struct cpu_entry_area, tss.x86_tss.sp0) -
+	       offsetofend(struct cpu_entry_area, entry_stack_page.stack));
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 	BLANK();

arch/x86/kernel/asm-offsets_64.c

@@ -23,6 +23,9 @@ int main(void)
 #ifdef CONFIG_PARAVIRT
 	OFFSET(PV_CPU_usergs_sysret64, pv_cpu_ops, usergs_sysret64);
 	OFFSET(PV_CPU_swapgs, pv_cpu_ops, swapgs);
+#ifdef CONFIG_DEBUG_ENTRY
+	OFFSET(PV_IRQ_save_fl, pv_irq_ops, save_fl);
+#endif
 	BLANK();
 #endif
 
@@ -63,6 +66,7 @@ int main(void)
 
 	OFFSET(TSS_ist, tss_struct, x86_tss.ist);
 	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
+	OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
 	BLANK();
 
 #ifdef CONFIG_CC_STACKPROTECTOR

arch/x86/kernel/cpu/common.c

@@ -476,8 +476,8 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c)
 	return NULL;		/* Not found */
 }
 
-__u32 cpu_caps_cleared[NCAPINTS];
-__u32 cpu_caps_set[NCAPINTS];
+__u32 cpu_caps_cleared[NCAPINTS + NBUGINTS];
+__u32 cpu_caps_set[NCAPINTS + NBUGINTS];
 
 void load_percpu_segment(int cpu)
 {
@@ -490,28 +490,23 @@ void load_percpu_segment(int cpu)
 	load_stack_canary_segment();
 }
 
-/* Setup the fixmap mapping only once per-processor */
-static inline void setup_fixmap_gdt(int cpu)
-{
-#ifdef CONFIG_X86_64
-	/* On 64-bit systems, we use a read-only fixmap GDT. */
-	pgprot_t prot = PAGE_KERNEL_RO;
-#else
-	/*
-	 * On native 32-bit systems, the GDT cannot be read-only because
-	 * our double fault handler uses a task gate, and entering through
-	 * a task gate needs to change an available TSS to busy.  If the GDT
-	 * is read-only, that will triple fault.
-	 *
-	 * On Xen PV, the GDT must be read-only because the hypervisor requires
-	 * it.
-	 */
-	pgprot_t prot = boot_cpu_has(X86_FEATURE_XENPV) ?
-		PAGE_KERNEL_RO : PAGE_KERNEL;
+#ifdef CONFIG_X86_32
+/* The 32-bit entry code needs to find cpu_entry_area. */
+DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area);
 #endif
 
-	__set_fixmap(get_cpu_gdt_ro_index(cpu), get_cpu_gdt_paddr(cpu), prot);
-}
+#ifdef CONFIG_X86_64
+/*
+ * Special IST stacks which the CPU switches to when it calls
+ * an IST-marked descriptor entry. Up to 7 stacks (hardware
+ * limit), all of them are 4K, except the debug stack which
+ * is 8K.
+ */
+static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
+	  [0 ... N_EXCEPTION_STACKS - 1]	= EXCEPTION_STKSZ,
+	  [DEBUG_STACK - 1]			= DEBUG_STKSZ
+};
+#endif
 
 /* Load the original GDT from the per-cpu structure */
 void load_direct_gdt(int cpu)
@@ -747,7 +742,7 @@ static void apply_forced_caps(struct cpuinfo_x86 *c)
 {
 	int i;
 
-	for (i = 0; i < NCAPINTS; i++) {
+	for (i = 0; i < NCAPINTS + NBUGINTS; i++) {
 		c->x86_capability[i] &= ~cpu_caps_cleared[i];
 		c->x86_capability[i] |= cpu_caps_set[i];
 	}
@@ -927,6 +922,10 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	}
 
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
+
+	/* Assume for now that ALL x86 CPUs are insecure */
+	setup_force_cpu_bug(X86_BUG_CPU_INSECURE);
+
 	fpu__init_system(c);
 
 #ifdef CONFIG_X86_32
@@ -1250,7 +1249,7 @@ void enable_sep_cpu(void)
 		return;
 
 	cpu = get_cpu();
-	tss = &per_cpu(cpu_tss, cpu);
+	tss = &per_cpu(cpu_tss_rw, cpu);
 
 	/*
 	 * We cache MSR_IA32_SYSENTER_CS's value in the TSS's ss1 field --
@@ -1259,11 +1258,7 @@ void enable_sep_cpu(void)
 
 	tss->x86_tss.ss1 = __KERNEL_CS;
 	wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0);
-
-	wrmsr(MSR_IA32_SYSENTER_ESP,
-	      (unsigned long)tss + offsetofend(struct tss_struct, SYSENTER_stack),
-	      0);
-
+	wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1), 0);
 	wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
 
 	put_cpu();
@@ -1357,25 +1352,22 @@ DEFINE_PER_CPU(unsigned int, irq_count) __visible = -1;
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
 
-/*
- * Special IST stacks which the CPU switches to when it calls
- * an IST-marked descriptor entry. Up to 7 stacks (hardware
- * limit), all of them are 4K, except the debug stack which
- * is 8K.
- */
-static const unsigned int exception_stack_sizes[N_EXCEPTION_STACKS] = {
-	  [0 ... N_EXCEPTION_STACKS - 1]	= EXCEPTION_STKSZ,
-	  [DEBUG_STACK - 1]			= DEBUG_STKSZ
-};
-
-static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
-	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
-
 /* May not be marked __init: used by software suspend */
 void syscall_init(void)
 {
+	extern char _entry_trampoline[];
+	extern char entry_SYSCALL_64_trampoline[];
+
+	int cpu = smp_processor_id();
+	unsigned long SYSCALL64_entry_trampoline =
+		(unsigned long)get_cpu_entry_area(cpu)->entry_trampoline +
+		(entry_SYSCALL_64_trampoline - _entry_trampoline);
+
 	wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS);
-	wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
+	if (static_cpu_has(X86_FEATURE_PTI))
+		wrmsrl(MSR_LSTAR, SYSCALL64_entry_trampoline);
+	else
+		wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
 
 #ifdef CONFIG_IA32_EMULATION
 	wrmsrl(MSR_CSTAR, (unsigned long)entry_SYSCALL_compat);
@@ -1386,7 +1378,7 @@ void syscall_init(void)
 	 * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
 	 */
 	wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
-	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+	wrmsrl_safe(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1));
 	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
 #else
 	wrmsrl(MSR_CSTAR, (unsigned long)ignore_sysret);
@@ -1530,7 +1522,7 @@ void cpu_init(void)
 	if (cpu)
 		load_ucode_ap();
 
-	t = &per_cpu(cpu_tss, cpu);
+	t = &per_cpu(cpu_tss_rw, cpu);
 	oist = &per_cpu(orig_ist, cpu);
 
 #ifdef CONFIG_NUMA
@@ -1569,7 +1561,7 @@ void cpu_init(void)
 	 * set up and load the per-CPU TSS
 	 */
 	if (!oist->ist[0]) {
-		char *estacks = per_cpu(exception_stacks, cpu);
+		char *estacks = get_cpu_entry_area(cpu)->exception_stacks;
 
 		for (v = 0; v < N_EXCEPTION_STACKS; v++) {
 			estacks += exception_stack_sizes[v];
@@ -1580,7 +1572,7 @@ void cpu_init(void)
 		}
 	}
 
-	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+	t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
 
 	/*
 	 * <= is required because the CPU will access up to
@@ -1596,11 +1588,12 @@ void cpu_init(void)
 	enter_lazy_tlb(&init_mm, me);
 
 	/*
-	 * Initialize the TSS.  Don't bother initializing sp0, as the initial
-	 * task never enters user mode.
+	 * Initialize the TSS.  sp0 points to the entry trampoline stack
+	 * regardless of what task is running.
 	 */
-	set_tss_desc(cpu, t);
+	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
 	load_TR_desc();
+	load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1));
 
 	load_mm_ldt(&init_mm);
 
@@ -1612,7 +1605,6 @@ void cpu_init(void)
 	if (is_uv_system())
 		uv_cpu_init();
 
-	setup_fixmap_gdt(cpu);
 	load_fixmap_gdt(cpu);
 }
 
@@ -1622,7 +1614,7 @@ void cpu_init(void)
 {
 	int cpu = smp_processor_id();
 	struct task_struct *curr = current;
-	struct tss_struct *t = &per_cpu(cpu_tss, cpu);
+	struct tss_struct *t = &per_cpu(cpu_tss_rw, cpu);
 
 	wait_for_master_cpu(cpu);
 
@@ -1657,12 +1649,12 @@ void cpu_init(void)
 	 * Initialize the TSS.  Don't bother initializing sp0, as the initial
 	 * task never enters user mode.
 	 */
-	set_tss_desc(cpu, t);
+	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
 	load_TR_desc();
 
 	load_mm_ldt(&init_mm);
 
-	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+	t->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET;
 
 #ifdef CONFIG_DOUBLEFAULT
 	/* Set up doublefault TSS pointer in the GDT */
@@ -1674,7 +1666,6 @@ void cpu_init(void)
 
 	fpu__init_cpu();
 
-	setup_fixmap_gdt(cpu);
 	load_fixmap_gdt(cpu);
 }
 #endif

arch/x86/kernel/cpu/microcode/intel.c

@@ -565,15 +565,6 @@ static void print_ucode(struct ucode_cpu_info *uci)
 }
 #else
 
-/*
- * Flush global tlb. We only do this in x86_64 where paging has been enabled
- * already and PGE should be enabled as well.
- */
-static inline void flush_tlb_early(void)
-{
-	__native_flush_tlb_global_irq_disabled();
-}
-
 static inline void print_ucode(struct ucode_cpu_info *uci)
 {
 	struct microcode_intel *mc;
@@ -602,10 +593,6 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early)
 	if (rev != mc->hdr.rev)
 		return -1;
 
-#ifdef CONFIG_X86_64
-	/* Flush global tlb. This is precaution. */
-	flush_tlb_early();
-#endif
 	uci->cpu_sig.rev = rev;
 
 	if (early)

arch/x86/kernel/doublefault.c

@@ -50,25 +50,23 @@ static void doublefault_fn(void)
 		cpu_relax();
 }
 
-struct tss_struct doublefault_tss __cacheline_aligned = {
-	.x86_tss = {
-		.sp0		= STACK_START,
-		.ss0		= __KERNEL_DS,
-		.ldt		= 0,
-		.io_bitmap_base	= INVALID_IO_BITMAP_OFFSET,
-
-		.ip		= (unsigned long) doublefault_fn,
-		/* 0x2 bit is always set */
-		.flags		= X86_EFLAGS_SF | 0x2,
-		.sp		= STACK_START,
-		.es		= __USER_DS,
-		.cs		= __KERNEL_CS,
-		.ss		= __KERNEL_DS,
-		.ds		= __USER_DS,
-		.fs		= __KERNEL_PERCPU,
-
-		.__cr3		= __pa_nodebug(swapper_pg_dir),
-	}
+struct x86_hw_tss doublefault_tss __cacheline_aligned = {
+	.sp0		= STACK_START,
+	.ss0		= __KERNEL_DS,
+	.ldt		= 0,
+	.io_bitmap_base	= INVALID_IO_BITMAP_OFFSET,
+
+	.ip		= (unsigned long) doublefault_fn,
+	/* 0x2 bit is always set */
+	.flags		= X86_EFLAGS_SF | 0x2,
+	.sp		= STACK_START,
+	.es		= __USER_DS,
+	.cs		= __KERNEL_CS,
+	.ss		= __KERNEL_DS,
+	.ds		= __USER_DS,
+	.fs		= __KERNEL_PERCPU,
+
+	.__cr3		= __pa_nodebug(swapper_pg_dir),
 };
 
 /* dummy for do_double_fault() call */

arch/x86/kernel/dumpstack.c

@@ -18,6 +18,7 @@
 #include <linux/nmi.h>
 #include <linux/sysfs.h>
 
+#include <asm/cpu_entry_area.h>
 #include <asm/stacktrace.h>
 #include <asm/unwind.h>
 
@@ -43,6 +44,24 @@ bool in_task_stack(unsigned long *stack, struct task_struct *task,
 	return true;
 }
 
+bool in_entry_stack(unsigned long *stack, struct stack_info *info)
+{
+	struct entry_stack *ss = cpu_entry_stack(smp_processor_id());
+
+	void *begin = ss;
+	void *end = ss + 1;
+
+	if ((void *)stack < begin || (void *)stack >= end)
+		return false;
+
+	info->type	= STACK_TYPE_ENTRY;
+	info->begin	= begin;
+	info->end	= end;
+	info->next_sp	= NULL;
+
+	return true;
+}
+
 static void printk_stack_address(unsigned long address, int reliable,
 				 char *log_lvl)
 {
@@ -50,6 +69,28 @@ static void printk_stack_address(unsigned long address, int reliable,
 	printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address);
 }
 
+void show_iret_regs(struct pt_regs *regs)
+{
+	printk(KERN_DEFAULT "RIP: %04x:%pS\n", (int)regs->cs, (void *)regs->ip);
+	printk(KERN_DEFAULT "RSP: %04x:%016lx EFLAGS: %08lx", (int)regs->ss,
+		regs->sp, regs->flags);
+}
+
+static void show_regs_safe(struct stack_info *info, struct pt_regs *regs)
+{
+	if (on_stack(info, regs, sizeof(*regs)))
+		__show_regs(regs, 0);
+	else if (on_stack(info, (void *)regs + IRET_FRAME_OFFSET,
+			  IRET_FRAME_SIZE)) {
+		/*
+		 * When an interrupt or exception occurs in entry code, the
+		 * full pt_regs might not have been saved yet.  In that case
+		 * just print the iret frame.
+		 */
+		show_iret_regs(regs);
+	}
+}
+
 void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			unsigned long *stack, char *log_lvl)
 {
@@ -71,31 +112,35 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	 * - task stack
 	 * - interrupt stack
 	 * - HW exception stacks (double fault, nmi, debug, mce)
+	 * - entry stack
 	 *
-	 * x86-32 can have up to three stacks:
+	 * x86-32 can have up to four stacks:
 	 * - task stack
 	 * - softirq stack
 	 * - hardirq stack
+	 * - entry stack
 	 */
 	for (regs = NULL; stack; stack = PTR_ALIGN(stack_info.next_sp, sizeof(long))) {
 		const char *stack_name;
 
-		/*
-		 * If we overflowed the task stack into a guard page, jump back
-		 * to the bottom of the usable stack.
-		 */
-		if (task_stack_page(task) - (void *)stack < PAGE_SIZE)
-			stack = task_stack_page(task);
-
-		if (get_stack_info(stack, task, &stack_info, &visit_mask))
-			break;
+		if (get_stack_info(stack, task, &stack_info, &visit_mask)) {
+			/*
+			 * We weren't on a valid stack.  It's possible that
+			 * we overflowed a valid stack into a guard page.
+			 * See if the next page up is valid so that we can
+			 * generate some kind of backtrace if this happens.
+			 */
+			stack = (unsigned long *)PAGE_ALIGN((unsigned long)stack);
+			if (get_stack_info(stack, task, &stack_info, &visit_mask))
+				break;
+		}
 
 		stack_name = stack_type_name(stack_info.type);
 		if (stack_name)
 			printk("%s <%s>\n", log_lvl, stack_name);
 
-		if (regs && on_stack(&stack_info, regs, sizeof(*regs)))
-			__show_regs(regs, 0);
+		if (regs)
+			show_regs_safe(&stack_info, regs);
 
 		/*
 		 * Scan the stack, printing any text addresses we find.  At the
@@ -119,7 +164,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 
 			/*
 			 * Don't print regs->ip again if it was already printed
-			 * by __show_regs() below.
+			 * by show_regs_safe() below.
 			 */
 			if (regs && stack == &regs->ip)
 				goto next;
@@ -155,8 +200,8 @@ next:
 
 			/* if the frame has entry regs, print them */
 			regs = unwind_get_entry_regs(&state);
-			if (regs && on_stack(&stack_info, regs, sizeof(*regs)))
-				__show_regs(regs, 0);
+			if (regs)
+				show_regs_safe(&stack_info, regs);
 		}
 
 		if (stack_name)
@@ -252,11 +297,13 @@ int __die(const char *str, struct pt_regs *regs, long err)
 	unsigned long sp;
 #endif
 	printk(KERN_DEFAULT
-	       "%s: %04lx [#%d]%s%s%s%s\n", str, err & 0xffff, ++die_counter,
+	       "%s: %04lx [#%d]%s%s%s%s%s\n", str, err & 0xffff, ++die_counter,
 	       IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT"         : "",
 	       IS_ENABLED(CONFIG_SMP)     ? " SMP"             : "",
 	       debug_pagealloc_enabled()  ? " DEBUG_PAGEALLOC" : "",
-	       IS_ENABLED(CONFIG_KASAN)   ? " KASAN"           : "");
+	       IS_ENABLED(CONFIG_KASAN)   ? " KASAN"           : "",
+	       IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ?
+	       (boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : "");
 
 	if (notify_die(DIE_OOPS, str, regs, err,
 			current->thread.trap_nr, SIGSEGV) == NOTIFY_STOP)

arch/x86/kernel/dumpstack_32.c

@@ -26,6 +26,9 @@ const char *stack_type_name(enum stack_type type)
 	if (type == STACK_TYPE_SOFTIRQ)
 		return "SOFTIRQ";
 
+	if (type == STACK_TYPE_ENTRY)
+		return "ENTRY_TRAMPOLINE";
+
 	return NULL;
 }
 
@@ -93,6 +96,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
 	if (task != current)
 		goto unknown;
 
+	if (in_entry_stack(stack, info))
+		goto recursion_check;
+
 	if (in_hardirq_stack(stack, info))
 		goto recursion_check;
 

arch/x86/kernel/dumpstack_64.c

@@ -37,6 +37,15 @@ const char *stack_type_name(enum stack_type type)
 	if (type == STACK_TYPE_IRQ)
 		return "IRQ";
 
+	if (type == STACK_TYPE_ENTRY) {
+		/*
+		 * On 64-bit, we have a generic entry stack that we
+		 * use for all the kernel entry points, including
+		 * SYSENTER.
+		 */
+		return "ENTRY_TRAMPOLINE";
+	}
+
 	if (type >= STACK_TYPE_EXCEPTION && type <= STACK_TYPE_EXCEPTION_LAST)
 		return exception_stack_names[type - STACK_TYPE_EXCEPTION];
 
@@ -115,6 +124,9 @@ int get_stack_info(unsigned long *stack, struct task_struct *task,
 	if (in_irq_stack(stack, info))
 		goto recursion_check;
 
+	if (in_entry_stack(stack, info))
+		goto recursion_check;
+
 	goto unknown;
 
 recursion_check:

arch/x86/kernel/head_64.S

@@ -341,6 +341,27 @@ GLOBAL(early_recursion_flag)
 	.balign	PAGE_SIZE; \
 GLOBAL(name)
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * Each PGD needs to be 8k long and 8k aligned.  We do not
+ * ever go out to userspace with these, so we do not
+ * strictly *need* the second page, but this allows us to
+ * have a single set_pgd() implementation that does not
+ * need to worry about whether it has 4k or 8k to work
+ * with.
+ *
+ * This ensures PGDs are 8k long:
+ */
+#define PTI_USER_PGD_FILL	512
+/* This ensures they are 8k-aligned: */
+#define NEXT_PGD_PAGE(name) \
+	.balign 2 * PAGE_SIZE; \
+GLOBAL(name)
+#else
+#define NEXT_PGD_PAGE(name) NEXT_PAGE(name)
+#define PTI_USER_PGD_FILL	0
+#endif
+
 /* Automate the creation of 1 to 1 mapping pmd entries */
 #define PMDS(START, PERM, COUNT)			\
 	i = 0 ;						\
@@ -350,13 +371,14 @@ GLOBAL(name)
 	.endr
 
 	__INITDATA
-NEXT_PAGE(early_top_pgt)
+NEXT_PGD_PAGE(early_top_pgt)
 	.fill	511,8,0
 #ifdef CONFIG_X86_5LEVEL
 	.quad	level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 #else
 	.quad	level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
 #endif
+	.fill	PTI_USER_PGD_FILL,8,0
 
 NEXT_PAGE(early_dynamic_pgts)
 	.fill	512*EARLY_DYNAMIC_PAGE_TABLES,8,0
@@ -364,13 +386,14 @@ NEXT_PAGE(early_dynamic_pgts)
 	.data
 
 #if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH)
-NEXT_PAGE(init_top_pgt)
+NEXT_PGD_PAGE(init_top_pgt)
 	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.org    init_top_pgt + PGD_PAGE_OFFSET*8, 0
 	.quad   level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
 	.org    init_top_pgt + PGD_START_KERNEL*8, 0
 	/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
 	.quad   level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
+	.fill	PTI_USER_PGD_FILL,8,0
 
 NEXT_PAGE(level3_ident_pgt)
 	.quad	level2_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
@@ -381,8 +404,9 @@ NEXT_PAGE(level2_ident_pgt)
 	 */
 	PMDS(0, __PAGE_KERNEL_IDENT_LARGE_EXEC, PTRS_PER_PMD)
 #else
-NEXT_PAGE(init_top_pgt)
+NEXT_PGD_PAGE(init_top_pgt)
 	.fill	512,8,0
+	.fill	PTI_USER_PGD_FILL,8,0
 #endif
 
 #ifdef CONFIG_X86_5LEVEL

arch/x86/kernel/ioport.c

@@ -67,7 +67,7 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
 	 * because the ->io_bitmap_max value must match the bitmap
 	 * contents:
 	 */
-	tss = &per_cpu(cpu_tss, get_cpu());
+	tss = &per_cpu(cpu_tss_rw, get_cpu());
 
 	if (turn_on)
 		bitmap_clear(t->io_bitmap_ptr, from, num);

arch/x86/kernel/irq.c

@@ -219,18 +219,6 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 	/* high bit used in ret_from_ code  */
 	unsigned vector = ~regs->orig_ax;
 
-	/*
-	 * NB: Unlike exception entries, IRQ entries do not reliably
-	 * handle context tracking in the low-level entry code.  This is
-	 * because syscall entries execute briefly with IRQs on before
-	 * updating context tracking state, so we can take an IRQ from
-	 * kernel mode with CONTEXT_USER.  The low-level entry code only
-	 * updates the context if we came from user mode, so we won't
-	 * switch to CONTEXT_KERNEL.  We'll fix that once the syscall
-	 * code is cleaned up enough that we can cleanly defer enabling
-	 * IRQs.
-	 */
-
 	entering_irq();
 
 	/* entering_irq() tells RCU that we're not quiescent.  Check it. */

arch/x86/kernel/irq_64.c

@@ -57,10 +57,10 @@ static inline void stack_overflow_check(struct pt_regs *regs)
 	if (regs->sp >= estack_top && regs->sp <= estack_bottom)
 		return;
 
-	WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx)\n",
+	WARN_ONCE(1, "do_IRQ(): %s has overflown the kernel stack (cur:%Lx,sp:%lx,irq stk top-bottom:%Lx-%Lx,exception stk top-bottom:%Lx-%Lx,ip:%pF)\n",
 		current->comm, curbase, regs->sp,
 		irq_stack_top, irq_stack_bottom,
-		estack_top, estack_bottom);
+		estack_top, estack_bottom, (void *)regs->ip);
 
 	if (sysctl_panic_on_stackoverflow)
 		panic("low stack detected by irq handler - check messages\n");

arch/x86/kernel/ldt.c

@@ -5,6 +5,11 @@
  * Copyright (C) 2002 Andi Kleen
  *
  * This handles calls from both 32bit and 64bit mode.
+ *
+ * Lock order:
+ *	contex.ldt_usr_sem
+ *	  mmap_sem
+ *	    context.lock
  */
 
 #include <linux/errno.h>
@@ -19,6 +24,7 @@
 #include <linux/uaccess.h>
 
 #include <asm/ldt.h>
+#include <asm/tlb.h>
 #include <asm/desc.h>
 #include <asm/mmu_context.h>
 #include <asm/syscalls.h>
@@ -42,17 +48,15 @@ static void refresh_ldt_segments(void)
 #endif
 }
 
-/* context.lock is held for us, so we don't need any locking. */
+/* context.lock is held by the task which issued the smp function call */
 static void flush_ldt(void *__mm)
 {
 	struct mm_struct *mm = __mm;
-	mm_context_t *pc;
 
 	if (this_cpu_read(cpu_tlbstate.loaded_mm) != mm)
 		return;
 
-	pc = &mm->context;
-	set_ldt(pc->ldt->entries, pc->ldt->nr_entries);
+	load_mm_ldt(mm);
 
 	refresh_ldt_segments();
 }
@@ -89,25 +93,143 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
 		return NULL;
 	}
 
+	/* The new LDT isn't aliased for PTI yet. */
+	new_ldt->slot = -1;
+
 	new_ldt->nr_entries = num_entries;
 	return new_ldt;
 }
 
+/*
+ * If PTI is enabled, this maps the LDT into the kernelmode and
+ * usermode tables for the given mm.
+ *
+ * There is no corresponding unmap function.  Even if the LDT is freed, we
+ * leave the PTEs around until the slot is reused or the mm is destroyed.
+ * This is harmless: the LDT is always in ordinary memory, and no one will
+ * access the freed slot.
+ *
+ * If we wanted to unmap freed LDTs, we'd also need to do a flush to make
+ * it useful, and the flush would slow down modify_ldt().
+ */
+static int
+map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	bool is_vmalloc, had_top_level_entry;
+	unsigned long va;
+	spinlock_t *ptl;
+	pgd_t *pgd;
+	int i;
+
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return 0;
+
+	/*
+	 * Any given ldt_struct should have map_ldt_struct() called at most
+	 * once.
+	 */
+	WARN_ON(ldt->slot != -1);
+
+	/*
+	 * Did we already have the top level entry allocated?  We can't
+	 * use pgd_none() for this because it doens't do anything on
+	 * 4-level page table kernels.
+	 */
+	pgd = pgd_offset(mm, LDT_BASE_ADDR);
+	had_top_level_entry = (pgd->pgd != 0);
+
+	is_vmalloc = is_vmalloc_addr(ldt->entries);
+
+	for (i = 0; i * PAGE_SIZE < ldt->nr_entries * LDT_ENTRY_SIZE; i++) {
+		unsigned long offset = i << PAGE_SHIFT;
+		const void *src = (char *)ldt->entries + offset;
+		unsigned long pfn;
+		pte_t pte, *ptep;
+
+		va = (unsigned long)ldt_slot_va(slot) + offset;
+		pfn = is_vmalloc ? vmalloc_to_pfn(src) :
+			page_to_pfn(virt_to_page(src));
+		/*
+		 * Treat the PTI LDT range as a *userspace* range.
+		 * get_locked_pte() will allocate all needed pagetables
+		 * and account for them in this mm.
+		 */
+		ptep = get_locked_pte(mm, va, &ptl);
+		if (!ptep)
+			return -ENOMEM;
+		/*
+		 * Map it RO so the easy to find address is not a primary
+		 * target via some kernel interface which misses a
+		 * permission check.
+		 */
+		pte = pfn_pte(pfn, __pgprot(__PAGE_KERNEL_RO & ~_PAGE_GLOBAL));
+		set_pte_at(mm, va, ptep, pte);
+		pte_unmap_unlock(ptep, ptl);
+	}
+
+	if (mm->context.ldt) {
+		/*
+		 * We already had an LDT.  The top-level entry should already
+		 * have been allocated and synchronized with the usermode
+		 * tables.
+		 */
+		WARN_ON(!had_top_level_entry);
+		if (static_cpu_has(X86_FEATURE_PTI))
+			WARN_ON(!kernel_to_user_pgdp(pgd)->pgd);
+	} else {
+		/*
+		 * This is the first time we're mapping an LDT for this process.
+		 * Sync the pgd to the usermode tables.
+		 */
+		WARN_ON(had_top_level_entry);
+		if (static_cpu_has(X86_FEATURE_PTI)) {
+			WARN_ON(kernel_to_user_pgdp(pgd)->pgd);
+			set_pgd(kernel_to_user_pgdp(pgd), *pgd);
+		}
+	}
+
+	va = (unsigned long)ldt_slot_va(slot);
+	flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, 0);
+
+	ldt->slot = slot;
+#endif
+	return 0;
+}
+
+static void free_ldt_pgtables(struct mm_struct *mm)
+{
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	struct mmu_gather tlb;
+	unsigned long start = LDT_BASE_ADDR;
+	unsigned long end = start + (1UL << PGDIR_SHIFT);
+
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
+
+	tlb_gather_mmu(&tlb, mm, start, end);
+	free_pgd_range(&tlb, start, end, start, end);
+	tlb_finish_mmu(&tlb, start, end);
+#endif
+}
+
 /* After calling this, the LDT is immutable. */
 static void finalize_ldt_struct(struct ldt_struct *ldt)
 {
 	paravirt_alloc_ldt(ldt->entries, ldt->nr_entries);
 }
 
-/* context.lock is held */
-static void install_ldt(struct mm_struct *current_mm,
-			struct ldt_struct *ldt)
+static void install_ldt(struct mm_struct *mm, struct ldt_struct *ldt)
 {
+	mutex_lock(&mm->context.lock);
+
 	/* Synchronizes with READ_ONCE in load_mm_ldt. */
-	smp_store_release(&current_mm->context.ldt, ldt);
+	smp_store_release(&mm->context.ldt, ldt);
 
-	/* Activate the LDT for all CPUs using current_mm. */
-	on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true);
+	/* Activate the LDT for all CPUs using currents mm. */
+	on_each_cpu_mask(mm_cpumask(mm), flush_ldt, mm, true);
+
+	mutex_unlock(&mm->context.lock);
 }
 
 static void free_ldt_struct(struct ldt_struct *ldt)
@@ -124,27 +246,20 @@ static void free_ldt_struct(struct ldt_struct *ldt)
 }
 
 /*
- * we do not have to muck with descriptors here, that is
- * done in switch_mm() as needed.
+ * Called on fork from arch_dup_mmap(). Just copy the current LDT state,
+ * the new task is not running, so nothing can be installed.
  */
-int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm)
+int ldt_dup_context(struct mm_struct *old_mm, struct mm_struct *mm)
 {
 	struct ldt_struct *new_ldt;
-	struct mm_struct *old_mm;
 	int retval = 0;
 
-	mutex_init(&mm->context.lock);
-	old_mm = current->mm;
-	if (!old_mm) {
-		mm->context.ldt = NULL;
+	if (!old_mm)
 		return 0;
-	}
 
 	mutex_lock(&old_mm->context.lock);
-	if (!old_mm->context.ldt) {
-		mm->context.ldt = NULL;
+	if (!old_mm->context.ldt)
 		goto out_unlock;
-	}
 
 	new_ldt = alloc_ldt_struct(old_mm->context.ldt->nr_entries);
 	if (!new_ldt) {
@@ -156,6 +271,12 @@ int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm)
 	       new_ldt->nr_entries * LDT_ENTRY_SIZE);
 	finalize_ldt_struct(new_ldt);
 
+	retval = map_ldt_struct(mm, new_ldt, 0);
+	if (retval) {
+		free_ldt_pgtables(mm);
+		free_ldt_struct(new_ldt);
+		goto out_unlock;
+	}
 	mm->context.ldt = new_ldt;
 
 out_unlock:
@@ -174,13 +295,18 @@ void destroy_context_ldt(struct mm_struct *mm)
 	mm->context.ldt = NULL;
 }
 
+void ldt_arch_exit_mmap(struct mm_struct *mm)
+{
+	free_ldt_pgtables(mm);
+}
+
 static int read_ldt(void __user *ptr, unsigned long bytecount)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long entries_size;
 	int retval;
 
-	mutex_lock(&mm->context.lock);
+	down_read(&mm->context.ldt_usr_sem);
 
 	if (!mm->context.ldt) {
 		retval = 0;
@@ -209,7 +335,7 @@ static int read_ldt(void __user *ptr, unsigned long bytecount)
 	retval = bytecount;
 
 out_unlock:
-	mutex_unlock(&mm->context.lock);
+	up_read(&mm->context.ldt_usr_sem);
 	return retval;
 }
 
@@ -269,7 +395,8 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 			ldt.avl = 0;
 	}
 
-	mutex_lock(&mm->context.lock);
+	if (down_write_killable(&mm->context.ldt_usr_sem))
+		return -EINTR;
 
 	old_ldt       = mm->context.ldt;
 	old_nr_entries = old_ldt ? old_ldt->nr_entries : 0;
@@ -286,12 +413,31 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 	new_ldt->entries[ldt_info.entry_number] = ldt;
 	finalize_ldt_struct(new_ldt);
 
+	/*
+	 * If we are using PTI, map the new LDT into the userspace pagetables.
+	 * If there is already an LDT, use the other slot so that other CPUs
+	 * will continue to use the old LDT until install_ldt() switches
+	 * them over to the new LDT.
+	 */
+	error = map_ldt_struct(mm, new_ldt, old_ldt ? !old_ldt->slot : 0);
+	if (error) {
+		/*
+		 * This only can fail for the first LDT setup. If an LDT is
+		 * already installed then the PTE page is already
+		 * populated. Mop up a half populated page table.
+		 */
+		if (!WARN_ON_ONCE(old_ldt))
+			free_ldt_pgtables(mm);
+		free_ldt_struct(new_ldt);
+		goto out_unlock;
+	}
+
 	install_ldt(mm, new_ldt);
 	free_ldt_struct(old_ldt);
 	error = 0;
 
 out_unlock:
-	mutex_unlock(&mm->context.lock);
+	up_write(&mm->context.ldt_usr_sem);
 out:
 	return error;
 }