Resguardo inicial

linux-7.2.3/arch/powerpc/include/asm/8xx_immap.h

@@ -0,0 +1,566 @@
+/*
+ * MPC8xx Internal Memory Map
+ * Copyright (c) 1997 Dan Malek (dmalek@jlc.net)
+ *
+ * The I/O on the MPC860 is comprised of blocks of special registers
+ * and the dual port ram for the Communication Processor Module.
+ * Within this space are functional units such as the SIU, memory
+ * controller, system timers, and other control functions.  It is
+ * a combination that I found difficult to separate into logical
+ * functional files.....but anyone else is welcome to try.  -- Dan
+ */
+#ifdef __KERNEL__
+#ifndef __IMMAP_8XX__
+#define __IMMAP_8XX__
+
+/* System configuration registers.
+*/
+typedef	struct sys_conf {
+	uint	sc_siumcr;
+	uint	sc_sypcr;
+	uint	sc_swt;
+	char	res1[2];
+	ushort	sc_swsr;
+	uint	sc_sipend;
+	uint	sc_simask;
+	uint	sc_siel;
+	uint	sc_sivec;
+	uint	sc_tesr;
+	char	res2[0xc];
+	uint	sc_sdcr;
+	char	res3[0x4c];
+} sysconf8xx_t;
+
+/* PCMCIA configuration registers.
+*/
+typedef struct pcmcia_conf {
+	uint	pcmc_pbr0;
+	uint	pcmc_por0;
+	uint	pcmc_pbr1;
+	uint	pcmc_por1;
+	uint	pcmc_pbr2;
+	uint	pcmc_por2;
+	uint	pcmc_pbr3;
+	uint	pcmc_por3;
+	uint	pcmc_pbr4;
+	uint	pcmc_por4;
+	uint	pcmc_pbr5;
+	uint	pcmc_por5;
+	uint	pcmc_pbr6;
+	uint	pcmc_por6;
+	uint	pcmc_pbr7;
+	uint	pcmc_por7;
+	char	res1[0x20];
+	uint	pcmc_pgcra;
+	uint	pcmc_pgcrb;
+	uint	pcmc_pscr;
+	char	res2[4];
+	uint	pcmc_pipr;
+	char	res3[4];
+	uint	pcmc_per;
+	char	res4[4];
+} pcmconf8xx_t;
+
+/* Memory controller registers.
+*/
+typedef struct	mem_ctlr {
+	uint	memc_br0;
+	uint	memc_or0;
+	uint	memc_br1;
+	uint	memc_or1;
+	uint	memc_br2;
+	uint	memc_or2;
+	uint	memc_br3;
+	uint	memc_or3;
+	uint	memc_br4;
+	uint	memc_or4;
+	uint	memc_br5;
+	uint	memc_or5;
+	uint	memc_br6;
+	uint	memc_or6;
+	uint	memc_br7;
+	uint	memc_or7;
+	char	res1[0x24];
+	uint	memc_mar;
+	uint	memc_mcr;
+	char	res2[4];
+	uint	memc_mamr;
+	uint	memc_mbmr;
+	ushort	memc_mstat;
+	ushort	memc_mptpr;
+	uint	memc_mdr;
+	char	res3[0x80];
+} memctl8xx_t;
+
+/*-----------------------------------------------------------------------
+ * BR - Memory Controller: Base Register					16-9
+ */
+#define BR_BA_MSK	0xffff8000	/* Base Address Mask			*/
+#define BR_AT_MSK	0x00007000	/* Address Type Mask			*/
+#define BR_PS_MSK	0x00000c00	/* Port Size Mask			*/
+#define BR_PS_32	0x00000000	/* 32 bit port size			*/
+#define BR_PS_16	0x00000800	/* 16 bit port size			*/
+#define BR_PS_8		0x00000400	/*  8 bit port size			*/
+#define BR_PARE		0x00000200	/* Parity Enable			*/
+#define BR_WP		0x00000100	/* Write Protect			*/
+#define BR_MS_MSK	0x000000c0	/* Machine Select Mask			*/
+#define BR_MS_GPCM	0x00000000	/* G.P.C.M. Machine Select		*/
+#define BR_MS_UPMA	0x00000080	/* U.P.M.A Machine Select		*/
+#define BR_MS_UPMB	0x000000c0	/* U.P.M.B Machine Select		*/
+#define BR_V		0x00000001	/* Bank Valid				*/
+
+/*-----------------------------------------------------------------------
+ * OR - Memory Controller: Option Register				16-11
+ */
+#define OR_AM_MSK	0xffff8000	/* Address Mask Mask			*/
+#define OR_ATM_MSK	0x00007000	/* Address Type Mask Mask		*/
+#define OR_CSNT_SAM	0x00000800	/* Chip Select Negation Time/ Start	*/
+					/* Address Multiplex			*/
+#define OR_ACS_MSK	0x00000600	/* Address to Chip Select Setup mask	*/
+#define OR_ACS_DIV1	0x00000000	/* CS is output at the same time	*/
+#define OR_ACS_DIV4	0x00000400	/* CS is output 1/4 a clock later	*/
+#define OR_ACS_DIV2	0x00000600	/* CS is output 1/2 a clock later	*/
+#define OR_G5LA		0x00000400	/* Output #GPL5 on #GPL_A5		*/
+#define OR_G5LS		0x00000200	/* Drive #GPL high on falling edge of...*/
+#define OR_BI		0x00000100	/* Burst inhibit			*/
+#define OR_SCY_MSK	0x000000f0	/* Cycle Length in Clocks		*/
+#define OR_SCY_0_CLK	0x00000000	/* 0 clock cycles wait states		*/
+#define OR_SCY_1_CLK	0x00000010	/* 1 clock cycles wait states		*/
+#define OR_SCY_2_CLK	0x00000020	/* 2 clock cycles wait states		*/
+#define OR_SCY_3_CLK	0x00000030	/* 3 clock cycles wait states		*/
+#define OR_SCY_4_CLK	0x00000040	/* 4 clock cycles wait states		*/
+#define OR_SCY_5_CLK	0x00000050	/* 5 clock cycles wait states		*/
+#define OR_SCY_6_CLK	0x00000060	/* 6 clock cycles wait states		*/
+#define OR_SCY_7_CLK	0x00000070	/* 7 clock cycles wait states		*/
+#define OR_SCY_8_CLK	0x00000080	/* 8 clock cycles wait states		*/
+#define OR_SCY_9_CLK	0x00000090	/* 9 clock cycles wait states		*/
+#define OR_SCY_10_CLK	0x000000a0	/* 10 clock cycles wait states		*/
+#define OR_SCY_11_CLK	0x000000b0	/* 11 clock cycles wait states		*/
+#define OR_SCY_12_CLK	0x000000c0	/* 12 clock cycles wait states		*/
+#define OR_SCY_13_CLK	0x000000d0	/* 13 clock cycles wait states		*/
+#define OR_SCY_14_CLK	0x000000e0	/* 14 clock cycles wait states		*/
+#define OR_SCY_15_CLK	0x000000f0	/* 15 clock cycles wait states		*/
+#define OR_SETA		0x00000008	/* External Transfer Acknowledge	*/
+#define OR_TRLX		0x00000004	/* Timing Relaxed			*/
+#define OR_EHTR		0x00000002	/* Extended Hold Time on Read		*/
+
+/* System Integration Timers.
+*/
+typedef struct	sys_int_timers {
+	ushort	sit_tbscr;
+	char	res0[0x02];
+	uint	sit_tbreff0;
+	uint	sit_tbreff1;
+	char	res1[0x14];
+	ushort	sit_rtcsc;
+	char	res2[0x02];
+	uint	sit_rtc;
+	uint	sit_rtsec;
+	uint	sit_rtcal;
+	char	res3[0x10];
+	ushort	sit_piscr;
+	char	res4[2];
+	uint	sit_pitc;
+	uint	sit_pitr;
+	char	res5[0x34];
+} sit8xx_t;
+
+#define TBSCR_TBIRQ_MASK	((ushort)0xff00)
+#define TBSCR_REFA		((ushort)0x0080)
+#define TBSCR_REFB		((ushort)0x0040)
+#define TBSCR_REFAE		((ushort)0x0008)
+#define TBSCR_REFBE		((ushort)0x0004)
+#define TBSCR_TBF		((ushort)0x0002)
+#define TBSCR_TBE		((ushort)0x0001)
+
+#define RTCSC_RTCIRQ_MASK	((ushort)0xff00)
+#define RTCSC_SEC		((ushort)0x0080)
+#define RTCSC_ALR		((ushort)0x0040)
+#define RTCSC_38K		((ushort)0x0010)
+#define RTCSC_SIE		((ushort)0x0008)
+#define RTCSC_ALE		((ushort)0x0004)
+#define RTCSC_RTF		((ushort)0x0002)
+#define RTCSC_RTE		((ushort)0x0001)
+
+#define PISCR_PIRQ_MASK		((ushort)0xff00)
+#define PISCR_PS		((ushort)0x0080)
+#define PISCR_PIE		((ushort)0x0004)
+#define PISCR_PTF		((ushort)0x0002)
+#define PISCR_PTE		((ushort)0x0001)
+
+/* Clocks and Reset.
+*/
+typedef struct clk_and_reset {
+	uint	car_sccr;
+	uint	car_plprcr;
+	uint	car_rsr;
+	char	res[0x74];        /* Reserved area                  */
+} car8xx_t;
+
+/* System Integration Timers keys.
+*/
+typedef struct sitk {
+	uint	sitk_tbscrk;
+	uint	sitk_tbreff0k;
+	uint	sitk_tbreff1k;
+	uint	sitk_tbk;
+	char	res1[0x10];
+	uint	sitk_rtcsck;
+	uint	sitk_rtck;
+	uint	sitk_rtseck;
+	uint	sitk_rtcalk;
+	char	res2[0x10];
+	uint	sitk_piscrk;
+	uint	sitk_pitck;
+	char	res3[0x38];
+} sitk8xx_t;
+
+/* Clocks and reset keys.
+*/
+typedef struct cark {
+	uint	cark_sccrk;
+	uint	cark_plprcrk;
+	uint	cark_rsrk;
+	char	res[0x474];
+} cark8xx_t;
+
+/* The key to unlock registers maintained by keep-alive power.
+*/
+#define KAPWR_KEY	((unsigned int)0x55ccaa33)
+
+/* Video interface.  MPC823 Only.
+*/
+typedef struct vid823 {
+	ushort	vid_vccr;
+	ushort	res1;
+	u_char	vid_vsr;
+	u_char	res2;
+	u_char	vid_vcmr;
+	u_char	res3;
+	uint	vid_vbcb;
+	uint	res4;
+	uint	vid_vfcr0;
+	uint	vid_vfaa0;
+	uint	vid_vfba0;
+	uint	vid_vfcr1;
+	uint	vid_vfaa1;
+	uint	vid_vfba1;
+	u_char	res5[0x18];
+} vid823_t;
+
+/* LCD interface.  823 Only.
+*/
+typedef struct lcd {
+	uint	lcd_lccr;
+	uint	lcd_lchcr;
+	uint	lcd_lcvcr;
+	char	res1[4];
+	uint	lcd_lcfaa;
+	uint	lcd_lcfba;
+	char	lcd_lcsr;
+	char	res2[0x7];
+} lcd823_t;
+
+/* I2C
+*/
+typedef struct i2c {
+	u_char	i2c_i2mod;
+	char	res1[3];
+	u_char	i2c_i2add;
+	char	res2[3];
+	u_char	i2c_i2brg;
+	char	res3[3];
+	u_char	i2c_i2com;
+	char	res4[3];
+	u_char	i2c_i2cer;
+	char	res5[3];
+	u_char	i2c_i2cmr;
+	char	res6[0x8b];
+} i2c8xx_t;
+
+/* DMA control/status registers.
+*/
+typedef struct sdma_csr {
+	char	res1[4];
+	uint	sdma_sdar;
+	u_char	sdma_sdsr;
+	char	res3[3];
+	u_char	sdma_sdmr;
+	char	res4[3];
+	u_char	sdma_idsr1;
+	char	res5[3];
+	u_char	sdma_idmr1;
+	char	res6[3];
+	u_char	sdma_idsr2;
+	char	res7[3];
+	u_char	sdma_idmr2;
+	char	res8[0x13];
+} sdma8xx_t;
+
+/* Communication Processor Module Interrupt Controller.
+*/
+typedef struct cpm_ic {
+	ushort	cpic_civr;
+	char	res[0xe];
+	uint	cpic_cicr;
+	uint	cpic_cipr;
+	uint	cpic_cimr;
+	uint	cpic_cisr;
+} cpic8xx_t;
+
+/* Input/Output Port control/status registers.
+*/
+typedef struct io_port {
+	ushort	iop_padir;
+	ushort	iop_papar;
+	ushort	iop_paodr;
+	ushort	iop_padat;
+	char	res1[8];
+	ushort	iop_pcdir;
+	ushort	iop_pcpar;
+	ushort	iop_pcso;
+	ushort	iop_pcdat;
+	ushort	iop_pcint;
+	char	res2[6];
+	ushort	iop_pddir;
+	ushort	iop_pdpar;
+	char	res3[2];
+	ushort	iop_pddat;
+	uint	utmode;
+	char	res4[4];
+} iop8xx_t;
+
+/* Communication Processor Module Timers
+*/
+typedef struct cpm_timers {
+	ushort	cpmt_tgcr;
+	char	res1[0xe];
+	ushort	cpmt_tmr1;
+	ushort	cpmt_tmr2;
+	ushort	cpmt_trr1;
+	ushort	cpmt_trr2;
+	ushort	cpmt_tcr1;
+	ushort	cpmt_tcr2;
+	ushort	cpmt_tcn1;
+	ushort	cpmt_tcn2;
+	ushort	cpmt_tmr3;
+	ushort	cpmt_tmr4;
+	ushort	cpmt_trr3;
+	ushort	cpmt_trr4;
+	ushort	cpmt_tcr3;
+	ushort	cpmt_tcr4;
+	ushort	cpmt_tcn3;
+	ushort	cpmt_tcn4;
+	ushort	cpmt_ter1;
+	ushort	cpmt_ter2;
+	ushort	cpmt_ter3;
+	ushort	cpmt_ter4;
+	char	res2[8];
+} cpmtimer8xx_t;
+
+/* Finally, the Communication Processor stuff.....
+*/
+typedef struct scc {		/* Serial communication channels */
+	uint	scc_gsmrl;
+	uint	scc_gsmrh;
+	ushort	scc_psmr;
+	char	res1[2];
+	ushort	scc_todr;
+	ushort	scc_dsr;
+	ushort	scc_scce;
+	char	res2[2];
+	ushort	scc_sccm;
+	char	res3;
+	u_char	scc_sccs;
+	char	res4[8];
+} scc_t;
+
+typedef struct smc {		/* Serial management channels */
+	char	res1[2];
+	ushort	smc_smcmr;
+	char	res2[2];
+	u_char	smc_smce;
+	char	res3[3];
+	u_char	smc_smcm;
+	char	res4[5];
+} smc_t;
+
+/* MPC860T Fast Ethernet Controller.  It isn't part of the CPM, but
+ * it fits within the address space.
+ */
+
+typedef struct fec {
+	uint	fec_addr_low;		/* lower 32 bits of station address	*/
+	ushort	fec_addr_high;		/* upper 16 bits of station address	*/
+	ushort	res1;			/* reserved				*/
+	uint	fec_grp_hash_table_high;	/* upper 32-bits of hash table		*/
+	uint	fec_grp_hash_table_low;	/* lower 32-bits of hash table		*/
+	uint	fec_r_des_start;	/* beginning of Rx descriptor ring	*/
+	uint	fec_x_des_start;	/* beginning of Tx descriptor ring	*/
+	uint	fec_r_buff_size;	/* Rx buffer size			*/
+	uint	res2[9];		/* reserved				*/
+	uint	fec_ecntrl;		/* ethernet control register		*/
+	uint	fec_ievent;		/* interrupt event register		*/
+	uint	fec_imask;		/* interrupt mask register		*/
+	uint	fec_ivec;		/* interrupt level and vector status	*/
+	uint	fec_r_des_active;	/* Rx ring updated flag			*/
+	uint	fec_x_des_active;	/* Tx ring updated flag			*/
+	uint	res3[10];		/* reserved				*/
+	uint	fec_mii_data;		/* MII data register			*/
+	uint	fec_mii_speed;		/* MII speed control register		*/
+	uint	res4[17];		/* reserved				*/
+	uint	fec_r_bound;		/* end of RAM (read-only)		*/
+	uint	fec_r_fstart;		/* Rx FIFO start address		*/
+	uint	res5[6];		/* reserved				*/
+	uint	fec_x_fstart;		/* Tx FIFO start address		*/
+	uint	res6[17];		/* reserved				*/
+	uint	fec_fun_code;		/* fec SDMA function code		*/
+	uint	res7[3];		/* reserved				*/
+	uint	fec_r_cntrl;		/* Rx control register			*/
+	uint	fec_r_hash;		/* Rx hash register			*/
+	uint	res8[14];		/* reserved				*/
+	uint	fec_x_cntrl;		/* Tx control register			*/
+	uint	res9[0x1e];		/* reserved				*/
+} fec_t;
+
+/* The FEC and LCD color map share the same address space....
+ * I guess we will never see an 823T :-).
+ */
+union fec_lcd {
+	fec_t	fl_un_fec;
+	u_char	fl_un_cmap[0x200];
+};
+
+typedef struct comm_proc {
+	/* General control and status registers.
+	*/
+	ushort	cp_cpcr;
+	u_char	res1[2];
+	ushort	cp_rccr;
+	u_char	res2;
+	u_char	cp_rmds;
+	u_char	res3[4];
+	ushort	cp_cpmcr1;
+	ushort	cp_cpmcr2;
+	ushort	cp_cpmcr3;
+	ushort	cp_cpmcr4;
+	u_char	res4[2];
+	ushort	cp_rter;
+	u_char	res5[2];
+	ushort	cp_rtmr;
+	u_char	res6[0x14];
+
+	/* Baud rate generators.
+	*/
+	uint	cp_brgc1;
+	uint	cp_brgc2;
+	uint	cp_brgc3;
+	uint	cp_brgc4;
+
+	/* Serial Communication Channels.
+	*/
+	scc_t	cp_scc[4];
+
+	/* Serial Management Channels.
+	*/
+	smc_t	cp_smc[2];
+
+	/* Serial Peripheral Interface.
+	*/
+	ushort	cp_spmode;
+	u_char	res7[4];
+	u_char	cp_spie;
+	u_char	res8[3];
+	u_char	cp_spim;
+	u_char	res9[2];
+	u_char	cp_spcom;
+	u_char	res10[2];
+
+	/* Parallel Interface Port.
+	*/
+	u_char	res11[2];
+	ushort	cp_pipc;
+	u_char	res12[2];
+	ushort	cp_ptpr;
+	uint	cp_pbdir;
+	uint	cp_pbpar;
+	u_char	res13[2];
+	ushort	cp_pbodr;
+	uint	cp_pbdat;
+
+	/* Port E - MPC87x/88x only.
+	 */
+	uint	cp_pedir;
+	uint	cp_pepar;
+	uint	cp_peso;
+	uint	cp_peodr;
+	uint	cp_pedat;
+
+	/* Communications Processor Timing Register -
+	   Contains RMII Timing for the FECs on MPC87x/88x only.
+	*/
+	uint	cp_cptr;
+
+	/* Serial Interface and Time Slot Assignment.
+	*/
+	uint	cp_simode;
+	u_char	cp_sigmr;
+	u_char	res15;
+	u_char	cp_sistr;
+	u_char	cp_sicmr;
+	u_char	res16[4];
+	uint	cp_sicr;
+	uint	cp_sirp;
+	u_char	res17[0xc];
+
+	/* 256 bytes of MPC823 video controller RAM array.
+	*/
+	u_char	cp_vcram[0x100];
+	u_char	cp_siram[0x200];
+
+	/* The fast ethernet controller is not really part of the CPM,
+	 * but it resides in the address space.
+	 * The LCD color map is also here.
+	 */
+	union	fec_lcd	fl_un;
+#define cp_fec		fl_un.fl_un_fec
+#define lcd_cmap	fl_un.fl_un_cmap
+	char	res18[0xE00];
+
+	/* The DUET family has a second FEC here */
+	fec_t	cp_fec2;
+#define cp_fec1	cp_fec	/* consistency macro */
+
+	/* Dual Ported RAM follows.
+	 * There are many different formats for this memory area
+	 * depending upon the devices used and options chosen.
+	 * Some processors don't have all of it populated.
+	 */
+	u_char	cp_dpmem[0x1C00];	/* BD / Data / ucode */
+	u_char	cp_dparam[0x400];	/* Parameter RAM */
+} cpm8xx_t;
+
+/* Internal memory map.
+*/
+typedef struct immap {
+	sysconf8xx_t	im_siu_conf;	/* SIU Configuration */
+	pcmconf8xx_t	im_pcmcia;	/* PCMCIA Configuration */
+	memctl8xx_t	im_memctl;	/* Memory Controller */
+	sit8xx_t	im_sit;		/* System integration timers */
+	car8xx_t	im_clkrst;	/* Clocks and reset */
+	sitk8xx_t	im_sitk;	/* Sys int timer keys */
+	cark8xx_t	im_clkrstk;	/* Clocks and reset keys */
+	vid823_t	im_vid;		/* Video (823 only) */
+	lcd823_t	im_lcd;		/* LCD (823 only) */
+	i2c8xx_t	im_i2c;		/* I2C control/status */
+	sdma8xx_t	im_sdma;	/* SDMA control/status */
+	cpic8xx_t	im_cpic;	/* CPM Interrupt Controller */
+	iop8xx_t	im_ioport;	/* IO Port control/status */
+	cpmtimer8xx_t	im_cpmtimer;	/* CPM timers */
+	cpm8xx_t	im_cpm;		/* Communication processor */
+} immap_t;
+
+extern immap_t __iomem *mpc8xx_immr;
+
+#endif /* __IMMAP_8XX__ */
+#endif /* __KERNEL__ */

linux-7.2.3/arch/powerpc/include/asm/Kbuild

@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+generated-y += syscall_table_32.h
+generated-y += syscall_table_64.h
+generated-y += syscall_table_spu.h
+generic-y += agp.h
+generic-y += mcs_spinlock.h
+generic-y += qrwlock.h
+generic-y += ring_buffer.h
+generic-y += early_ioremap.h

linux-7.2.3/arch/powerpc/include/asm/accounting.h

@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Common time accounting prototypes and such for all ppc machines.
+ */
+
+#ifndef __POWERPC_ACCOUNTING_H
+#define __POWERPC_ACCOUNTING_H
+
+/* Stuff for accurate time accounting */
+struct cpu_accounting_data {
+	/* Accumulated cputime values to flush on ticks*/
+	unsigned long utime;
+	unsigned long stime;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
+	unsigned long utime_scaled;
+	unsigned long stime_scaled;
+#endif
+	unsigned long gtime;
+	unsigned long hardirq_time;
+	unsigned long softirq_time;
+	unsigned long steal_time;
+	unsigned long idle_time;
+	/* Internal counters */
+	unsigned long starttime;	/* TB value snapshot */
+	unsigned long starttime_user;	/* TB value on exit to usermode */
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
+	unsigned long startspurr;	/* SPURR value snapshot */
+	unsigned long utime_sspurr;	/* ->user_time when ->startspurr set */
+#endif
+};
+
+#endif

linux-7.2.3/arch/powerpc/include/asm/archrandom.h

@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_ARCHRANDOM_H
+#define _ASM_POWERPC_ARCHRANDOM_H
+
+static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs)
+{
+	return 0;
+}
+
+size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs);
+
+#ifdef CONFIG_PPC_POWERNV
+int pnv_get_random_long(unsigned long *v);
+#endif
+
+#endif /* _ASM_POWERPC_ARCHRANDOM_H */

linux-7.2.3/arch/powerpc/include/asm/asm-compat.h

@@ -0,0 +1,68 @@
+#ifndef _ASM_POWERPC_ASM_COMPAT_H
+#define _ASM_POWERPC_ASM_COMPAT_H
+
+#include <asm/asm-const.h>
+#include <asm/types.h>
+#include <asm/ppc-opcode.h>
+
+#ifdef __powerpc64__
+
+/* operations for longs and pointers */
+#define PPC_LL		stringify_in_c(ld)
+#define PPC_STL		stringify_in_c(std)
+#define PPC_STLU	stringify_in_c(stdu)
+#define PPC_LCMPI	stringify_in_c(cmpdi)
+#define PPC_LCMPLI	stringify_in_c(cmpldi)
+#define PPC_LCMP	stringify_in_c(cmpd)
+#define PPC_LONG	stringify_in_c(.8byte)
+#define PPC_LONG_ALIGN	stringify_in_c(.balign 8)
+#define PPC_TLNEI	stringify_in_c(tdnei)
+#define PPC_LLARX	stringify_in_c(ldarx)
+#define PPC_STLCX	stringify_in_c(stdcx.)
+#define PPC_CNTLZL	stringify_in_c(cntlzd)
+#define PPC_MTOCRF(FXM, RS) MTOCRF((FXM), RS)
+#define PPC_SRL		stringify_in_c(srd)
+#define PPC_LR_STKOFF	16
+#define PPC_MIN_STKFRM	112
+
+#ifdef __BIG_ENDIAN__
+#define LWZX_BE	stringify_in_c(lwzx)
+#define LDX_BE	stringify_in_c(ldx)
+#define STWX_BE	stringify_in_c(stwx)
+#define STDX_BE	stringify_in_c(stdx)
+#else
+#define LWZX_BE	stringify_in_c(lwbrx)
+#define LDX_BE	stringify_in_c(ldbrx)
+#define STWX_BE	stringify_in_c(stwbrx)
+#define STDX_BE	stringify_in_c(stdbrx)
+#endif
+
+#ifdef CONFIG_CC_IS_CLANG
+#define DS_FORM_CONSTRAINT "Z<>"
+#else
+#define DS_FORM_CONSTRAINT "YZ<>"
+#endif
+
+#else /* 32-bit */
+
+/* operations for longs and pointers */
+#define PPC_LL		stringify_in_c(lwz)
+#define PPC_STL		stringify_in_c(stw)
+#define PPC_STLU	stringify_in_c(stwu)
+#define PPC_LCMPI	stringify_in_c(cmpwi)
+#define PPC_LCMPLI	stringify_in_c(cmplwi)
+#define PPC_LCMP	stringify_in_c(cmpw)
+#define PPC_LONG	stringify_in_c(.long)
+#define PPC_LONG_ALIGN	stringify_in_c(.balign 4)
+#define PPC_TLNEI	stringify_in_c(twnei)
+#define PPC_LLARX	stringify_in_c(lwarx)
+#define PPC_STLCX	stringify_in_c(stwcx.)
+#define PPC_CNTLZL	stringify_in_c(cntlzw)
+#define PPC_MTOCRF	stringify_in_c(mtcrf)
+#define PPC_SRL		stringify_in_c(srw)
+#define PPC_LR_STKOFF	4
+#define PPC_MIN_STKFRM	16
+
+#endif
+
+#endif /* _ASM_POWERPC_ASM_COMPAT_H */

linux-7.2.3/arch/powerpc/include/asm/asm-const.h

@@ -0,0 +1,15 @@
+#ifndef _ASM_POWERPC_ASM_CONST_H
+#define _ASM_POWERPC_ASM_CONST_H
+
+#ifdef __ASSEMBLER__
+#  define stringify_in_c(...)	__VA_ARGS__
+#  define ASM_CONST(x)		x
+#else
+/* This version of stringify will deal with commas... */
+#  define __stringify_in_c(...)	#__VA_ARGS__
+#  define stringify_in_c(...)	__stringify_in_c(__VA_ARGS__) " "
+#  define __ASM_CONST(x)	x##UL
+#  define ASM_CONST(x)		__ASM_CONST(x)
+#endif
+
+#endif /* _ASM_POWERPC_ASM_CONST_H */

linux-7.2.3/arch/powerpc/include/asm/asm-offsets.h

@@ -0,0 +1 @@
+#include <generated/asm-offsets.h>

linux-7.2.3/arch/powerpc/include/asm/asm-prototypes.h

@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ASM_POWERPC_ASM_PROTOTYPES_H
+#define _ASM_POWERPC_ASM_PROTOTYPES_H
+/*
+ * This file is for C prototypes of asm symbols that are EXPORTed.
+ * It allows the modversions logic to see their prototype and
+ * generate proper CRCs for them.
+ *
+ * Copyright 2016, Daniel Axtens, IBM Corporation.
+ */
+
+#include <linux/threads.h>
+#include <asm/cacheflush.h>
+#include <asm/checksum.h>
+#include <linux/uaccess.h>
+#include <asm/epapr_hcalls.h>
+#include <asm/dcr.h>
+#include <asm/mmu_context.h>
+#include <asm/ultravisor-api.h>
+
+#include <uapi/asm/ucontext.h>
+
+/* Ultravisor */
+#if defined(CONFIG_PPC_POWERNV) || defined(CONFIG_PPC_SVM)
+long ucall_norets(unsigned long opcode, ...);
+#else
+static inline long ucall_norets(unsigned long opcode, ...)
+{
+	return U_NOT_AVAILABLE;
+}
+#endif
+
+/* OPAL */
+int64_t __opal_call(int64_t a0, int64_t a1, int64_t a2, int64_t a3,
+		    int64_t a4, int64_t a5, int64_t a6, int64_t a7,
+		    int64_t opcode, uint64_t msr);
+
+/* misc runtime */
+void enable_machine_check(void);
+extern u64 __bswapdi2(u64);
+extern s64 __lshrdi3(s64, int);
+extern s64 __ashldi3(s64, int);
+extern s64 __ashrdi3(s64, int);
+extern int __cmpdi2(s64, s64);
+extern int __ucmpdi2(u64, u64);
+
+/* tracing */
+void _mcount(void);
+
+/* Transaction memory related */
+void tm_enable(void);
+void tm_disable(void);
+void tm_abort(uint8_t cause);
+
+struct kvm_vcpu;
+void _kvmppc_restore_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr);
+void _kvmppc_save_tm_pr(struct kvm_vcpu *vcpu, u64 guest_msr);
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+void kvmppc_save_tm_hv(struct kvm_vcpu *vcpu, u64 msr, bool preserve_nv);
+void kvmppc_restore_tm_hv(struct kvm_vcpu *vcpu, u64 msr, bool preserve_nv);
+#else
+static inline void kvmppc_save_tm_hv(struct kvm_vcpu *vcpu, u64 msr,
+				     bool preserve_nv) { }
+static inline void kvmppc_restore_tm_hv(struct kvm_vcpu *vcpu, u64 msr,
+					bool preserve_nv) { }
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+
+void kvmppc_p9_enter_guest(struct kvm_vcpu *vcpu);
+
+long kvmppc_h_set_dabr(struct kvm_vcpu *vcpu, unsigned long dabr);
+long kvmppc_h_set_xdabr(struct kvm_vcpu *vcpu, unsigned long dabr,
+			unsigned long dabrx);
+
+#endif /* _ASM_POWERPC_ASM_PROTOTYPES_H */

linux-7.2.3/arch/powerpc/include/asm/asm.h

@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_ASM_H
+#define _ASM_POWERPC_ASM_H
+
+#define _ASM_PTR	" .long "
+
+#endif /* _ASM_POWERPC_ASM_H */

linux-7.2.3/arch/powerpc/include/asm/async_tx.h

@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2008-2009 DENX Software Engineering.
+ *
+ * Author: Yuri Tikhonov <yur@emcraft.com>
+ */
+#ifndef _ASM_POWERPC_ASYNC_TX_H_
+#define _ASM_POWERPC_ASYNC_TX_H_
+
+#if defined(CONFIG_440SPe) || defined(CONFIG_440SP)
+extern struct dma_chan *
+ppc440spe_async_tx_find_best_channel(enum dma_transaction_type cap,
+	struct page **dst_lst, int dst_cnt, struct page **src_lst,
+	int src_cnt, size_t src_sz);
+
+#define async_tx_find_channel(dep, cap, dst_lst, dst_cnt, src_lst, \
+			      src_cnt, src_sz) \
+	ppc440spe_async_tx_find_best_channel(cap, dst_lst, dst_cnt, src_lst, \
+					     src_cnt, src_sz)
+#else
+
+#define async_tx_find_channel(dep, type, dst, dst_count, src, src_count, len) \
+	__async_tx_find_channel(dep, type)
+
+struct dma_chan *
+__async_tx_find_channel(struct async_submit_ctl *submit,
+			enum dma_transaction_type tx_type);
+
+#endif
+
+#endif

linux-7.2.3/arch/powerpc/include/asm/atomic.h

@@ -0,0 +1,453 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_ATOMIC_H_
+#define _ASM_POWERPC_ATOMIC_H_
+
+/*
+ * PowerPC atomic operations
+ */
+
+#ifdef __KERNEL__
+#include <linux/types.h>
+#include <asm/cmpxchg.h>
+#include <asm/barrier.h>
+#include <asm/asm-const.h>
+#include <asm/asm-compat.h>
+
+/*
+ * Since *_return_relaxed and {cmp}xchg_relaxed are implemented with
+ * a "bne-" instruction at the end, so an isync is enough as a acquire barrier
+ * on the platform without lwsync.
+ */
+#define __atomic_acquire_fence()					\
+	__asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory")
+
+#define __atomic_release_fence()					\
+	__asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory")
+
+static __inline__ int arch_atomic_read(const atomic_t *v)
+{
+	int t;
+
+	/* -mprefixed can generate offsets beyond range, fall back hack */
+	if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED))
+		__asm__ __volatile__("lwz %0,0(%1)" : "=r"(t) : "b"(&v->counter));
+	else
+		__asm__ __volatile__("lwz%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter));
+
+	return t;
+}
+
+static __inline__ void arch_atomic_set(atomic_t *v, int i)
+{
+	/* -mprefixed can generate offsets beyond range, fall back hack */
+	if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED))
+		__asm__ __volatile__("stw %1,0(%2)" : "=m"(v->counter) : "r"(i), "b"(&v->counter));
+	else
+		__asm__ __volatile__("stw%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i));
+}
+
+#define ATOMIC_OP(op, asm_op, suffix, sign, ...)			\
+static __inline__ void arch_atomic_##op(int a, atomic_t *v)		\
+{									\
+	int t;								\
+									\
+	__asm__ __volatile__(						\
+"1:	lwarx	%0,0,%3		# atomic_" #op "\n"			\
+	#asm_op "%I2" suffix " %0,%0,%2\n"				\
+"	stwcx.	%0,0,%3 \n"						\
+"	bne-	1b\n"							\
+	: "=&r" (t), "+m" (v->counter)					\
+	: "r"#sign (a), "r" (&v->counter)				\
+	: "cc", ##__VA_ARGS__);						\
+}									\
+
+#define ATOMIC_OP_RETURN_RELAXED(op, asm_op, suffix, sign, ...)		\
+static inline int arch_atomic_##op##_return_relaxed(int a, atomic_t *v)	\
+{									\
+	int t;								\
+									\
+	__asm__ __volatile__(						\
+"1:	lwarx	%0,0,%3		# atomic_" #op "_return_relaxed\n"	\
+	#asm_op "%I2" suffix " %0,%0,%2\n"				\
+"	stwcx.	%0,0,%3\n"						\
+"	bne-	1b\n"							\
+	: "=&r" (t), "+m" (v->counter)					\
+	: "r"#sign (a), "r" (&v->counter)				\
+	: "cc", ##__VA_ARGS__);						\
+									\
+	return t;							\
+}
+
+#define ATOMIC_FETCH_OP_RELAXED(op, asm_op, suffix, sign, ...)		\
+static inline int arch_atomic_fetch_##op##_relaxed(int a, atomic_t *v)	\
+{									\
+	int res, t;							\
+									\
+	__asm__ __volatile__(						\
+"1:	lwarx	%0,0,%4		# atomic_fetch_" #op "_relaxed\n"	\
+	#asm_op "%I3" suffix " %1,%0,%3\n"				\
+"	stwcx.	%1,0,%4\n"						\
+"	bne-	1b\n"							\
+	: "=&r" (res), "=&r" (t), "+m" (v->counter)			\
+	: "r"#sign (a), "r" (&v->counter)				\
+	: "cc", ##__VA_ARGS__);						\
+									\
+	return res;							\
+}
+
+#define ATOMIC_OPS(op, asm_op, suffix, sign, ...)			\
+	ATOMIC_OP(op, asm_op, suffix, sign, ##__VA_ARGS__)		\
+	ATOMIC_OP_RETURN_RELAXED(op, asm_op, suffix, sign, ##__VA_ARGS__)\
+	ATOMIC_FETCH_OP_RELAXED(op, asm_op, suffix, sign, ##__VA_ARGS__)
+
+ATOMIC_OPS(add, add, "c", I, "xer")
+ATOMIC_OPS(sub, sub, "c", I, "xer")
+
+#define arch_atomic_add_return_relaxed arch_atomic_add_return_relaxed
+#define arch_atomic_sub_return_relaxed arch_atomic_sub_return_relaxed
+
+#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add_relaxed
+#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub_relaxed
+
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, asm_op, suffix, sign)				\
+	ATOMIC_OP(op, asm_op, suffix, sign)				\
+	ATOMIC_FETCH_OP_RELAXED(op, asm_op, suffix, sign)
+
+ATOMIC_OPS(and, and, ".", K)
+ATOMIC_OPS(or, or, "", K)
+ATOMIC_OPS(xor, xor, "", K)
+
+#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and_relaxed
+#define arch_atomic_fetch_or_relaxed  arch_atomic_fetch_or_relaxed
+#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor_relaxed
+
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP_RELAXED
+#undef ATOMIC_OP_RETURN_RELAXED
+#undef ATOMIC_OP
+
+/**
+ * atomic_fetch_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as it was not @u.
+ * Returns the old value of @v.
+ */
+static __inline__ int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u)
+{
+	int t;
+
+	__asm__ __volatile__ (
+	PPC_ATOMIC_ENTRY_BARRIER
+"1:	lwarx	%0,0,%1		# atomic_fetch_add_unless\n\
+	cmpw	0,%0,%3 \n\
+	beq	2f \n\
+	add%I2c	%0,%0,%2 \n"
+"	stwcx.	%0,0,%1 \n\
+	bne-	1b \n"
+	PPC_ATOMIC_EXIT_BARRIER
+"	sub%I2c	%0,%0,%2 \n\
+2:"
+	: "=&r" (t)
+	: "r" (&v->counter), "rI" (a), "r" (u)
+	: "cc", "memory", "xer");
+
+	return t;
+}
+#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless
+
+/*
+ * Atomically test *v and decrement if it is greater than 0.
+ * The function returns the old value of *v minus 1, even if
+ * the atomic variable, v, was not decremented.
+ */
+static __inline__ int arch_atomic_dec_if_positive(atomic_t *v)
+{
+	int t;
+
+	__asm__ __volatile__(
+	PPC_ATOMIC_ENTRY_BARRIER
+"1:	lwarx	%0,0,%1		# atomic_dec_if_positive\n\
+	cmpwi	%0,1\n\
+	addi	%0,%0,-1\n\
+	blt-	2f\n"
+"	stwcx.	%0,0,%1\n\
+	bne-	1b"
+	PPC_ATOMIC_EXIT_BARRIER
+	"\n\
+2:"	: "=&b" (t)
+	: "r" (&v->counter)
+	: "cc", "memory");
+
+	return t;
+}
+#define arch_atomic_dec_if_positive arch_atomic_dec_if_positive
+
+#ifdef __powerpc64__
+
+#define ATOMIC64_INIT(i)	{ (i) }
+
+static __inline__ s64 arch_atomic64_read(const atomic64_t *v)
+{
+	s64 t;
+
+	/* -mprefixed can generate offsets beyond range, fall back hack */
+	if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED))
+		__asm__ __volatile__("ld %0,0(%1)" : "=r"(t) : "b"(&v->counter));
+	else
+		__asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : DS_FORM_CONSTRAINT (v->counter));
+
+	return t;
+}
+
+static __inline__ void arch_atomic64_set(atomic64_t *v, s64 i)
+{
+	/* -mprefixed can generate offsets beyond range, fall back hack */
+	if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED))
+		__asm__ __volatile__("std %1,0(%2)" : "=m"(v->counter) : "r"(i), "b"(&v->counter));
+	else
+		__asm__ __volatile__("std%U0%X0 %1,%0" : "=" DS_FORM_CONSTRAINT (v->counter) : "r"(i));
+}
+
+#define ATOMIC64_OP(op, asm_op)						\
+static __inline__ void arch_atomic64_##op(s64 a, atomic64_t *v)		\
+{									\
+	s64 t;								\
+									\
+	__asm__ __volatile__(						\
+"1:	ldarx	%0,0,%3		# atomic64_" #op "\n"			\
+	#asm_op " %0,%2,%0\n"						\
+"	stdcx.	%0,0,%3 \n"						\
+"	bne-	1b\n"							\
+	: "=&r" (t), "+m" (v->counter)					\
+	: "r" (a), "r" (&v->counter)					\
+	: "cc");							\
+}
+
+#define ATOMIC64_OP_RETURN_RELAXED(op, asm_op)				\
+static inline s64							\
+arch_atomic64_##op##_return_relaxed(s64 a, atomic64_t *v)		\
+{									\
+	s64 t;								\
+									\
+	__asm__ __volatile__(						\
+"1:	ldarx	%0,0,%3		# atomic64_" #op "_return_relaxed\n"	\
+	#asm_op " %0,%2,%0\n"						\
+"	stdcx.	%0,0,%3\n"						\
+"	bne-	1b\n"							\
+	: "=&r" (t), "+m" (v->counter)					\
+	: "r" (a), "r" (&v->counter)					\
+	: "cc");							\
+									\
+	return t;							\
+}
+
+#define ATOMIC64_FETCH_OP_RELAXED(op, asm_op)				\
+static inline s64							\
+arch_atomic64_fetch_##op##_relaxed(s64 a, atomic64_t *v)		\
+{									\
+	s64 res, t;							\
+									\
+	__asm__ __volatile__(						\
+"1:	ldarx	%0,0,%4		# atomic64_fetch_" #op "_relaxed\n"	\
+	#asm_op " %1,%3,%0\n"						\
+"	stdcx.	%1,0,%4\n"						\
+"	bne-	1b\n"							\
+	: "=&r" (res), "=&r" (t), "+m" (v->counter)			\
+	: "r" (a), "r" (&v->counter)					\
+	: "cc");							\
+									\
+	return res;							\
+}
+
+#define ATOMIC64_OPS(op, asm_op)					\
+	ATOMIC64_OP(op, asm_op)						\
+	ATOMIC64_OP_RETURN_RELAXED(op, asm_op)				\
+	ATOMIC64_FETCH_OP_RELAXED(op, asm_op)
+
+ATOMIC64_OPS(add, add)
+ATOMIC64_OPS(sub, subf)
+
+#define arch_atomic64_add_return_relaxed arch_atomic64_add_return_relaxed
+#define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return_relaxed
+
+#define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add_relaxed
+#define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub_relaxed
+
+#undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op, asm_op)					\
+	ATOMIC64_OP(op, asm_op)						\
+	ATOMIC64_FETCH_OP_RELAXED(op, asm_op)
+
+ATOMIC64_OPS(and, and)
+ATOMIC64_OPS(or, or)
+ATOMIC64_OPS(xor, xor)
+
+#define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and_relaxed
+#define arch_atomic64_fetch_or_relaxed  arch_atomic64_fetch_or_relaxed
+#define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor_relaxed
+
+#undef ATOPIC64_OPS
+#undef ATOMIC64_FETCH_OP_RELAXED
+#undef ATOMIC64_OP_RETURN_RELAXED
+#undef ATOMIC64_OP
+
+static __inline__ void arch_atomic64_inc(atomic64_t *v)
+{
+	s64 t;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%2		# atomic64_inc\n\
+	addic	%0,%0,1\n\
+	stdcx.	%0,0,%2 \n\
+	bne-	1b"
+	: "=&r" (t), "+m" (v->counter)
+	: "r" (&v->counter)
+	: "cc", "xer");
+}
+#define arch_atomic64_inc arch_atomic64_inc
+
+static __inline__ s64 arch_atomic64_inc_return_relaxed(atomic64_t *v)
+{
+	s64 t;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%2		# atomic64_inc_return_relaxed\n"
+"	addic	%0,%0,1\n"
+"	stdcx.	%0,0,%2\n"
+"	bne-	1b"
+	: "=&r" (t), "+m" (v->counter)
+	: "r" (&v->counter)
+	: "cc", "xer");
+
+	return t;
+}
+
+static __inline__ void arch_atomic64_dec(atomic64_t *v)
+{
+	s64 t;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%2		# atomic64_dec\n\
+	addic	%0,%0,-1\n\
+	stdcx.	%0,0,%2\n\
+	bne-	1b"
+	: "=&r" (t), "+m" (v->counter)
+	: "r" (&v->counter)
+	: "cc", "xer");
+}
+#define arch_atomic64_dec arch_atomic64_dec
+
+static __inline__ s64 arch_atomic64_dec_return_relaxed(atomic64_t *v)
+{
+	s64 t;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%2		# atomic64_dec_return_relaxed\n"
+"	addic	%0,%0,-1\n"
+"	stdcx.	%0,0,%2\n"
+"	bne-	1b"
+	: "=&r" (t), "+m" (v->counter)
+	: "r" (&v->counter)
+	: "cc", "xer");
+
+	return t;
+}
+
+#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return_relaxed
+#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return_relaxed
+
+/*
+ * Atomically test *v and decrement if it is greater than 0.
+ * The function returns the old value of *v minus 1.
+ */
+static __inline__ s64 arch_atomic64_dec_if_positive(atomic64_t *v)
+{
+	s64 t;
+
+	__asm__ __volatile__(
+	PPC_ATOMIC_ENTRY_BARRIER
+"1:	ldarx	%0,0,%1		# atomic64_dec_if_positive\n\
+	addic.	%0,%0,-1\n\
+	blt-	2f\n\
+	stdcx.	%0,0,%1\n\
+	bne-	1b"
+	PPC_ATOMIC_EXIT_BARRIER
+	"\n\
+2:"	: "=&r" (t)
+	: "r" (&v->counter)
+	: "cc", "xer", "memory");
+
+	return t;
+}
+#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
+
+/**
+ * atomic64_fetch_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic64_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as it was not @u.
+ * Returns the old value of @v.
+ */
+static __inline__ s64 arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
+{
+	s64 t;
+
+	__asm__ __volatile__ (
+	PPC_ATOMIC_ENTRY_BARRIER
+"1:	ldarx	%0,0,%1		# atomic64_fetch_add_unless\n\
+	cmpd	0,%0,%3 \n\
+	beq	2f \n\
+	add	%0,%2,%0 \n"
+"	stdcx.	%0,0,%1 \n\
+	bne-	1b \n"
+	PPC_ATOMIC_EXIT_BARRIER
+"	subf	%0,%2,%0 \n\
+2:"
+	: "=&r" (t)
+	: "r" (&v->counter), "r" (a), "r" (u)
+	: "cc", "memory");
+
+	return t;
+}
+#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless
+
+/**
+ * atomic_inc64_not_zero - increment unless the number is zero
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically increments @v by 1, so long as @v is non-zero.
+ * Returns non-zero if @v was non-zero, and zero otherwise.
+ */
+static __inline__ int arch_atomic64_inc_not_zero(atomic64_t *v)
+{
+	s64 t1, t2;
+
+	__asm__ __volatile__ (
+	PPC_ATOMIC_ENTRY_BARRIER
+"1:	ldarx	%0,0,%2		# atomic64_inc_not_zero\n\
+	cmpdi	0,%0,0\n\
+	beq-	2f\n\
+	addic	%1,%0,1\n\
+	stdcx.	%1,0,%2\n\
+	bne-	1b\n"
+	PPC_ATOMIC_EXIT_BARRIER
+	"\n\
+2:"
+	: "=&r" (t1), "=&r" (t2)
+	: "r" (&v->counter)
+	: "cc", "xer", "memory");
+
+	return t1 != 0;
+}
+#define arch_atomic64_inc_not_zero(v) arch_atomic64_inc_not_zero((v))
+
+#endif /* __powerpc64__ */
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_ATOMIC_H_ */

linux-7.2.3/arch/powerpc/include/asm/backlight.h

@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Routines for handling backlight control on PowerBooks
+ *
+ * For now, implementation resides in
+ * arch/powerpc/platforms/powermac/backlight.c
+ *
+ */
+#ifndef __ASM_POWERPC_BACKLIGHT_H
+#define __ASM_POWERPC_BACKLIGHT_H
+#ifdef __KERNEL__
+
+#include <linux/mutex.h>
+
+struct backlight_device;
+
+/* For locking instructions, see the implementation file */
+extern struct backlight_device *pmac_backlight;
+extern struct mutex pmac_backlight_mutex;
+
+extern int pmac_has_backlight_type(const char *type);
+
+extern void pmac_backlight_key(int direction);
+static inline void pmac_backlight_key_up(void)
+{
+	pmac_backlight_key(0);
+}
+static inline void pmac_backlight_key_down(void)
+{
+	pmac_backlight_key(1);
+}
+
+extern void pmac_backlight_set_legacy_brightness_pmu(int brightness);
+extern int pmac_backlight_set_legacy_brightness(int brightness);
+extern int pmac_backlight_get_legacy_brightness(void);
+
+extern void pmac_backlight_enable(void);
+extern void pmac_backlight_disable(void);
+
+#endif /* __KERNEL__ */
+#endif

linux-7.2.3/arch/powerpc/include/asm/barrier.h

@@ -0,0 +1,119 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
+ */
+#ifndef _ASM_POWERPC_BARRIER_H
+#define _ASM_POWERPC_BARRIER_H
+
+#include <asm/asm-const.h>
+
+#ifndef __ASSEMBLER__
+#include <asm/ppc-opcode.h>
+#endif
+
+/*
+ * Memory barrier.
+ * The sync instruction guarantees that all memory accesses initiated
+ * by this processor have been performed (with respect to all other
+ * mechanisms that access memory).  The eieio instruction is a barrier
+ * providing an ordering (separately) for (a) cacheable stores and (b)
+ * loads and stores to non-cacheable memory (e.g. I/O devices).
+ *
+ * mb() prevents loads and stores being reordered across this point.
+ * rmb() prevents loads being reordered across this point.
+ * wmb() prevents stores being reordered across this point.
+ *
+ * *mb() variants without smp_ prefix must order all types of memory
+ * operations with one another. sync is the only instruction sufficient
+ * to do this.
+ *
+ * For the smp_ barriers, ordering is for cacheable memory operations
+ * only. We have to use the sync instruction for smp_mb(), since lwsync
+ * doesn't order loads with respect to previous stores.  Lwsync can be
+ * used for smp_rmb() and smp_wmb().
+ *
+ * However, on CPUs that don't support lwsync, lwsync actually maps to a
+ * heavy-weight sync, so smp_wmb() can be a lighter-weight eieio.
+ */
+#define __mb()   __asm__ __volatile__ ("sync" : : : "memory")
+#define __rmb()  __asm__ __volatile__ ("sync" : : : "memory")
+#define __wmb()  __asm__ __volatile__ ("sync" : : : "memory")
+
+/* The sub-arch has lwsync */
+#if defined(CONFIG_PPC64) || defined(CONFIG_PPC_E500MC)
+#    define SMPWMB      LWSYNC
+#elif defined(CONFIG_BOOKE)
+#    define SMPWMB      mbar
+#else
+#    define SMPWMB      eieio
+#endif
+
+/* clang defines this macro for a builtin, which will not work with runtime patching */
+#undef __lwsync
+#define __lwsync()	__asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+#define __dma_rmb()	__lwsync()
+#define __dma_wmb()	__asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory")
+
+#define __smp_lwsync()	__lwsync()
+
+#define __smp_mb()	__mb()
+#define __smp_rmb()	__lwsync()
+#define __smp_wmb()	__asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory")
+
+/*
+ * This is a barrier which prevents following instructions from being
+ * started until the value of the argument x is known.  For example, if
+ * x is a variable loaded from memory, this prevents following
+ * instructions from being executed until the load has been performed.
+ */
+#define data_barrier(x)	\
+	asm volatile("twi 0,%0,0; isync" : : "r" (x) : "memory");
+
+#define __smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	__smp_lwsync();							\
+	WRITE_ONCE(*p, v);						\
+} while (0)
+
+#define __smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	__smp_lwsync();							\
+	___p1;								\
+})
+
+#ifdef CONFIG_PPC_BOOK3S_64
+#define NOSPEC_BARRIER_SLOT   nop
+#elif defined(CONFIG_PPC_E500)
+#define NOSPEC_BARRIER_SLOT   nop; nop
+#endif
+
+#ifdef CONFIG_PPC_BARRIER_NOSPEC
+/*
+ * Prevent execution of subsequent instructions until preceding branches have
+ * been fully resolved and are no longer executing speculatively.
+ */
+#define barrier_nospec_asm NOSPEC_BARRIER_FIXUP_SECTION; NOSPEC_BARRIER_SLOT
+
+// This also acts as a compiler barrier due to the memory clobber.
+#define barrier_nospec() asm (stringify_in_c(barrier_nospec_asm) ::: "memory")
+
+#else /* !CONFIG_PPC_BARRIER_NOSPEC */
+#define barrier_nospec_asm
+#define barrier_nospec()	do {} while (0)
+#endif /* CONFIG_PPC_BARRIER_NOSPEC */
+
+/*
+ * pmem_wmb() ensures that all stores for which the modification
+ * are written to persistent storage by preceding dcbfps/dcbstps
+ * instructions have updated persistent storage before any data
+ * access or data transfer caused by subsequent instructions is
+ * initiated.
+ */
+#define pmem_wmb() __asm__ __volatile__(PPC_PHWSYNC ::: "memory")
+
+#include <asm-generic/barrier.h>
+
+#endif /* _ASM_POWERPC_BARRIER_H */

linux-7.2.3/arch/powerpc/include/asm/bitops.h

@@ -0,0 +1,335 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * PowerPC atomic bit operations.
+ *
+ * Merged version by David Gibson <david@gibson.dropbear.id.au>.
+ * Based on ppc64 versions by: Dave Engebretsen, Todd Inglett, Don
+ * Reed, Pat McCarthy, Peter Bergner, Anton Blanchard.  They
+ * originally took it from the ppc32 code.
+ *
+ * Within a word, bits are numbered LSB first.  Lot's of places make
+ * this assumption by directly testing bits with (val & (1<<nr)).
+ * This can cause confusion for large (> 1 word) bitmaps on a
+ * big-endian system because, unlike little endian, the number of each
+ * bit depends on the word size.
+ *
+ * The bitop functions are defined to work on unsigned longs, so for a
+ * ppc64 system the bits end up numbered:
+ *   |63..............0|127............64|191...........128|255...........192|
+ * and on ppc32:
+ *   |31.....0|63....32|95....64|127...96|159..128|191..160|223..192|255..224|
+ *
+ * There are a few little-endian macros used mostly for filesystem
+ * bitmaps, these work on similar bit arrays layouts, but
+ * byte-oriented:
+ *   |7...0|15...8|23...16|31...24|39...32|47...40|55...48|63...56|
+ *
+ * The main difference is that bit 3-5 (64b) or 3-4 (32b) in the bit
+ * number field needs to be reversed compared to the big-endian bit
+ * fields. This can be achieved by XOR with 0x38 (64b) or 0x18 (32b).
+ */
+
+#ifndef _ASM_POWERPC_BITOPS_H
+#define _ASM_POWERPC_BITOPS_H
+
+#ifdef __KERNEL__
+
+#ifndef _LINUX_BITOPS_H
+#error only <linux/bitops.h> can be included directly
+#endif
+
+#include <linux/compiler.h>
+#include <asm/asm-compat.h>
+#include <asm/synch.h>
+
+/* PPC bit number conversion */
+#define PPC_BITLSHIFT(be)	(BITS_PER_LONG - 1 - (be))
+#define PPC_BIT(bit)		(1UL << PPC_BITLSHIFT(bit))
+#define PPC_BITMASK(bs, be)	((PPC_BIT(bs) - PPC_BIT(be)) | PPC_BIT(bs))
+
+/* Put a PPC bit into a "normal" bit position */
+#define PPC_BITEXTRACT(bits, ppc_bit, dst_bit)			\
+	((((bits) >> PPC_BITLSHIFT(ppc_bit)) & 1) << (dst_bit))
+
+#define PPC_BITLSHIFT32(be)	(32 - 1 - (be))
+#define PPC_BIT32(bit)		(1UL << PPC_BITLSHIFT32(bit))
+#define PPC_BITMASK32(bs, be)	((PPC_BIT32(bs) - PPC_BIT32(be))|PPC_BIT32(bs))
+
+#define PPC_BITLSHIFT8(be)	(8 - 1 - (be))
+#define PPC_BIT8(bit)		(1UL << PPC_BITLSHIFT8(bit))
+#define PPC_BITMASK8(bs, be)	((PPC_BIT8(bs) - PPC_BIT8(be))|PPC_BIT8(bs))
+
+#include <asm/barrier.h>
+
+/* Macro for generating the ***_bits() functions */
+#define DEFINE_BITOP(fn, op, prefix)		\
+static inline void fn(unsigned long mask,	\
+		volatile unsigned long *_p)	\
+{						\
+	unsigned long old;			\
+	unsigned long *p = (unsigned long *)_p;	\
+	__asm__ __volatile__ (			\
+	prefix					\
+"1:"	PPC_LLARX "%0,0,%3,0\n"			\
+	#op "%I2 %0,%0,%2\n"			\
+	PPC_STLCX "%0,0,%3\n"			\
+	"bne- 1b\n"				\
+	: "=&r" (old), "+m" (*p)		\
+	: "rK" (mask), "r" (p)			\
+	: "cc", "memory");			\
+}
+
+DEFINE_BITOP(set_bits, or, "")
+DEFINE_BITOP(change_bits, xor, "")
+
+static __always_inline bool is_rlwinm_mask_valid(unsigned long x)
+{
+	if (!x)
+		return false;
+	if (x & 1)
+		x = ~x;	// make the mask non-wrapping
+	x += x & -x;	// adding the low set bit results in at most one bit set
+
+	return !(x & (x - 1));
+}
+
+#define DEFINE_CLROP(fn, prefix)					\
+static inline void fn(unsigned long mask, volatile unsigned long *_p)	\
+{									\
+	unsigned long old;						\
+	unsigned long *p = (unsigned long *)_p;				\
+									\
+	if (IS_ENABLED(CONFIG_PPC32) &&					\
+	    __builtin_constant_p(mask) && is_rlwinm_mask_valid(~mask)) {\
+		asm volatile (						\
+			prefix						\
+		"1:"	"lwarx	%0,0,%3\n"				\
+			"rlwinm	%0,%0,0,%2\n"				\
+			"stwcx.	%0,0,%3\n"				\
+			"bne- 1b\n"					\
+			: "=&r" (old), "+m" (*p)			\
+			: "n" (~mask), "r" (p)				\
+			: "cc", "memory");				\
+	} else {							\
+		asm volatile (						\
+			prefix						\
+		"1:"	PPC_LLARX "%0,0,%3,0\n"				\
+			"andc %0,%0,%2\n"				\
+			PPC_STLCX "%0,0,%3\n"				\
+			"bne- 1b\n"					\
+			: "=&r" (old), "+m" (*p)			\
+			: "r" (mask), "r" (p)				\
+			: "cc", "memory");				\
+	}								\
+}
+
+DEFINE_CLROP(clear_bits, "")
+DEFINE_CLROP(clear_bits_unlock, PPC_RELEASE_BARRIER)
+
+static inline void arch_set_bit(int nr, volatile unsigned long *addr)
+{
+	set_bits(BIT_MASK(nr), addr + BIT_WORD(nr));
+}
+
+static inline void arch_clear_bit(int nr, volatile unsigned long *addr)
+{
+	clear_bits(BIT_MASK(nr), addr + BIT_WORD(nr));
+}
+
+static inline void arch_clear_bit_unlock(int nr, volatile unsigned long *addr)
+{
+	clear_bits_unlock(BIT_MASK(nr), addr + BIT_WORD(nr));
+}
+
+static inline void arch_change_bit(int nr, volatile unsigned long *addr)
+{
+	change_bits(BIT_MASK(nr), addr + BIT_WORD(nr));
+}
+
+/* Like DEFINE_BITOP(), with changes to the arguments to 'op' and the output
+ * operands. */
+#define DEFINE_TESTOP(fn, op, prefix, postfix, eh)	\
+static inline unsigned long fn(			\
+		unsigned long mask,			\
+		volatile unsigned long *_p)		\
+{							\
+	unsigned long old, t;				\
+	unsigned long *p = (unsigned long *)_p;		\
+	__asm__ __volatile__ (				\
+	prefix						\
+"1:"	PPC_LLARX "%0,0,%3,%4\n"			\
+	#op "%I2 %1,%0,%2\n"				\
+	PPC_STLCX "%1,0,%3\n"				\
+	"bne- 1b\n"					\
+	postfix						\
+	: "=&r" (old), "=&r" (t)			\
+	: "rK" (mask), "r" (p), "n" (eh)		\
+	: "cc", "memory");				\
+	return (old & mask);				\
+}
+
+DEFINE_TESTOP(test_and_set_bits, or, PPC_ATOMIC_ENTRY_BARRIER,
+	      PPC_ATOMIC_EXIT_BARRIER, 0)
+DEFINE_TESTOP(test_and_set_bits_lock, or, "",
+	      PPC_ACQUIRE_BARRIER, IS_ENABLED(CONFIG_PPC64))
+DEFINE_TESTOP(test_and_change_bits, xor, PPC_ATOMIC_ENTRY_BARRIER,
+	      PPC_ATOMIC_EXIT_BARRIER, 0)
+
+static inline unsigned long test_and_clear_bits(unsigned long mask, volatile unsigned long *_p)
+{
+	unsigned long old, t;
+	unsigned long *p = (unsigned long *)_p;
+
+	if (IS_ENABLED(CONFIG_PPC32) &&
+	    __builtin_constant_p(mask) && is_rlwinm_mask_valid(~mask)) {
+		asm volatile (
+			PPC_ATOMIC_ENTRY_BARRIER
+		"1:"	"lwarx %0,0,%3\n"
+			"rlwinm	%1,%0,0,%2\n"
+			"stwcx. %1,0,%3\n"
+			"bne- 1b\n"
+			PPC_ATOMIC_EXIT_BARRIER
+			: "=&r" (old), "=&r" (t)
+			: "n" (~mask), "r" (p)
+			: "cc", "memory");
+	} else {
+		asm volatile (
+			PPC_ATOMIC_ENTRY_BARRIER
+		"1:"	PPC_LLARX "%0,0,%3,0\n"
+			"andc	%1,%0,%2\n"
+			PPC_STLCX "%1,0,%3\n"
+			"bne- 1b\n"
+			PPC_ATOMIC_EXIT_BARRIER
+			: "=&r" (old), "=&r" (t)
+			: "r" (mask), "r" (p)
+			: "cc", "memory");
+	}
+
+	return (old & mask);
+}
+
+static inline int arch_test_and_set_bit(unsigned long nr,
+					volatile unsigned long *addr)
+{
+	return test_and_set_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0;
+}
+
+static inline int arch_test_and_set_bit_lock(unsigned long nr,
+					     volatile unsigned long *addr)
+{
+	return test_and_set_bits_lock(BIT_MASK(nr),
+				addr + BIT_WORD(nr)) != 0;
+}
+
+static inline int arch_test_and_clear_bit(unsigned long nr,
+					  volatile unsigned long *addr)
+{
+	return test_and_clear_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0;
+}
+
+static inline int arch_test_and_change_bit(unsigned long nr,
+					   volatile unsigned long *addr)
+{
+	return test_and_change_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0;
+}
+
+static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
+		volatile unsigned long *p)
+{
+	unsigned long old, t;
+
+	__asm__ __volatile__ (
+	PPC_RELEASE_BARRIER
+"1:"	PPC_LLARX "%0,0,%3,0\n"
+	"xor %1,%0,%2\n"
+	PPC_STLCX "%1,0,%3\n"
+	"bne- 1b\n"
+	: "=&r" (old), "=&r" (t)
+	: "r" (mask), "r" (p)
+	: "cc", "memory");
+
+	return (old & BIT_MASK(7)) != 0;
+}
+#define arch_xor_unlock_is_negative_byte arch_xor_unlock_is_negative_byte
+
+#include <asm-generic/bitops/non-atomic.h>
+
+static inline void arch___clear_bit_unlock(int nr, volatile unsigned long *addr)
+{
+	__asm__ __volatile__(PPC_RELEASE_BARRIER "" ::: "memory");
+	__clear_bit(nr, addr);
+}
+
+/*
+ * Return the zero-based bit position (LE, not IBM bit numbering) of
+ * the most significant 1-bit in a double word.
+ */
+#define __ilog2(x)	ilog2(x)
+
+#include <asm-generic/bitops/ffz.h>
+
+#include <asm-generic/bitops/builtin-__ffs.h>
+
+#include <asm-generic/bitops/builtin-ffs.h>
+
+/*
+ * fls: find last (most-significant) bit set.
+ * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
+ */
+static __always_inline __attribute_const__ int fls(unsigned int x)
+{
+	int lz;
+
+	if (__builtin_constant_p(x))
+		return x ? 32 - __builtin_clz(x) : 0;
+	asm("cntlzw %0,%1" : "=r" (lz) : "r" (x));
+	return 32 - lz;
+}
+
+#include <asm-generic/bitops/builtin-__fls.h>
+
+/*
+ * 64-bit can do this using one cntlzd (count leading zeroes doubleword)
+ * instruction; for 32-bit we use the generic version, which does two
+ * 32-bit fls calls.
+ */
+#ifdef CONFIG_PPC64
+static __always_inline __attribute_const__ int fls64(__u64 x)
+{
+	int lz;
+
+	if (__builtin_constant_p(x))
+		return x ? 64 - __builtin_clzll(x) : 0;
+	asm("cntlzd %0,%1" : "=r" (lz) : "r" (x));
+	return 64 - lz;
+}
+#else
+#include <asm-generic/bitops/fls64.h>
+#endif
+
+#ifdef CONFIG_PPC64
+unsigned int __arch_hweight8(unsigned int w);
+unsigned int __arch_hweight16(unsigned int w);
+unsigned int __arch_hweight32(unsigned int w);
+unsigned long __arch_hweight64(__u64 w);
+#include <asm-generic/bitops/const_hweight.h>
+#else
+#include <asm-generic/bitops/hweight.h>
+#endif
+
+/* wrappers that deal with KASAN instrumentation */
+#include <asm-generic/bitops/instrumented-atomic.h>
+#include <asm-generic/bitops/instrumented-lock.h>
+
+/* Little-endian versions */
+#include <asm-generic/bitops/le.h>
+
+/* Bitmap functions for the ext2 filesystem */
+
+#include <asm-generic/bitops/ext2-atomic-setbit.h>
+
+#include <asm-generic/bitops/sched.h>
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_POWERPC_BITOPS_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/32/kup.h

@@ -0,0 +1,174 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_32_KUP_H
+#define _ASM_POWERPC_BOOK3S_32_KUP_H
+
+#include <asm/bug.h>
+#include <asm/book3s/32/mmu-hash.h>
+#include <asm/mmu.h>
+#include <asm/synch.h>
+
+#ifndef __ASSEMBLER__
+
+#ifdef CONFIG_PPC_KUAP
+
+#include <linux/sched.h>
+
+#define KUAP_NONE	(~0UL)
+
+static __always_inline void kuap_lock_one(unsigned long addr)
+{
+	mtsr(mfsr(addr) | SR_KS, addr);
+	isync();	/* Context sync required after mtsr() */
+}
+
+static __always_inline void kuap_unlock_one(unsigned long addr)
+{
+	mtsr(mfsr(addr) & ~SR_KS, addr);
+	isync();	/* Context sync required after mtsr() */
+}
+
+static __always_inline void uaccess_begin_32s(unsigned long addr)
+{
+	unsigned long tmp;
+
+	asm volatile(ASM_MMU_FTR_IFSET(
+		"mfsrin %0, %1;"
+		"rlwinm %0, %0, 0, %2;"
+		"mtsrin %0, %1;"
+		"isync", "", %3)
+		: "=&r"(tmp)
+		: "r"(addr), "i"(~SR_KS), "i"(MMU_FTR_KUAP)
+		: "memory");
+}
+
+static __always_inline void uaccess_end_32s(unsigned long addr)
+{
+	unsigned long tmp;
+
+	asm volatile(ASM_MMU_FTR_IFSET(
+		"mfsrin %0, %1;"
+		"oris %0, %0, %2;"
+		"mtsrin %0, %1;"
+		"isync", "", %3)
+		: "=&r"(tmp)
+		: "r"(addr), "i"(SR_KS >> 16), "i"(MMU_FTR_KUAP)
+		: "memory");
+}
+
+static __always_inline void __kuap_save_and_lock(struct pt_regs *regs)
+{
+	unsigned long kuap = current->thread.kuap;
+
+	regs->kuap = kuap;
+	if (unlikely(kuap == KUAP_NONE))
+		return;
+
+	current->thread.kuap = KUAP_NONE;
+	kuap_lock_one(kuap);
+}
+#define __kuap_save_and_lock __kuap_save_and_lock
+
+static __always_inline void kuap_user_restore(struct pt_regs *regs)
+{
+}
+
+static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long kuap)
+{
+	if (unlikely(kuap != KUAP_NONE)) {
+		current->thread.kuap = KUAP_NONE;
+		kuap_lock_one(kuap);
+	}
+
+	if (likely(regs->kuap == KUAP_NONE))
+		return;
+
+	current->thread.kuap = regs->kuap;
+
+	kuap_unlock_one(regs->kuap);
+}
+
+static __always_inline unsigned long __kuap_get_and_assert_locked(void)
+{
+	unsigned long kuap = current->thread.kuap;
+
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_PPC_KUAP_DEBUG) && kuap != KUAP_NONE);
+
+	return kuap;
+}
+#define __kuap_get_and_assert_locked __kuap_get_and_assert_locked
+
+static __always_inline void allow_user_access(void __user *to, unsigned long dir)
+{
+	BUILD_BUG_ON(!__builtin_constant_p(dir));
+
+	if (!(dir & KUAP_WRITE))
+		return;
+
+	current->thread.kuap = (__force u32)to;
+	uaccess_begin_32s((__force u32)to);
+}
+
+static __always_inline void prevent_user_access(unsigned long dir)
+{
+	u32 kuap = current->thread.kuap;
+
+	BUILD_BUG_ON(!__builtin_constant_p(dir));
+
+	if (!(dir & KUAP_WRITE))
+		return;
+
+	current->thread.kuap = KUAP_NONE;
+	uaccess_end_32s(kuap);
+}
+
+static __always_inline unsigned long prevent_user_access_return(void)
+{
+	unsigned long flags = current->thread.kuap;
+
+	if (flags != KUAP_NONE) {
+		current->thread.kuap = KUAP_NONE;
+		uaccess_end_32s(flags);
+	}
+
+	return flags;
+}
+
+static __always_inline void restore_user_access(unsigned long flags)
+{
+	if (flags != KUAP_NONE) {
+		current->thread.kuap = flags;
+		uaccess_begin_32s(flags);
+	}
+}
+
+static __always_inline bool
+__bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
+{
+	unsigned long kuap = regs->kuap;
+
+	if (!is_write)
+		return false;
+	if (kuap == KUAP_NONE)
+		return true;
+
+	/*
+	 * If faulting address doesn't match unlocked segment, change segment.
+	 * In case of unaligned store crossing two segments, emulate store.
+	 */
+	if ((kuap ^ address) & 0xf0000000) {
+		if (!(kuap & 0x0fffffff) && address > kuap - 4 && fix_alignment(regs)) {
+			regs_add_return_ip(regs, 4);
+			emulate_single_step(regs);
+		} else {
+			regs->kuap = address;
+		}
+	}
+
+	return false;
+}
+
+#endif /* CONFIG_PPC_KUAP */
+
+#endif /* __ASSEMBLER__ */
+
+#endif /* _ASM_POWERPC_BOOK3S_32_KUP_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/32/mmu-hash.h

@@ -0,0 +1,239 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_32_MMU_HASH_H_
+#define _ASM_POWERPC_BOOK3S_32_MMU_HASH_H_
+
+/*
+ * 32-bit hash table MMU support
+ */
+
+/*
+ * BATs
+ */
+
+/* Block size masks */
+#define BL_128K	0x000
+#define BL_256K 0x001
+#define BL_512K 0x003
+#define BL_1M   0x007
+#define BL_2M   0x00F
+#define BL_4M   0x01F
+#define BL_8M   0x03F
+#define BL_16M  0x07F
+#define BL_32M  0x0FF
+#define BL_64M  0x1FF
+#define BL_128M 0x3FF
+#define BL_256M 0x7FF
+
+/* BAT Access Protection */
+#define BPP_XX	0x00		/* No access */
+#define BPP_RX	0x01		/* Read only */
+#define BPP_RW	0x02		/* Read/write */
+
+#ifndef __ASSEMBLER__
+/* Contort a phys_addr_t into the right format/bits for a BAT */
+#ifdef CONFIG_PHYS_64BIT
+#define BAT_PHYS_ADDR(x) ((u32)((x & 0x00000000fffe0000ULL) | \
+				((x & 0x0000000e00000000ULL) >> 24) | \
+				((x & 0x0000000100000000ULL) >> 30)))
+#define PHYS_BAT_ADDR(x) (((u64)(x) & 0x00000000fffe0000ULL) | \
+			  (((u64)(x) << 24) & 0x0000000e00000000ULL) | \
+			  (((u64)(x) << 30) & 0x0000000100000000ULL))
+#else
+#define BAT_PHYS_ADDR(x) (x)
+#define PHYS_BAT_ADDR(x) ((x) & 0xfffe0000)
+#endif
+
+struct ppc_bat {
+	u32 batu;
+	u32 batl;
+};
+#endif /* !__ASSEMBLER__ */
+
+/*
+ * Hash table
+ */
+
+/* Values for PP (assumes Ks=0, Kp=1) */
+#define PP_RWXX	0	/* Supervisor read/write, User none */
+#define PP_RWRX 1	/* Supervisor read/write, User read */
+#define PP_RWRW 2	/* Supervisor read/write, User read/write */
+#define PP_RXRX 3	/* Supervisor read,       User read */
+
+/* Values for Segment Registers */
+#define SR_NX	0x10000000	/* No Execute */
+#define SR_KP	0x20000000	/* User key */
+#define SR_KS	0x40000000	/* Supervisor key */
+
+#ifdef __ASSEMBLER__
+
+#include <asm/asm-offsets.h>
+
+.macro uus_addi sr reg1 reg2 imm
+	.if NUM_USER_SEGMENTS > \sr
+	addi	\reg1,\reg2,\imm
+	.endif
+.endm
+
+.macro uus_mtsr sr reg1
+	.if NUM_USER_SEGMENTS > \sr
+	mtsr	\sr, \reg1
+	.endif
+.endm
+
+/*
+ * This isync() shouldn't be necessary as the kernel is not excepted to run
+ * any instruction in userspace soon after the update of segments and 'rfi'
+ * instruction is used to return to userspace, but hash based cores
+ * (at least G3) seem to exhibit a random behaviour when the 'isync' is not
+ * there. 603 cores don't have this behaviour so don't do the 'isync' as it
+ * saves several CPU cycles.
+ */
+.macro uus_isync
+#ifdef CONFIG_PPC_BOOK3S_604
+BEGIN_MMU_FTR_SECTION
+	isync
+END_MMU_FTR_SECTION_IFSET(MMU_FTR_HPTE_TABLE)
+#endif
+.endm
+
+.macro update_user_segments_by_4 tmp1 tmp2 tmp3 tmp4
+	uus_addi	1, \tmp2, \tmp1, 0x111
+	uus_addi	2, \tmp3, \tmp1, 0x222
+	uus_addi	3, \tmp4, \tmp1, 0x333
+
+	uus_mtsr	0, \tmp1
+	uus_mtsr	1, \tmp2
+	uus_mtsr	2, \tmp3
+	uus_mtsr	3, \tmp4
+
+	uus_addi	4, \tmp1, \tmp1, 0x444
+	uus_addi	5, \tmp2, \tmp2, 0x444
+	uus_addi	6, \tmp3, \tmp3, 0x444
+	uus_addi	7, \tmp4, \tmp4, 0x444
+
+	uus_mtsr	4, \tmp1
+	uus_mtsr	5, \tmp2
+	uus_mtsr	6, \tmp3
+	uus_mtsr	7, \tmp4
+
+	uus_addi	8, \tmp1, \tmp1, 0x444
+	uus_addi	9, \tmp2, \tmp2, 0x444
+	uus_addi	10, \tmp3, \tmp3, 0x444
+	uus_addi	11, \tmp4, \tmp4, 0x444
+
+	uus_mtsr	8, \tmp1
+	uus_mtsr	9, \tmp2
+	uus_mtsr	10, \tmp3
+	uus_mtsr	11, \tmp4
+
+	uus_addi	12, \tmp1, \tmp1, 0x444
+	uus_addi	13, \tmp2, \tmp2, 0x444
+	uus_addi	14, \tmp3, \tmp3, 0x444
+	uus_addi	15, \tmp4, \tmp4, 0x444
+
+	uus_mtsr	12, \tmp1
+	uus_mtsr	13, \tmp2
+	uus_mtsr	14, \tmp3
+	uus_mtsr	15, \tmp4
+
+	uus_isync
+.endm
+
+#else
+
+/*
+ * This macro defines the mapping from contexts to VSIDs (virtual
+ * segment IDs).  We use a skew on both the context and the high 4 bits
+ * of the 32-bit virtual address (the "effective segment ID") in order
+ * to spread out the entries in the MMU hash table.  Note, if this
+ * function is changed then hash functions will have to be
+ * changed to correspond.
+ */
+#define CTX_TO_VSID(c, id)	((((c) * (897 * 16)) + (id * 0x111)) & 0xffffff)
+
+/*
+ * Hardware Page Table Entry
+ * Note that the xpn and x bitfields are used only by processors that
+ * support extended addressing; otherwise, those bits are reserved.
+ */
+struct hash_pte {
+	unsigned long v:1;	/* Entry is valid */
+	unsigned long vsid:24;	/* Virtual segment identifier */
+	unsigned long h:1;	/* Hash algorithm indicator */
+	unsigned long api:6;	/* Abbreviated page index */
+	unsigned long rpn:20;	/* Real (physical) page number */
+	unsigned long xpn:3;	/* Real page number bits 0-2, optional */
+	unsigned long r:1;	/* Referenced */
+	unsigned long c:1;	/* Changed */
+	unsigned long w:1;	/* Write-thru cache mode */
+	unsigned long i:1;	/* Cache inhibited */
+	unsigned long m:1;	/* Memory coherence */
+	unsigned long g:1;	/* Guarded */
+	unsigned long x:1;	/* Real page number bit 3, optional */
+	unsigned long pp:2;	/* Page protection */
+};
+
+typedef struct {
+	unsigned long id;
+	unsigned long sr0;
+	void __user *vdso;
+} mm_context_t;
+
+#ifdef CONFIG_PPC_KUEP
+#define INIT_MM_CONTEXT(mm) .context.sr0 = SR_NX
+#endif
+
+void update_bats(void);
+static inline void cleanup_cpu_mmu_context(void) { }
+
+/* patch sites */
+extern s32 patch__hash_page_A0, patch__hash_page_A1, patch__hash_page_A2;
+extern s32 patch__hash_page_B, patch__hash_page_C;
+extern s32 patch__flush_hash_A0, patch__flush_hash_A1, patch__flush_hash_A2;
+extern s32 patch__flush_hash_B;
+
+#include <linux/sizes.h>
+#include <linux/align.h>
+
+#include <asm/reg.h>
+#include <asm/task_size_32.h>
+
+static __always_inline void update_user_segment(u32 n, u32 val)
+{
+	if (n << 28 < ALIGN(TASK_SIZE, SZ_256M))
+		mtsr(val + n * 0x111, n << 28);
+}
+
+static __always_inline void update_user_segments(u32 val)
+{
+	val &= 0xf0ffffff;
+
+	update_user_segment(0, val);
+	update_user_segment(1, val);
+	update_user_segment(2, val);
+	update_user_segment(3, val);
+	update_user_segment(4, val);
+	update_user_segment(5, val);
+	update_user_segment(6, val);
+	update_user_segment(7, val);
+	update_user_segment(8, val);
+	update_user_segment(9, val);
+	update_user_segment(10, val);
+	update_user_segment(11, val);
+	update_user_segment(12, val);
+	update_user_segment(13, val);
+	update_user_segment(14, val);
+	update_user_segment(15, val);
+}
+
+int __init find_free_bat(void);
+unsigned int bat_block_size(unsigned long base, unsigned long top);
+#endif /* !__ASSEMBLER__ */
+
+/* We happily ignore the smaller BATs on 601, we don't actually use
+ * those definitions on hash32 at the moment anyway
+ */
+#define mmu_virtual_psize	MMU_PAGE_4K
+#define mmu_linear_psize	MMU_PAGE_256M
+
+#endif /* _ASM_POWERPC_BOOK3S_32_MMU_HASH_H_ */

linux-7.2.3/arch/powerpc/include/asm/book3s/32/pgalloc.h

@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_32_PGALLOC_H
+#define _ASM_POWERPC_BOOK3S_32_PGALLOC_H
+
+#include <linux/threads.h>
+#include <linux/slab.h>
+
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+	pgd_t *pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
+				      pgtable_gfp_flags(mm, GFP_KERNEL));
+
+#ifdef CONFIG_PPC_BOOK3S_603
+	memcpy(pgd + USER_PTRS_PER_PGD, swapper_pg_dir + USER_PTRS_PER_PGD,
+	       (MAX_PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
+#endif
+	return pgd;
+}
+
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
+}
+
+/*
+ * We don't have any real pmd's, and this code never triggers because
+ * the pgd will always be present..
+ */
+/* #define pmd_alloc_one(mm,address)       ({ BUG(); ((pmd_t *)2); }) */
+#define pmd_free(mm, x) 		do { } while (0)
+#define __pmd_free_tlb(tlb,x,a)		do { } while (0)
+/* #define pgd_populate(mm, pmd, pte)      BUG() */
+
+static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp,
+				       pte_t *pte)
+{
+	*pmdp = __pmd(__pa(pte) | _PMD_PRESENT);
+}
+
+static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
+				pgtable_t pte_page)
+{
+	*pmdp = __pmd(__pa(pte_page) | _PMD_PRESENT);
+}
+
+static inline void pgtable_free(void *table, unsigned index_size)
+{
+	if (!index_size) {
+		pte_fragment_free((unsigned long *)table, 0);
+	} else {
+		BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE);
+		kmem_cache_free(PGT_CACHE(index_size), table);
+	}
+}
+
+static inline void pgtable_free_tlb(struct mmu_gather *tlb,
+				    void *table, int shift)
+{
+	unsigned long pgf = (unsigned long)table;
+	BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+	pgf |= shift;
+	tlb_remove_table(tlb, (void *)pgf);
+}
+
+static inline void __tlb_remove_table(void *_table)
+{
+	void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
+	unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
+
+	pgtable_free(table, shift);
+}
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
+				  unsigned long address)
+{
+	pgtable_free_tlb(tlb, table, 0);
+}
+#endif /* _ASM_POWERPC_BOOK3S_32_PGALLOC_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/32/pgtable.h

@@ -0,0 +1,613 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_32_PGTABLE_H
+#define _ASM_POWERPC_BOOK3S_32_PGTABLE_H
+
+#include <asm-generic/pgtable-nopmd.h>
+
+/*
+ * The "classic" 32-bit implementation of the PowerPC MMU uses a hash
+ * table containing PTEs, together with a set of 16 segment registers,
+ * to define the virtual to physical address mapping.
+ *
+ * We use the hash table as an extended TLB, i.e. a cache of currently
+ * active mappings.  We maintain a two-level page table tree, much
+ * like that used by the i386, for the sake of the Linux memory
+ * management code.  Low-level assembler code in hash_low_32.S
+ * (procedure hash_page) is responsible for extracting ptes from the
+ * tree and putting them into the hash table when necessary, and
+ * updating the accessed and modified bits in the page table tree.
+ */
+
+#define _PAGE_PRESENT	0x001	/* software: pte contains a translation */
+#define _PAGE_HASHPTE	0x002	/* hash_page has made an HPTE for this pte */
+#define _PAGE_READ	0x004	/* software: read access allowed */
+#define _PAGE_GUARDED	0x008	/* G: prohibit speculative access */
+#define _PAGE_COHERENT	0x010	/* M: enforce memory coherence (SMP systems) */
+#define _PAGE_NO_CACHE	0x020	/* I: cache inhibit */
+#define _PAGE_WRITETHRU	0x040	/* W: cache write-through */
+#define _PAGE_DIRTY	0x080	/* C: page changed */
+#define _PAGE_ACCESSED	0x100	/* R: page referenced */
+#define _PAGE_EXEC	0x200	/* software: exec allowed */
+#define _PAGE_WRITE	0x400	/* software: user write access allowed */
+#define _PAGE_SPECIAL	0x800	/* software: Special page */
+
+#ifdef CONFIG_PTE_64BIT
+/* We never clear the high word of the pte */
+#define _PTE_NONE_MASK	(0xffffffff00000000ULL | _PAGE_HASHPTE)
+#else
+#define _PTE_NONE_MASK	_PAGE_HASHPTE
+#endif
+
+#define _PMD_PRESENT	0
+#define _PMD_PRESENT_MASK (PAGE_MASK)
+#define _PMD_BAD	(~PAGE_MASK)
+
+/* We borrow the _PAGE_READ bit to store the exclusive marker in swap PTEs. */
+#define _PAGE_SWP_EXCLUSIVE	_PAGE_READ
+
+/* And here we include common definitions */
+
+#define _PAGE_HPTEFLAGS _PAGE_HASHPTE
+
+/*
+ * Location of the PFN in the PTE. Most 32-bit platforms use the same
+ * as _PAGE_SHIFT here (ie, naturally aligned).
+ * Platform who don't just pre-define the value so we don't override it here.
+ */
+#define PTE_RPN_SHIFT	(PAGE_SHIFT)
+
+/*
+ * The mask covered by the RPN must be a ULL on 32-bit platforms with
+ * 64-bit PTEs.
+ */
+#ifdef CONFIG_PTE_64BIT
+#define PTE_RPN_MASK	(~((1ULL << PTE_RPN_SHIFT) - 1))
+#define MAX_POSSIBLE_PHYSMEM_BITS 36
+#else
+#define PTE_RPN_MASK	(~((1UL << PTE_RPN_SHIFT) - 1))
+#define MAX_POSSIBLE_PHYSMEM_BITS 32
+#endif
+
+/*
+ * _PAGE_CHG_MASK masks of bits that are to be preserved across
+ * pgprot changes.
+ */
+#define _PAGE_CHG_MASK	(PTE_RPN_MASK | _PAGE_HASHPTE | _PAGE_DIRTY | \
+			 _PAGE_ACCESSED | _PAGE_SPECIAL)
+
+/*
+ * We define 2 sets of base prot bits, one for basic pages (ie,
+ * cacheable kernel and user pages) and one for non cacheable
+ * pages. We always set _PAGE_COHERENT when SMP is enabled or
+ * the processor might need it for DMA coherency.
+ */
+#define _PAGE_BASE_NC	(_PAGE_PRESENT | _PAGE_ACCESSED)
+#define _PAGE_BASE	(_PAGE_BASE_NC | _PAGE_COHERENT)
+
+#include <asm/pgtable-masks.h>
+
+/* Permission masks used for kernel mappings */
+#define PAGE_KERNEL	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RW)
+#define PAGE_KERNEL_NC	__pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NO_CACHE)
+#define PAGE_KERNEL_NCG	__pgprot(_PAGE_BASE_NC | _PAGE_KERNEL_RW | _PAGE_NO_CACHE | _PAGE_GUARDED)
+#define PAGE_KERNEL_X	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RWX)
+#define PAGE_KERNEL_RO	__pgprot(_PAGE_BASE | _PAGE_KERNEL_RO)
+#define PAGE_KERNEL_ROX	__pgprot(_PAGE_BASE | _PAGE_KERNEL_ROX)
+
+#define PTE_INDEX_SIZE	PTE_SHIFT
+#define PMD_INDEX_SIZE	0
+#define PUD_INDEX_SIZE	0
+#define PGD_INDEX_SIZE	(32 - PGDIR_SHIFT)
+
+#define PMD_CACHE_INDEX	PMD_INDEX_SIZE
+#define PUD_CACHE_INDEX	PUD_INDEX_SIZE
+
+#ifndef __ASSEMBLER__
+#define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_INDEX_SIZE)
+#define PMD_TABLE_SIZE	0
+#define PUD_TABLE_SIZE	0
+#define PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
+
+/* Bits to mask out from a PMD to get to the PTE page */
+#define PMD_MASKED_BITS		(PTE_TABLE_SIZE - 1)
+#endif	/* __ASSEMBLER__ */
+
+#define PTRS_PER_PTE	(1 << PTE_INDEX_SIZE)
+#define PTRS_PER_PGD	(1 << PGD_INDEX_SIZE)
+
+/*
+ * The normal case is that PTEs are 32-bits and we have a 1-page
+ * 1024-entry pgdir pointing to 1-page 1024-entry PTE pages.  -- paulus
+ *
+ * For any >32-bit physical address platform, we can use the following
+ * two level page table layout where the pgdir is 8KB and the MS 13 bits
+ * are an index to the second level table.  The combined pgdir/pmd first
+ * level has 2048 entries and the second level has 512 64-bit PTE entries.
+ * -Matt
+ */
+/* PGDIR_SHIFT determines what a top-level page table entry can map */
+#define PGDIR_SHIFT	(PAGE_SHIFT + PTE_INDEX_SIZE)
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK	(~(PGDIR_SIZE-1))
+
+#define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
+
+#ifndef __ASSEMBLER__
+
+int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot);
+void unmap_kernel_page(unsigned long va);
+
+#endif /* !__ASSEMBLER__ */
+
+/*
+ * This is the bottom of the PKMAP area with HIGHMEM or an arbitrary
+ * value (for now) on others, from where we can start layout kernel
+ * virtual space that goes below PKMAP and FIXMAP
+ */
+
+#define FIXADDR_SIZE	0
+#ifdef CONFIG_KASAN
+#include <asm/kasan.h>
+#define FIXADDR_TOP	(KASAN_SHADOW_START - PAGE_SIZE)
+#else
+#define FIXADDR_TOP	((unsigned long)(-PAGE_SIZE))
+#endif
+
+/*
+ * ioremap_bot starts at that address. Early ioremaps move down from there,
+ * until mem_init() at which point this becomes the top of the vmalloc
+ * and ioremap space
+ */
+#ifdef CONFIG_HIGHMEM
+#define IOREMAP_TOP	PKMAP_BASE
+#else
+#define IOREMAP_TOP	FIXADDR_START
+#endif
+
+/* PPC32 shares vmalloc area with ioremap */
+#define IOREMAP_START	VMALLOC_START
+#define IOREMAP_END	VMALLOC_END
+
+/*
+ * Just any arbitrary offset to the start of the vmalloc VM area: the
+ * current 16MB value just means that there will be a 64MB "hole" after the
+ * physical memory until the kernel virtual memory starts.  That means that
+ * any out-of-bounds memory accesses will hopefully be caught.
+ * The vmalloc() routines leaves a hole of 4kB between each vmalloced
+ * area for the same reason. ;)
+ *
+ * We no longer map larger than phys RAM with the BATs so we don't have
+ * to worry about the VMALLOC_OFFSET causing problems.  We do have to worry
+ * about clashes between our early calls to ioremap() that start growing down
+ * from ioremap_base being run into the VM area allocations (growing upwards
+ * from VMALLOC_START).  For this reason we have ioremap_bot to check when
+ * we actually run into our mappings setup in the early boot with the VM
+ * system.  This really does become a problem for machines with good amounts
+ * of RAM.  -- Cort
+ */
+#define VMALLOC_OFFSET (0x1000000) /* 16M */
+
+#define VMALLOC_START ((((long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1)))
+
+#ifdef CONFIG_KASAN_VMALLOC
+#define VMALLOC_END	ALIGN_DOWN(ioremap_bot, PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
+#else
+#define VMALLOC_END	ioremap_bot
+#endif
+
+#ifndef __ASSEMBLER__
+#include <linux/sched.h>
+#include <linux/threads.h>
+#include <linux/page_table_check.h>
+
+/* Bits to mask out from a PGD to get to the PUD page */
+#define PGD_MASKED_BITS		0
+
+#define pgd_ERROR(e) \
+	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+/*
+ * Bits in a linux-style PTE.  These match the bits in the
+ * (hardware-defined) PowerPC PTE as closely as possible.
+ */
+
+#define pte_clear(mm, addr, ptep) \
+	do { pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, 0, 0); } while (0)
+
+#define pmd_none(pmd)		(!pmd_val(pmd))
+#define	pmd_bad(pmd)		(pmd_val(pmd) & _PMD_BAD)
+#define	pmd_present(pmd)	(pmd_val(pmd) & _PMD_PRESENT_MASK)
+static inline void pmd_clear(pmd_t *pmdp)
+{
+	*pmdp = __pmd(0);
+}
+
+
+/*
+ * When flushing the tlb entry for a page, we also need to flush the hash
+ * table entry.  flush_hash_pages is assembler (for speed) in hashtable.S.
+ */
+extern int flush_hash_pages(unsigned context, unsigned long va,
+			    unsigned long pmdval, int count);
+
+/* Add an HPTE to the hash table */
+extern void add_hash_page(unsigned context, unsigned long va,
+			  unsigned long pmdval);
+
+/* Flush an entry from the TLB/hash table */
+static inline void flush_hash_entry(struct mm_struct *mm, pte_t *ptep, unsigned long addr)
+{
+	if (mmu_has_feature(MMU_FTR_HPTE_TABLE)) {
+		unsigned long ptephys = __pa(ptep) & PAGE_MASK;
+
+		flush_hash_pages(mm->context.id, addr, ptephys, 1);
+	}
+}
+
+/*
+ * PTE updates. This function is called whenever an existing
+ * valid PTE is updated. This does -not- include set_pte_at()
+ * which nowadays only sets a new PTE.
+ *
+ * Depending on the type of MMU, we may need to use atomic updates
+ * and the PTE may be either 32 or 64 bit wide. In the later case,
+ * when using atomic updates, only the low part of the PTE is
+ * accessed atomically.
+ */
+static inline pte_basic_t pte_update(struct mm_struct *mm, unsigned long addr, pte_t *p,
+				     unsigned long clr, unsigned long set, int huge)
+{
+	pte_basic_t old;
+
+	if (mmu_has_feature(MMU_FTR_HPTE_TABLE)) {
+		unsigned long tmp;
+
+		asm volatile(
+#ifndef CONFIG_PTE_64BIT
+	"1:	lwarx	%0, 0, %3\n"
+	"	andc	%1, %0, %4\n"
+#else
+	"1:	lwarx	%L0, 0, %3\n"
+	"	lwz	%0, -4(%3)\n"
+	"	andc	%1, %L0, %4\n"
+#endif
+	"	or	%1, %1, %5\n"
+	"	stwcx.	%1, 0, %3\n"
+	"	bne-	1b"
+		: "=&r" (old), "=&r" (tmp), "=m" (*p)
+#ifndef CONFIG_PTE_64BIT
+		: "r" (p),
+#else
+		: "b" ((unsigned long)(p) + 4),
+#endif
+		  "r" (clr), "r" (set), "m" (*p)
+		: "cc" );
+	} else {
+		old = pte_val(*p);
+
+		*p = __pte((old & ~(pte_basic_t)clr) | set);
+	}
+
+	return old;
+}
+
+/*
+ * 2.6 calls this without flushing the TLB entry; this is wrong
+ * for our hash-based implementation, we fix that up here.
+ */
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+static inline bool __ptep_test_and_clear_young(struct mm_struct *mm,
+		unsigned long addr, pte_t *ptep)
+{
+	unsigned long old;
+	old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0);
+	if (old & _PAGE_HASHPTE)
+		flush_hash_entry(mm, ptep, addr);
+
+	return (old & _PAGE_ACCESSED) != 0;
+}
+#define ptep_test_and_clear_young(__vma, __addr, __ptep) \
+	__ptep_test_and_clear_young((__vma)->vm_mm, __addr, __ptep)
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				       pte_t *ptep)
+{
+	pte_t old_pte = __pte(pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, 0, 0));
+
+	page_table_check_pte_clear(mm, addr, old_pte);
+
+	return old_pte;
+}
+
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
+				      pte_t *ptep)
+{
+	pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
+}
+
+static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
+					   pte_t *ptep, pte_t entry,
+					   unsigned long address,
+					   int psize)
+{
+	unsigned long set = pte_val(entry) &
+		(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_RW | _PAGE_EXEC);
+
+	pte_update(vma->vm_mm, address, ptep, 0, set, 0);
+
+	flush_tlb_page(vma, address);
+}
+
+#define __HAVE_ARCH_PTE_SAME
+#define pte_same(A,B)	(((pte_val(A) ^ pte_val(B)) & ~_PAGE_HASHPTE) == 0)
+
+#define pmd_pfn(pmd)		(pmd_val(pmd) >> PAGE_SHIFT)
+#define pmd_page(pmd)		pfn_to_page(pmd_pfn(pmd))
+
+/*
+ * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that
+ * are !pte_none() && !pte_present().
+ *
+ * Format of swap PTEs (32bit PTEs):
+ *
+ *                         1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 3 3
+ *   0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
+ *   <----------------- offset --------------------> < type -> E H P
+ *
+ *   E is the exclusive marker that is not stored in swap entries.
+ *   _PAGE_PRESENT (P) and __PAGE_HASHPTE (H) must be 0.
+ *
+ * For 64bit PTEs, the offset is extended by 32bit.
+ */
+#define __swp_type(entry)		((entry).val & 0x1f)
+#define __swp_offset(entry)		((entry).val >> 5)
+#define __swp_entry(type, offset)	((swp_entry_t) { ((type) & 0x1f) | ((offset) << 5) })
+#define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) >> 3 })
+#define __swp_entry_to_pte(x)		((pte_t) { (x).val << 3 })
+
+static inline bool pte_swp_exclusive(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
+}
+
+static inline pte_t pte_swp_mkexclusive(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SWP_EXCLUSIVE);
+}
+
+static inline pte_t pte_swp_clear_exclusive(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_SWP_EXCLUSIVE);
+}
+
+/* Generic accessors to PTE bits */
+static inline bool pte_read(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_READ);
+}
+
+static inline bool pte_write(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_WRITE);
+}
+
+static inline int pte_dirty(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_DIRTY); }
+static inline int pte_young(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_ACCESSED); }
+static inline int pte_special(pte_t pte)	{ return !!(pte_val(pte) & _PAGE_SPECIAL); }
+static inline int pte_none(pte_t pte)		{ return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; }
+static inline bool pte_exec(pte_t pte)		{ return pte_val(pte) & _PAGE_EXEC; }
+
+static inline int pte_present(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_PRESENT;
+}
+
+static inline bool pte_hw_valid(pte_t pte)
+{
+	return pte_val(pte) & _PAGE_PRESENT;
+}
+
+static inline bool pte_hashpte(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_HASHPTE);
+}
+
+static inline bool pte_ci(pte_t pte)
+{
+	return !!(pte_val(pte) & _PAGE_NO_CACHE);
+}
+
+/*
+ * We only find page table entry in the last level
+ * Hence no need for other accessors
+ */
+#define pte_access_permitted pte_access_permitted
+static inline bool pte_access_permitted(pte_t pte, bool write)
+{
+	/*
+	 * A read-only access is controlled by _PAGE_READ bit.
+	 * We have _PAGE_READ set for WRITE
+	 */
+	if (!pte_present(pte) || !pte_read(pte))
+		return false;
+
+	if (write && !pte_write(pte))
+		return false;
+
+	return true;
+}
+
+static inline bool pte_user_accessible_page(struct mm_struct *mm, unsigned long addr, pte_t pte)
+{
+	return pte_present(pte) && !is_kernel_addr(addr);
+}
+
+/* Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ *
+ * Even if PTEs can be unsigned long long, a PFN is always an unsigned
+ * long for now.
+ */
+static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
+{
+	return __pte(((pte_basic_t)(pfn) << PTE_RPN_SHIFT) |
+		     pgprot_val(pgprot));
+}
+
+/* Generic modifiers for PTE bits */
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_WRITE);
+}
+
+static inline pte_t pte_exprotect(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_EXEC);
+}
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_DIRTY);
+}
+
+static inline pte_t pte_mkold(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
+}
+
+static inline pte_t pte_mkexec(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_EXEC);
+}
+
+static inline pte_t pte_mkpte(pte_t pte)
+{
+	return pte;
+}
+
+static inline pte_t pte_mkwrite_novma(pte_t pte)
+{
+	/*
+	 * write implies read, hence set both
+	 */
+	return __pte(pte_val(pte) | _PAGE_RW);
+}
+
+static inline pte_t pte_mkdirty(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_DIRTY);
+}
+
+static inline pte_t pte_mkyoung(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_ACCESSED);
+}
+
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SPECIAL);
+}
+
+static inline pte_t pte_mkhuge(pte_t pte)
+{
+	return pte;
+}
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	return __pte((pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot));
+}
+
+
+
+/* This low level function performs the actual PTE insertion
+ * Setting the PTE depends on the MMU type and other factors.
+ *
+ * First case is 32-bit in UP mode with 32-bit PTEs, we need to preserve
+ * the _PAGE_HASHPTE bit since we may not have invalidated the previous
+ * translation in the hash yet (done in a subsequent flush_tlb_xxx())
+ * and see we need to keep track that this PTE needs invalidating.
+ *
+ * Second case is 32-bit with 64-bit PTE.  In this case, we
+ * can just store as long as we do the two halves in the right order
+ * with a barrier in between. This is possible because we take care,
+ * in the hash code, to pre-invalidate if the PTE was already hashed,
+ * which synchronizes us with any concurrent invalidation.
+ * In the percpu case, we fallback to the simple update preserving
+ * the hash bits (ie, same as the non-SMP case).
+ *
+ * Third case is 32-bit in SMP mode with 32-bit PTEs. We use the
+ * helper pte_update() which does an atomic update. We need to do that
+ * because a concurrent invalidation can clear _PAGE_HASHPTE. If it's a
+ * per-CPU PTE such as a kmap_atomic, we also do a simple update preserving
+ * the hash bits instead.
+ */
+static inline void __set_pte_at(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte, int percpu)
+{
+	if ((!IS_ENABLED(CONFIG_SMP) && !IS_ENABLED(CONFIG_PTE_64BIT)) || percpu) {
+		*ptep = __pte((pte_val(*ptep) & _PAGE_HASHPTE) |
+			      (pte_val(pte) & ~_PAGE_HASHPTE));
+	} else if (IS_ENABLED(CONFIG_PTE_64BIT)) {
+		if (pte_val(*ptep) & _PAGE_HASHPTE)
+			flush_hash_entry(mm, ptep, addr);
+
+		asm volatile("stw%X0 %2,%0; eieio; stw%X1 %L2,%1" :
+			     "=m" (*ptep), "=m" (*((unsigned char *)ptep+4)) :
+			     "r" (pte) : "memory");
+	} else {
+		pte_update(mm, addr, ptep, ~_PAGE_HASHPTE, pte_val(pte), 0);
+	}
+}
+
+/*
+ * Macro to mark a page protection value as "uncacheable".
+ */
+
+#define _PAGE_CACHE_CTL	(_PAGE_COHERENT | _PAGE_GUARDED | _PAGE_NO_CACHE | \
+			 _PAGE_WRITETHRU)
+
+#define pgprot_noncached pgprot_noncached
+static inline pgprot_t pgprot_noncached(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_NO_CACHE | _PAGE_GUARDED);
+}
+
+#define pgprot_noncached_wc pgprot_noncached_wc
+static inline pgprot_t pgprot_noncached_wc(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_NO_CACHE);
+}
+
+#define pgprot_cached pgprot_cached
+static inline pgprot_t pgprot_cached(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_COHERENT);
+}
+
+#define pgprot_cached_wthru pgprot_cached_wthru
+static inline pgprot_t pgprot_cached_wthru(pgprot_t prot)
+{
+	return __pgprot((pgprot_val(prot) & ~_PAGE_CACHE_CTL) |
+			_PAGE_COHERENT | _PAGE_WRITETHRU);
+}
+
+#define pgprot_cached_noncoherent pgprot_cached_noncoherent
+static inline pgprot_t pgprot_cached_noncoherent(pgprot_t prot)
+{
+	return __pgprot(pgprot_val(prot) & ~_PAGE_CACHE_CTL);
+}
+
+#define pgprot_writecombine pgprot_writecombine
+static inline pgprot_t pgprot_writecombine(pgprot_t prot)
+{
+	return pgprot_noncached_wc(prot);
+}
+
+#endif /* !__ASSEMBLER__ */
+
+#endif /*  _ASM_POWERPC_BOOK3S_32_PGTABLE_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/32/tlbflush.h

@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_32_TLBFLUSH_H
+#define _ASM_POWERPC_BOOK3S_32_TLBFLUSH_H
+
+#include <linux/build_bug.h>
+
+#define MMU_NO_CONTEXT      (0)
+/*
+ * TLB flushing for "classic" hash-MMU 32-bit CPUs, 6xx, 7xx, 7xxx
+ */
+void hash__flush_tlb_mm(struct mm_struct *mm);
+void hash__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
+void hash__flush_range(struct mm_struct *mm, unsigned long start, unsigned long end);
+void hash__flush_gather(struct mmu_gather *tlb);
+
+#ifdef CONFIG_SMP
+void _tlbie(unsigned long address);
+#else
+static inline void _tlbie(unsigned long address)
+{
+	asm volatile ("tlbie %0; sync" : : "r" (address) : "memory");
+}
+#endif
+void _tlbia(void);
+
+/*
+ * Called at the end of a mmu_gather operation to make sure the
+ * TLB flush is completely done.
+ */
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+	/* 603 needs to flush the whole TLB here since it doesn't use a hash table. */
+	if (mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		hash__flush_gather(tlb);
+	else
+		_tlbia();
+}
+
+static inline void flush_range(struct mm_struct *mm, unsigned long start, unsigned long end)
+{
+	start &= PAGE_MASK;
+	if (mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		hash__flush_range(mm, start, end);
+	else if (end - start <= PAGE_SIZE)
+		_tlbie(start);
+	else
+		_tlbia();
+}
+
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+	if (mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		hash__flush_tlb_mm(mm);
+	else
+		_tlbia();
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
+{
+	if (mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		hash__flush_tlb_page(vma, vmaddr);
+	else
+		_tlbie(vmaddr);
+}
+
+static inline void
+flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
+{
+	flush_range(vma->vm_mm, start, end);
+}
+
+static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	flush_range(&init_mm, start, end);
+}
+
+static inline void local_flush_tlb_page(struct vm_area_struct *vma,
+					unsigned long vmaddr)
+{
+	flush_tlb_page(vma, vmaddr);
+}
+
+static inline void local_flush_tlb_page_psize(struct mm_struct *mm,
+					      unsigned long vmaddr, int psize)
+{
+	flush_range(mm, vmaddr, vmaddr);
+}
+
+static inline void local_flush_tlb_mm(struct mm_struct *mm)
+{
+	flush_tlb_mm(mm);
+}
+
+#endif /* _ASM_POWERPC_BOOK3S_32_TLBFLUSH_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/64/hash-4k.h

@@ -0,0 +1,173 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_HASH_4K_H
+#define _ASM_POWERPC_BOOK3S_64_HASH_4K_H
+
+#define H_PTE_INDEX_SIZE  9  // size: 8B << 9 = 4KB, maps: 2^9 x   4KB =   2MB
+#define H_PMD_INDEX_SIZE  7  // size: 8B << 7 = 1KB, maps: 2^7 x   2MB = 256MB
+#define H_PUD_INDEX_SIZE  9  // size: 8B << 9 = 4KB, maps: 2^9 x 256MB = 128GB
+#define H_PGD_INDEX_SIZE  9  // size: 8B << 9 = 4KB, maps: 2^9 x 128GB =  64TB
+
+/*
+ * Each context is 512TB. But on 4k we restrict our max TASK size to 64TB
+ * Hence also limit max EA bits to 64TB.
+ */
+#define MAX_EA_BITS_PER_CONTEXT		46
+
+
+/*
+ * Our page table limit us to 64TB. For 64TB physical memory, we only need 64GB
+ * of vmemmap space. To better support sparse memory layout, we use 61TB
+ * linear map range, 1TB of vmalloc, 1TB of I/O and 1TB of vmememmap.
+ */
+#define REGION_SHIFT		(40)
+#define H_KERN_MAP_SIZE		(ASM_CONST(1) << REGION_SHIFT)
+
+/*
+ * Limits the linear mapping range
+ */
+#define H_MAX_PHYSMEM_BITS	46
+
+/*
+ * Define the address range of the kernel non-linear virtual area (61TB)
+ */
+#define H_KERN_VIRT_START	ASM_CONST(0xc0003d0000000000)
+
+#ifndef __ASSEMBLER__
+#define H_PTE_TABLE_SIZE	(sizeof(pte_t) << H_PTE_INDEX_SIZE)
+#define H_PMD_TABLE_SIZE	(sizeof(pmd_t) << H_PMD_INDEX_SIZE)
+#define H_PUD_TABLE_SIZE	(sizeof(pud_t) << H_PUD_INDEX_SIZE)
+#define H_PGD_TABLE_SIZE	(sizeof(pgd_t) << H_PGD_INDEX_SIZE)
+
+#define H_PAGE_F_GIX_SHIFT	_PAGE_PA_MAX
+#define H_PAGE_F_SECOND		_RPAGE_PKEY_BIT0 /* HPTE is in 2ndary HPTEG */
+#define H_PAGE_F_GIX		(_RPAGE_RPN43 | _RPAGE_RPN42 | _RPAGE_RPN41)
+#define H_PAGE_BUSY		_RPAGE_RSV1
+#define H_PAGE_HASHPTE		_RPAGE_PKEY_BIT4
+
+/* PTE flags to conserve for HPTE identification */
+#define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_HASHPTE | \
+			 H_PAGE_F_SECOND | H_PAGE_F_GIX)
+/*
+ * Not supported by 4k linux page size
+ */
+#define H_PAGE_4K_PFN	0x0
+#define H_PAGE_THP_HUGE 0x0
+#define H_PAGE_COMBO	0x0
+
+/* 8 bytes per each pte entry */
+#define H_PTE_FRAG_SIZE_SHIFT  (H_PTE_INDEX_SIZE + 3)
+#define H_PTE_FRAG_NR	(PAGE_SIZE >> H_PTE_FRAG_SIZE_SHIFT)
+#define H_PMD_FRAG_SIZE_SHIFT  (H_PMD_INDEX_SIZE + 3)
+#define H_PMD_FRAG_NR	(PAGE_SIZE >> H_PMD_FRAG_SIZE_SHIFT)
+
+/* memory key bits, only 8 keys supported */
+#define H_PTE_PKEY_BIT4	0
+#define H_PTE_PKEY_BIT3	0
+#define H_PTE_PKEY_BIT2	_RPAGE_PKEY_BIT3
+#define H_PTE_PKEY_BIT1	_RPAGE_PKEY_BIT2
+#define H_PTE_PKEY_BIT0	_RPAGE_PKEY_BIT1
+
+
+/*
+ * On all 4K setups, remap_4k_pfn() equates to remap_pfn_range()
+ */
+#define remap_4k_pfn(vma, addr, pfn, prot)	\
+	remap_pfn_range((vma), (addr), (pfn), PAGE_SIZE, (prot))
+
+/*
+ * With 4K page size the real_pte machinery is all nops.
+ */
+static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep, int offset)
+{
+	return (real_pte_t){pte};
+}
+
+#define __rpte_to_pte(r)	((r).pte)
+
+static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
+{
+	return pte_val(__rpte_to_pte(rpte)) >> H_PAGE_F_GIX_SHIFT;
+}
+
+#define pte_iterate_hashed_subpages(rpte, psize, va, index, shift)       \
+	do {							         \
+		index = 0;					         \
+		shift = mmu_psize_defs[psize].shift;		         \
+
+#define pte_iterate_hashed_end() } while(0)
+
+/*
+ * We expect this to be called only for user addresses or kernel virtual
+ * addresses other than the linear mapping.
+ */
+#define pte_pagesize_index(mm, addr, pte)	MMU_PAGE_4K
+
+/*
+ * 4K PTE format is different from 64K PTE format. Saving the hash_slot is just
+ * a matter of returning the PTE bits that need to be modified. On 64K PTE,
+ * things are a little more involved and hence needs many more parameters to
+ * accomplish the same. However we want to abstract this out from the caller by
+ * keeping the prototype consistent across the two formats.
+ */
+static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte,
+					 unsigned int subpg_index, unsigned long hidx,
+					 int offset)
+{
+	return (hidx << H_PAGE_F_GIX_SHIFT) &
+		(H_PAGE_F_SECOND | H_PAGE_F_GIX);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+
+static inline char *get_hpte_slot_array(pmd_t *pmdp)
+{
+	BUG();
+	return NULL;
+}
+
+static inline unsigned int hpte_valid(unsigned char *hpte_slot_array, int index)
+{
+	BUG();
+	return 0;
+}
+
+static inline unsigned int hpte_hash_index(unsigned char *hpte_slot_array,
+					   int index)
+{
+	BUG();
+	return 0;
+}
+
+static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array,
+					unsigned int index, unsigned int hidx)
+{
+	BUG();
+}
+
+static inline int hash__pmd_trans_huge(pmd_t pmd)
+{
+	return 0;
+}
+
+static inline pmd_t hash__pmd_mkhuge(pmd_t pmd)
+{
+	BUG();
+	return pmd;
+}
+
+extern unsigned long hash__pmd_hugepage_update(struct mm_struct *mm,
+					   unsigned long addr, pmd_t *pmdp,
+					   unsigned long clr, unsigned long set);
+extern pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma,
+				   unsigned long address, pmd_t *pmdp);
+extern void hash__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+					 pgtable_t pgtable);
+extern pgtable_t hash__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
+extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm,
+				       unsigned long addr, pmd_t *pmdp);
+extern int hash__has_transparent_hugepage(void);
+#endif
+
+#endif /* !__ASSEMBLER__ */
+
+#endif /* _ASM_POWERPC_BOOK3S_64_HASH_4K_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/64/hash-64k.h

@@ -0,0 +1,286 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_HASH_64K_H
+#define _ASM_POWERPC_BOOK3S_64_HASH_64K_H
+
+#define H_PTE_INDEX_SIZE   8  // size: 8B <<  8 = 2KB, maps 2^8  x 64KB = 16MB
+#define H_PMD_INDEX_SIZE  10  // size: 8B << 10 = 8KB, maps 2^10 x 16MB = 16GB
+#define H_PUD_INDEX_SIZE  10  // size: 8B << 10 = 8KB, maps 2^10 x 16GB = 16TB
+#define H_PGD_INDEX_SIZE   8  // size: 8B <<  8 = 2KB, maps 2^8  x 16TB =  4PB
+
+/*
+ * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS
+ * if we increase SECTIONS_WIDTH we will not store node details in page->flags and
+ * page_to_nid does a page->section->node lookup
+ * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce
+ * memory requirements with large number of sections.
+ * 51 bits is the max physical real address on POWER9
+ */
+#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME)
+#define H_MAX_PHYSMEM_BITS	51
+#else
+#define H_MAX_PHYSMEM_BITS	46
+#endif
+
+/*
+ * Each context is 512TB size. SLB miss for first context/default context
+ * is handled in the hotpath.
+ */
+#define MAX_EA_BITS_PER_CONTEXT		49
+#define REGION_SHIFT		MAX_EA_BITS_PER_CONTEXT
+
+/*
+ * We use one context for each MAP area.
+ */
+#define H_KERN_MAP_SIZE		(1UL << MAX_EA_BITS_PER_CONTEXT)
+
+/*
+ * Define the address range of the kernel non-linear virtual area
+ * 2PB
+ */
+#define H_KERN_VIRT_START	ASM_CONST(0xc008000000000000)
+
+/*
+ * 64k aligned address free up few of the lower bits of RPN for us
+ * We steal that here. For more deatils look at pte_pfn/pfn_pte()
+ */
+#define H_PAGE_COMBO	_RPAGE_RPN0 /* this is a combo 4k page */
+#define H_PAGE_4K_PFN	_RPAGE_RPN1 /* PFN is for a single 4k page */
+#define H_PAGE_BUSY	_RPAGE_RSV1     /* software: PTE & hash are busy */
+#define H_PAGE_HASHPTE	_RPAGE_RPN43	/* PTE has associated HPTE */
+
+/* memory key bits. */
+#define H_PTE_PKEY_BIT4		_RPAGE_PKEY_BIT4
+#define H_PTE_PKEY_BIT3		_RPAGE_PKEY_BIT3
+#define H_PTE_PKEY_BIT2		_RPAGE_PKEY_BIT2
+#define H_PTE_PKEY_BIT1		_RPAGE_PKEY_BIT1
+#define H_PTE_PKEY_BIT0		_RPAGE_PKEY_BIT0
+
+/*
+ * We need to differentiate between explicit huge page and THP huge
+ * page, since THP huge page also need to track real subpage details
+ */
+#define H_PAGE_THP_HUGE  H_PAGE_4K_PFN
+
+/* PTE flags to conserve for HPTE identification */
+#define _PAGE_HPTEFLAGS (H_PAGE_BUSY | H_PAGE_HASHPTE | H_PAGE_COMBO)
+/*
+ * We use a 2K PTE page fragment and another 2K for storing
+ * real_pte_t hash index
+ * 8 bytes per each pte entry and another 8 bytes for storing
+ * slot details.
+ */
+#define H_PTE_FRAG_SIZE_SHIFT  (H_PTE_INDEX_SIZE + 3 + 1)
+#define H_PTE_FRAG_NR	(PAGE_SIZE >> H_PTE_FRAG_SIZE_SHIFT)
+
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)
+#define H_PMD_FRAG_SIZE_SHIFT  (H_PMD_INDEX_SIZE + 3 + 1)
+#else
+#define H_PMD_FRAG_SIZE_SHIFT  (H_PMD_INDEX_SIZE + 3)
+#endif
+#define H_PMD_FRAG_NR	(PAGE_SIZE >> H_PMD_FRAG_SIZE_SHIFT)
+
+#ifndef __ASSEMBLER__
+#include <asm/errno.h>
+
+/*
+ * With 64K pages on hash table, we have a special PTE format that
+ * uses a second "half" of the page table to encode sub-page information
+ * in order to deal with 64K made of 4K HW pages. Thus we override the
+ * generic accessors and iterators here
+ */
+#define __real_pte __real_pte
+static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep, int offset)
+{
+	real_pte_t rpte;
+	unsigned long *hidxp;
+
+	rpte.pte = pte;
+
+	/*
+	 * Ensure that we do not read the hidx before we read the PTE. Because
+	 * the writer side is expected to finish writing the hidx first followed
+	 * by the PTE, by using smp_wmb(). pte_set_hash_slot() ensures that.
+	 */
+	smp_rmb();
+
+	hidxp = (unsigned long *)(ptep + offset);
+	rpte.hidx = *hidxp;
+	return rpte;
+}
+
+/*
+ * shift the hidx representation by one-modulo-0xf; i.e hidx 0 is respresented
+ * as 1, 1 as 2,... , and 0xf as 0.  This convention lets us represent a
+ * invalid hidx 0xf with a 0x0 bit value. PTEs are anyway zero'd when
+ * allocated. We dont have to zero them gain; thus save on the initialization.
+ */
+#define HIDX_UNSHIFT_BY_ONE(x) ((x + 0xfUL) & 0xfUL) /* shift backward by one */
+#define HIDX_SHIFT_BY_ONE(x) ((x + 0x1UL) & 0xfUL)   /* shift forward by one */
+#define HIDX_BITS(x, index)  (x << (index << 2))
+#define BITS_TO_HIDX(x, index)  ((x >> (index << 2)) & 0xfUL)
+#define INVALID_RPTE_HIDX  0x0UL
+
+static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
+{
+	return HIDX_UNSHIFT_BY_ONE(BITS_TO_HIDX(rpte.hidx, index));
+}
+
+/*
+ * Commit the hidx and return PTE bits that needs to be modified. The caller is
+ * expected to modify the PTE bits accordingly and commit the PTE to memory.
+ */
+static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte,
+					 unsigned int subpg_index,
+					 unsigned long hidx, int offset)
+{
+	unsigned long *hidxp = (unsigned long *)(ptep + offset);
+
+	rpte.hidx &= ~HIDX_BITS(0xfUL, subpg_index);
+	*hidxp = rpte.hidx  | HIDX_BITS(HIDX_SHIFT_BY_ONE(hidx), subpg_index);
+
+	/*
+	 * Anyone reading PTE must ensure hidx bits are read after reading the
+	 * PTE by using the read-side barrier smp_rmb(). __real_pte() can be
+	 * used for that.
+	 */
+	smp_wmb();
+
+	/* No PTE bits to be modified, return 0x0UL */
+	return 0x0UL;
+}
+
+#define __rpte_to_pte(r)	((r).pte)
+extern bool __rpte_sub_valid(real_pte_t rpte, unsigned long index);
+/*
+ * Trick: we set __end to va + 64k, which happens works for
+ * a 16M page as well as we want only one iteration
+ */
+#define pte_iterate_hashed_subpages(rpte, psize, vpn, index, shift)	\
+	do {								\
+		unsigned long __end = vpn + (1UL << (PAGE_SHIFT - VPN_SHIFT));	\
+		unsigned __split = (psize == MMU_PAGE_4K ||		\
+				    psize == MMU_PAGE_64K_AP);		\
+		shift = mmu_psize_defs[psize].shift;			\
+		for (index = 0; vpn < __end; index++,			\
+			     vpn += (1L << (shift - VPN_SHIFT))) {	\
+		if (!__split || __rpte_sub_valid(rpte, index))
+
+#define pte_iterate_hashed_end()  } } while(0)
+
+#define pte_pagesize_index(mm, addr, pte)	\
+	(((pte) & H_PAGE_COMBO)? MMU_PAGE_4K: MMU_PAGE_64K)
+
+extern int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
+			   unsigned long pfn, unsigned long size, pgprot_t);
+static inline int hash__remap_4k_pfn(struct vm_area_struct *vma, unsigned long addr,
+				 unsigned long pfn, pgprot_t prot)
+{
+	if (pfn > (PTE_RPN_MASK >> PAGE_SHIFT)) {
+		WARN(1, "remap_4k_pfn called with wrong pfn value\n");
+		return -EINVAL;
+	}
+	return remap_pfn_range(vma, addr, pfn, PAGE_SIZE,
+			       __pgprot(pgprot_val(prot) | H_PAGE_4K_PFN));
+}
+
+#define H_PTE_TABLE_SIZE	PTE_FRAG_SIZE
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined (CONFIG_HUGETLB_PAGE)
+#define H_PMD_TABLE_SIZE	((sizeof(pmd_t) << PMD_INDEX_SIZE) + \
+				 (sizeof(unsigned long) << PMD_INDEX_SIZE))
+#else
+#define H_PMD_TABLE_SIZE	(sizeof(pmd_t) << PMD_INDEX_SIZE)
+#endif
+#ifdef CONFIG_HUGETLB_PAGE
+#define H_PUD_TABLE_SIZE	((sizeof(pud_t) << PUD_INDEX_SIZE) +	\
+				 (sizeof(unsigned long) << PUD_INDEX_SIZE))
+#else
+#define H_PUD_TABLE_SIZE	(sizeof(pud_t) << PUD_INDEX_SIZE)
+#endif
+#define H_PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline char *get_hpte_slot_array(pmd_t *pmdp)
+{
+	/*
+	 * The hpte hindex is stored in the pgtable whose address is in the
+	 * second half of the PMD
+	 *
+	 * Order this load with the test for pmd_trans_huge in the caller
+	 */
+	smp_rmb();
+	return *(char **)(pmdp + PTRS_PER_PMD);
+
+
+}
+/*
+ * The linux hugepage PMD now include the pmd entries followed by the address
+ * to the stashed pgtable_t. The stashed pgtable_t contains the hpte bits.
+ * [ 000 | 1 bit secondary | 3 bit hidx | 1 bit valid]. We use one byte per
+ * each HPTE entry. With 16MB hugepage and 64K HPTE we need 256 entries and
+ * with 4K HPTE we need 4096 entries. Both will fit in a 4K pgtable_t.
+ *
+ * The top three bits are intentionally left as zero. This memory location
+ * are also used as normal page PTE pointers. So if we have any pointers
+ * left around while we collapse a hugepage, we need to make sure
+ * _PAGE_PRESENT bit of that is zero when we look at them
+ */
+static inline unsigned int hpte_valid(unsigned char *hpte_slot_array, int index)
+{
+	return hpte_slot_array[index] & 0x1;
+}
+
+static inline unsigned int hpte_hash_index(unsigned char *hpte_slot_array,
+					   int index)
+{
+	return hpte_slot_array[index] >> 1;
+}
+
+static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array,
+					unsigned int index, unsigned int hidx)
+{
+	hpte_slot_array[index] = (hidx << 1) | 0x1;
+}
+
+/*
+ *
+ * For core kernel code by design pmd_trans_huge is never run on any hugetlbfs
+ * page. The hugetlbfs page table walking and mangling paths are totally
+ * separated form the core VM paths and they're differentiated by
+ *  VM_HUGETLB being set on vm_flags well before any pmd_trans_huge could run.
+ *
+ * pmd_trans_huge() is defined as false at build time if
+ * CONFIG_TRANSPARENT_HUGEPAGE=n to optimize away code blocks at build
+ * time in such case.
+ *
+ * For ppc64 we need to differntiate from explicit hugepages from THP, because
+ * for THP we also track the subpage details at the pmd level. We don't do
+ * that for explicit huge pages.
+ *
+ */
+static inline int hash__pmd_trans_huge(pmd_t pmd)
+{
+	return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE)) ==
+		  (_PAGE_PTE | H_PAGE_THP_HUGE));
+}
+
+static inline pmd_t hash__pmd_mkhuge(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | (_PAGE_PTE | H_PAGE_THP_HUGE));
+}
+
+extern unsigned long hash__pmd_hugepage_update(struct mm_struct *mm,
+					   unsigned long addr, pmd_t *pmdp,
+					   unsigned long clr, unsigned long set);
+extern pmd_t hash__pmdp_collapse_flush(struct vm_area_struct *vma,
+				   unsigned long address, pmd_t *pmdp);
+extern void hash__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+					 pgtable_t pgtable);
+extern pgtable_t hash__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
+extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm,
+				       unsigned long addr, pmd_t *pmdp);
+extern int hash__has_transparent_hugepage(void);
+#endif /*  CONFIG_TRANSPARENT_HUGEPAGE */
+
+#endif	/* __ASSEMBLER__ */
+
+#endif /* _ASM_POWERPC_BOOK3S_64_HASH_64K_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/64/hash-pkey.h

@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_HASH_PKEY_H
+#define _ASM_POWERPC_BOOK3S_64_HASH_PKEY_H
+
+/*  We use key 3 for KERNEL */
+#define HASH_DEFAULT_KERNEL_KEY (HPTE_R_KEY_BIT0 | HPTE_R_KEY_BIT1)
+
+static inline u64 hash__vmflag_to_pte_pkey_bits(u64 vm_flags)
+{
+	return (((vm_flags & VM_PKEY_BIT0) ? H_PTE_PKEY_BIT0 : 0x0UL) |
+		((vm_flags & VM_PKEY_BIT1) ? H_PTE_PKEY_BIT1 : 0x0UL) |
+		((vm_flags & VM_PKEY_BIT2) ? H_PTE_PKEY_BIT2 : 0x0UL) |
+		((vm_flags & VM_PKEY_BIT3) ? H_PTE_PKEY_BIT3 : 0x0UL) |
+		((vm_flags & VM_PKEY_BIT4) ? H_PTE_PKEY_BIT4 : 0x0UL));
+}
+
+static inline u64 pte_to_hpte_pkey_bits(u64 pteflags, unsigned long flags)
+{
+	unsigned long pte_pkey;
+
+	pte_pkey = (((pteflags & H_PTE_PKEY_BIT4) ? HPTE_R_KEY_BIT4 : 0x0UL) |
+		    ((pteflags & H_PTE_PKEY_BIT3) ? HPTE_R_KEY_BIT3 : 0x0UL) |
+		    ((pteflags & H_PTE_PKEY_BIT2) ? HPTE_R_KEY_BIT2 : 0x0UL) |
+		    ((pteflags & H_PTE_PKEY_BIT1) ? HPTE_R_KEY_BIT1 : 0x0UL) |
+		    ((pteflags & H_PTE_PKEY_BIT0) ? HPTE_R_KEY_BIT0 : 0x0UL));
+
+	if (mmu_has_feature(MMU_FTR_KUAP) ||
+	    mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) {
+		if ((pte_pkey == 0) && (flags & HPTE_USE_KERNEL_KEY))
+			return HASH_DEFAULT_KERNEL_KEY;
+	}
+
+	return pte_pkey;
+}
+
+static inline u16 hash__pte_to_pkey_bits(u64 pteflags)
+{
+	return (((pteflags & H_PTE_PKEY_BIT4) ? 0x10 : 0x0UL) |
+		((pteflags & H_PTE_PKEY_BIT3) ? 0x8 : 0x0UL) |
+		((pteflags & H_PTE_PKEY_BIT2) ? 0x4 : 0x0UL) |
+		((pteflags & H_PTE_PKEY_BIT1) ? 0x2 : 0x0UL) |
+		((pteflags & H_PTE_PKEY_BIT0) ? 0x1 : 0x0UL));
+}
+
+#endif

linux-7.2.3/arch/powerpc/include/asm/book3s/64/hash.h

@@ -0,0 +1,300 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_HASH_H
+#define _ASM_POWERPC_BOOK3S_64_HASH_H
+#ifdef __KERNEL__
+
+#include <asm/asm-const.h>
+#include <asm/book3s/64/slice.h>
+
+/*
+ * Common bits between 4K and 64K pages in a linux-style PTE.
+ * Additional bits may be defined in pgtable-hash64-*.h
+ *
+ */
+#define H_PTE_NONE_MASK		_PAGE_HPTEFLAGS
+
+#ifdef CONFIG_PPC_64K_PAGES
+#include <asm/book3s/64/hash-64k.h>
+#else
+#include <asm/book3s/64/hash-4k.h>
+#endif
+
+#define H_PTRS_PER_PTE		(1 << H_PTE_INDEX_SIZE)
+#define H_PTRS_PER_PMD		(1 << H_PMD_INDEX_SIZE)
+#define H_PTRS_PER_PUD		(1 << H_PUD_INDEX_SIZE)
+
+/* Bits to set in a PMD/PUD/PGD entry valid bit*/
+#define HASH_PMD_VAL_BITS		(0x8000000000000000UL)
+#define HASH_PUD_VAL_BITS		(0x8000000000000000UL)
+#define HASH_PGD_VAL_BITS		(0x8000000000000000UL)
+
+/*
+ * Size of EA range mapped by our pagetables.
+ */
+#define H_PGTABLE_EADDR_SIZE	(H_PTE_INDEX_SIZE + H_PMD_INDEX_SIZE + \
+				 H_PUD_INDEX_SIZE + H_PGD_INDEX_SIZE + PAGE_SHIFT)
+#define H_PGTABLE_RANGE		(ASM_CONST(1) << H_PGTABLE_EADDR_SIZE)
+/*
+ * Top 2 bits are ignored in page table walk.
+ */
+#define EA_MASK			(~(0xcUL << 60))
+
+/*
+ * We store the slot details in the second half of page table.
+ * Increase the pud level table so that hugetlb ptes can be stored
+ * at pud level.
+ */
+#if defined(CONFIG_HUGETLB_PAGE) &&  defined(CONFIG_PPC_64K_PAGES)
+#define H_PUD_CACHE_INDEX	(H_PUD_INDEX_SIZE + 1)
+#else
+#define H_PUD_CACHE_INDEX	(H_PUD_INDEX_SIZE)
+#endif
+
+/*
+ * +------------------------------+
+ * |                              |
+ * |                              |
+ * |                              |
+ * +------------------------------+  Kernel virtual map end (0xc00e000000000000)
+ * |                              |
+ * |                              |
+ * |      512TB/16TB of vmemmap   |
+ * |                              |
+ * |                              |
+ * +------------------------------+  Kernel vmemmap  start
+ * |                              |
+ * |      512TB/16TB of IO map    |
+ * |                              |
+ * +------------------------------+  Kernel IO map start
+ * |                              |
+ * |      512TB/16TB of vmap      |
+ * |                              |
+ * +------------------------------+  Kernel virt start (0xc008000000000000)
+ * |                              |
+ * |                              |
+ * |                              |
+ * +------------------------------+  Kernel linear (0xc.....)
+ */
+
+#define H_VMALLOC_START		H_KERN_VIRT_START
+#define H_VMALLOC_SIZE		H_KERN_MAP_SIZE
+#define H_VMALLOC_END		(H_VMALLOC_START + H_VMALLOC_SIZE)
+
+#define H_KERN_IO_START		H_VMALLOC_END
+#define H_KERN_IO_SIZE		H_KERN_MAP_SIZE
+#define H_KERN_IO_END		(H_KERN_IO_START + H_KERN_IO_SIZE)
+
+#define H_VMEMMAP_START		H_KERN_IO_END
+#define H_VMEMMAP_SIZE		H_KERN_MAP_SIZE
+#define H_VMEMMAP_END		(H_VMEMMAP_START + H_VMEMMAP_SIZE)
+
+#define NON_LINEAR_REGION_ID(ea)	((((unsigned long)ea - H_KERN_VIRT_START) >> REGION_SHIFT) + 2)
+
+/*
+ * Region IDs
+ */
+#define USER_REGION_ID		0
+#define LINEAR_MAP_REGION_ID	1
+#define VMALLOC_REGION_ID	NON_LINEAR_REGION_ID(H_VMALLOC_START)
+#define IO_REGION_ID		NON_LINEAR_REGION_ID(H_KERN_IO_START)
+#define VMEMMAP_REGION_ID	NON_LINEAR_REGION_ID(H_VMEMMAP_START)
+#define INVALID_REGION_ID	(VMEMMAP_REGION_ID + 1)
+
+/*
+ * Defines the address of the vmemap area, in its own region on
+ * hash table CPUs.
+ */
+
+/* PTEIDX nibble */
+#define _PTEIDX_SECONDARY	0x8
+#define _PTEIDX_GROUP_IX	0x7
+
+#define H_PMD_BAD_BITS		(PTE_TABLE_SIZE-1)
+#define H_PUD_BAD_BITS		(PMD_TABLE_SIZE-1)
+
+#ifndef __ASSEMBLER__
+static inline int get_region_id(unsigned long ea)
+{
+	int region_id;
+	int id = (ea >> 60UL);
+
+	if (id == 0)
+		return USER_REGION_ID;
+
+	if (id != (PAGE_OFFSET >> 60))
+		return INVALID_REGION_ID;
+
+	if (ea < H_KERN_VIRT_START)
+		return LINEAR_MAP_REGION_ID;
+
+	BUILD_BUG_ON(NON_LINEAR_REGION_ID(H_VMALLOC_START) != 2);
+
+	region_id = NON_LINEAR_REGION_ID(ea);
+	return region_id;
+}
+
+static inline int hash__pmd_same(pmd_t pmd_a, pmd_t pmd_b)
+{
+	return (((pmd_raw(pmd_a) ^ pmd_raw(pmd_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0);
+}
+
+#define	hash__pmd_bad(pmd)		(pmd_val(pmd) & H_PMD_BAD_BITS)
+
+/*
+ * pud comparison that will work with both pte and page table pointer.
+ */
+static inline int hash__pud_same(pud_t pud_a, pud_t pud_b)
+{
+	return (((pud_raw(pud_a) ^ pud_raw(pud_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0);
+}
+#define	hash__pud_bad(pud)		(pud_val(pud) & H_PUD_BAD_BITS)
+
+static inline int hash__p4d_bad(p4d_t p4d)
+{
+	return (p4d_val(p4d) == 0);
+}
+#ifdef CONFIG_STRICT_KERNEL_RWX
+extern void hash__mark_rodata_ro(void);
+extern void hash__mark_initmem_nx(void);
+#endif
+
+extern void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
+			    pte_t *ptep, unsigned long pte, int huge);
+unsigned long htab_convert_pte_flags(unsigned long pteflags, unsigned long flags);
+/* Atomic PTE updates */
+static inline unsigned long hash__pte_update_one(pte_t *ptep, unsigned long clr,
+						 unsigned long set)
+{
+	__be64 old_be, tmp_be;
+
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%3		# pte_update\n\
+	and.	%1,%0,%6\n\
+	bne-	1b \n\
+	andc	%1,%0,%4 \n\
+	or	%1,%1,%7\n\
+	stdcx.	%1,0,%3 \n\
+	bne-	1b"
+	: "=&r" (old_be), "=&r" (tmp_be), "=m" (*ptep)
+	: "r" (ptep), "r" (cpu_to_be64(clr)), "m" (*ptep),
+	  "r" (cpu_to_be64(H_PAGE_BUSY)), "r" (cpu_to_be64(set))
+	: "cc" );
+
+	return be64_to_cpu(old_be);
+}
+
+static inline unsigned long hash__pte_update(struct mm_struct *mm,
+					 unsigned long addr,
+					 pte_t *ptep, unsigned long clr,
+					 unsigned long set,
+					 int huge)
+{
+	unsigned long old;
+
+	old = hash__pte_update_one(ptep, clr, set);
+
+	if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && huge) {
+		unsigned int psize = get_slice_psize(mm, addr);
+		int nb, i;
+
+		if (psize == MMU_PAGE_16M)
+			nb = SZ_16M / PMD_SIZE;
+		else if (psize == MMU_PAGE_16G)
+			nb = SZ_16G / PUD_SIZE;
+		else
+			nb = 1;
+
+		WARN_ON_ONCE(nb == 1);	/* Should never happen */
+
+		for (i = 1; i < nb; i++)
+			hash__pte_update_one(ptep + i, clr, set);
+	}
+	/* huge pages use the old page table lock */
+	if (!huge)
+		assert_pte_locked(mm, addr);
+
+	if (old & H_PAGE_HASHPTE)
+		hpte_need_flush(mm, addr, ptep, old, huge);
+
+	return old;
+}
+
+/* Set the dirty and/or accessed bits atomically in a linux PTE, this
+ * function doesn't need to flush the hash entry
+ */
+static inline void hash__ptep_set_access_flags(pte_t *ptep, pte_t entry)
+{
+	__be64 old, tmp, val, mask;
+
+	mask = cpu_to_be64(_PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_READ | _PAGE_WRITE |
+			   _PAGE_EXEC | _PAGE_SOFT_DIRTY);
+
+	val = pte_raw(entry) & mask;
+
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%4\n\
+		and.	%1,%0,%6\n\
+		bne-	1b \n\
+		or	%0,%3,%0\n\
+		stdcx.	%0,0,%4\n\
+		bne-	1b"
+	:"=&r" (old), "=&r" (tmp), "=m" (*ptep)
+	:"r" (val), "r" (ptep), "m" (*ptep), "r" (cpu_to_be64(H_PAGE_BUSY))
+	:"cc");
+}
+
+static inline int hash__pte_same(pte_t pte_a, pte_t pte_b)
+{
+	return (((pte_raw(pte_a) ^ pte_raw(pte_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0);
+}
+
+static inline int hash__pte_none(pte_t pte)
+{
+	return (pte_val(pte) & ~H_PTE_NONE_MASK) == 0;
+}
+
+unsigned long pte_get_hash_gslot(unsigned long vpn, unsigned long shift,
+		int ssize, real_pte_t rpte, unsigned int subpg_index);
+
+/* This low level function performs the actual PTE insertion
+ * Setting the PTE depends on the MMU type and other factors. It's
+ * an horrible mess that I'm not going to try to clean up now but
+ * I'm keeping it in one place rather than spread around
+ */
+static inline void hash__set_pte_at(struct mm_struct *mm, unsigned long addr,
+				  pte_t *ptep, pte_t pte, int percpu)
+{
+	/*
+	 * Anything else just stores the PTE normally. That covers all 64-bit
+	 * cases, and 32-bit non-hash with 32-bit PTEs.
+	 */
+	*ptep = pte;
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
+				   pmd_t *pmdp, unsigned long old_pmd);
+#else
+static inline void hpte_do_hugepage_flush(struct mm_struct *mm,
+					  unsigned long addr, pmd_t *pmdp,
+					  unsigned long old_pmd)
+{
+	WARN(1, "%s called with THP disabled\n", __func__);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+
+int hash__map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot);
+extern int __meminit hash__vmemmap_create_mapping(unsigned long start,
+					      unsigned long page_size,
+					      unsigned long phys);
+extern void hash__vmemmap_remove_mapping(unsigned long start,
+				     unsigned long page_size);
+
+int hash__create_section_mapping(unsigned long start, unsigned long end,
+				 int nid, pgprot_t prot);
+int hash__remove_section_mapping(unsigned long start, unsigned long end);
+
+#endif /* !__ASSEMBLER__ */
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_BOOK3S_64_HASH_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/64/hugetlb.h

@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_HUGETLB_H
+#define _ASM_POWERPC_BOOK3S_64_HUGETLB_H
+
+#include <asm/firmware.h>
+
+/*
+ * For radix we want generic code to handle hugetlb. But then if we want
+ * both hash and radix to be enabled together we need to workaround the
+ * limitations.
+ */
+void radix__flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
+void radix__local_flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
+
+extern void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+						unsigned long addr, pte_t *ptep,
+						pte_t old_pte, pte_t pte);
+
+static inline int hstate_get_psize(struct hstate *hstate)
+{
+	unsigned long shift;
+
+	shift = huge_page_shift(hstate);
+	if (shift == mmu_psize_defs[MMU_PAGE_2M].shift)
+		return MMU_PAGE_2M;
+	else if (shift == mmu_psize_defs[MMU_PAGE_1G].shift)
+		return MMU_PAGE_1G;
+	else if (shift == mmu_psize_defs[MMU_PAGE_16M].shift)
+		return MMU_PAGE_16M;
+	else if (shift == mmu_psize_defs[MMU_PAGE_16G].shift)
+		return MMU_PAGE_16G;
+	else {
+		WARN(1, "Wrong huge page shift\n");
+		return mmu_virtual_psize;
+	}
+}
+
+#define __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED
+static inline bool gigantic_page_runtime_supported(void)
+{
+	/*
+	 * We used gigantic page reservation with hypervisor assist in some case.
+	 * We cannot use runtime allocation of gigantic pages in those platforms
+	 * This is hash translation mode LPARs.
+	 */
+	if (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled())
+		return false;
+
+	return true;
+}
+
+#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
+extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep);
+
+#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
+extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep,
+					 pte_t old_pte, pte_t new_pte);
+
+static inline void flush_hugetlb_page(struct vm_area_struct *vma,
+				      unsigned long vmaddr)
+{
+	if (radix_enabled())
+		return radix__flush_hugetlb_page(vma, vmaddr);
+}
+
+void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
+
+static inline int check_and_get_huge_psize(int shift)
+{
+	int mmu_psize;
+
+	if (shift > SLICE_HIGH_SHIFT)
+		return -EINVAL;
+
+	mmu_psize = shift_to_mmu_psize(shift);
+
+	/*
+	 * We need to make sure that for different page sizes reported by
+	 * firmware we only add hugetlb support for page sizes that can be
+	 * supported by linux page table layout.
+	 * For now we have
+	 * Radix: 2M and 1G
+	 * Hash: 16M and 16G
+	 */
+	if (radix_enabled()) {
+		if (mmu_psize != MMU_PAGE_2M && mmu_psize != MMU_PAGE_1G)
+			return -EINVAL;
+	} else {
+		if (mmu_psize != MMU_PAGE_16M && mmu_psize != MMU_PAGE_16G)
+			return -EINVAL;
+	}
+	return mmu_psize;
+}
+
+#define arch_has_huge_bootmem_alloc arch_has_huge_bootmem_alloc
+
+static inline bool arch_has_huge_bootmem_alloc(void)
+{
+	return (firmware_has_feature(FW_FEATURE_LPAR) && !radix_enabled());
+}
+#endif

linux-7.2.3/arch/powerpc/include/asm/book3s/64/kexec.h

@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_POWERPC_BOOK3S_64_KEXEC_H_
+#define _ASM_POWERPC_BOOK3S_64_KEXEC_H_
+
+#include <asm/plpar_wrappers.h>
+
+#define reset_sprs reset_sprs
+static inline void reset_sprs(void)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_206)) {
+		mtspr(SPRN_AMR, 0);
+		mtspr(SPRN_UAMOR, 0);
+	}
+
+	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+		mtspr(SPRN_IAMR, 0);
+		if (cpu_has_feature(CPU_FTR_HVMODE))
+			mtspr(SPRN_CIABR, 0);
+		else
+			plpar_set_ciabr(0);
+	}
+
+	if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+		mtspr(SPRN_DEXCR, 0);
+		mtspr(SPRN_HASHKEYR, 0);
+	}
+
+	/*  Do we need isync()? We are going via a kexec reset */
+	isync();
+}
+
+#endif

linux-7.2.3/arch/powerpc/include/asm/book3s/64/kup.h

@@ -0,0 +1,416 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_KUP_H
+#define _ASM_POWERPC_BOOK3S_64_KUP_H
+
+#include <linux/const.h>
+#include <asm/reg.h>
+
+#define AMR_KUAP_BLOCK_READ	UL(0x5455555555555555)
+#define AMR_KUAP_BLOCK_WRITE	UL(0xa8aaaaaaaaaaaaaa)
+#define AMR_KUEP_BLOCKED	UL(0x5455555555555555)
+#define AMR_KUAP_BLOCKED	(AMR_KUAP_BLOCK_READ | AMR_KUAP_BLOCK_WRITE)
+
+#ifdef __ASSEMBLER__
+
+.macro kuap_user_restore gpr1, gpr2
+#if defined(CONFIG_PPC_PKEY)
+	BEGIN_MMU_FTR_SECTION_NESTED(67)
+	b	100f  // skip_restore_amr
+	END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_PKEY, 67)
+	/*
+	 * AMR and IAMR are going to be different when
+	 * returning to userspace.
+	 */
+	ld	\gpr1, STACK_REGS_AMR(r1)
+
+	/*
+	 * If kuap feature is not enabled, do the mtspr
+	 * only if AMR value is different.
+	 */
+	BEGIN_MMU_FTR_SECTION_NESTED(68)
+	mfspr	\gpr2, SPRN_AMR
+	cmpd	\gpr1, \gpr2
+	beq	99f
+	END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_KUAP, 68)
+
+	isync
+	mtspr	SPRN_AMR, \gpr1
+99:
+	/*
+	 * Restore IAMR only when returning to userspace
+	 */
+	ld	\gpr1, STACK_REGS_IAMR(r1)
+
+	/*
+	 * If kuep feature is not enabled, do the mtspr
+	 * only if IAMR value is different.
+	 */
+	BEGIN_MMU_FTR_SECTION_NESTED(69)
+	mfspr	\gpr2, SPRN_IAMR
+	cmpd	\gpr1, \gpr2
+	beq	100f
+	END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_BOOK3S_KUEP, 69)
+
+	isync
+	mtspr	SPRN_IAMR, \gpr1
+
+100: //skip_restore_amr
+	/* No isync required, see kuap_user_restore() */
+#endif
+.endm
+
+.macro kuap_kernel_restore gpr1, gpr2
+#if defined(CONFIG_PPC_PKEY)
+
+	BEGIN_MMU_FTR_SECTION_NESTED(67)
+	/*
+	 * AMR is going to be mostly the same since we are
+	 * returning to the kernel. Compare and do a mtspr.
+	 */
+	ld	\gpr2, STACK_REGS_AMR(r1)
+	mfspr	\gpr1, SPRN_AMR
+	cmpd	\gpr1, \gpr2
+	beq	100f
+	isync
+	mtspr	SPRN_AMR, \gpr2
+	/*
+	 * No isync required, see kuap_restore_amr()
+	 * No need to restore IAMR when returning to kernel space.
+	 */
+100:
+	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_KUAP, 67)
+#endif
+.endm
+
+#ifdef CONFIG_PPC_KUAP
+.macro kuap_check_amr gpr1, gpr2
+#ifdef CONFIG_PPC_KUAP_DEBUG
+	BEGIN_MMU_FTR_SECTION_NESTED(67)
+	mfspr	\gpr1, SPRN_AMR
+	/* Prevent access to userspace using any key values */
+	LOAD_REG_IMMEDIATE(\gpr2, AMR_KUAP_BLOCKED)
+999:	tdne	\gpr1, \gpr2
+	EMIT_WARN_ENTRY 999b, __FILE__, __LINE__, (BUGFLAG_WARNING | BUGFLAG_ONCE)
+	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_KUAP, 67)
+#endif
+.endm
+#endif
+
+/*
+ *	if (pkey) {
+ *
+ *		save AMR -> stack;
+ *		if (kuap) {
+ *			if (AMR != BLOCKED)
+ *				KUAP_BLOCKED -> AMR;
+ *		}
+ *		if (from_user) {
+ *			save IAMR -> stack;
+ *			if (kuep) {
+ *				KUEP_BLOCKED ->IAMR
+ *			}
+ *		}
+ *		return;
+ *	}
+ *
+ *	if (kuap) {
+ *		if (from_kernel) {
+ *			save AMR -> stack;
+ *			if (AMR != BLOCKED)
+ *				KUAP_BLOCKED -> AMR;
+ *		}
+ *
+ *	}
+ */
+.macro kuap_save_amr_and_lock gpr1, gpr2, use_cr, msr_pr_cr
+#if defined(CONFIG_PPC_PKEY)
+
+	/*
+	 * if both pkey and kuap is disabled, nothing to do
+	 */
+	BEGIN_MMU_FTR_SECTION_NESTED(68)
+	b	100f  // skip_save_amr
+	END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_PKEY | MMU_FTR_KUAP, 68)
+
+	/*
+	 * if pkey is disabled and we are entering from userspace
+	 * don't do anything.
+	 */
+	BEGIN_MMU_FTR_SECTION_NESTED(67)
+	.ifnb \msr_pr_cr
+	/*
+	 * Without pkey we are not changing AMR outside the kernel
+	 * hence skip this completely.
+	 */
+	bne	\msr_pr_cr, 100f  // from userspace
+	.endif
+        END_MMU_FTR_SECTION_NESTED_IFCLR(MMU_FTR_PKEY, 67)
+
+	/*
+	 * pkey is enabled or pkey is disabled but entering from kernel
+	 */
+	mfspr	\gpr1, SPRN_AMR
+	std	\gpr1, STACK_REGS_AMR(r1)
+
+	/*
+	 * update kernel AMR with AMR_KUAP_BLOCKED only
+	 * if KUAP feature is enabled
+	 */
+	BEGIN_MMU_FTR_SECTION_NESTED(69)
+	LOAD_REG_IMMEDIATE(\gpr2, AMR_KUAP_BLOCKED)
+	cmpd	\use_cr, \gpr1, \gpr2
+	beq	\use_cr, 102f
+	/*
+	 * We don't isync here because we very recently entered via an interrupt
+	 */
+	mtspr	SPRN_AMR, \gpr2
+	isync
+102:
+	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_KUAP, 69)
+
+	/*
+	 * if entering from kernel we don't need save IAMR
+	 */
+	.ifnb \msr_pr_cr
+	beq	\msr_pr_cr, 100f // from kernel space
+	mfspr	\gpr1, SPRN_IAMR
+	std	\gpr1, STACK_REGS_IAMR(r1)
+
+	/*
+	 * update kernel IAMR with AMR_KUEP_BLOCKED only
+	 * if KUEP feature is enabled
+	 */
+	BEGIN_MMU_FTR_SECTION_NESTED(70)
+	LOAD_REG_IMMEDIATE(\gpr2, AMR_KUEP_BLOCKED)
+	mtspr	SPRN_IAMR, \gpr2
+	isync
+	END_MMU_FTR_SECTION_NESTED_IFSET(MMU_FTR_BOOK3S_KUEP, 70)
+	.endif
+
+100: // skip_save_amr
+#endif
+.endm
+
+#else /* !__ASSEMBLER__ */
+
+#include <linux/jump_label.h>
+#include <linux/sched.h>
+
+DECLARE_STATIC_KEY_FALSE(uaccess_flush_key);
+
+#ifdef CONFIG_PPC_PKEY
+
+extern u64 __ro_after_init default_uamor;
+extern u64 __ro_after_init default_amr;
+extern u64 __ro_after_init default_iamr;
+
+#include <asm/mmu.h>
+#include <asm/ptrace.h>
+
+/* usage of kthread_use_mm() should inherit the
+ * AMR value of the operating address space. But, the AMR value is
+ * thread-specific and we inherit the address space and not thread
+ * access restrictions. Because of this ignore AMR value when accessing
+ * userspace via kernel thread.
+ */
+static __always_inline u64 current_thread_amr(void)
+{
+	if (current->thread.regs)
+		return current->thread.regs->amr;
+	return default_amr;
+}
+
+static __always_inline u64 current_thread_iamr(void)
+{
+	if (current->thread.regs)
+		return current->thread.regs->iamr;
+	return default_iamr;
+}
+#endif /* CONFIG_PPC_PKEY */
+
+#ifdef CONFIG_PPC_KUAP
+
+static __always_inline void kuap_user_restore(struct pt_regs *regs)
+{
+	bool restore_amr = false, restore_iamr = false;
+	unsigned long amr, iamr;
+
+	if (!mmu_has_feature(MMU_FTR_PKEY))
+		return;
+
+	if (!mmu_has_feature(MMU_FTR_KUAP)) {
+		amr = mfspr(SPRN_AMR);
+		if (amr != regs->amr)
+			restore_amr = true;
+	} else {
+		restore_amr = true;
+	}
+
+	if (!mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) {
+		iamr = mfspr(SPRN_IAMR);
+		if (iamr != regs->iamr)
+			restore_iamr = true;
+	} else {
+		restore_iamr = true;
+	}
+
+
+	if (restore_amr || restore_iamr) {
+		isync();
+		if (restore_amr)
+			mtspr(SPRN_AMR, regs->amr);
+		if (restore_iamr)
+			mtspr(SPRN_IAMR, regs->iamr);
+	}
+	/*
+	 * No isync required here because we are about to rfi
+	 * back to previous context before any user accesses
+	 * would be made, which is a CSI.
+	 */
+}
+
+static __always_inline void __kuap_kernel_restore(struct pt_regs *regs, unsigned long amr)
+{
+	if (likely(regs->amr == amr))
+		return;
+
+	isync();
+	mtspr(SPRN_AMR, regs->amr);
+	/*
+	 * No isync required here because we are about to rfi
+	 * back to previous context before any user accesses
+	 * would be made, which is a CSI.
+	 *
+	 * No need to restore IAMR when returning to kernel space.
+	 */
+}
+
+static __always_inline unsigned long __kuap_get_and_assert_locked(void)
+{
+	unsigned long amr = mfspr(SPRN_AMR);
+
+	if (IS_ENABLED(CONFIG_PPC_KUAP_DEBUG)) /* kuap_check_amr() */
+		WARN_ON_ONCE(amr != AMR_KUAP_BLOCKED);
+	return amr;
+}
+#define __kuap_get_and_assert_locked __kuap_get_and_assert_locked
+
+/* __kuap_lock() not required, book3s/64 does that in ASM */
+
+/*
+ * We support individually allowing read or write, but we don't support nesting
+ * because that would require an expensive read/modify write of the AMR.
+ */
+
+static __always_inline unsigned long get_kuap(void)
+{
+	/*
+	 * We return AMR_KUAP_BLOCKED when we don't support KUAP because
+	 * prevent_user_access_return needs to return AMR_KUAP_BLOCKED to
+	 * cause restore_user_access to do a flush.
+	 *
+	 * This has no effect in terms of actually blocking things on hash,
+	 * so it doesn't break anything.
+	 */
+	if (!mmu_has_feature(MMU_FTR_KUAP))
+		return AMR_KUAP_BLOCKED;
+
+	return mfspr(SPRN_AMR);
+}
+
+static __always_inline void set_kuap(unsigned long value)
+{
+	if (!mmu_has_feature(MMU_FTR_KUAP))
+		return;
+
+	/*
+	 * ISA v3.0B says we need a CSI (Context Synchronising Instruction) both
+	 * before and after the move to AMR. See table 6 on page 1134.
+	 */
+	isync();
+	mtspr(SPRN_AMR, value);
+	isync();
+}
+
+static __always_inline bool
+__bad_kuap_fault(struct pt_regs *regs, unsigned long address, bool is_write)
+{
+	/*
+	 * For radix this will be a storage protection fault (DSISR_PROTFAULT).
+	 * For hash this will be a key fault (DSISR_KEYFAULT)
+	 */
+	/*
+	 * We do have exception table entry, but accessing the
+	 * userspace results in fault.  This could be because we
+	 * didn't unlock the AMR or access is denied by userspace
+	 * using a key value that blocks access. We are only interested
+	 * in catching the use case of accessing without unlocking
+	 * the AMR. Hence check for BLOCK_WRITE/READ against AMR.
+	 */
+	if (is_write) {
+		return (regs->amr & AMR_KUAP_BLOCK_WRITE) == AMR_KUAP_BLOCK_WRITE;
+	}
+	return (regs->amr & AMR_KUAP_BLOCK_READ) == AMR_KUAP_BLOCK_READ;
+}
+
+static __always_inline void allow_user_access(void __user *to, unsigned long dir)
+{
+	unsigned long thread_amr = 0;
+
+	// This is written so we can resolve to a single case at build time
+	BUILD_BUG_ON(!__builtin_constant_p(dir));
+
+	if (mmu_has_feature(MMU_FTR_PKEY))
+		thread_amr = current_thread_amr();
+
+	if (dir == KUAP_READ)
+		set_kuap(thread_amr | AMR_KUAP_BLOCK_WRITE);
+	else if (dir == KUAP_WRITE)
+		set_kuap(thread_amr | AMR_KUAP_BLOCK_READ);
+	else if (dir == KUAP_READ_WRITE)
+		set_kuap(thread_amr);
+	else
+		BUILD_BUG();
+}
+
+#else /* CONFIG_PPC_KUAP */
+
+static __always_inline unsigned long get_kuap(void)
+{
+	return AMR_KUAP_BLOCKED;
+}
+
+static __always_inline void set_kuap(unsigned long value) { }
+
+static __always_inline void allow_user_access(void __user *to, unsigned long dir)
+{ }
+
+#endif /* !CONFIG_PPC_KUAP */
+
+static __always_inline void prevent_user_access(unsigned long dir)
+{
+	set_kuap(AMR_KUAP_BLOCKED);
+	if (static_branch_unlikely(&uaccess_flush_key))
+		do_uaccess_flush();
+}
+
+static __always_inline unsigned long prevent_user_access_return(void)
+{
+	unsigned long flags = get_kuap();
+
+	set_kuap(AMR_KUAP_BLOCKED);
+	if (static_branch_unlikely(&uaccess_flush_key))
+		do_uaccess_flush();
+
+	return flags;
+}
+
+static __always_inline void restore_user_access(unsigned long flags)
+{
+	set_kuap(flags);
+	if (static_branch_unlikely(&uaccess_flush_key) && flags == AMR_KUAP_BLOCKED)
+		do_uaccess_flush();
+}
+#endif /* __ASSEMBLER__ */
+
+#endif /* _ASM_POWERPC_BOOK3S_64_KUP_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/64/mmu-hash.h

@@ -0,0 +1,884 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ASM_POWERPC_BOOK3S_64_MMU_HASH_H_
+#define _ASM_POWERPC_BOOK3S_64_MMU_HASH_H_
+/*
+ * PowerPC64 memory management structures
+ *
+ * Dave Engebretsen & Mike Corrigan <{engebret|mikejc}@us.ibm.com>
+ *   PPC64 rework.
+ */
+
+#include <asm/page.h>
+#include <asm/bug.h>
+#include <asm/asm-const.h>
+
+/*
+ * This is necessary to get the definition of PGTABLE_RANGE which we
+ * need for various slices related matters. Note that this isn't the
+ * complete pgtable.h but only a portion of it.
+ */
+#include <asm/book3s/64/pgtable.h>
+#include <asm/book3s/64/slice.h>
+#include <asm/task_size_64.h>
+#include <asm/cpu_has_feature.h>
+
+/*
+ * SLB
+ */
+
+#define SLB_NUM_BOLTED		2
+#define SLB_CACHE_ENTRIES	8
+#define SLB_MIN_SIZE		32
+
+/* Bits in the SLB ESID word */
+#define SLB_ESID_V		ASM_CONST(0x0000000008000000) /* valid */
+
+/* Bits in the SLB VSID word */
+#define SLB_VSID_SHIFT		12
+#define SLB_VSID_SHIFT_256M	SLB_VSID_SHIFT
+#define SLB_VSID_SHIFT_1T	24
+#define SLB_VSID_SSIZE_SHIFT	62
+#define SLB_VSID_B		ASM_CONST(0xc000000000000000)
+#define SLB_VSID_B_256M		ASM_CONST(0x0000000000000000)
+#define SLB_VSID_B_1T		ASM_CONST(0x4000000000000000)
+#define SLB_VSID_KS		ASM_CONST(0x0000000000000800)
+#define SLB_VSID_KP		ASM_CONST(0x0000000000000400)
+#define SLB_VSID_N		ASM_CONST(0x0000000000000200) /* no-execute */
+#define SLB_VSID_L		ASM_CONST(0x0000000000000100)
+#define SLB_VSID_C		ASM_CONST(0x0000000000000080) /* class */
+#define SLB_VSID_LP		ASM_CONST(0x0000000000000030)
+#define SLB_VSID_LP_00		ASM_CONST(0x0000000000000000)
+#define SLB_VSID_LP_01		ASM_CONST(0x0000000000000010)
+#define SLB_VSID_LP_10		ASM_CONST(0x0000000000000020)
+#define SLB_VSID_LP_11		ASM_CONST(0x0000000000000030)
+#define SLB_VSID_LLP		(SLB_VSID_L|SLB_VSID_LP)
+
+#define SLB_VSID_KERNEL		(SLB_VSID_KP)
+#define SLB_VSID_USER		(SLB_VSID_KP|SLB_VSID_KS|SLB_VSID_C)
+
+#define SLBIE_C			(0x08000000)
+#define SLBIE_SSIZE_SHIFT	25
+
+/*
+ * Hash table
+ */
+
+#define HPTES_PER_GROUP 8
+
+#define HPTE_V_SSIZE_SHIFT	62
+#define HPTE_V_AVPN_SHIFT	7
+#define HPTE_V_COMMON_BITS	ASM_CONST(0x000fffffffffffff)
+#define HPTE_V_AVPN		ASM_CONST(0x3fffffffffffff80)
+#define HPTE_V_AVPN_3_0		ASM_CONST(0x000fffffffffff80)
+#define HPTE_V_AVPN_VAL(x)	(((x) & HPTE_V_AVPN) >> HPTE_V_AVPN_SHIFT)
+#define HPTE_V_COMPARE(x,y)	(!(((x) ^ (y)) & 0xffffffffffffff80UL))
+#define HPTE_V_BOLTED		ASM_CONST(0x0000000000000010)
+#define HPTE_V_LOCK		ASM_CONST(0x0000000000000008)
+#define HPTE_V_LARGE		ASM_CONST(0x0000000000000004)
+#define HPTE_V_SECONDARY	ASM_CONST(0x0000000000000002)
+#define HPTE_V_VALID		ASM_CONST(0x0000000000000001)
+
+/*
+ * ISA 3.0 has a different HPTE format.
+ */
+#define HPTE_R_3_0_SSIZE_SHIFT	58
+#define HPTE_R_3_0_SSIZE_MASK	(3ull << HPTE_R_3_0_SSIZE_SHIFT)
+#define HPTE_R_PP0		ASM_CONST(0x8000000000000000)
+#define HPTE_R_TS		ASM_CONST(0x4000000000000000)
+#define HPTE_R_KEY_HI		ASM_CONST(0x3000000000000000)
+#define HPTE_R_KEY_BIT4		ASM_CONST(0x2000000000000000)
+#define HPTE_R_KEY_BIT3		ASM_CONST(0x1000000000000000)
+#define HPTE_R_RPN_SHIFT	12
+#define HPTE_R_RPN		ASM_CONST(0x0ffffffffffff000)
+#define HPTE_R_RPN_3_0		ASM_CONST(0x01fffffffffff000)
+#define HPTE_R_PP		ASM_CONST(0x0000000000000003)
+#define HPTE_R_PPP		ASM_CONST(0x8000000000000003)
+#define HPTE_R_N		ASM_CONST(0x0000000000000004)
+#define HPTE_R_G		ASM_CONST(0x0000000000000008)
+#define HPTE_R_M		ASM_CONST(0x0000000000000010)
+#define HPTE_R_I		ASM_CONST(0x0000000000000020)
+#define HPTE_R_W		ASM_CONST(0x0000000000000040)
+#define HPTE_R_WIMG		ASM_CONST(0x0000000000000078)
+#define HPTE_R_C		ASM_CONST(0x0000000000000080)
+#define HPTE_R_R		ASM_CONST(0x0000000000000100)
+#define HPTE_R_KEY_LO		ASM_CONST(0x0000000000000e00)
+#define HPTE_R_KEY_BIT2		ASM_CONST(0x0000000000000800)
+#define HPTE_R_KEY_BIT1		ASM_CONST(0x0000000000000400)
+#define HPTE_R_KEY_BIT0		ASM_CONST(0x0000000000000200)
+#define HPTE_R_KEY		(HPTE_R_KEY_LO | HPTE_R_KEY_HI)
+
+#define HPTE_V_1TB_SEG		ASM_CONST(0x4000000000000000)
+#define HPTE_V_VRMA_MASK	ASM_CONST(0x4001ffffff000000)
+
+/* Values for PP (assumes Ks=0, Kp=1) */
+#define PP_RWXX	0	/* Supervisor read/write, User none */
+#define PP_RWRX 1	/* Supervisor read/write, User read */
+#define PP_RWRW 2	/* Supervisor read/write, User read/write */
+#define PP_RXRX 3	/* Supervisor read,       User read */
+#define PP_RXXX	(HPTE_R_PP0 | 2)	/* Supervisor read, user none */
+
+/* Fields for tlbiel instruction in architecture 2.06 */
+#define TLBIEL_INVAL_SEL_MASK	0xc00	/* invalidation selector */
+#define  TLBIEL_INVAL_PAGE	0x000	/* invalidate a single page */
+#define  TLBIEL_INVAL_SET_LPID	0x800	/* invalidate a set for current LPID */
+#define  TLBIEL_INVAL_SET	0xc00	/* invalidate a set for all LPIDs */
+#define TLBIEL_INVAL_SET_MASK	0xfff000	/* set number to inval. */
+#define TLBIEL_INVAL_SET_SHIFT	12
+
+#define POWER7_TLB_SETS		128	/* # sets in POWER7 TLB */
+#define POWER8_TLB_SETS		512	/* # sets in POWER8 TLB */
+#define POWER9_TLB_SETS_HASH	256	/* # sets in POWER9 TLB Hash mode */
+#define POWER9_TLB_SETS_RADIX	128	/* # sets in POWER9 TLB Radix mode */
+
+#ifndef __ASSEMBLER__
+
+struct mmu_hash_ops {
+	void            (*hpte_invalidate)(unsigned long slot,
+					   unsigned long vpn,
+					   int bpsize, int apsize,
+					   int ssize, int local);
+	long		(*hpte_updatepp)(unsigned long slot,
+					 unsigned long newpp,
+					 unsigned long vpn,
+					 int bpsize, int apsize,
+					 int ssize, unsigned long flags);
+	void            (*hpte_updateboltedpp)(unsigned long newpp,
+					       unsigned long ea,
+					       int psize, int ssize);
+	long		(*hpte_insert)(unsigned long hpte_group,
+				       unsigned long vpn,
+				       unsigned long prpn,
+				       unsigned long rflags,
+				       unsigned long vflags,
+				       int psize, int apsize,
+				       int ssize);
+	long		(*hpte_remove)(unsigned long hpte_group);
+	int             (*hpte_removebolted)(unsigned long ea,
+					     int psize, int ssize);
+	void		(*flush_hash_range)(unsigned long number, int local);
+	void		(*hugepage_invalidate)(unsigned long vsid,
+					       unsigned long addr,
+					       unsigned char *hpte_slot_array,
+					       int psize, int ssize, int local);
+	int		(*resize_hpt)(unsigned long shift);
+	/*
+	 * Special for kexec.
+	 * To be called in real mode with interrupts disabled. No locks are
+	 * taken as such, concurrent access on pre POWER5 hardware could result
+	 * in a deadlock.
+	 * The linear mapping is destroyed as well.
+	 */
+	void		(*hpte_clear_all)(void);
+};
+extern struct mmu_hash_ops mmu_hash_ops;
+
+struct hash_pte {
+	__be64 v;
+	__be64 r;
+};
+
+extern struct hash_pte *htab_address;
+extern unsigned long htab_size_bytes;
+extern unsigned long htab_hash_mask;
+
+
+static inline int shift_to_mmu_psize(unsigned int shift)
+{
+	int psize;
+
+	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize)
+		if (mmu_psize_defs[psize].shift == shift)
+			return psize;
+	return -1;
+}
+
+static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
+{
+	if (mmu_psize_defs[mmu_psize].shift)
+		return mmu_psize_defs[mmu_psize].shift;
+	BUG();
+}
+
+static inline unsigned int ap_to_shift(unsigned long ap)
+{
+	int psize;
+
+	for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
+		if (mmu_psize_defs[psize].ap == ap)
+			return mmu_psize_defs[psize].shift;
+	}
+
+	return -1;
+}
+
+static inline unsigned long get_sllp_encoding(int psize)
+{
+	unsigned long sllp;
+
+	sllp = ((mmu_psize_defs[psize].sllp & SLB_VSID_L) >> 6) |
+		((mmu_psize_defs[psize].sllp & SLB_VSID_LP) >> 4);
+	return sllp;
+}
+
+#endif /* __ASSEMBLER__ */
+
+/*
+ * Segment sizes.
+ * These are the values used by hardware in the B field of
+ * SLB entries and the first dword of MMU hashtable entries.
+ * The B field is 2 bits; the values 2 and 3 are unused and reserved.
+ */
+#define MMU_SEGSIZE_256M	0
+#define MMU_SEGSIZE_1T		1
+
+/*
+ * encode page number shift.
+ * in order to fit the 78 bit va in a 64 bit variable we shift the va by
+ * 12 bits. This enable us to address upto 76 bit va.
+ * For hpt hash from a va we can ignore the page size bits of va and for
+ * hpte encoding we ignore up to 23 bits of va. So ignoring lower 12 bits ensure
+ * we work in all cases including 4k page size.
+ */
+#define VPN_SHIFT	12
+
+/*
+ * HPTE Large Page (LP) details
+ */
+#define LP_SHIFT	12
+#define LP_BITS		8
+#define LP_MASK(i)	((0xFF >> (i)) << LP_SHIFT)
+
+#ifndef __ASSEMBLER__
+
+static inline int slb_vsid_shift(int ssize)
+{
+	if (ssize == MMU_SEGSIZE_256M)
+		return SLB_VSID_SHIFT;
+	return SLB_VSID_SHIFT_1T;
+}
+
+static inline int segment_shift(int ssize)
+{
+	if (ssize == MMU_SEGSIZE_256M)
+		return SID_SHIFT;
+	return SID_SHIFT_1T;
+}
+
+/*
+ * This array is indexed by the LP field of the HPTE second dword.
+ * Since this field may contain some RPN bits, some entries are
+ * replicated so that we get the same value irrespective of RPN.
+ * The top 4 bits are the page size index (MMU_PAGE_*) for the
+ * actual page size, the bottom 4 bits are the base page size.
+ */
+extern u8 hpte_page_sizes[1 << LP_BITS];
+
+static inline unsigned long __hpte_page_size(unsigned long h, unsigned long l,
+					     bool is_base_size)
+{
+	unsigned int i, lp;
+
+	if (!(h & HPTE_V_LARGE))
+		return 1ul << 12;
+
+	/* Look at the 8 bit LP value */
+	lp = (l >> LP_SHIFT) & ((1 << LP_BITS) - 1);
+	i = hpte_page_sizes[lp];
+	if (!i)
+		return 0;
+	if (!is_base_size)
+		i >>= 4;
+	return 1ul << mmu_psize_defs[i & 0xf].shift;
+}
+
+static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
+{
+	return __hpte_page_size(h, l, 0);
+}
+
+static inline unsigned long hpte_base_page_size(unsigned long h, unsigned long l)
+{
+	return __hpte_page_size(h, l, 1);
+}
+
+/*
+ * The current system page and segment sizes
+ */
+extern int mmu_kernel_ssize;
+extern int mmu_highuser_ssize;
+extern u16 mmu_slb_size;
+extern unsigned long tce_alloc_start, tce_alloc_end;
+
+/*
+ * If the processor supports 64k normal pages but not 64k cache
+ * inhibited pages, we have to be prepared to switch processes
+ * to use 4k pages when they create cache-inhibited mappings.
+ * If this is the case, mmu_ci_restrictions will be set to 1.
+ */
+extern int mmu_ci_restrictions;
+
+/*
+ * This computes the AVPN and B fields of the first dword of a HPTE,
+ * for use when we want to match an existing PTE.  The bottom 7 bits
+ * of the returned value are zero.
+ */
+static inline unsigned long hpte_encode_avpn(unsigned long vpn, int psize,
+					     int ssize)
+{
+	unsigned long v;
+	/*
+	 * The AVA field omits the low-order 23 bits of the 78 bits VA.
+	 * These bits are not needed in the PTE, because the
+	 * low-order b of these bits are part of the byte offset
+	 * into the virtual page and, if b < 23, the high-order
+	 * 23-b of these bits are always used in selecting the
+	 * PTEGs to be searched
+	 */
+	v = (vpn >> (23 - VPN_SHIFT)) & ~(mmu_psize_defs[psize].avpnm);
+	v <<= HPTE_V_AVPN_SHIFT;
+	v |= ((unsigned long) ssize) << HPTE_V_SSIZE_SHIFT;
+	return v;
+}
+
+/*
+ * ISA v3.0 defines a new HPTE format, which differs from the old
+ * format in having smaller AVPN and ARPN fields, and the B field
+ * in the second dword instead of the first.
+ */
+static inline unsigned long hpte_old_to_new_v(unsigned long v)
+{
+	/* trim AVPN, drop B */
+	return v & HPTE_V_COMMON_BITS;
+}
+
+static inline unsigned long hpte_old_to_new_r(unsigned long v, unsigned long r)
+{
+	/* move B field from 1st to 2nd dword, trim ARPN */
+	return (r & ~HPTE_R_3_0_SSIZE_MASK) |
+		(((v) >> HPTE_V_SSIZE_SHIFT) << HPTE_R_3_0_SSIZE_SHIFT);
+}
+
+static inline unsigned long hpte_new_to_old_v(unsigned long v, unsigned long r)
+{
+	/* insert B field */
+	return (v & HPTE_V_COMMON_BITS) |
+		((r & HPTE_R_3_0_SSIZE_MASK) <<
+		 (HPTE_V_SSIZE_SHIFT - HPTE_R_3_0_SSIZE_SHIFT));
+}
+
+static inline unsigned long hpte_new_to_old_r(unsigned long r)
+{
+	/* clear out B field */
+	return r & ~HPTE_R_3_0_SSIZE_MASK;
+}
+
+static inline unsigned long hpte_get_old_v(struct hash_pte *hptep)
+{
+	unsigned long hpte_v;
+
+	hpte_v = be64_to_cpu(hptep->v);
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		hpte_v = hpte_new_to_old_v(hpte_v, be64_to_cpu(hptep->r));
+	return hpte_v;
+}
+
+/*
+ * This function sets the AVPN and L fields of the HPTE  appropriately
+ * using the base page size and actual page size.
+ */
+static inline unsigned long hpte_encode_v(unsigned long vpn, int base_psize,
+					  int actual_psize, int ssize)
+{
+	unsigned long v;
+	v = hpte_encode_avpn(vpn, base_psize, ssize);
+	if (actual_psize != MMU_PAGE_4K)
+		v |= HPTE_V_LARGE;
+	return v;
+}
+
+/*
+ * This function sets the ARPN, and LP fields of the HPTE appropriately
+ * for the page size. We assume the pa is already "clean" that is properly
+ * aligned for the requested page size
+ */
+static inline unsigned long hpte_encode_r(unsigned long pa, int base_psize,
+					  int actual_psize)
+{
+	/* A 4K page needs no special encoding */
+	if (actual_psize == MMU_PAGE_4K)
+		return pa & HPTE_R_RPN;
+	else {
+		unsigned int penc = mmu_psize_defs[base_psize].penc[actual_psize];
+		unsigned int shift = mmu_psize_defs[actual_psize].shift;
+		return (pa & ~((1ul << shift) - 1)) | (penc << LP_SHIFT);
+	}
+}
+
+/*
+ * Build a VPN_SHIFT bit shifted va given VSID, EA and segment size.
+ */
+static inline unsigned long hpt_vpn(unsigned long ea,
+				    unsigned long vsid, int ssize)
+{
+	unsigned long mask;
+	int s_shift = segment_shift(ssize);
+
+	mask = (1ul << (s_shift - VPN_SHIFT)) - 1;
+	return (vsid << (s_shift - VPN_SHIFT)) | ((ea >> VPN_SHIFT) & mask);
+}
+
+/*
+ * This hashes a virtual address
+ */
+static inline unsigned long hpt_hash(unsigned long vpn,
+				     unsigned int shift, int ssize)
+{
+	unsigned long mask;
+	unsigned long hash, vsid;
+
+	/* VPN_SHIFT can be atmost 12 */
+	if (ssize == MMU_SEGSIZE_256M) {
+		mask = (1ul << (SID_SHIFT - VPN_SHIFT)) - 1;
+		hash = (vpn >> (SID_SHIFT - VPN_SHIFT)) ^
+			((vpn & mask) >> (shift - VPN_SHIFT));
+	} else {
+		mask = (1ul << (SID_SHIFT_1T - VPN_SHIFT)) - 1;
+		vsid = vpn >> (SID_SHIFT_1T - VPN_SHIFT);
+		hash = vsid ^ (vsid << 25) ^
+			((vpn & mask) >> (shift - VPN_SHIFT)) ;
+	}
+	return hash & 0x7fffffffffUL;
+}
+
+#define HPTE_LOCAL_UPDATE	0x1
+#define HPTE_NOHPTE_UPDATE	0x2
+#define HPTE_USE_KERNEL_KEY	0x4
+
+long hpte_insert_repeating(unsigned long hash, unsigned long vpn, unsigned long pa,
+			   unsigned long rlags, unsigned long vflags, int psize, int ssize);
+extern int __hash_page_4K(unsigned long ea, unsigned long access,
+			  unsigned long vsid, pte_t *ptep, unsigned long trap,
+			  unsigned long flags, int ssize, int subpage_prot);
+extern int __hash_page_64K(unsigned long ea, unsigned long access,
+			   unsigned long vsid, pte_t *ptep, unsigned long trap,
+			   unsigned long flags, int ssize);
+struct mm_struct;
+unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap);
+extern int hash_page_mm(struct mm_struct *mm, unsigned long ea,
+			unsigned long access, unsigned long trap,
+			unsigned long flags);
+extern int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
+		     unsigned long dsisr);
+void low_hash_fault(struct pt_regs *regs, unsigned long address, int rc);
+int __hash_page(unsigned long trap, unsigned long ea, unsigned long dsisr, unsigned long msr);
+int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
+		     pte_t *ptep, unsigned long trap, unsigned long flags,
+		     int ssize, unsigned int shift, unsigned int mmu_psize);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern int __hash_page_thp(unsigned long ea, unsigned long access,
+			   unsigned long vsid, pmd_t *pmdp, unsigned long trap,
+			   unsigned long flags, int ssize, unsigned int psize);
+#else
+static inline int __hash_page_thp(unsigned long ea, unsigned long access,
+				  unsigned long vsid, pmd_t *pmdp,
+				  unsigned long trap, unsigned long flags,
+				  int ssize, unsigned int psize)
+{
+	BUG();
+	return -1;
+}
+#endif
+extern void hash_failure_debug(unsigned long ea, unsigned long access,
+			       unsigned long vsid, unsigned long trap,
+			       int ssize, int psize, int lpsize,
+			       unsigned long pte);
+extern int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
+			     unsigned long pstart, unsigned long prot,
+			     int psize, int ssize);
+int htab_remove_mapping(unsigned long vstart, unsigned long vend,
+			int psize, int ssize);
+extern void pseries_add_gpage(u64 addr, u64 page_size, unsigned long number_of_pages);
+extern void demote_segment_4k(struct mm_struct *mm, unsigned long addr);
+
+extern void hash__setup_new_exec(void);
+
+#ifdef CONFIG_PPC_PSERIES
+void hpte_init_pseries(void);
+#else
+static inline void hpte_init_pseries(void) { }
+#endif
+
+extern void hpte_init_native(void);
+
+struct slb_entry {
+	u64	esid;
+	u64	vsid;
+};
+
+extern void slb_initialize(void);
+void slb_flush_and_restore_bolted(void);
+void slb_flush_all_realmode(void);
+void __slb_restore_bolted_realmode(void);
+void slb_restore_bolted_realmode(void);
+void slb_save_contents(struct slb_entry *slb_ptr);
+void slb_dump_contents(struct slb_entry *slb_ptr);
+
+extern void slb_vmalloc_update(void);
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
+void slb_set_size(u16 size);
+#else
+static inline void slb_set_size(u16 size) { }
+#endif
+
+#endif /* __ASSEMBLER__ */
+
+/*
+ * VSID allocation (256MB segment)
+ *
+ * We first generate a 37-bit "proto-VSID". Proto-VSIDs are generated
+ * from mmu context id and effective segment id of the address.
+ *
+ * For user processes max context id is limited to MAX_USER_CONTEXT.
+ * more details in get_user_context
+ *
+ * For kernel space get_kernel_context
+ *
+ * The proto-VSIDs are then scrambled into real VSIDs with the
+ * multiplicative hash:
+ *
+ *	VSID = (proto-VSID * VSID_MULTIPLIER) % VSID_MODULUS
+ *
+ * VSID_MULTIPLIER is prime, so in particular it is
+ * co-prime to VSID_MODULUS, making this a 1:1 scrambling function.
+ * Because the modulus is 2^n-1 we can compute it efficiently without
+ * a divide or extra multiply (see below). The scramble function gives
+ * robust scattering in the hash table (at least based on some initial
+ * results).
+ *
+ * We use VSID 0 to indicate an invalid VSID. The means we can't use context id
+ * 0, because a context id of 0 and an EA of 0 gives a proto-VSID of 0, which
+ * will produce a VSID of 0.
+ *
+ * We also need to avoid the last segment of the last context, because that
+ * would give a protovsid of 0x1fffffffff. That will result in a VSID 0
+ * because of the modulo operation in vsid scramble.
+ */
+
+/*
+ * Max Va bits we support as of now is 68 bits. We want 19 bit
+ * context ID.
+ * Restrictions:
+ * GPU has restrictions of not able to access beyond 128TB
+ * (47 bit effective address). We also cannot do more than 20bit PID.
+ * For p4 and p5 which can only do 65 bit VA, we restrict our CONTEXT_BITS
+ * to 16 bits (ie, we can only have 2^16 pids at the same time).
+ */
+#define VA_BITS			68
+#define CONTEXT_BITS		19
+#define ESID_BITS		(VA_BITS - (SID_SHIFT + CONTEXT_BITS))
+#define ESID_BITS_1T		(VA_BITS - (SID_SHIFT_1T + CONTEXT_BITS))
+
+#define ESID_BITS_MASK		((1 << ESID_BITS) - 1)
+#define ESID_BITS_1T_MASK	((1 << ESID_BITS_1T) - 1)
+
+/*
+ * Now certain config support MAX_PHYSMEM more than 512TB. Hence we will need
+ * to use more than one context for linear mapping the kernel.
+ * For vmalloc and memmap, we use just one context with 512TB. With 64 byte
+ * struct page size, we need ony 32 TB in memmap for 2PB (51 bits (MAX_PHYSMEM_BITS)).
+ */
+#if (H_MAX_PHYSMEM_BITS > MAX_EA_BITS_PER_CONTEXT)
+#define MAX_KERNEL_CTX_CNT	(1UL << (H_MAX_PHYSMEM_BITS - MAX_EA_BITS_PER_CONTEXT))
+#else
+#define MAX_KERNEL_CTX_CNT	1
+#endif
+
+#define MAX_VMALLOC_CTX_CNT	1
+#define MAX_IO_CTX_CNT		1
+#define MAX_VMEMMAP_CTX_CNT	1
+
+/*
+ * 256MB segment
+ * The proto-VSID space has 2^(CONTEX_BITS + ESID_BITS) - 1 segments
+ * available for user + kernel mapping. VSID 0 is reserved as invalid, contexts
+ * 1-4 are used for kernel mapping. Each segment contains 2^28 bytes. Each
+ * context maps 2^49 bytes (512TB).
+ *
+ * We also need to avoid the last segment of the last context, because that
+ * would give a protovsid of 0x1fffffffff. That will result in a VSID 0
+ * because of the modulo operation in vsid scramble.
+ *
+ */
+#define MAX_USER_CONTEXT	((ASM_CONST(1) << CONTEXT_BITS) - 2)
+
+// The + 2 accounts for INVALID_REGION and 1 more to avoid overlap with kernel
+#define MIN_USER_CONTEXT	(MAX_KERNEL_CTX_CNT + MAX_VMALLOC_CTX_CNT + \
+				 MAX_IO_CTX_CNT + MAX_VMEMMAP_CTX_CNT + 2)
+
+/*
+ * For platforms that support on 65bit VA we limit the context bits
+ */
+#define MAX_USER_CONTEXT_65BIT_VA ((ASM_CONST(1) << (65 - (SID_SHIFT + ESID_BITS))) - 2)
+
+/*
+ * This should be computed such that protovosid * vsid_mulitplier
+ * doesn't overflow 64 bits. The vsid_mutliplier should also be
+ * co-prime to vsid_modulus. We also need to make sure that number
+ * of bits in multiplied result (dividend) is less than twice the number of
+ * protovsid bits for our modulus optmization to work.
+ *
+ * The below table shows the current values used.
+ * |-------+------------+----------------------+------------+-------------------|
+ * |       | Prime Bits | proto VSID_BITS_65VA | Total Bits | 2* prot VSID_BITS |
+ * |-------+------------+----------------------+------------+-------------------|
+ * | 1T    |         24 |                   25 |         49 |                50 |
+ * |-------+------------+----------------------+------------+-------------------|
+ * | 256MB |         24 |                   37 |         61 |                74 |
+ * |-------+------------+----------------------+------------+-------------------|
+ *
+ * |-------+------------+----------------------+------------+--------------------|
+ * |       | Prime Bits | proto VSID_BITS_68VA | Total Bits | 2* proto VSID_BITS |
+ * |-------+------------+----------------------+------------+--------------------|
+ * | 1T    |         24 |                   28 |         52 |                 56 |
+ * |-------+------------+----------------------+------------+--------------------|
+ * | 256MB |         24 |                   40 |         64 |                 80 |
+ * |-------+------------+----------------------+------------+--------------------|
+ *
+ */
+#define VSID_MULTIPLIER_256M	ASM_CONST(12538073)	/* 24-bit prime */
+#define VSID_BITS_256M		(VA_BITS - SID_SHIFT)
+#define VSID_BITS_65_256M	(65 - SID_SHIFT)
+/*
+ * Modular multiplicative inverse of VSID_MULTIPLIER under modulo VSID_MODULUS
+ */
+#define VSID_MULINV_256M	ASM_CONST(665548017062)
+
+#define VSID_MULTIPLIER_1T	ASM_CONST(12538073)	/* 24-bit prime */
+#define VSID_BITS_1T		(VA_BITS - SID_SHIFT_1T)
+#define VSID_BITS_65_1T		(65 - SID_SHIFT_1T)
+#define VSID_MULINV_1T		ASM_CONST(209034062)
+
+/* 1TB VSID reserved for VRMA */
+#define VRMA_VSID	0x1ffffffUL
+#define USER_VSID_RANGE	(1UL << (ESID_BITS + SID_SHIFT))
+
+/* 4 bits per slice and we have one slice per 1TB */
+#define SLICE_ARRAY_SIZE	(H_PGTABLE_RANGE >> 41)
+#define LOW_SLICE_ARRAY_SZ	(BITS_PER_LONG / BITS_PER_BYTE)
+#define TASK_SLICE_ARRAY_SZ(x)	((x)->hash_context->slb_addr_limit >> 41)
+#ifndef __ASSEMBLER__
+
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+/*
+ * For the sub-page protection option, we extend the PGD with one of
+ * these.  Basically we have a 3-level tree, with the top level being
+ * the protptrs array.  To optimize speed and memory consumption when
+ * only addresses < 4GB are being protected, pointers to the first
+ * four pages of sub-page protection words are stored in the low_prot
+ * array.
+ * Each page of sub-page protection words protects 1GB (4 bytes
+ * protects 64k).  For the 3-level tree, each page of pointers then
+ * protects 8TB.
+ */
+struct subpage_prot_table {
+	unsigned long maxaddr;	/* only addresses < this are protected */
+	unsigned int **protptrs[(TASK_SIZE_USER64 >> 43)];
+	unsigned int *low_prot[4];
+};
+
+#define SBP_L1_BITS		(PAGE_SHIFT - 2)
+#define SBP_L2_BITS		(PAGE_SHIFT - 3)
+#define SBP_L1_COUNT		(1 << SBP_L1_BITS)
+#define SBP_L2_COUNT		(1 << SBP_L2_BITS)
+#define SBP_L2_SHIFT		(PAGE_SHIFT + SBP_L1_BITS)
+#define SBP_L3_SHIFT		(SBP_L2_SHIFT + SBP_L2_BITS)
+
+extern void subpage_prot_free(struct mm_struct *mm);
+#else
+static inline void subpage_prot_free(struct mm_struct *mm) {}
+#endif /* CONFIG_PPC_SUBPAGE_PROT */
+
+/*
+ * One bit per slice. We have lower slices which cover 256MB segments
+ * upto 4G range. That gets us 16 low slices. For the rest we track slices
+ * in 1TB size.
+ */
+struct slice_mask {
+	u64 low_slices;
+	DECLARE_BITMAP(high_slices, SLICE_NUM_HIGH);
+};
+
+struct hash_mm_context {
+	u16 user_psize; /* page size index */
+
+	/* SLB page size encodings*/
+	unsigned char low_slices_psize[LOW_SLICE_ARRAY_SZ];
+	unsigned char high_slices_psize[SLICE_ARRAY_SIZE];
+	unsigned long slb_addr_limit;
+#ifdef CONFIG_PPC_64K_PAGES
+	struct slice_mask mask_64k;
+#endif
+	struct slice_mask mask_4k;
+#ifdef CONFIG_HUGETLB_PAGE
+	struct slice_mask mask_16m;
+	struct slice_mask mask_16g;
+#endif
+
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+	struct subpage_prot_table *spt;
+#endif /* CONFIG_PPC_SUBPAGE_PROT */
+};
+
+#if 0
+/*
+ * The code below is equivalent to this function for arguments
+ * < 2^VSID_BITS, which is all this should ever be called
+ * with.  However gcc is not clever enough to compute the
+ * modulus (2^n-1) without a second multiply.
+ */
+#define vsid_scramble(protovsid, size) \
+	((((protovsid) * VSID_MULTIPLIER_##size) % VSID_MODULUS_##size))
+
+/* simplified form avoiding mod operation */
+#define vsid_scramble(protovsid, size) \
+	({								 \
+		unsigned long x;					 \
+		x = (protovsid) * VSID_MULTIPLIER_##size;		 \
+		x = (x >> VSID_BITS_##size) + (x & VSID_MODULUS_##size); \
+		(x + ((x+1) >> VSID_BITS_##size)) & VSID_MODULUS_##size; \
+	})
+
+#else /* 1 */
+static inline unsigned long vsid_scramble(unsigned long protovsid,
+				  unsigned long vsid_multiplier, int vsid_bits)
+{
+	unsigned long vsid;
+	unsigned long vsid_modulus = ((1UL << vsid_bits) - 1);
+	/*
+	 * We have same multipler for both 256 and 1T segements now
+	 */
+	vsid = protovsid * vsid_multiplier;
+	vsid = (vsid >> vsid_bits) + (vsid & vsid_modulus);
+	return (vsid + ((vsid + 1) >> vsid_bits)) & vsid_modulus;
+}
+
+#endif /* 1 */
+
+/* Returns the segment size indicator for a user address */
+static inline int user_segment_size(unsigned long addr)
+{
+	/* Use 1T segments if possible for addresses >= 1T */
+	if (addr >= (1UL << SID_SHIFT_1T))
+		return mmu_highuser_ssize;
+	return MMU_SEGSIZE_256M;
+}
+
+static inline unsigned long get_vsid(unsigned long context, unsigned long ea,
+				     int ssize)
+{
+	unsigned long va_bits = VA_BITS;
+	unsigned long vsid_bits;
+	unsigned long protovsid;
+
+	/*
+	 * Bad address. We return VSID 0 for that
+	 */
+	if ((ea & EA_MASK)  >= H_PGTABLE_RANGE)
+		return 0;
+
+	if (!mmu_has_feature(MMU_FTR_68_BIT_VA))
+		va_bits = 65;
+
+	if (ssize == MMU_SEGSIZE_256M) {
+		vsid_bits = va_bits - SID_SHIFT;
+		protovsid = (context << ESID_BITS) |
+			((ea >> SID_SHIFT) & ESID_BITS_MASK);
+		return vsid_scramble(protovsid, VSID_MULTIPLIER_256M, vsid_bits);
+	}
+	/* 1T segment */
+	vsid_bits = va_bits - SID_SHIFT_1T;
+	protovsid = (context << ESID_BITS_1T) |
+		((ea >> SID_SHIFT_1T) & ESID_BITS_1T_MASK);
+	return vsid_scramble(protovsid, VSID_MULTIPLIER_1T, vsid_bits);
+}
+
+/*
+ * For kernel space, we use context ids as
+ * below. Range is 512TB per context.
+ *
+ * 0x00001 -  [ 0xc000000000000000 - 0xc001ffffffffffff]
+ * 0x00002 -  [ 0xc002000000000000 - 0xc003ffffffffffff]
+ * 0x00003 -  [ 0xc004000000000000 - 0xc005ffffffffffff]
+ * 0x00004 -  [ 0xc006000000000000 - 0xc007ffffffffffff]
+ *
+ * vmap, IO, vmemap
+ *
+ * 0x00005 -  [ 0xc008000000000000 - 0xc009ffffffffffff]
+ * 0x00006 -  [ 0xc00a000000000000 - 0xc00bffffffffffff]
+ * 0x00007 -  [ 0xc00c000000000000 - 0xc00dffffffffffff]
+ *
+ */
+static inline unsigned long get_kernel_context(unsigned long ea)
+{
+	unsigned long region_id = get_region_id(ea);
+	unsigned long ctx;
+	/*
+	 * Depending on Kernel config, kernel region can have one context
+	 * or more.
+	 */
+	if (region_id == LINEAR_MAP_REGION_ID) {
+		/*
+		 * We already verified ea to be not beyond the addr limit.
+		 */
+		ctx =  1 + ((ea & EA_MASK) >> MAX_EA_BITS_PER_CONTEXT);
+	} else
+		ctx = region_id + MAX_KERNEL_CTX_CNT - 1;
+	return ctx;
+}
+
+/*
+ * This is only valid for addresses >= PAGE_OFFSET
+ */
+static inline unsigned long get_kernel_vsid(unsigned long ea, int ssize)
+{
+	unsigned long context;
+
+	if (!is_kernel_addr(ea))
+		return 0;
+
+	context = get_kernel_context(ea);
+	return get_vsid(context, ea, ssize);
+}
+
+unsigned htab_shift_for_mem_size(unsigned long mem_size);
+
+enum slb_index {
+	LINEAR_INDEX	= 0, /* Kernel linear map  (0xc000000000000000) */
+	KSTACK_INDEX	= 1, /* Kernel stack map */
+};
+
+#define slb_esid_mask(ssize)	\
+	(((ssize) == MMU_SEGSIZE_256M) ? ESID_MASK : ESID_MASK_1T)
+
+static inline unsigned long mk_esid_data(unsigned long ea, int ssize,
+					 enum slb_index index)
+{
+	return (ea & slb_esid_mask(ssize)) | SLB_ESID_V | index;
+}
+
+static inline unsigned long __mk_vsid_data(unsigned long vsid, int ssize,
+					   unsigned long flags)
+{
+	return (vsid << slb_vsid_shift(ssize)) | flags |
+		((unsigned long)ssize << SLB_VSID_SSIZE_SHIFT);
+}
+
+static inline unsigned long mk_vsid_data(unsigned long ea, int ssize,
+					 unsigned long flags)
+{
+	return __mk_vsid_data(get_kernel_vsid(ea, ssize), ssize, flags);
+}
+
+#endif /* __ASSEMBLER__ */
+#endif /* _ASM_POWERPC_BOOK3S_64_MMU_HASH_H_ */

linux-7.2.3/arch/powerpc/include/asm/book3s/64/mmu.h

@@ -0,0 +1,292 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_MMU_H_
+#define _ASM_POWERPC_BOOK3S_64_MMU_H_
+
+#include <asm/page.h>
+
+#ifndef __ASSEMBLER__
+/*
+ * Page size definition
+ *
+ *    shift : is the "PAGE_SHIFT" value for that page size
+ *    sllp  : is a bit mask with the value of SLB L || LP to be or'ed
+ *            directly to a slbmte "vsid" value
+ *    penc  : is the HPTE encoding mask for the "LP" field:
+ *
+ */
+struct mmu_psize_def {
+	unsigned int	shift;	/* number of bits */
+	int		penc[MMU_PAGE_COUNT];	/* HPTE encoding */
+	unsigned int	tlbiel;	/* tlbiel supported for that page size */
+	unsigned long	avpnm;	/* bits to mask out in AVPN in the HPTE */
+	unsigned long   h_rpt_pgsize; /* H_RPT_INVALIDATE page size encoding */
+	union {
+		unsigned long	sllp;	/* SLB L||LP (exact mask to use in slbmte) */
+		unsigned long ap;	/* Ap encoding used by PowerISA 3.0 */
+	};
+};
+extern struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
+#endif /* __ASSEMBLER__ */
+
+/* 64-bit classic hash table MMU */
+#include <asm/book3s/64/mmu-hash.h>
+
+#ifndef __ASSEMBLER__
+/*
+ * ISA 3.0 partition and process table entry format
+ */
+struct prtb_entry {
+	__be64 prtb0;
+	__be64 prtb1;
+};
+extern struct prtb_entry *process_tb;
+
+struct patb_entry {
+	__be64 patb0;
+	__be64 patb1;
+};
+extern struct patb_entry *partition_tb;
+
+/* Bits in patb0 field */
+#define PATB_HR		(1UL << 63)
+#define RPDB_MASK	0x0fffffffffffff00UL
+#define RPDB_SHIFT	(1UL << 8)
+#define RTS1_SHIFT	61		/* top 2 bits of radix tree size */
+#define RTS1_MASK	(3UL << RTS1_SHIFT)
+#define RTS2_SHIFT	5		/* bottom 3 bits of radix tree size */
+#define RTS2_MASK	(7UL << RTS2_SHIFT)
+#define RPDS_MASK	0x1f		/* root page dir. size field */
+
+/* Bits in patb1 field */
+#define PATB_GR		(1UL << 63)	/* guest uses radix; must match HR */
+#define PRTS_MASK	0x1f		/* process table size field */
+#define PRTB_MASK	0x0ffffffffffff000UL
+
+/* Number of supported LPID bits */
+extern unsigned int mmu_lpid_bits;
+
+/* Number of supported PID bits */
+extern unsigned int mmu_pid_bits;
+
+/* Base PID to allocate from */
+extern unsigned int mmu_base_pid;
+
+extern unsigned long __ro_after_init memory_block_size;
+
+#define PRTB_SIZE_SHIFT	(mmu_pid_bits + 4)
+#define PRTB_ENTRIES	(1ul << mmu_pid_bits)
+
+#define PATB_SIZE_SHIFT	(mmu_lpid_bits + 4)
+#define PATB_ENTRIES	(1ul << mmu_lpid_bits)
+
+typedef unsigned long mm_context_id_t;
+struct spinlock;
+
+/* Maximum possible number of NPUs in a system. */
+#define NV_MAX_NPUS 8
+
+typedef struct {
+	union {
+		/*
+		 * We use id as the PIDR content for radix. On hash we can use
+		 * more than one id. The extended ids are used when we start
+		 * having address above 512TB. We allocate one extended id
+		 * for each 512TB. The new id is then used with the 49 bit
+		 * EA to build a new VA. We always use ESID_BITS_1T_MASK bits
+		 * from EA and new context ids to build the new VAs.
+		 */
+		mm_context_id_t id;
+#ifdef CONFIG_PPC_64S_HASH_MMU
+		mm_context_id_t extended_id[TASK_SIZE_USER64/TASK_CONTEXT_SIZE];
+#endif
+	};
+
+	/* Number of bits in the mm_cpumask */
+	atomic_t active_cpus;
+
+	/* Number of users of the external (Nest) MMU */
+	atomic_t copros;
+
+	/* Number of user space windows opened in process mm_context */
+	atomic_t vas_windows;
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
+	struct hash_mm_context *hash_context;
+#endif
+
+	void __user *vdso;
+	/*
+	 * pagetable fragment support
+	 */
+	void *pte_frag;
+	void *pmd_frag;
+#ifdef CONFIG_SPAPR_TCE_IOMMU
+	struct list_head iommu_group_mem_list;
+#endif
+
+#ifdef CONFIG_PPC_MEM_KEYS
+	/*
+	 * Each bit represents one protection key.
+	 * bit set   -> key allocated
+	 * bit unset -> key available for allocation
+	 */
+	u32 pkey_allocation_map;
+	s16 execute_only_pkey; /* key holding execute-only protection */
+#endif
+} mm_context_t;
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
+static inline u16 mm_ctx_user_psize(mm_context_t *ctx)
+{
+	return ctx->hash_context->user_psize;
+}
+
+static inline void mm_ctx_set_user_psize(mm_context_t *ctx, u16 user_psize)
+{
+	ctx->hash_context->user_psize = user_psize;
+}
+
+static inline unsigned char *mm_ctx_low_slices(mm_context_t *ctx)
+{
+	return ctx->hash_context->low_slices_psize;
+}
+
+static inline unsigned char *mm_ctx_high_slices(mm_context_t *ctx)
+{
+	return ctx->hash_context->high_slices_psize;
+}
+
+static inline unsigned long mm_ctx_slb_addr_limit(mm_context_t *ctx)
+{
+	return ctx->hash_context->slb_addr_limit;
+}
+
+static inline void mm_ctx_set_slb_addr_limit(mm_context_t *ctx, unsigned long limit)
+{
+	ctx->hash_context->slb_addr_limit = limit;
+}
+
+static inline struct slice_mask *slice_mask_for_size(mm_context_t *ctx, int psize)
+{
+#ifdef CONFIG_PPC_64K_PAGES
+	if (psize == MMU_PAGE_64K)
+		return &ctx->hash_context->mask_64k;
+#endif
+#ifdef CONFIG_HUGETLB_PAGE
+	if (psize == MMU_PAGE_16M)
+		return &ctx->hash_context->mask_16m;
+	if (psize == MMU_PAGE_16G)
+		return &ctx->hash_context->mask_16g;
+#endif
+	BUG_ON(psize != MMU_PAGE_4K);
+
+	return &ctx->hash_context->mask_4k;
+}
+
+#ifdef CONFIG_PPC_SUBPAGE_PROT
+static inline struct subpage_prot_table *mm_ctx_subpage_prot(mm_context_t *ctx)
+{
+	return ctx->hash_context->spt;
+}
+#endif
+
+/*
+ * The current system page and segment sizes
+ */
+extern int mmu_virtual_psize;
+extern int mmu_vmalloc_psize;
+extern int mmu_io_psize;
+#else /* CONFIG_PPC_64S_HASH_MMU */
+#ifdef CONFIG_PPC_64K_PAGES
+#define mmu_virtual_psize MMU_PAGE_64K
+#else
+#define mmu_virtual_psize MMU_PAGE_4K
+#endif
+#endif
+extern int mmu_linear_psize;
+extern int mmu_vmemmap_psize;
+
+/* MMU initialization */
+void mmu_early_init_devtree(void);
+void hash__early_init_devtree(void);
+void radix__early_init_devtree(void);
+#ifdef CONFIG_PPC_PKEY
+void pkey_early_init_devtree(void);
+#else
+static inline void pkey_early_init_devtree(void) {}
+#endif
+
+extern void hash__early_init_mmu(void);
+extern void radix__early_init_mmu(void);
+static inline void __init early_init_mmu(void)
+{
+	if (radix_enabled())
+		return radix__early_init_mmu();
+	return hash__early_init_mmu();
+}
+extern void hash__early_init_mmu_secondary(void);
+extern void radix__early_init_mmu_secondary(void);
+static inline void early_init_mmu_secondary(void)
+{
+	if (radix_enabled())
+		return radix__early_init_mmu_secondary();
+	return hash__early_init_mmu_secondary();
+}
+
+extern void hash__setup_initial_memory_limit(phys_addr_t first_memblock_base,
+					 phys_addr_t first_memblock_size);
+static inline void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+					      phys_addr_t first_memblock_size)
+{
+	/*
+	 * Hash has more strict restrictions. At this point we don't
+	 * know which translations we will pick. Hence go with hash
+	 * restrictions.
+	 */
+	if (!early_radix_enabled())
+		hash__setup_initial_memory_limit(first_memblock_base,
+						 first_memblock_size);
+}
+
+#ifdef CONFIG_PPC_PSERIES
+void __init radix_init_pseries(void);
+#else
+static inline void radix_init_pseries(void) { }
+#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
+#define arch_clear_mm_cpumask_cpu(cpu, mm)				\
+	do {								\
+		if (cpumask_test_cpu(cpu, mm_cpumask(mm))) {		\
+			dec_mm_active_cpus(mm);				\
+			cpumask_clear_cpu(cpu, mm_cpumask(mm));		\
+		}							\
+	} while (0)
+
+void cleanup_cpu_mmu_context(void);
+#endif
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
+static inline int get_user_context(mm_context_t *ctx, unsigned long ea)
+{
+	int index = ea >> MAX_EA_BITS_PER_CONTEXT;
+
+	if (likely(index < ARRAY_SIZE(ctx->extended_id)))
+		return ctx->extended_id[index];
+
+	/* should never happen */
+	WARN_ON(1);
+	return 0;
+}
+
+static inline unsigned long get_user_vsid(mm_context_t *ctx,
+					  unsigned long ea, int ssize)
+{
+	unsigned long context = get_user_context(ctx, ea);
+
+	return get_vsid(context, ea, ssize);
+}
+#endif
+
+#endif /* __ASSEMBLER__ */
+#endif /* _ASM_POWERPC_BOOK3S_64_MMU_H_ */

linux-7.2.3/arch/powerpc/include/asm/book3s/64/pgalloc.h

@@ -0,0 +1,183 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ASM_POWERPC_BOOK3S_64_PGALLOC_H
+#define _ASM_POWERPC_BOOK3S_64_PGALLOC_H
+/*
+ */
+
+#include <linux/slab.h>
+#include <linux/cpumask.h>
+#include <linux/kmemleak.h>
+#include <linux/percpu.h>
+
+struct vmemmap_backing {
+	struct vmemmap_backing *list;
+	unsigned long phys;
+	unsigned long virt_addr;
+};
+extern struct vmemmap_backing *vmemmap_list;
+
+extern pmd_t *pmd_fragment_alloc(struct mm_struct *, unsigned long);
+extern void pmd_fragment_free(unsigned long *);
+extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift);
+extern void __tlb_remove_table(void *_table);
+void pte_frag_destroy(void *pte_frag);
+
+static inline pgd_t *radix__pgd_alloc(struct mm_struct *mm)
+{
+#ifdef CONFIG_PPC_64K_PAGES
+	return (pgd_t *)__get_free_page(pgtable_gfp_flags(mm, PGALLOC_GFP));
+#else
+	struct page *page;
+	page = alloc_pages(pgtable_gfp_flags(mm, PGALLOC_GFP | __GFP_RETRY_MAYFAIL),
+				4);
+	if (!page)
+		return NULL;
+	return (pgd_t *) page_address(page);
+#endif
+}
+
+static inline void radix__pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+#ifdef CONFIG_PPC_64K_PAGES
+	free_page((unsigned long)pgd);
+#else
+	free_pages((unsigned long)pgd, 4);
+#endif
+}
+
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+	pgd_t *pgd;
+
+	if (radix_enabled())
+		return radix__pgd_alloc(mm);
+
+	pgd = kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
+			       pgtable_gfp_flags(mm, GFP_KERNEL));
+	if (unlikely(!pgd))
+		return pgd;
+
+	/*
+	 * Don't scan the PGD for pointers, it contains references to PUDs but
+	 * those references are not full pointers and so can't be recognised by
+	 * kmemleak.
+	 */
+	kmemleak_no_scan(pgd);
+
+	/*
+	 * With hugetlb, we don't clear the second half of the page table.
+	 * If we share the same slab cache with the pmd or pud level table,
+	 * we need to make sure we zero out the full table on alloc.
+	 * With 4K we don't store slot in the second half. Hence we don't
+	 * need to do this for 4k.
+	 */
+#if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_PPC_64K_PAGES) && \
+	(H_PGD_INDEX_SIZE == H_PUD_CACHE_INDEX)
+	memset(pgd, 0, PGD_TABLE_SIZE);
+#endif
+	return pgd;
+}
+
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	if (radix_enabled())
+		return radix__pgd_free(mm, pgd);
+	kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
+}
+
+static inline void p4d_populate(struct mm_struct *mm, p4d_t *pgd, pud_t *pud)
+{
+	*pgd =  __p4d(__pgtable_ptr_val(pud) | PGD_VAL_BITS);
+}
+
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	pud_t *pud;
+
+	pud = kmem_cache_alloc(PGT_CACHE(PUD_CACHE_INDEX),
+			       pgtable_gfp_flags(mm, GFP_KERNEL));
+	/*
+	 * Tell kmemleak to ignore the PUD, that means don't scan it for
+	 * pointers and don't consider it a leak. PUDs are typically only
+	 * referred to by their PGD, but kmemleak is not able to recognise those
+	 * as pointers, leading to false leak reports.
+	 */
+	kmemleak_ignore(pud);
+
+	return pud;
+}
+
+static inline void __pud_free(pud_t *pud)
+{
+	struct page *page = virt_to_page(pud);
+
+	/*
+	 * Early pud pages allocated via memblock allocator
+	 * can't be directly freed to slab. KFENCE pages have
+	 * both reserved and slab flags set so need to be freed
+	 * kmem_cache_free.
+	 */
+	if (PageReserved(page) && !PageSlab(page))
+		free_reserved_page(page);
+	else
+		kmem_cache_free(PGT_CACHE(PUD_CACHE_INDEX), pud);
+}
+
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	return __pud_free(pud);
+}
+
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+{
+	*pud = __pud(__pgtable_ptr_val(pmd) | PUD_VAL_BITS);
+}
+
+static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
+				  unsigned long address)
+{
+	pgtable_free_tlb(tlb, pud, PUD_INDEX);
+}
+
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return pmd_fragment_alloc(mm, addr);
+}
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+	pmd_fragment_free((unsigned long *)pmd);
+}
+
+static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
+				  unsigned long address)
+{
+	return pgtable_free_tlb(tlb, pmd, PMD_INDEX);
+}
+
+static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
+				       pte_t *pte)
+{
+	*pmd = __pmd(__pgtable_ptr_val(pte) | PMD_VAL_BITS);
+}
+
+static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
+				pgtable_t pte_page)
+{
+	*pmd = __pmd(__pgtable_ptr_val(pte_page) | PMD_VAL_BITS);
+}
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
+				  unsigned long address)
+{
+	pgtable_free_tlb(tlb, table, PTE_INDEX);
+}
+
+extern atomic_long_t direct_pages_count[MMU_PAGE_COUNT];
+static inline void update_page_count(int psize, long count)
+{
+	if (IS_ENABLED(CONFIG_PROC_FS))
+		atomic_long_add(count, &direct_pages_count[psize]);
+}
+
+#endif /* _ASM_POWERPC_BOOK3S_64_PGALLOC_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/64/pgtable-64k.h

@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_64K_H
+#define _ASM_POWERPC_BOOK3S_64_PGTABLE_64K_H
+
+#ifndef __ASSEMBLER__
+#ifdef CONFIG_HUGETLB_PAGE
+
+#endif /* CONFIG_HUGETLB_PAGE */
+
+static inline int remap_4k_pfn(struct vm_area_struct *vma, unsigned long addr,
+			       unsigned long pfn, pgprot_t prot)
+{
+	if (radix_enabled())
+		BUG();
+	return hash__remap_4k_pfn(vma, addr, pfn, prot);
+}
+#endif	/* __ASSEMBLER__ */
+#endif /*_ASM_POWERPC_BOOK3S_64_PGTABLE_64K_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/64/pkeys.h

@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _ASM_POWERPC_BOOK3S_64_PKEYS_H
+#define _ASM_POWERPC_BOOK3S_64_PKEYS_H
+
+#include <asm/book3s/64/hash-pkey.h>
+
+static inline u64 vmflag_to_pte_pkey_bits(vm_flags_t vm_flags)
+{
+	if (!mmu_has_feature(MMU_FTR_PKEY))
+		return 0x0UL;
+
+	if (radix_enabled())
+		BUG();
+	return hash__vmflag_to_pte_pkey_bits(vm_flags);
+}
+
+static inline u16 pte_to_pkey_bits(u64 pteflags)
+{
+	if (radix_enabled())
+		BUG();
+	return hash__pte_to_pkey_bits(pteflags);
+}
+
+#endif /*_ASM_POWERPC_KEYS_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/64/radix-4k.h

@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_PGTABLE_RADIX_4K_H
+#define _ASM_POWERPC_PGTABLE_RADIX_4K_H
+
+/*
+ * For 4K page size supported index is 13/9/9/9
+ */
+#define RADIX_PTE_INDEX_SIZE   9  // size: 8B <<  9 =  4KB, maps 2^9  x    4K =   2MB
+#define RADIX_PMD_INDEX_SIZE   9  // size: 8B <<  9 =  4KB, maps 2^9  x   2MB =   1GB
+#define RADIX_PUD_INDEX_SIZE   9  // size: 8B <<  9 =  4KB, maps 2^9  x   1GB = 512GB
+#define RADIX_PGD_INDEX_SIZE  13  // size: 8B << 13 = 64KB, maps 2^13 x 512GB =   4PB
+
+/*
+ * One fragment per page
+ */
+#define RADIX_PTE_FRAG_SIZE_SHIFT  (RADIX_PTE_INDEX_SIZE + 3)
+#define RADIX_PTE_FRAG_NR	(PAGE_SIZE >> RADIX_PTE_FRAG_SIZE_SHIFT)
+
+#define RADIX_PMD_FRAG_SIZE_SHIFT  (RADIX_PMD_INDEX_SIZE + 3)
+#define RADIX_PMD_FRAG_NR	(PAGE_SIZE >> RADIX_PMD_FRAG_SIZE_SHIFT)
+
+#endif /* _ASM_POWERPC_PGTABLE_RADIX_4K_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/64/radix-64k.h

@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_PGTABLE_RADIX_64K_H
+#define _ASM_POWERPC_PGTABLE_RADIX_64K_H
+
+/*
+ * For 64K page size supported index is 13/9/9/5
+ */
+#define RADIX_PTE_INDEX_SIZE   5  // size: 8B <<  5 = 256B, maps 2^5  x   64K =   2MB
+#define RADIX_PMD_INDEX_SIZE   9  // size: 8B <<  9 =  4KB, maps 2^9  x   2MB =   1GB
+#define RADIX_PUD_INDEX_SIZE   9  // size: 8B <<  9 =  4KB, maps 2^9  x   1GB = 512GB
+#define RADIX_PGD_INDEX_SIZE  13  // size: 8B << 13 = 64KB, maps 2^13 x 512GB =   4PB
+
+/*
+ * We use a 256 byte PTE page fragment in radix
+ * 8 bytes per each PTE entry.
+ */
+#define RADIX_PTE_FRAG_SIZE_SHIFT  (RADIX_PTE_INDEX_SIZE + 3)
+#define RADIX_PTE_FRAG_NR	(PAGE_SIZE >> RADIX_PTE_FRAG_SIZE_SHIFT)
+
+#define RADIX_PMD_FRAG_SIZE_SHIFT  (RADIX_PMD_INDEX_SIZE + 3)
+#define RADIX_PMD_FRAG_NR	(PAGE_SIZE >> RADIX_PMD_FRAG_SIZE_SHIFT)
+
+#endif /* _ASM_POWERPC_PGTABLE_RADIX_64K_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/64/radix.h

@@ -0,0 +1,366 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_PGTABLE_RADIX_H
+#define _ASM_POWERPC_PGTABLE_RADIX_H
+
+#include <asm/asm-const.h>
+
+#ifndef __ASSEMBLER__
+#include <asm/cmpxchg.h>
+#endif
+
+#ifdef CONFIG_PPC_64K_PAGES
+#include <asm/book3s/64/radix-64k.h>
+#else
+#include <asm/book3s/64/radix-4k.h>
+#endif
+
+#ifndef __ASSEMBLER__
+#include <asm/book3s/64/tlbflush-radix.h>
+#include <asm/cpu_has_feature.h>
+#endif
+
+/* An empty PTE can still have a R or C writeback */
+#define RADIX_PTE_NONE_MASK		(_PAGE_DIRTY | _PAGE_ACCESSED)
+
+/* Bits to set in a RPMD/RPUD/RPGD */
+#define RADIX_PMD_VAL_BITS		(0x8000000000000000UL | RADIX_PTE_INDEX_SIZE)
+#define RADIX_PUD_VAL_BITS		(0x8000000000000000UL | RADIX_PMD_INDEX_SIZE)
+#define RADIX_PGD_VAL_BITS		(0x8000000000000000UL | RADIX_PUD_INDEX_SIZE)
+
+/* Don't have anything in the reserved bits and leaf bits */
+#define RADIX_PMD_BAD_BITS		0x60000000000000e0UL
+#define RADIX_PUD_BAD_BITS		0x60000000000000e0UL
+#define RADIX_P4D_BAD_BITS		0x60000000000000e0UL
+
+#define RADIX_PMD_SHIFT		(PAGE_SHIFT + RADIX_PTE_INDEX_SIZE)
+#define RADIX_PUD_SHIFT		(RADIX_PMD_SHIFT + RADIX_PMD_INDEX_SIZE)
+#define RADIX_PGD_SHIFT		(RADIX_PUD_SHIFT + RADIX_PUD_INDEX_SIZE)
+
+#define R_PTRS_PER_PTE		(1 << RADIX_PTE_INDEX_SIZE)
+#define R_PTRS_PER_PMD		(1 << RADIX_PMD_INDEX_SIZE)
+#define R_PTRS_PER_PUD		(1 << RADIX_PUD_INDEX_SIZE)
+
+/*
+ * Size of EA range mapped by our pagetables.
+ */
+#define RADIX_PGTABLE_EADDR_SIZE (RADIX_PTE_INDEX_SIZE + RADIX_PMD_INDEX_SIZE +	\
+			      RADIX_PUD_INDEX_SIZE + RADIX_PGD_INDEX_SIZE + PAGE_SHIFT)
+#define RADIX_PGTABLE_RANGE (ASM_CONST(1) << RADIX_PGTABLE_EADDR_SIZE)
+
+/*
+ * We support 52 bit address space, Use top bit for kernel
+ * virtual mapping. Also make sure kernel fit in the top
+ * quadrant.
+ *
+ *           +------------------+
+ *           +------------------+  Kernel virtual map (0xc008000000000000)
+ *           |                  |
+ *           |                  |
+ *           |                  |
+ * 0b11......+------------------+  Kernel linear map (0xc....)
+ *           |                  |
+ *           |     2 quadrant   |
+ *           |                  |
+ * 0b10......+------------------+
+ *           |                  |
+ *           |    1 quadrant    |
+ *           |                  |
+ * 0b01......+------------------+
+ *           |                  |
+ *           |    0 quadrant    |
+ *           |                  |
+ * 0b00......+------------------+
+ *
+ *
+ * 3rd quadrant expanded:
+ * +------------------------------+  Highest address (0xc010000000000000)
+ * +------------------------------+  KASAN shadow end (0xc00fc00000000000)
+ * |                              |
+ * |                              |
+ * +------------------------------+  Kernel vmemmap end/shadow start (0xc00e000000000000)
+ * |                              |
+ * |           512TB		  |
+ * |                              |
+ * +------------------------------+  Kernel IO map end/vmemap start
+ * |                              |
+ * |           512TB		  |
+ * |                              |
+ * +------------------------------+  Kernel vmap end/ IO map start
+ * |                              |
+ * |           512TB		  |
+ * |                              |
+ * +------------------------------+  Kernel virt start (0xc008000000000000)
+ * |                              |
+ * |                              |
+ * |                              |
+ * +------------------------------+  Kernel linear (0xc.....)
+ */
+
+/* For the sizes of the shadow area, see kasan.h */
+
+/*
+ * If we store section details in page->flags we can't increase the MAX_PHYSMEM_BITS
+ * if we increase SECTIONS_WIDTH we will not store node details in page->flags and
+ * page_to_nid does a page->section->node lookup
+ * Hence only increase for VMEMMAP. Further depending on SPARSEMEM_EXTREME reduce
+ * memory requirements with large number of sections.
+ * 51 bits is the max physical real address on POWER9
+ */
+
+#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_SPARSEMEM_EXTREME)
+#define R_MAX_PHYSMEM_BITS	51
+#else
+#define R_MAX_PHYSMEM_BITS	46
+#endif
+
+#define RADIX_KERN_VIRT_START	ASM_CONST(0xc008000000000000)
+/*
+ * 49 =  MAX_EA_BITS_PER_CONTEXT (hash specific). To make sure we pick
+ * the same value as hash.
+ */
+#define RADIX_KERN_MAP_SIZE	(1UL << 49)
+
+#define RADIX_VMALLOC_START	RADIX_KERN_VIRT_START
+#define RADIX_VMALLOC_SIZE	RADIX_KERN_MAP_SIZE
+#define RADIX_VMALLOC_END	(RADIX_VMALLOC_START + RADIX_VMALLOC_SIZE)
+
+#define RADIX_KERN_IO_START	RADIX_VMALLOC_END
+#define RADIX_KERN_IO_SIZE	RADIX_KERN_MAP_SIZE
+#define RADIX_KERN_IO_END	(RADIX_KERN_IO_START + RADIX_KERN_IO_SIZE)
+
+#define RADIX_VMEMMAP_START	RADIX_KERN_IO_END
+#define RADIX_VMEMMAP_SIZE	RADIX_KERN_MAP_SIZE
+#define RADIX_VMEMMAP_END	(RADIX_VMEMMAP_START + RADIX_VMEMMAP_SIZE)
+
+#ifndef __ASSEMBLER__
+#define RADIX_PTE_TABLE_SIZE	(sizeof(pte_t) << RADIX_PTE_INDEX_SIZE)
+#define RADIX_PMD_TABLE_SIZE	(sizeof(pmd_t) << RADIX_PMD_INDEX_SIZE)
+#define RADIX_PUD_TABLE_SIZE	(sizeof(pud_t) << RADIX_PUD_INDEX_SIZE)
+#define RADIX_PGD_TABLE_SIZE	(sizeof(pgd_t) << RADIX_PGD_INDEX_SIZE)
+
+#ifdef CONFIG_STRICT_KERNEL_RWX
+extern void radix__mark_rodata_ro(void);
+extern void radix__mark_initmem_nx(void);
+#endif
+
+extern void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep,
+					 pte_t entry, unsigned long address,
+					 int psize);
+
+extern void radix__ptep_modify_prot_commit(struct vm_area_struct *vma,
+					   unsigned long addr, pte_t *ptep,
+					   pte_t old_pte, pte_t pte);
+
+static inline unsigned long __radix_pte_update(pte_t *ptep, unsigned long clr,
+					       unsigned long set)
+{
+	__be64 old_be, tmp_be;
+
+	__asm__ __volatile__(
+	"1:	ldarx	%0,0,%3		# pte_update\n"
+	"	andc	%1,%0,%5	\n"
+	"	or	%1,%1,%4	\n"
+	"	stdcx.	%1,0,%3		\n"
+	"	bne-	1b"
+	: "=&r" (old_be), "=&r" (tmp_be), "=m" (*ptep)
+	: "r" (ptep), "r" (cpu_to_be64(set)), "r" (cpu_to_be64(clr))
+	: "cc" );
+
+	return be64_to_cpu(old_be);
+}
+
+static inline unsigned long radix__pte_update(struct mm_struct *mm,
+					unsigned long addr,
+					pte_t *ptep, unsigned long clr,
+					unsigned long set,
+					int huge)
+{
+	unsigned long old_pte;
+
+	old_pte = __radix_pte_update(ptep, clr, set);
+	if (!huge)
+		assert_pte_locked(mm, addr);
+
+	return old_pte;
+}
+
+static inline pte_t radix__ptep_get_and_clear_full(struct mm_struct *mm,
+						   unsigned long addr,
+						   pte_t *ptep, int full)
+{
+	unsigned long old_pte;
+
+	if (full) {
+		old_pte = pte_val(*ptep);
+		*ptep = __pte(0);
+	} else
+		old_pte = radix__pte_update(mm, addr, ptep, ~0ul, 0, 0);
+
+	return __pte(old_pte);
+}
+
+static inline int radix__pte_same(pte_t pte_a, pte_t pte_b)
+{
+	return ((pte_raw(pte_a) ^ pte_raw(pte_b)) == 0);
+}
+
+static inline int radix__pte_none(pte_t pte)
+{
+	return (pte_val(pte) & ~RADIX_PTE_NONE_MASK) == 0;
+}
+
+static inline void radix__set_pte_at(struct mm_struct *mm, unsigned long addr,
+				 pte_t *ptep, pte_t pte, int percpu)
+{
+	*ptep = pte;
+
+	/*
+	 * The architecture suggests a ptesync after setting the pte, which
+	 * orders the store that updates the pte with subsequent page table
+	 * walk accesses which may load the pte. Without this it may be
+	 * possible for a subsequent access to result in spurious fault.
+	 *
+	 * This is not necessary for correctness, because a spurious fault
+	 * is tolerated by the page fault handler, and this store will
+	 * eventually be seen. In testing, there was no noticable increase
+	 * in user faults on POWER9. Avoiding ptesync here is a significant
+	 * win for things like fork. If a future microarchitecture benefits
+	 * from ptesync, it should probably go into update_mmu_cache, rather
+	 * than set_pte_at (which is used to set ptes unrelated to faults).
+	 *
+	 * Spurious faults from the kernel memory are not tolerated, so there
+	 * is a ptesync in flush_cache_vmap, and __map_kernel_page() follows
+	 * the pte update sequence from ISA Book III 6.10 Translation Table
+	 * Update Synchronization Requirements.
+	 */
+}
+
+static inline int radix__pmd_bad(pmd_t pmd)
+{
+	return !!(pmd_val(pmd) & RADIX_PMD_BAD_BITS);
+}
+
+static inline int radix__pmd_same(pmd_t pmd_a, pmd_t pmd_b)
+{
+	return ((pmd_raw(pmd_a) ^ pmd_raw(pmd_b)) == 0);
+}
+
+static inline int radix__pud_bad(pud_t pud)
+{
+	return !!(pud_val(pud) & RADIX_PUD_BAD_BITS);
+}
+
+static inline int radix__pud_same(pud_t pud_a, pud_t pud_b)
+{
+	return ((pud_raw(pud_a) ^ pud_raw(pud_b)) == 0);
+}
+
+static inline int radix__p4d_bad(p4d_t p4d)
+{
+	return !!(p4d_val(p4d) & RADIX_P4D_BAD_BITS);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+
+static inline int radix__pmd_trans_huge(pmd_t pmd)
+{
+	return (pmd_val(pmd) & _PAGE_PTE) == _PAGE_PTE;
+}
+
+static inline pmd_t radix__pmd_mkhuge(pmd_t pmd)
+{
+	return __pmd(pmd_val(pmd) | _PAGE_PTE);
+}
+
+static inline int radix__pud_trans_huge(pud_t pud)
+{
+	return (pud_val(pud) & _PAGE_PTE) == _PAGE_PTE;
+}
+
+static inline pud_t radix__pud_mkhuge(pud_t pud)
+{
+	return __pud(pud_val(pud) | _PAGE_PTE);
+}
+
+extern unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
+					  pmd_t *pmdp, unsigned long clr,
+					  unsigned long set);
+extern unsigned long radix__pud_hugepage_update(struct mm_struct *mm, unsigned long addr,
+						pud_t *pudp, unsigned long clr,
+						unsigned long set);
+extern pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma,
+				  unsigned long address, pmd_t *pmdp);
+extern void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
+					pgtable_t pgtable);
+extern pgtable_t radix__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
+extern pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm,
+				      unsigned long addr, pmd_t *pmdp);
+pud_t radix__pudp_huge_get_and_clear(struct mm_struct *mm,
+				     unsigned long addr, pud_t *pudp);
+
+static inline int radix__has_transparent_hugepage(void)
+{
+	/* For radix 2M at PMD level means thp */
+	if (mmu_psize_defs[MMU_PAGE_2M].shift == PMD_SHIFT)
+		return 1;
+	return 0;
+}
+
+static inline int radix__has_transparent_pud_hugepage(void)
+{
+	/* For radix 1G at PUD level means pud hugepage support */
+	if (mmu_psize_defs[MMU_PAGE_1G].shift == PUD_SHIFT)
+		return 1;
+	return 0;
+}
+#endif
+
+struct vmem_altmap;
+struct dev_pagemap;
+extern int __meminit radix__vmemmap_create_mapping(unsigned long start,
+					     unsigned long page_size,
+					     unsigned long phys);
+int __meminit radix__vmemmap_populate(unsigned long start, unsigned long end,
+				      int node, struct vmem_altmap *altmap);
+void __ref radix__vmemmap_free(unsigned long start, unsigned long end,
+			       struct vmem_altmap *altmap);
+extern void radix__vmemmap_remove_mapping(unsigned long start,
+				    unsigned long page_size);
+
+extern int radix__map_kernel_page(unsigned long ea, unsigned long pa,
+				 pgprot_t flags, unsigned int psz);
+
+static inline unsigned long radix__get_tree_size(void)
+{
+	unsigned long rts_field;
+	/*
+	 * We support 52 bits, hence:
+	 * bits 52 - 31 = 21, 0b10101
+	 * RTS encoding details
+	 * bits 0 - 3 of rts -> bits 6 - 8 unsigned long
+	 * bits 4 - 5 of rts -> bits 62 - 63 of unsigned long
+	 */
+	rts_field = (0x5UL << 5); /* 6 - 8 bits */
+	rts_field |= (0x2UL << 61);
+
+	return rts_field;
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+int radix__create_section_mapping(unsigned long start, unsigned long end,
+				  int nid, pgprot_t prot);
+int radix__remove_section_mapping(unsigned long start, unsigned long end);
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
+#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP
+#define vmemmap_can_optimize vmemmap_can_optimize
+bool vmemmap_can_optimize(struct vmem_altmap *altmap, struct dev_pagemap *pgmap);
+#endif
+
+#define vmemmap_populate_compound_pages vmemmap_populate_compound_pages
+int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn,
+					      unsigned long start,
+					      unsigned long end, int node,
+					      struct dev_pagemap *pgmap);
+#endif /* __ASSEMBLER__ */
+#endif

linux-7.2.3/arch/powerpc/include/asm/book3s/64/slice.h

@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_SLICE_H
+#define _ASM_POWERPC_BOOK3S_64_SLICE_H
+
+#ifndef __ASSEMBLER__
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
+#ifdef CONFIG_HUGETLB_PAGE
+#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+#endif
+#define HAVE_ARCH_UNMAPPED_AREA
+#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
+#endif
+
+#define SLICE_LOW_SHIFT		28
+#define SLICE_LOW_TOP		(0x100000000ul)
+#define SLICE_NUM_LOW		(SLICE_LOW_TOP >> SLICE_LOW_SHIFT)
+#define GET_LOW_SLICE_INDEX(addr)	((addr) >> SLICE_LOW_SHIFT)
+
+#define SLICE_HIGH_SHIFT	40
+#define SLICE_NUM_HIGH		(H_PGTABLE_RANGE >> SLICE_HIGH_SHIFT)
+#define GET_HIGH_SLICE_INDEX(addr)	((addr) >> SLICE_HIGH_SHIFT)
+
+#define SLB_ADDR_LIMIT_DEFAULT	DEFAULT_MAP_WINDOW_USER64
+
+struct mm_struct;
+
+unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
+				      unsigned long flags, unsigned int psize,
+				      int topdown);
+
+unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr);
+
+void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
+			   unsigned long len, unsigned int psize);
+
+void slice_init_new_context_exec(struct mm_struct *mm);
+void slice_setup_new_exec(void);
+
+#endif /* __ASSEMBLER__ */
+
+#endif /* _ASM_POWERPC_BOOK3S_64_SLICE_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/64/tlbflush-hash.h

@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_TLBFLUSH_HASH_H
+#define _ASM_POWERPC_BOOK3S_64_TLBFLUSH_HASH_H
+
+/*
+ * TLB flushing for 64-bit hash-MMU CPUs
+ */
+
+#include <linux/percpu.h>
+#include <asm/page.h>
+
+#define PPC64_TLB_BATCH_NR 192
+
+struct ppc64_tlb_batch {
+	unsigned long		index;
+	struct mm_struct	*mm;
+	real_pte_t		pte[PPC64_TLB_BATCH_NR];
+	unsigned long		vpn[PPC64_TLB_BATCH_NR];
+	unsigned int		psize;
+	int			ssize;
+};
+DECLARE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch);
+
+extern void __flush_tlb_pending(struct ppc64_tlb_batch *batch);
+
+static inline void arch_enter_lazy_mmu_mode(void)
+{
+	if (radix_enabled())
+		return;
+	/*
+	 * apply_to_page_range can call us this preempt enabled when
+	 * operating on kernel page tables.
+	 */
+	preempt_disable();
+}
+
+static inline void arch_flush_lazy_mmu_mode(void)
+{
+	struct ppc64_tlb_batch *batch;
+
+	if (radix_enabled())
+		return;
+	batch = this_cpu_ptr(&ppc64_tlb_batch);
+
+	if (batch->index)
+		__flush_tlb_pending(batch);
+}
+
+static inline void arch_leave_lazy_mmu_mode(void)
+{
+	if (radix_enabled())
+		return;
+
+	arch_flush_lazy_mmu_mode();
+	preempt_enable();
+}
+
+extern void hash__tlbiel_all(unsigned int action);
+
+extern void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize,
+			    int ssize, unsigned long flags);
+extern void flush_hash_range(unsigned long number, int local);
+extern void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
+				pmd_t *pmdp, unsigned int psize, int ssize,
+				unsigned long flags);
+
+struct mmu_gather;
+extern void hash__tlb_flush(struct mmu_gather *tlb);
+
+#ifdef CONFIG_PPC_64S_HASH_MMU
+/* Private function for use by PCI IO mapping code */
+extern void __flush_hash_table_range(unsigned long start, unsigned long end);
+void flush_hash_table_pmd_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr);
+#else
+static inline void __flush_hash_table_range(unsigned long start, unsigned long end) { }
+#endif
+#endif /*  _ASM_POWERPC_BOOK3S_64_TLBFLUSH_HASH_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h

@@ -0,0 +1,98 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_TLBFLUSH_RADIX_H
+#define _ASM_POWERPC_TLBFLUSH_RADIX_H
+
+#include <asm/hvcall.h>
+
+#define RIC_FLUSH_TLB 0
+#define RIC_FLUSH_PWC 1
+#define RIC_FLUSH_ALL 2
+
+struct vm_area_struct;
+struct mm_struct;
+struct mmu_gather;
+
+static inline u64 psize_to_rpti_pgsize(unsigned long psize)
+{
+	if (psize == MMU_PAGE_4K)
+		return H_RPTI_PAGE_4K;
+	if (psize == MMU_PAGE_64K)
+		return H_RPTI_PAGE_64K;
+	if (psize == MMU_PAGE_2M)
+		return H_RPTI_PAGE_2M;
+	if (psize == MMU_PAGE_1G)
+		return H_RPTI_PAGE_1G;
+	return H_RPTI_PAGE_ALL;
+}
+
+static inline int mmu_get_ap(int psize)
+{
+	return mmu_psize_defs[psize].ap;
+}
+
+#ifdef CONFIG_PPC_RADIX_MMU
+extern void radix__tlbiel_all(unsigned int action);
+extern void radix__flush_tlb_lpid_page(unsigned int lpid,
+					unsigned long addr,
+					unsigned long page_size);
+extern void radix__flush_pwc_lpid(unsigned int lpid);
+extern void radix__flush_all_lpid(unsigned int lpid);
+extern void radix__flush_all_lpid_guest(unsigned int lpid);
+#else
+static inline void radix__tlbiel_all(unsigned int action) { WARN_ON(1); }
+static inline void radix__flush_tlb_lpid_page(unsigned int lpid,
+					unsigned long addr,
+					unsigned long page_size)
+{
+	WARN_ON(1);
+}
+static inline void radix__flush_pwc_lpid(unsigned int lpid)
+{
+	WARN_ON(1);
+}
+static inline void radix__flush_all_lpid(unsigned int lpid)
+{
+	WARN_ON(1);
+}
+static inline void radix__flush_all_lpid_guest(unsigned int lpid)
+{
+	WARN_ON(1);
+}
+#endif
+
+extern void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma,
+					   unsigned long start, unsigned long end);
+extern void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
+					 unsigned long end, int psize);
+void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start,
+				      unsigned long end, int psize);
+extern void radix__flush_pmd_tlb_range(struct vm_area_struct *vma,
+				       unsigned long start, unsigned long end);
+extern void radix__flush_pud_tlb_range(struct vm_area_struct *vma,
+				       unsigned long start, unsigned long end);
+extern void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
+			    unsigned long end);
+extern void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end);
+
+extern void radix__local_flush_tlb_mm(struct mm_struct *mm);
+extern void radix__local_flush_all_mm(struct mm_struct *mm);
+extern void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
+extern void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
+					      int psize);
+extern void radix__tlb_flush(struct mmu_gather *tlb);
+#ifdef CONFIG_SMP
+extern void radix__flush_tlb_mm(struct mm_struct *mm);
+extern void radix__flush_all_mm(struct mm_struct *mm);
+extern void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
+extern void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
+					int psize);
+#else
+#define radix__flush_tlb_mm(mm)		radix__local_flush_tlb_mm(mm)
+#define radix__flush_all_mm(mm)		radix__local_flush_all_mm(mm)
+#define radix__flush_tlb_page(vma,addr)	radix__local_flush_tlb_page(vma,addr)
+#define radix__flush_tlb_page_psize(mm,addr,p) radix__local_flush_tlb_page_psize(mm,addr,p)
+#endif
+extern void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr);
+extern void radix__flush_tlb_all(void);
+
+#endif

linux-7.2.3/arch/powerpc/include/asm/book3s/64/tlbflush.h

@@ -0,0 +1,225 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_TLBFLUSH_H
+#define _ASM_POWERPC_BOOK3S_64_TLBFLUSH_H
+
+#define MMU_NO_CONTEXT	~0UL
+
+#include <linux/mm_types.h>
+#include <linux/mmu_notifier.h>
+#include <asm/book3s/64/tlbflush-hash.h>
+#include <asm/book3s/64/tlbflush-radix.h>
+
+/* TLB flush actions. Used as argument to tlbiel_all() */
+enum {
+	TLB_INVAL_SCOPE_GLOBAL = 0,	/* invalidate all TLBs */
+	TLB_INVAL_SCOPE_LPID = 1,	/* invalidate TLBs for current LPID */
+};
+
+static inline void tlbiel_all(void)
+{
+	/*
+	 * This is used for host machine check and bootup.
+	 *
+	 * This uses early_radix_enabled and implementations use
+	 * early_cpu_has_feature etc because that works early in boot
+	 * and this is the machine check path which is not performance
+	 * critical.
+	 */
+	if (early_radix_enabled())
+		radix__tlbiel_all(TLB_INVAL_SCOPE_GLOBAL);
+	else
+		hash__tlbiel_all(TLB_INVAL_SCOPE_GLOBAL);
+}
+
+static inline void tlbiel_all_lpid(bool radix)
+{
+	/*
+	 * This is used for guest machine check.
+	 */
+	if (radix)
+		radix__tlbiel_all(TLB_INVAL_SCOPE_LPID);
+	else
+		hash__tlbiel_all(TLB_INVAL_SCOPE_LPID);
+}
+
+
+#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
+static inline void flush_pmd_tlb_range(struct vm_area_struct *vma,
+				       unsigned long start, unsigned long end)
+{
+	if (radix_enabled())
+		radix__flush_pmd_tlb_range(vma, start, end);
+}
+
+#define __HAVE_ARCH_FLUSH_PUD_TLB_RANGE
+static inline void flush_pud_tlb_range(struct vm_area_struct *vma,
+				       unsigned long start, unsigned long end)
+{
+	if (radix_enabled())
+		radix__flush_pud_tlb_range(vma, start, end);
+}
+
+#define __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE
+static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma,
+					   unsigned long start,
+					   unsigned long end)
+{
+	if (radix_enabled())
+		radix__flush_hugetlb_tlb_range(vma, start, end);
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+				   unsigned long start, unsigned long end)
+{
+	if (radix_enabled())
+		radix__flush_tlb_range(vma, start, end);
+}
+
+static inline void flush_tlb_kernel_range(unsigned long start,
+					  unsigned long end)
+{
+	if (radix_enabled())
+		radix__flush_tlb_kernel_range(start, end);
+}
+
+static inline void local_flush_tlb_mm(struct mm_struct *mm)
+{
+	if (radix_enabled())
+		radix__local_flush_tlb_mm(mm);
+}
+
+static inline void local_flush_tlb_page(struct vm_area_struct *vma,
+					unsigned long vmaddr)
+{
+	if (radix_enabled())
+		radix__local_flush_tlb_page(vma, vmaddr);
+}
+
+static inline void local_flush_tlb_page_psize(struct mm_struct *mm,
+					      unsigned long vmaddr, int psize)
+{
+	if (radix_enabled())
+		radix__local_flush_tlb_page_psize(mm, vmaddr, psize);
+}
+
+static inline void tlb_flush(struct mmu_gather *tlb)
+{
+	if (radix_enabled())
+		radix__tlb_flush(tlb);
+	else
+		hash__tlb_flush(tlb);
+}
+
+#ifdef CONFIG_SMP
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+	if (radix_enabled())
+		radix__flush_tlb_mm(mm);
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+				  unsigned long vmaddr)
+{
+	if (radix_enabled())
+		radix__flush_tlb_page(vma, vmaddr);
+}
+#else
+#define flush_tlb_mm(mm)		local_flush_tlb_mm(mm)
+#define flush_tlb_page(vma, addr)	local_flush_tlb_page(vma, addr)
+#endif /* CONFIG_SMP */
+
+#define flush_tlb_fix_spurious_fault flush_tlb_fix_spurious_fault
+static inline void flush_tlb_fix_spurious_fault(struct vm_area_struct *vma,
+						unsigned long address,
+						pte_t *ptep)
+{
+	/*
+	 * Book3S 64 does not require spurious fault flushes because the PTE
+	 * must be re-fetched in case of an access permission problem. So the
+	 * only reason for a spurious fault should be concurrent modification
+	 * to the PTE, in which case the PTE will eventually be re-fetched by
+	 * the MMU when it attempts the access again.
+	 *
+	 * See: Power ISA Version 3.1B, 6.10.1.2 Modifying a Translation Table
+	 * Entry, Setting a Reference or Change Bit or Upgrading Access
+	 * Authority (PTE Subject to Atomic Hardware Updates):
+	 *
+	 * "If the only change being made to a valid PTE that is subject to
+	 *  atomic hardware updates is to set the Reference or Change bit to
+	 *  1 or to upgrade access authority, a simpler sequence suffices
+	 *  because the translation hardware will refetch the PTE if an
+	 *  access is attempted for which the only problems were reference
+	 *  and/or change bits needing to be set or insufficient access
+	 *  authority."
+	 *
+	 * The nest MMU in POWER9 does not perform this PTE re-fetch, but
+	 * it avoids the spurious fault problem by flushing the TLB before
+	 * upgrading PTE permissions, see radix__ptep_set_access_flags.
+	 */
+}
+
+static inline bool __pte_flags_need_flush(unsigned long oldval,
+					  unsigned long newval)
+{
+	unsigned long delta = oldval ^ newval;
+
+	/*
+	 * The return value of this function doesn't matter for hash,
+	 * ptep_modify_prot_start() does a pte_update() which does or schedules
+	 * any necessary hash table update and flush.
+	 */
+	if (!radix_enabled())
+		return true;
+
+	/*
+	 * We do not expect kernel mappings or non-PTEs or not-present PTEs.
+	 */
+	VM_WARN_ON_ONCE(oldval & _PAGE_PRIVILEGED);
+	VM_WARN_ON_ONCE(newval & _PAGE_PRIVILEGED);
+	VM_WARN_ON_ONCE(!(oldval & _PAGE_PTE));
+	VM_WARN_ON_ONCE(!(newval & _PAGE_PTE));
+	VM_WARN_ON_ONCE(!(oldval & _PAGE_PRESENT));
+	VM_WARN_ON_ONCE(!(newval & _PAGE_PRESENT));
+
+	/*
+	*  Must flush on any change except READ, WRITE, EXEC, DIRTY, ACCESSED.
+	*
+	 * In theory, some changed software bits could be tolerated, in
+	 * practice those should rarely if ever matter.
+	 */
+
+	if (delta & ~(_PAGE_RWX | _PAGE_DIRTY | _PAGE_ACCESSED))
+		return true;
+
+	/*
+	 * If any of the above was present in old but cleared in new, flush.
+	 * With the exception of _PAGE_ACCESSED, don't worry about flushing
+	 * if that was cleared (see the comment in ptep_clear_flush_young()).
+	 */
+	if ((delta & ~_PAGE_ACCESSED) & oldval)
+		return true;
+
+	return false;
+}
+
+static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte)
+{
+	return __pte_flags_need_flush(pte_val(oldpte), pte_val(newpte));
+}
+#define pte_needs_flush pte_needs_flush
+
+static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd)
+{
+	return __pte_flags_need_flush(pmd_val(oldpmd), pmd_val(newpmd));
+}
+#define huge_pmd_needs_flush huge_pmd_needs_flush
+
+extern bool tlbie_capable;
+extern bool tlbie_enabled;
+
+static inline bool cputlb_use_tlbie(void)
+{
+	return tlbie_enabled;
+}
+
+#endif /*  _ASM_POWERPC_BOOK3S_64_TLBFLUSH_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/pgalloc.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_PGALLOC_H
+#define _ASM_POWERPC_BOOK3S_PGALLOC_H
+
+#include <linux/mm.h>
+
+extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
+
+#ifdef CONFIG_PPC64
+#include <asm/book3s/64/pgalloc.h>
+#else
+#include <asm/book3s/32/pgalloc.h>
+#endif
+
+#endif /* _ASM_POWERPC_BOOK3S_PGALLOC_H */

linux-7.2.3/arch/powerpc/include/asm/book3s/pgtable.h

@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_PGTABLE_H
+#define _ASM_POWERPC_BOOK3S_PGTABLE_H
+
+#ifdef CONFIG_PPC64
+#include <asm/book3s/64/pgtable.h>
+#else
+#include <asm/book3s/32/pgtable.h>
+#endif
+
+#endif

linux-7.2.3/arch/powerpc/include/asm/book3s/tlbflush.h

@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_TLBFLUSH_H
+#define _ASM_POWERPC_BOOK3S_TLBFLUSH_H
+
+#ifdef CONFIG_PPC64
+#include <asm/book3s/64/tlbflush.h>
+#else
+#include <asm/book3s/32/tlbflush.h>
+#endif
+
+#endif /* _ASM_POWERPC_BOOK3S_TLBFLUSH_H */

linux-7.2.3/arch/powerpc/include/asm/bootx.h

@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This file describes the structure passed from the BootX application
+ * (for MacOS) when it is used to boot Linux.
+ *
+ * Written by Benjamin Herrenschmidt.
+ */
+
+#ifndef __ASM_BOOTX_H__
+#define __ASM_BOOTX_H__
+
+#include <uapi/asm/bootx.h>
+
+/* (*) The format of the colormap is 256 * 3 * 2 bytes. Each color index
+ * is represented by 3 short words containing a 16 bits (unsigned) color
+ * component. Later versions may contain the gamma table for direct-color
+ * devices here.
+ */
+#define BOOTX_COLORTABLE_SIZE    (256UL*3UL*2UL)
+
+/* BootX passes the device-tree using a format that comes from earlier
+ * ppc32 kernels. This used to match what is in prom.h, but not anymore
+ * so we now define it here
+ */
+struct bootx_dt_prop {
+	u32	name;
+	int	length;
+	u32	value;
+	u32	next;
+};
+
+struct bootx_dt_node {
+	u32	unused0;
+	u32	unused1;
+	u32	phandle;	/* not really available */
+	u32	unused2;
+	u32	unused3;
+	u32	unused4;
+	u32	unused5;
+	u32	full_name;
+	u32	properties;
+	u32	parent;
+	u32	child;
+	u32	sibling;
+	u32	next;
+	u32	allnext;
+};
+
+extern void bootx_init(unsigned long r4, unsigned long phys);
+
+#endif

linux-7.2.3/arch/powerpc/include/asm/bpf_perf_event.h

@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BPF_PERF_EVENT_H
+#define _ASM_POWERPC_BPF_PERF_EVENT_H
+
+#include <asm/ptrace.h>
+
+typedef struct user_pt_regs bpf_user_pt_regs_t;
+
+#endif /* _ASM_POWERPC_BPF_PERF_EVENT_H */

linux-7.2.3/arch/powerpc/include/asm/btext.h

@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Definitions for using the procedures in btext.c.
+ *
+ * Benjamin Herrenschmidt <benh@kernel.crashing.org>
+ */
+#ifndef __PPC_BTEXT_H
+#define __PPC_BTEXT_H
+#ifdef __KERNEL__
+
+extern int btext_find_display(int allow_nonstdout);
+extern void btext_update_display(unsigned long phys, int width, int height,
+				 int depth, int pitch);
+extern void btext_setup_display(int width, int height, int depth, int pitch,
+				unsigned long address);
+#ifdef CONFIG_PPC32
+extern void btext_prepare_BAT(void);
+#else
+static inline void btext_prepare_BAT(void) { }
+#endif
+extern void btext_map(void);
+extern void btext_unmap(void);
+
+extern void btext_drawchar(char c);
+extern void btext_drawstring(const char *str);
+void __init btext_drawhex(unsigned long v);
+void __init btext_drawtext(const char *c, unsigned int len);
+
+void __init btext_clearscreen(void);
+void __init btext_flushscreen(void);
+void __init btext_flushline(void);
+
+#endif /* __KERNEL__ */
+#endif /* __PPC_BTEXT_H */

linux-7.2.3/arch/powerpc/include/asm/bug.h

@@ -0,0 +1,134 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BUG_H
+#define _ASM_POWERPC_BUG_H
+#ifdef __KERNEL__
+
+#include <asm/asm-compat.h>
+
+#ifdef CONFIG_BUG
+
+#ifdef __ASSEMBLER__
+#include <asm/asm-offsets.h>
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+.macro EMIT_BUG_ENTRY addr,file,line,flags
+	 .section __bug_table,"aw"
+5001:	 .4byte \addr - .
+	 .4byte 5002f - .
+	 .short \line, \flags
+	 .org 5001b+BUG_ENTRY_SIZE
+	 .previous
+	 .section .rodata,"a"
+5002:	 .asciz "\file"
+	 .previous
+.endm
+#else
+.macro EMIT_BUG_ENTRY addr,file,line,flags
+	 .section __bug_table,"aw"
+5001:	 .4byte \addr - .
+	 .short \flags
+	 .org 5001b+BUG_ENTRY_SIZE
+	 .previous
+.endm
+#endif /* verbose */
+
+#else /* !__ASSEMBLER__ */
+/* _EMIT_BUG_ENTRY expects args %0,%1,%2,%3 to be FILE, LINE, flags and
+   sizeof(struct bug_entry), respectively */
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+#define _EMIT_BUG_ENTRY				\
+	".section __bug_table,\"aw\"\n"		\
+	"2:	.4byte 1b - .\n"		\
+	"	.4byte %0 - .\n"		\
+	"	.short %1, %2\n"		\
+	".org 2b+%3\n"				\
+	".previous\n"
+#else
+#define _EMIT_BUG_ENTRY				\
+	".section __bug_table,\"aw\"\n"		\
+	"2:	.4byte 1b - .\n"		\
+	"	.short %2\n"			\
+	".org 2b+%3\n"				\
+	".previous\n"
+#endif
+
+#define BUG_ENTRY(cond_str, insn, flags, ...)		\
+	__asm__ __volatile__(				\
+		"1:	" insn "\n"			\
+		_EMIT_BUG_ENTRY				\
+		: : "i" (WARN_CONDITION_STR(cond_str) __FILE__), "i" (__LINE__),	\
+		  "i" (flags),				\
+		  "i" (sizeof(struct bug_entry)),	\
+		  ##__VA_ARGS__)
+
+/*
+ * BUG_ON() and WARN_ON() do their best to cooperate with compile-time
+ * optimisations. However depending on the complexity of the condition
+ * some compiler versions may not produce optimal results.
+ */
+
+#define BUG() do {						\
+	BUG_ENTRY("", "twi 31, 0, 0", 0);			\
+	unreachable();						\
+} while (0)
+#define HAVE_ARCH_BUG
+
+#define __WARN_FLAGS(cond_str, flags) BUG_ENTRY(cond_str, "twi 31, 0, 0", BUGFLAG_WARNING | (flags))
+
+#ifdef CONFIG_PPC64
+#define BUG_ON(x) do {						\
+	if (__builtin_constant_p(x)) {				\
+		if (x)						\
+			BUG();					\
+	} else {						\
+		BUG_ENTRY(#x, PPC_TLNEI " %4, 0", 0, "r" ((__force long)(x)));	\
+	}							\
+} while (0)
+
+#define WARN_ON(x) ({						\
+	int __ret_warn_on = !!(x);				\
+	if (__builtin_constant_p(__ret_warn_on)) {		\
+		if (__ret_warn_on)				\
+			__WARN();				\
+	} else {						\
+		BUG_ENTRY(#x, PPC_TLNEI " %4, 0",			\
+			  BUGFLAG_WARNING | BUGFLAG_TAINT(TAINT_WARN),	\
+			  "r" (__ret_warn_on));	\
+	}							\
+	unlikely(__ret_warn_on);				\
+})
+
+#define HAVE_ARCH_BUG_ON
+#define HAVE_ARCH_WARN_ON
+#endif
+
+#endif /* __ASSEMBLER__ */
+#else
+#ifdef __ASSEMBLER__
+.macro EMIT_BUG_ENTRY addr,file,line,flags
+.endm
+#else /* !__ASSEMBLER__ */
+#define _EMIT_BUG_ENTRY
+#endif
+#endif /* CONFIG_BUG */
+
+#define EMIT_WARN_ENTRY EMIT_BUG_ENTRY
+
+#include <asm-generic/bug.h>
+
+#ifndef __ASSEMBLER__
+
+struct pt_regs;
+void hash__do_page_fault(struct pt_regs *);
+void bad_page_fault(struct pt_regs *, int);
+void emulate_single_step(struct pt_regs *regs);
+extern void _exception(int, struct pt_regs *, int, unsigned long);
+extern void _exception_pkey(struct pt_regs *, unsigned long, int);
+extern void die(const char *, struct pt_regs *, long);
+void die_mce(const char *str, struct pt_regs *regs, long err);
+extern bool die_will_crash(void);
+extern void panic_flush_kmsg_start(void);
+extern void panic_flush_kmsg_end(void);
+#endif /* !__ASSEMBLER__ */
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_BUG_H */

linux-7.2.3/arch/powerpc/include/asm/cache.h

@@ -0,0 +1,150 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_CACHE_H
+#define _ASM_POWERPC_CACHE_H
+
+#ifdef __KERNEL__
+
+
+/* bytes per L1 cache line */
+#if defined(CONFIG_PPC_8xx)
+#define L1_CACHE_SHIFT		4
+#define MAX_COPY_PREFETCH	1
+#define IFETCH_ALIGN_SHIFT	2
+#elif defined(CONFIG_PPC_E500MC)
+#define L1_CACHE_SHIFT		6
+#define MAX_COPY_PREFETCH	4
+#define IFETCH_ALIGN_SHIFT	3
+#elif defined(CONFIG_PPC32)
+#define MAX_COPY_PREFETCH	4
+#define IFETCH_ALIGN_SHIFT	3	/* 603 fetches 2 insn at a time */
+#if defined(CONFIG_PPC_47x)
+#define L1_CACHE_SHIFT		7
+#else
+#define L1_CACHE_SHIFT		5
+#endif
+#else /* CONFIG_PPC64 */
+#define L1_CACHE_SHIFT		7
+#define IFETCH_ALIGN_SHIFT	4 /* POWER8,9 */
+#endif
+
+#define	L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
+
+#define	SMP_CACHE_BYTES		L1_CACHE_BYTES
+
+#define IFETCH_ALIGN_BYTES	(1 << IFETCH_ALIGN_SHIFT)
+
+#ifdef CONFIG_NOT_COHERENT_CACHE
+#define ARCH_DMA_MINALIGN	L1_CACHE_BYTES
+#endif
+
+#if !defined(__ASSEMBLER__)
+#ifdef CONFIG_PPC64
+
+struct ppc_cache_info {
+	u32 size;
+	u32 line_size;
+	u32 block_size;	/* L1 only */
+	u32 log_block_size;
+	u32 blocks_per_page;
+	u32 sets;
+	u32 assoc;
+};
+
+struct ppc64_caches {
+	struct ppc_cache_info l1d;
+	struct ppc_cache_info l1i;
+	struct ppc_cache_info l2;
+	struct ppc_cache_info l3;
+};
+
+extern struct ppc64_caches ppc64_caches;
+
+static inline u32 l1_dcache_shift(void)
+{
+	return ppc64_caches.l1d.log_block_size;
+}
+
+static inline u32 l1_dcache_bytes(void)
+{
+	return ppc64_caches.l1d.block_size;
+}
+
+static inline u32 l1_icache_shift(void)
+{
+	return ppc64_caches.l1i.log_block_size;
+}
+
+static inline u32 l1_icache_bytes(void)
+{
+	return ppc64_caches.l1i.block_size;
+}
+#else
+static inline u32 l1_dcache_shift(void)
+{
+	return L1_CACHE_SHIFT;
+}
+
+static inline u32 l1_dcache_bytes(void)
+{
+	return L1_CACHE_BYTES;
+}
+
+static inline u32 l1_icache_shift(void)
+{
+	return L1_CACHE_SHIFT;
+}
+
+static inline u32 l1_icache_bytes(void)
+{
+	return L1_CACHE_BYTES;
+}
+
+#endif
+
+#define __read_mostly __section(".data..read_mostly")
+
+#ifdef CONFIG_PPC_BOOK3S_32
+extern long _get_L2CR(void);
+extern long _get_L3CR(void);
+extern void _set_L2CR(unsigned long);
+extern void _set_L3CR(unsigned long);
+#else
+#define _get_L2CR()	0L
+#define _get_L3CR()	0L
+#define _set_L2CR(val)	do { } while(0)
+#define _set_L3CR(val)	do { } while(0)
+#endif
+
+static inline void dcbz(void *addr)
+{
+	__asm__ __volatile__ ("dcbz 0, %0" : : "r"(addr) : "memory");
+}
+
+static inline void dcbi(void *addr)
+{
+	__asm__ __volatile__ ("dcbi 0, %0" : : "r"(addr) : "memory");
+}
+
+static inline void dcbf(void *addr)
+{
+	__asm__ __volatile__ ("dcbf 0, %0" : : "r"(addr) : "memory");
+}
+
+static inline void dcbst(void *addr)
+{
+	__asm__ __volatile__ ("dcbst 0, %0" : : "r"(addr) : "memory");
+}
+
+static inline void icbi(void *addr)
+{
+	asm volatile ("icbi 0, %0" : : "r"(addr) : "memory");
+}
+
+static inline void iccci(void *addr)
+{
+	asm volatile ("iccci 0, %0" : : "r"(addr) : "memory");
+}
+
+#endif /* !__ASSEMBLER__ */
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_CACHE_H */

linux-7.2.3/arch/powerpc/include/asm/cacheflush.h

@@ -0,0 +1,136 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ */
+#ifndef _ASM_POWERPC_CACHEFLUSH_H
+#define _ASM_POWERPC_CACHEFLUSH_H
+
+#include <linux/mm.h>
+#include <asm/cputable.h>
+#include <asm/cpu_has_feature.h>
+
+/*
+ * This flag is used to indicate that the page pointed to by a pte is clean
+ * and does not require cleaning before returning it to the user.
+ */
+#define PG_dcache_clean PG_arch_1
+
+#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * Book3s has no ptesync after setting a pte, so without this ptesync it's
+ * possible for a kernel virtual mapping access to return a spurious fault
+ * if it's accessed right after the pte is set. The page fault handler does
+ * not expect this type of fault. flush_cache_vmap is not exactly the right
+ * place to put this, but it seems to work well enough.
+ */
+static inline void flush_cache_vmap(unsigned long start, unsigned long end)
+{
+	asm volatile("ptesync" ::: "memory");
+}
+#define flush_cache_vmap flush_cache_vmap
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
+/*
+ * This is called when a page has been modified by the kernel.
+ * It just marks the page as not i-cache clean.  We do the i-cache
+ * flush later when the page is given to a user process, if necessary.
+ */
+static inline void flush_dcache_folio(struct folio *folio)
+{
+	if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
+		return;
+	/* avoid an atomic op if possible */
+	if (test_bit(PG_dcache_clean, &folio->flags.f))
+		clear_bit(PG_dcache_clean, &folio->flags.f);
+}
+#define flush_dcache_folio flush_dcache_folio
+
+static inline void flush_dcache_page(struct page *page)
+{
+	flush_dcache_folio(page_folio(page));
+}
+
+void flush_icache_range(unsigned long start, unsigned long stop);
+#define flush_icache_range flush_icache_range
+
+void flush_icache_user_page(struct vm_area_struct *vma, struct page *page,
+		unsigned long addr, int len);
+#define flush_icache_user_page flush_icache_user_page
+
+void flush_dcache_icache_folio(struct folio *folio);
+
+/**
+ * flush_dcache_range(): Write any modified data cache blocks out to memory and
+ * invalidate them. Does not invalidate the corresponding instruction cache
+ * blocks.
+ *
+ * @start: the start address
+ * @stop: the stop address (exclusive)
+ */
+static inline void flush_dcache_range(unsigned long start, unsigned long stop)
+{
+	unsigned long shift = l1_dcache_shift();
+	unsigned long bytes = l1_dcache_bytes();
+	void *addr = (void *)(start & ~(bytes - 1));
+	unsigned long size = stop - (unsigned long)addr + (bytes - 1);
+	unsigned long i;
+
+	if (IS_ENABLED(CONFIG_PPC64))
+		mb();	/* sync */
+
+	for (i = 0; i < size >> shift; i++, addr += bytes)
+		dcbf(addr);
+	mb();	/* sync */
+
+}
+
+/*
+ * Write any modified data cache blocks out to memory.
+ * Does not invalidate the corresponding cache lines (especially for
+ * any corresponding instruction cache).
+ */
+static inline void clean_dcache_range(unsigned long start, unsigned long stop)
+{
+	unsigned long shift = l1_dcache_shift();
+	unsigned long bytes = l1_dcache_bytes();
+	void *addr = (void *)(start & ~(bytes - 1));
+	unsigned long size = stop - (unsigned long)addr + (bytes - 1);
+	unsigned long i;
+
+	for (i = 0; i < size >> shift; i++, addr += bytes)
+		dcbst(addr);
+	mb();	/* sync */
+}
+
+/*
+ * Like above, but invalidate the D-cache.  This is used by the 8xx
+ * to invalidate the cache so the PPC core doesn't get stale data
+ * from the CPM (no cache snooping here :-).
+ */
+static inline void invalidate_dcache_range(unsigned long start,
+					   unsigned long stop)
+{
+	unsigned long shift = l1_dcache_shift();
+	unsigned long bytes = l1_dcache_bytes();
+	void *addr = (void *)(start & ~(bytes - 1));
+	unsigned long size = stop - (unsigned long)addr + (bytes - 1);
+	unsigned long i;
+
+	for (i = 0; i < size >> shift; i++, addr += bytes)
+		dcbi(addr);
+	mb();	/* sync */
+}
+
+#ifdef CONFIG_44x
+static inline void flush_instruction_cache(void)
+{
+	iccci((void *)KERNELBASE);
+	isync();
+}
+#else
+void flush_instruction_cache(void);
+#endif
+
+#include <asm-generic/cacheflush.h>
+
+#endif /* _ASM_POWERPC_CACHEFLUSH_H */

linux-7.2.3/arch/powerpc/include/asm/cell-pmu.h

@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Cell Broadband Engine Performance Monitor
+ *
+ * (C) Copyright IBM Corporation 2006
+ *
+ * Author:
+ *   David Erb (djerb@us.ibm.com)
+ *   Kevin Corry (kevcorry@us.ibm.com)
+ */
+
+#ifndef __ASM_CELL_PMU_H__
+#define __ASM_CELL_PMU_H__
+
+/* The Cell PMU has four hardware performance counters, which can be
+ * configured as four 32-bit counters or eight 16-bit counters.
+ */
+#define NR_PHYS_CTRS 4
+#define NR_CTRS      (NR_PHYS_CTRS * 2)
+
+/* Macros for the pm_control register. */
+#define CBE_PM_16BIT_CTR(ctr)              (1 << (24 - ((ctr) & (NR_PHYS_CTRS - 1))))
+
+/* Macros for the trace_address register. */
+#define CBE_PM_TRACE_BUF_EMPTY             0x00000400
+
+enum pm_reg_name {
+	group_control,
+	debug_bus_control,
+	trace_address,
+	ext_tr_timer,
+	pm_status,
+	pm_control,
+	pm_interval,
+	pm_start_stop,
+};
+
+#endif /* __ASM_CELL_PMU_H__ */

linux-7.2.3/arch/powerpc/include/asm/cell-regs.h

@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * cbe_regs.h
+ *
+ * This file is intended to hold the various register definitions for CBE
+ * on-chip system devices (memory controller, IO controller, etc...)
+ *
+ * (C) Copyright IBM Corporation 2001,2006
+ *
+ * Authors: Maximino Aguilar (maguilar@us.ibm.com)
+ *          David J. Erb (djerb@us.ibm.com)
+ *
+ * (c) 2006 Benjamin Herrenschmidt <benh@kernel.crashing.org>, IBM Corp.
+ */
+
+#ifndef CBE_REGS_H
+#define CBE_REGS_H
+
+#include <asm/cell-pmu.h>
+
+/* Cell page table entries */
+#define CBE_IOPTE_PP_W		0x8000000000000000ul /* protection: write */
+#define CBE_IOPTE_PP_R		0x4000000000000000ul /* protection: read */
+#define CBE_IOPTE_M		0x2000000000000000ul /* coherency required */
+#define CBE_IOPTE_SO_R		0x1000000000000000ul /* ordering: writes */
+#define CBE_IOPTE_SO_RW		0x1800000000000000ul /* ordering: r & w */
+#define CBE_IOPTE_RPN_Mask	0x07fffffffffff000ul /* RPN */
+#define CBE_IOPTE_H		0x0000000000000800ul /* cache hint */
+#define CBE_IOPTE_IOID_Mask	0x00000000000007fful /* ioid */
+
+#endif /* CBE_REGS_H */

linux-7.2.3/arch/powerpc/include/asm/checksum.h

@@ -0,0 +1,235 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ASM_POWERPC_CHECKSUM_H
+#define _ASM_POWERPC_CHECKSUM_H
+#ifdef __KERNEL__
+
+/*
+ */
+
+#include <linux/bitops.h>
+#include <linux/in6.h>
+#include <linux/uaccess.h>
+/*
+ * Computes the checksum of a memory block at src, length len,
+ * and adds in "sum" (32-bit), while copying the block to dst.
+ * If an access exception occurs on src or dst, it stores -EFAULT
+ * to *src_err or *dst_err respectively (if that pointer is not
+ * NULL), and, for an error on src, zeroes the rest of dst.
+ *
+ * Like csum_partial, this must be called with even lengths,
+ * except for the last fragment.
+ */
+extern __wsum csum_partial_copy_generic(const void *src, void *dst, int len);
+
+#define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
+static inline __wsum csum_and_copy_from_user(const void __user *src, void *dst, int len)
+{
+	scoped_user_read_access_size(src, len, efault)
+		return csum_partial_copy_generic((void __force *)src, dst, len);
+
+efault:
+	return 0;
+}
+
+#define HAVE_CSUM_COPY_USER
+static inline __wsum csum_and_copy_to_user(const void *src, void __user *dst, int len)
+{
+	scoped_user_write_access_size(dst, len, efault)
+		return csum_partial_copy_generic(src, (void __force *)dst, len);
+
+efault:
+	return 0;
+}
+
+#define _HAVE_ARCH_CSUM_AND_COPY
+#define csum_partial_copy_nocheck(src, dst, len)   \
+        csum_partial_copy_generic((src), (dst), (len))
+
+
+/*
+ * turns a 32-bit partial checksum (e.g. from csum_partial) into a
+ * 1's complement 16-bit checksum.
+ */
+static inline __sum16 csum_fold(__wsum sum)
+{
+	u32 tmp = (__force u32)sum;
+
+	/*
+	 * swap the two 16-bit halves of sum
+	 * if there is a carry from adding the two 16-bit halves,
+	 * it will carry from the lower half into the upper half,
+	 * giving us the correct sum in the upper half.
+	 */
+	return (__force __sum16)(~(tmp + rol32(tmp, 16)) >> 16);
+}
+
+static inline u32 from64to32(u64 x)
+{
+	return (x + ror64(x, 32)) >> 32;
+}
+
+static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
+					__u8 proto, __wsum sum)
+{
+#ifdef __powerpc64__
+	u64 s = (__force u32)sum;
+
+	s += (__force u32)saddr;
+	s += (__force u32)daddr;
+#ifdef __BIG_ENDIAN__
+	s += proto + len;
+#else
+	s += (proto + len) << 8;
+#endif
+	return (__force __wsum) from64to32(s);
+#else
+    __asm__("\n\
+	addc %0,%0,%1 \n\
+	adde %0,%0,%2 \n\
+	adde %0,%0,%3 \n\
+	addze %0,%0 \n\
+	"
+	: "=r" (sum)
+	: "r" (daddr), "r"(saddr), "r"(proto + len), "0"(sum));
+	return sum;
+#endif
+}
+
+/*
+ * computes the checksum of the TCP/UDP pseudo-header
+ * returns a 16-bit checksum, already complemented
+ */
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len,
+					__u8 proto, __wsum sum)
+{
+	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
+}
+
+#define HAVE_ARCH_CSUM_ADD
+static __always_inline __wsum csum_add(__wsum csum, __wsum addend)
+{
+#ifdef __powerpc64__
+	u64 res = (__force u64)csum;
+
+	res += (__force u64)addend;
+	return (__force __wsum)((u32)res + (res >> 32));
+#else
+	if (__builtin_constant_p(csum) && csum == 0)
+		return addend;
+	if (__builtin_constant_p(addend) && addend == 0)
+		return csum;
+
+	asm("addc %0,%0,%1;"
+	    "addze %0,%0;"
+	    : "+r" (csum) : "r" (addend) : "xer");
+	return csum;
+#endif
+}
+
+#define HAVE_ARCH_CSUM_SHIFT
+static __always_inline __wsum csum_shift(__wsum sum, int offset)
+{
+	/* rotate sum to align it with a 16b boundary */
+	return (__force __wsum)rol32((__force u32)sum, (offset & 1) << 3);
+}
+
+/*
+ * This is a version of ip_compute_csum() optimized for IP headers,
+ * which always checksum on 4 octet boundaries.  ihl is the number
+ * of 32-bit words and is always >= 5.
+ */
+static inline __wsum ip_fast_csum_nofold(const void *iph, unsigned int ihl)
+{
+	const u32 *ptr = (const u32 *)iph + 1;
+#ifdef __powerpc64__
+	unsigned int i;
+	u64 s = *(const u32 *)iph;
+
+	for (i = 0; i < ihl - 1; i++, ptr++)
+		s += *ptr;
+	return (__force __wsum)from64to32(s);
+#else
+	__wsum sum, tmp;
+
+	asm("mtctr %3;"
+	    "addc %0,%4,%5;"
+	    "1: lwzu %1, 4(%2);"
+	    "adde %0,%0,%1;"
+	    "bdnz 1b;"
+	    "addze %0,%0;"
+	    : "=r" (sum), "=r" (tmp), "+b" (ptr)
+	    : "r" (ihl - 2), "r" (*(const u32 *)iph), "r" (*ptr)
+	    : "ctr", "xer", "memory");
+
+	return sum;
+#endif
+}
+
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	return csum_fold(ip_fast_csum_nofold(iph, ihl));
+}
+
+/*
+ * computes the checksum of a memory block at buff, length len,
+ * and adds in "sum" (32-bit)
+ *
+ * returns a 32-bit number suitable for feeding into itself
+ * or csum_tcpudp_magic
+ *
+ * this function must be called with even lengths, except
+ * for the last fragment, which may be odd
+ *
+ * it's best to have buff aligned on a 32-bit boundary
+ */
+__wsum __csum_partial(const void *buff, int len, __wsum sum);
+
+static __always_inline __wsum csum_partial(const void *buff, int len, __wsum sum)
+{
+	if (__builtin_constant_p(len) && len <= 16 && (len & 1) == 0) {
+		if (len == 2)
+			sum = csum_add(sum, (__force __wsum)*(const u16 *)buff);
+		if (len >= 4)
+			sum = csum_add(sum, (__force __wsum)*(const u32 *)buff);
+		if (len == 6)
+			sum = csum_add(sum, (__force __wsum)
+					    *(const u16 *)(buff + 4));
+		if (len >= 8)
+			sum = csum_add(sum, (__force __wsum)
+					    *(const u32 *)(buff + 4));
+		if (len == 10)
+			sum = csum_add(sum, (__force __wsum)
+					    *(const u16 *)(buff + 8));
+		if (len >= 12)
+			sum = csum_add(sum, (__force __wsum)
+					    *(const u32 *)(buff + 8));
+		if (len == 14)
+			sum = csum_add(sum, (__force __wsum)
+					    *(const u16 *)(buff + 12));
+		if (len >= 16)
+			sum = csum_add(sum, (__force __wsum)
+					    *(const u32 *)(buff + 12));
+	} else if (__builtin_constant_p(len) && (len & 3) == 0) {
+		sum = csum_add(sum, ip_fast_csum_nofold(buff, len >> 2));
+	} else {
+		sum = __csum_partial(buff, len, sum);
+	}
+	return sum;
+}
+
+/*
+ * this routine is used for miscellaneous IP-like checksums, mainly
+ * in icmp.c
+ */
+static inline __sum16 ip_compute_csum(const void *buff, int len)
+{
+	return csum_fold(csum_partial(buff, len, 0));
+}
+
+#define _HAVE_ARCH_IPV6_CSUM
+__sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+			const struct in6_addr *daddr,
+			__u32 len, __u8 proto, __wsum sum);
+
+#endif /* __KERNEL__ */
+#endif

linux-7.2.3/arch/powerpc/include/asm/clocksource.h

@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_CLOCKSOURCE_H
+#define _ASM_POWERPC_CLOCKSOURCE_H
+
+#include <asm/vdso/clocksource.h>
+
+#endif /* _ASM_POWERPC_CLOCKSOURCE_H */

linux-7.2.3/arch/powerpc/include/asm/cmpxchg.h

@@ -0,0 +1,760 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_CMPXCHG_H_
+#define _ASM_POWERPC_CMPXCHG_H_
+
+#ifdef __KERNEL__
+#include <linux/compiler.h>
+#include <asm/synch.h>
+#include <linux/bug.h>
+
+#ifdef __BIG_ENDIAN
+#define BITOFF_CAL(size, off)	((sizeof(u32) - size - off) * BITS_PER_BYTE)
+#else
+#define BITOFF_CAL(size, off)	(off * BITS_PER_BYTE)
+#endif
+
+#define XCHG_GEN(type, sfx, cl)				\
+static inline u32 __xchg_##type##sfx(volatile void *p, u32 val)	\
+{								\
+	unsigned int prev, prev_mask, tmp, bitoff, off;		\
+								\
+	off = (unsigned long)p % sizeof(u32);			\
+	bitoff = BITOFF_CAL(sizeof(type), off);			\
+	p -= off;						\
+	val <<= bitoff;						\
+	prev_mask = (u32)(type)-1 << bitoff;			\
+								\
+	__asm__ __volatile__(					\
+"1:	lwarx   %0,0,%3\n"					\
+"	andc	%1,%0,%5\n"					\
+"	or	%1,%1,%4\n"					\
+"	stwcx.	%1,0,%3\n"					\
+"	bne-	1b\n"						\
+	: "=&r" (prev), "=&r" (tmp), "+m" (*(u32*)p)		\
+	: "r" (p), "r" (val), "r" (prev_mask)			\
+	: "cc", cl);						\
+								\
+	return prev >> bitoff;					\
+}
+
+#define CMPXCHG_GEN(type, sfx, br, br2, cl)			\
+static inline							\
+u32 __cmpxchg_##type##sfx(volatile void *p, u32 old, u32 new)	\
+{								\
+	unsigned int prev, prev_mask, tmp, bitoff, off;		\
+								\
+	off = (unsigned long)p % sizeof(u32);			\
+	bitoff = BITOFF_CAL(sizeof(type), off);			\
+	p -= off;						\
+	old <<= bitoff;						\
+	new <<= bitoff;						\
+	prev_mask = (u32)(type)-1 << bitoff;			\
+								\
+	__asm__ __volatile__(					\
+	br							\
+"1:	lwarx   %0,0,%3\n"					\
+"	and	%1,%0,%6\n"					\
+"	cmpw	0,%1,%4\n"					\
+"	bne-	2f\n"						\
+"	andc	%1,%0,%6\n"					\
+"	or	%1,%1,%5\n"					\
+"	stwcx.  %1,0,%3\n"					\
+"	bne-    1b\n"						\
+	br2							\
+	"\n"							\
+"2:"								\
+	: "=&r" (prev), "=&r" (tmp), "+m" (*(u32*)p)		\
+	: "r" (p), "r" (old), "r" (new), "r" (prev_mask)	\
+	: "cc", cl);						\
+								\
+	return prev >> bitoff;					\
+}
+
+/*
+ * Atomic exchange
+ *
+ * Changes the memory location '*p' to be val and returns
+ * the previous value stored there.
+ */
+
+#ifndef CONFIG_PPC_HAS_LBARX_LHARX
+XCHG_GEN(u8, _local, "memory");
+XCHG_GEN(u8, _relaxed, "cc");
+XCHG_GEN(u16, _local, "memory");
+XCHG_GEN(u16, _relaxed, "cc");
+#else
+static __always_inline unsigned long
+__xchg_u8_local(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	lbarx	%0,0,%2		# __xchg_u8_local\n"
+"	stbcx.	%3,0,%2 \n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*(volatile unsigned char *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__xchg_u8_relaxed(u8 *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	lbarx	%0,0,%2		# __xchg_u8_relaxed\n"
+"	stbcx.	%3,0,%2\n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (val)
+	: "cc");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__xchg_u16_local(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	lharx	%0,0,%2		# __xchg_u16_local\n"
+"	sthcx.	%3,0,%2\n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*(volatile unsigned short *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__xchg_u16_relaxed(u16 *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	lharx	%0,0,%2		# __xchg_u16_relaxed\n"
+"	sthcx.	%3,0,%2\n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (val)
+	: "cc");
+
+	return prev;
+}
+#endif
+
+static __always_inline unsigned long
+__xchg_u32_local(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	lwarx	%0,0,%2 \n"
+"	stwcx.	%3,0,%2 \n\
+	bne-	1b"
+	: "=&r" (prev), "+m" (*(volatile unsigned int *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__xchg_u32_relaxed(u32 *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	lwarx	%0,0,%2\n"
+"	stwcx.	%3,0,%2\n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (val)
+	: "cc");
+
+	return prev;
+}
+
+#ifdef CONFIG_PPC64
+static __always_inline unsigned long
+__xchg_u64_local(volatile void *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%2 \n"
+"	stdcx.	%3,0,%2 \n\
+	bne-	1b"
+	: "=&r" (prev), "+m" (*(volatile unsigned long *)p)
+	: "r" (p), "r" (val)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__xchg_u64_relaxed(u64 *p, unsigned long val)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__(
+"1:	ldarx	%0,0,%2\n"
+"	stdcx.	%3,0,%2\n"
+"	bne-	1b"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (val)
+	: "cc");
+
+	return prev;
+}
+#endif
+
+static __always_inline unsigned long
+__xchg_local(void *ptr, unsigned long x, unsigned int size)
+{
+	switch (size) {
+	case 1:
+		return __xchg_u8_local(ptr, x);
+	case 2:
+		return __xchg_u16_local(ptr, x);
+	case 4:
+		return __xchg_u32_local(ptr, x);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __xchg_u64_local(ptr, x);
+#endif
+	}
+	BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg_local");
+	return x;
+}
+
+static __always_inline unsigned long
+__xchg_relaxed(void *ptr, unsigned long x, unsigned int size)
+{
+	switch (size) {
+	case 1:
+		return __xchg_u8_relaxed(ptr, x);
+	case 2:
+		return __xchg_u16_relaxed(ptr, x);
+	case 4:
+		return __xchg_u32_relaxed(ptr, x);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __xchg_u64_relaxed(ptr, x);
+#endif
+	}
+	BUILD_BUG_ON_MSG(1, "Unsupported size for __xchg_relaxed");
+	return x;
+}
+#define arch_xchg_local(ptr,x)						     \
+  ({									     \
+     __typeof__(*(ptr)) _x_ = (x);					     \
+     (__typeof__(*(ptr))) __xchg_local((ptr),				     \
+     		(unsigned long)_x_, sizeof(*(ptr))); 			     \
+  })
+
+#define arch_xchg_relaxed(ptr, x)					\
+({									\
+	__typeof__(*(ptr)) _x_ = (x);					\
+	(__typeof__(*(ptr))) __xchg_relaxed((ptr),			\
+			(unsigned long)_x_, sizeof(*(ptr)));		\
+})
+
+/*
+ * Compare and exchange - if *p == old, set it to new,
+ * and return the old value of *p.
+ */
+#ifndef CONFIG_PPC_HAS_LBARX_LHARX
+CMPXCHG_GEN(u8, , PPC_ATOMIC_ENTRY_BARRIER, PPC_ATOMIC_EXIT_BARRIER, "memory");
+CMPXCHG_GEN(u8, _local, , , "memory");
+CMPXCHG_GEN(u8, _acquire, , PPC_ACQUIRE_BARRIER, "memory");
+CMPXCHG_GEN(u8, _relaxed, , , "cc");
+CMPXCHG_GEN(u16, , PPC_ATOMIC_ENTRY_BARRIER, PPC_ATOMIC_EXIT_BARRIER, "memory");
+CMPXCHG_GEN(u16, _local, , , "memory");
+CMPXCHG_GEN(u16, _acquire, , PPC_ACQUIRE_BARRIER, "memory");
+CMPXCHG_GEN(u16, _relaxed, , , "cc");
+#else
+static __always_inline unsigned long
+__cmpxchg_u8(volatile unsigned char *p, unsigned long old, unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+	PPC_ATOMIC_ENTRY_BARRIER
+"1:	lbarx	%0,0,%2		# __cmpxchg_u8\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	stbcx.	%4,0,%2\n"
+"	bne-	1b"
+	PPC_ATOMIC_EXIT_BARRIER
+	"\n\
+2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u8_local(volatile unsigned char *p, unsigned long old,
+			unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+"1:	lbarx	%0,0,%2		# __cmpxchg_u8_local\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	stbcx.	%4,0,%2\n"
+"	bne-	1b\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u8_relaxed(u8 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lbarx	%0,0,%2		# __cmpxchg_u8_relaxed\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	stbcx.	%4,0,%2\n"
+"	bne-	1b\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u8_acquire(u8 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lbarx	%0,0,%2		# __cmpxchg_u8_acquire\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	stbcx.	%4,0,%2\n"
+"	bne-	1b\n"
+	PPC_ACQUIRE_BARRIER
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u16(volatile unsigned short *p, unsigned long old, unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+	PPC_ATOMIC_ENTRY_BARRIER
+"1:	lharx	%0,0,%2		# __cmpxchg_u16\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	sthcx.	%4,0,%2\n"
+"	bne-	1b\n"
+	PPC_ATOMIC_EXIT_BARRIER
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u16_local(volatile unsigned short *p, unsigned long old,
+			unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+"1:	lharx	%0,0,%2		# __cmpxchg_u16_local\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	sthcx.	%4,0,%2\n"
+"	bne-	1b"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u16_relaxed(u16 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lharx	%0,0,%2		# __cmpxchg_u16_relaxed\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	sthcx.	%4,0,%2\n"
+"	bne-	1b\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u16_acquire(u16 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lharx	%0,0,%2		# __cmpxchg_u16_acquire\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	sthcx.	%4,0,%2\n"
+"	bne-	1b\n"
+	PPC_ACQUIRE_BARRIER
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+#endif
+
+static __always_inline unsigned long
+__cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+	PPC_ATOMIC_ENTRY_BARRIER
+"1:	lwarx	%0,0,%2		# __cmpxchg_u32\n\
+	cmpw	0,%0,%3\n\
+	bne-	2f\n"
+"	stwcx.	%4,0,%2\n\
+	bne-	1b"
+	PPC_ATOMIC_EXIT_BARRIER
+	"\n\
+2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u32_local(volatile unsigned int *p, unsigned long old,
+			unsigned long new)
+{
+	unsigned int prev;
+
+	__asm__ __volatile__ (
+"1:	lwarx	%0,0,%2		# __cmpxchg_u32\n\
+	cmpw	0,%0,%3\n\
+	bne-	2f\n"
+"	stwcx.	%4,0,%2\n\
+	bne-	1b"
+	"\n\
+2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u32_relaxed(u32 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lwarx	%0,0,%2		# __cmpxchg_u32_relaxed\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	stwcx.	%4,0,%2\n"
+"	bne-	1b\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc");
+
+	return prev;
+}
+
+/*
+ * cmpxchg family don't have order guarantee if cmp part fails, therefore we
+ * can avoid superfluous barriers if we use assembly code to implement
+ * cmpxchg() and cmpxchg_acquire(), however we don't do the similar for
+ * cmpxchg_release() because that will result in putting a barrier in the
+ * middle of a ll/sc loop, which is probably a bad idea. For example, this
+ * might cause the conditional store more likely to fail.
+ */
+static __always_inline unsigned long
+__cmpxchg_u32_acquire(u32 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	lwarx	%0,0,%2		# __cmpxchg_u32_acquire\n"
+"	cmpw	0,%0,%3\n"
+"	bne-	2f\n"
+"	stwcx.	%4,0,%2\n"
+"	bne-	1b\n"
+	PPC_ACQUIRE_BARRIER
+	"\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+#ifdef CONFIG_PPC64
+static __always_inline unsigned long
+__cmpxchg_u64(volatile unsigned long *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+	PPC_ATOMIC_ENTRY_BARRIER
+"1:	ldarx	%0,0,%2		# __cmpxchg_u64\n\
+	cmpd	0,%0,%3\n\
+	bne-	2f\n\
+	stdcx.	%4,0,%2\n\
+	bne-	1b"
+	PPC_ATOMIC_EXIT_BARRIER
+	"\n\
+2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u64_local(volatile unsigned long *p, unsigned long old,
+			unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	ldarx	%0,0,%2		# __cmpxchg_u64\n\
+	cmpd	0,%0,%3\n\
+	bne-	2f\n\
+	stdcx.	%4,0,%2\n\
+	bne-	1b"
+	"\n\
+2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u64_relaxed(u64 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	ldarx	%0,0,%2		# __cmpxchg_u64_relaxed\n"
+"	cmpd	0,%0,%3\n"
+"	bne-	2f\n"
+"	stdcx.	%4,0,%2\n"
+"	bne-	1b\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc");
+
+	return prev;
+}
+
+static __always_inline unsigned long
+__cmpxchg_u64_acquire(u64 *p, unsigned long old, unsigned long new)
+{
+	unsigned long prev;
+
+	__asm__ __volatile__ (
+"1:	ldarx	%0,0,%2		# __cmpxchg_u64_acquire\n"
+"	cmpd	0,%0,%3\n"
+"	bne-	2f\n"
+"	stdcx.	%4,0,%2\n"
+"	bne-	1b\n"
+	PPC_ACQUIRE_BARRIER
+	"\n"
+"2:"
+	: "=&r" (prev), "+m" (*p)
+	: "r" (p), "r" (old), "r" (new)
+	: "cc", "memory");
+
+	return prev;
+}
+#endif
+
+static __always_inline unsigned long
+__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new,
+	  unsigned int size)
+{
+	switch (size) {
+	case 1:
+		return __cmpxchg_u8(ptr, old, new);
+	case 2:
+		return __cmpxchg_u16(ptr, old, new);
+	case 4:
+		return __cmpxchg_u32(ptr, old, new);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __cmpxchg_u64(ptr, old, new);
+#endif
+	}
+	BUILD_BUG_ON_MSG(1, "Unsupported size for __cmpxchg");
+	return old;
+}
+
+static __always_inline unsigned long
+__cmpxchg_local(void *ptr, unsigned long old, unsigned long new,
+	  unsigned int size)
+{
+	switch (size) {
+	case 1:
+		return __cmpxchg_u8_local(ptr, old, new);
+	case 2:
+		return __cmpxchg_u16_local(ptr, old, new);
+	case 4:
+		return __cmpxchg_u32_local(ptr, old, new);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __cmpxchg_u64_local(ptr, old, new);
+#endif
+	}
+	BUILD_BUG_ON_MSG(1, "Unsupported size for __cmpxchg_local");
+	return old;
+}
+
+static __always_inline unsigned long
+__cmpxchg_relaxed(void *ptr, unsigned long old, unsigned long new,
+		  unsigned int size)
+{
+	switch (size) {
+	case 1:
+		return __cmpxchg_u8_relaxed(ptr, old, new);
+	case 2:
+		return __cmpxchg_u16_relaxed(ptr, old, new);
+	case 4:
+		return __cmpxchg_u32_relaxed(ptr, old, new);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __cmpxchg_u64_relaxed(ptr, old, new);
+#endif
+	}
+	BUILD_BUG_ON_MSG(1, "Unsupported size for __cmpxchg_relaxed");
+	return old;
+}
+
+static __always_inline unsigned long
+__cmpxchg_acquire(void *ptr, unsigned long old, unsigned long new,
+		  unsigned int size)
+{
+	switch (size) {
+	case 1:
+		return __cmpxchg_u8_acquire(ptr, old, new);
+	case 2:
+		return __cmpxchg_u16_acquire(ptr, old, new);
+	case 4:
+		return __cmpxchg_u32_acquire(ptr, old, new);
+#ifdef CONFIG_PPC64
+	case 8:
+		return __cmpxchg_u64_acquire(ptr, old, new);
+#endif
+	}
+	BUILD_BUG_ON_MSG(1, "Unsupported size for __cmpxchg_acquire");
+	return old;
+}
+#define arch_cmpxchg(ptr, o, n)						 \
+  ({									 \
+     __typeof__(*(ptr)) _o_ = (o);					 \
+     __typeof__(*(ptr)) _n_ = (n);					 \
+     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		 \
+				    (unsigned long)_n_, sizeof(*(ptr))); \
+  })
+
+
+#define arch_cmpxchg_local(ptr, o, n)					 \
+  ({									 \
+     __typeof__(*(ptr)) _o_ = (o);					 \
+     __typeof__(*(ptr)) _n_ = (n);					 \
+     (__typeof__(*(ptr))) __cmpxchg_local((ptr), (unsigned long)_o_,	 \
+				    (unsigned long)_n_, sizeof(*(ptr))); \
+  })
+
+#define arch_cmpxchg_relaxed(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg_relaxed((ptr),			\
+			(unsigned long)_o_, (unsigned long)_n_,		\
+			sizeof(*(ptr)));				\
+})
+
+#define arch_cmpxchg_acquire(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) _o_ = (o);					\
+	__typeof__(*(ptr)) _n_ = (n);					\
+	(__typeof__(*(ptr))) __cmpxchg_acquire((ptr),			\
+			(unsigned long)_o_, (unsigned long)_n_,		\
+			sizeof(*(ptr)));				\
+})
+#ifdef CONFIG_PPC64
+#define arch_cmpxchg64(ptr, o, n)					\
+  ({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	arch_cmpxchg((ptr), (o), (n));					\
+  })
+#define arch_cmpxchg64_local(ptr, o, n)					\
+  ({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	arch_cmpxchg_local((ptr), (o), (n));				\
+  })
+#define arch_cmpxchg64_relaxed(ptr, o, n)				\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	arch_cmpxchg_relaxed((ptr), (o), (n));				\
+})
+#define arch_cmpxchg64_acquire(ptr, o, n)				\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	arch_cmpxchg_acquire((ptr), (o), (n));				\
+})
+#else
+#include <asm-generic/cmpxchg-local.h>
+#define arch_cmpxchg64_local(ptr, o, n) __generic_cmpxchg64_local((ptr), (o), (n))
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_CMPXCHG_H_ */

linux-7.2.3/arch/powerpc/include/asm/code-patching-asm.h

@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright 2018, Michael Ellerman, IBM Corporation.
+ */
+#ifndef _ASM_POWERPC_CODE_PATCHING_ASM_H
+#define _ASM_POWERPC_CODE_PATCHING_ASM_H
+
+/* Define a "site" that can be patched */
+.macro patch_site label name
+	.pushsection ".rodata"
+	.balign 4
+	.global \name
+\name:
+	.4byte	\label - .
+	.popsection
+.endm
+
+#endif /* _ASM_POWERPC_CODE_PATCHING_ASM_H */

linux-7.2.3/arch/powerpc/include/asm/compat.h

@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_COMPAT_H
+#define _ASM_POWERPC_COMPAT_H
+#ifdef __KERNEL__
+/*
+ * Architecture specific compatibility types
+ */
+#include <linux/types.h>
+#include <linux/sched.h>
+
+#define compat_ipc_pid_t compat_ipc_pid_t
+typedef u16		compat_ipc_pid_t;
+
+#define compat_ipc64_perm compat_ipc64_perm
+
+#include <asm-generic/compat.h>
+
+#ifdef __BIG_ENDIAN__
+#define COMPAT_UTS_MACHINE	"ppc\0\0"
+#else
+#define COMPAT_UTS_MACHINE	"ppcle\0\0"
+#endif
+
+typedef s16		compat_nlink_t;
+
+struct compat_stat {
+	compat_dev_t	st_dev;
+	compat_ino_t	st_ino;
+	compat_mode_t	st_mode;
+	compat_nlink_t	st_nlink;
+	__compat_uid32_t	st_uid;
+	__compat_gid32_t	st_gid;
+	compat_dev_t	st_rdev;
+	compat_off_t	st_size;
+	compat_off_t	st_blksize;
+	compat_off_t	st_blocks;
+	old_time32_t	st_atime;
+	u32		st_atime_nsec;
+	old_time32_t	st_mtime;
+	u32		st_mtime_nsec;
+	old_time32_t	st_ctime;
+	u32		st_ctime_nsec;
+	u32		__unused4[2];
+};
+
+/*
+ * ipc64_perm is actually 32/64bit clean but since the compat layer refers to
+ * it we may as well define it.
+ */
+struct compat_ipc64_perm {
+	compat_key_t key;
+	__compat_uid_t uid;
+	__compat_gid_t gid;
+	__compat_uid_t cuid;
+	__compat_gid_t cgid;
+	compat_mode_t mode;
+	unsigned int seq;
+	unsigned int __pad2;
+	unsigned long __unused1;	/* yes they really are 64bit pads */
+	unsigned long __unused2;
+};
+
+struct compat_semid64_ds {
+	struct compat_ipc64_perm sem_perm;
+	unsigned int sem_otime_high;
+	unsigned int sem_otime;
+	unsigned int sem_ctime_high;
+	unsigned int sem_ctime;
+	compat_ulong_t sem_nsems;
+	compat_ulong_t __unused3;
+	compat_ulong_t __unused4;
+};
+
+struct compat_msqid64_ds {
+	struct compat_ipc64_perm msg_perm;
+	unsigned int msg_stime_high;
+	unsigned int msg_stime;
+	unsigned int msg_rtime_high;
+	unsigned int msg_rtime;
+	unsigned int msg_ctime_high;
+	unsigned int msg_ctime;
+	compat_ulong_t msg_cbytes;
+	compat_ulong_t msg_qnum;
+	compat_ulong_t msg_qbytes;
+	compat_pid_t msg_lspid;
+	compat_pid_t msg_lrpid;
+	compat_ulong_t __unused4;
+	compat_ulong_t __unused5;
+};
+
+struct compat_shmid64_ds {
+	struct compat_ipc64_perm shm_perm;
+	unsigned int shm_atime_high;
+	unsigned int shm_atime;
+	unsigned int shm_dtime_high;
+	unsigned int shm_dtime;
+	unsigned int shm_ctime_high;
+	unsigned int shm_ctime;
+	unsigned int __unused4;
+	compat_size_t shm_segsz;
+	compat_pid_t shm_cpid;
+	compat_pid_t shm_lpid;
+	compat_ulong_t shm_nattch;
+	compat_ulong_t __unused5;
+	compat_ulong_t __unused6;
+};
+
+static inline int is_compat_task(void)
+{
+	return is_32bit_task();
+}
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_COMPAT_H */

linux-7.2.3/arch/powerpc/include/asm/context_tracking.h

@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_CONTEXT_TRACKING_H
+#define _ASM_POWERPC_CONTEXT_TRACKING_H
+
+#ifdef CONFIG_CONTEXT_TRACKING_USER
+#define SCHEDULE_USER bl	schedule_user
+#else
+#define SCHEDULE_USER bl	schedule
+#endif
+
+#endif

linux-7.2.3/arch/powerpc/include/asm/copro.h

@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright 2014 IBM Corp.
+ */
+
+#ifndef _ASM_POWERPC_COPRO_H
+#define _ASM_POWERPC_COPRO_H
+
+#include <linux/mm_types.h>
+
+struct copro_slb
+{
+	u64 esid, vsid;
+};
+
+int copro_handle_mm_fault(struct mm_struct *mm, unsigned long ea,
+			  unsigned long dsisr, vm_fault_t *flt);
+
+int copro_calculate_slb(struct mm_struct *mm, u64 ea, struct copro_slb *slb);
+
+#endif /* _ASM_POWERPC_COPRO_H */

linux-7.2.3/arch/powerpc/include/asm/cpm.h

@@ -0,0 +1 @@
+#include <soc/fsl/cpm.h>

linux-7.2.3/arch/powerpc/include/asm/cpm1.h

@@ -0,0 +1,607 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * MPC8xx Communication Processor Module.
+ * Copyright (c) 1997 Dan Malek (dmalek@jlc.net)
+ *
+ * This file contains structures and information for the communication
+ * processor channels.  Some CPM control and status is available
+ * through the MPC8xx internal memory map.  See immap.h for details.
+ * This file only contains what I need for the moment, not the total
+ * CPM capabilities.  I (or someone else) will add definitions as they
+ * are needed.  -- Dan
+ *
+ * On the MBX board, EPPC-Bug loads CPM microcode into the first 512
+ * bytes of the DP RAM and relocates the I2C parameter area to the
+ * IDMA1 space.  The remaining DP RAM is available for buffer descriptors
+ * or other use.
+ */
+#ifndef __CPM1__
+#define __CPM1__
+
+#include <linux/init.h>
+#include <asm/8xx_immap.h>
+#include <asm/ptrace.h>
+#include <asm/cpm.h>
+
+/* CPM Command register.
+*/
+#define CPM_CR_RST	((ushort)0x8000)
+#define CPM_CR_OPCODE	((ushort)0x0f00)
+#define CPM_CR_CHAN	((ushort)0x00f0)
+#define CPM_CR_FLG	((ushort)0x0001)
+
+/* Channel numbers.
+*/
+#define CPM_CR_CH_SCC1		((ushort)0x0000)
+#define CPM_CR_CH_I2C		((ushort)0x0001)	/* I2C and IDMA1 */
+#define CPM_CR_CH_SCC2		((ushort)0x0004)
+#define CPM_CR_CH_SPI		((ushort)0x0005)	/* SPI / IDMA2 / Timers */
+#define CPM_CR_CH_TIMER		CPM_CR_CH_SPI
+#define CPM_CR_CH_SCC3		((ushort)0x0008)
+#define CPM_CR_CH_SMC1		((ushort)0x0009)	/* SMC1 / DSP1 */
+#define CPM_CR_CH_SCC4		((ushort)0x000c)
+#define CPM_CR_CH_SMC2		((ushort)0x000d)	/* SMC2 / DSP2 */
+
+#define mk_cr_cmd(CH, CMD)	((CMD << 8) | (CH << 4))
+
+/* Export the base address of the communication processor registers
+ * and dual port ram.
+ */
+extern cpm8xx_t __iomem *cpmp; /* Pointer to comm processor */
+
+extern void cpm_setbrg(uint brg, uint rate);
+
+extern void __init cpm_load_patch(cpm8xx_t *cp);
+
+extern void cpm_reset(void);
+
+/* Parameter RAM offsets.
+*/
+#define PROFF_SCC1	((uint)0x0000)
+#define PROFF_IIC	((uint)0x0080)
+#define PROFF_SCC2	((uint)0x0100)
+#define PROFF_SPI	((uint)0x0180)
+#define PROFF_SCC3	((uint)0x0200)
+#define PROFF_SMC1	((uint)0x0280)
+#define PROFF_DSP1	((uint)0x02c0)
+#define PROFF_SCC4	((uint)0x0300)
+#define PROFF_SMC2	((uint)0x0380)
+
+/* Define enough so I can at least use the serial port as a UART.
+ * The MBX uses SMC1 as the host serial port.
+ */
+typedef struct smc_uart {
+	ushort	smc_rbase;	/* Rx Buffer descriptor base address */
+	ushort	smc_tbase;	/* Tx Buffer descriptor base address */
+	u_char	smc_rfcr;	/* Rx function code */
+	u_char	smc_tfcr;	/* Tx function code */
+	ushort	smc_mrblr;	/* Max receive buffer length */
+	uint	smc_rstate;	/* Internal */
+	uint	smc_idp;	/* Internal */
+	ushort	smc_rbptr;	/* Internal */
+	ushort	smc_ibc;	/* Internal */
+	uint	smc_rxtmp;	/* Internal */
+	uint	smc_tstate;	/* Internal */
+	uint	smc_tdp;	/* Internal */
+	ushort	smc_tbptr;	/* Internal */
+	ushort	smc_tbc;	/* Internal */
+	uint	smc_txtmp;	/* Internal */
+	ushort	smc_maxidl;	/* Maximum idle characters */
+	ushort	smc_tmpidl;	/* Temporary idle counter */
+	ushort	smc_brklen;	/* Last received break length */
+	ushort	smc_brkec;	/* rcv'd break condition counter */
+	ushort	smc_brkcr;	/* xmt break count register */
+	ushort	smc_rmask;	/* Temporary bit mask */
+	char	res1[8];	/* Reserved */
+	ushort	smc_rpbase;	/* Relocation pointer */
+} smc_uart_t;
+
+/* Function code bits.
+*/
+#define SMC_EB	((u_char)0x10)	/* Set big endian byte order */
+
+/* SMC uart mode register.
+*/
+#define	SMCMR_REN	((ushort)0x0001)
+#define SMCMR_TEN	((ushort)0x0002)
+#define SMCMR_DM	((ushort)0x000c)
+#define SMCMR_SM_GCI	((ushort)0x0000)
+#define SMCMR_SM_UART	((ushort)0x0020)
+#define SMCMR_SM_TRANS	((ushort)0x0030)
+#define SMCMR_SM_MASK	((ushort)0x0030)
+#define SMCMR_PM_EVEN	((ushort)0x0100)	/* Even parity, else odd */
+#define SMCMR_REVD	SMCMR_PM_EVEN
+#define SMCMR_PEN	((ushort)0x0200)	/* Parity enable */
+#define SMCMR_BS	SMCMR_PEN
+#define SMCMR_SL	((ushort)0x0400)	/* Two stops, else one */
+#define SMCR_CLEN_MASK	((ushort)0x7800)	/* Character length */
+#define smcr_mk_clen(C)	(((C) << 11) & SMCR_CLEN_MASK)
+
+/* SMC2 as Centronics parallel printer.  It is half duplex, in that
+ * it can only receive or transmit.  The parameter ram values for
+ * each direction are either unique or properly overlap, so we can
+ * include them in one structure.
+ */
+typedef struct smc_centronics {
+	ushort	scent_rbase;
+	ushort	scent_tbase;
+	u_char	scent_cfcr;
+	u_char	scent_smask;
+	ushort	scent_mrblr;
+	uint	scent_rstate;
+	uint	scent_r_ptr;
+	ushort	scent_rbptr;
+	ushort	scent_r_cnt;
+	uint	scent_rtemp;
+	uint	scent_tstate;
+	uint	scent_t_ptr;
+	ushort	scent_tbptr;
+	ushort	scent_t_cnt;
+	uint	scent_ttemp;
+	ushort	scent_max_sl;
+	ushort	scent_sl_cnt;
+	ushort	scent_character1;
+	ushort	scent_character2;
+	ushort	scent_character3;
+	ushort	scent_character4;
+	ushort	scent_character5;
+	ushort	scent_character6;
+	ushort	scent_character7;
+	ushort	scent_character8;
+	ushort	scent_rccm;
+	ushort	scent_rccr;
+} smc_cent_t;
+
+/* Centronics Status Mask Register.
+*/
+#define SMC_CENT_F	((u_char)0x08)
+#define SMC_CENT_PE	((u_char)0x04)
+#define SMC_CENT_S	((u_char)0x02)
+
+/* SMC Event and Mask register.
+*/
+#define	SMCM_BRKE	((unsigned char)0x40)	/* When in UART Mode */
+#define	SMCM_BRK	((unsigned char)0x10)	/* When in UART Mode */
+#define	SMCM_TXE	((unsigned char)0x10)	/* When in Transparent Mode */
+#define	SMCM_BSY	((unsigned char)0x04)
+#define	SMCM_TX		((unsigned char)0x02)
+#define	SMCM_RX		((unsigned char)0x01)
+
+/* Baud rate generators.
+*/
+#define CPM_BRG_RST		((uint)0x00020000)
+#define CPM_BRG_EN		((uint)0x00010000)
+#define CPM_BRG_EXTC_INT	((uint)0x00000000)
+#define CPM_BRG_EXTC_CLK2	((uint)0x00004000)
+#define CPM_BRG_EXTC_CLK6	((uint)0x00008000)
+#define CPM_BRG_ATB		((uint)0x00002000)
+#define CPM_BRG_CD_MASK		((uint)0x00001ffe)
+#define CPM_BRG_DIV16		((uint)0x00000001)
+
+/* SI Clock Route Register
+*/
+#define SICR_RCLK_SCC1_BRG1	((uint)0x00000000)
+#define SICR_TCLK_SCC1_BRG1	((uint)0x00000000)
+#define SICR_RCLK_SCC2_BRG2	((uint)0x00000800)
+#define SICR_TCLK_SCC2_BRG2	((uint)0x00000100)
+#define SICR_RCLK_SCC3_BRG3	((uint)0x00100000)
+#define SICR_TCLK_SCC3_BRG3	((uint)0x00020000)
+#define SICR_RCLK_SCC4_BRG4	((uint)0x18000000)
+#define SICR_TCLK_SCC4_BRG4	((uint)0x03000000)
+
+/* SCCs.
+*/
+#define SCC_GSMRH_IRP		((uint)0x00040000)
+#define SCC_GSMRH_GDE		((uint)0x00010000)
+#define SCC_GSMRH_TCRC_CCITT	((uint)0x00008000)
+#define SCC_GSMRH_TCRC_BISYNC	((uint)0x00004000)
+#define SCC_GSMRH_TCRC_HDLC	((uint)0x00000000)
+#define SCC_GSMRH_REVD		((uint)0x00002000)
+#define SCC_GSMRH_TRX		((uint)0x00001000)
+#define SCC_GSMRH_TTX		((uint)0x00000800)
+#define SCC_GSMRH_CDP		((uint)0x00000400)
+#define SCC_GSMRH_CTSP		((uint)0x00000200)
+#define SCC_GSMRH_CDS		((uint)0x00000100)
+#define SCC_GSMRH_CTSS		((uint)0x00000080)
+#define SCC_GSMRH_TFL		((uint)0x00000040)
+#define SCC_GSMRH_RFW		((uint)0x00000020)
+#define SCC_GSMRH_TXSY		((uint)0x00000010)
+#define SCC_GSMRH_SYNL16	((uint)0x0000000c)
+#define SCC_GSMRH_SYNL8		((uint)0x00000008)
+#define SCC_GSMRH_SYNL4		((uint)0x00000004)
+#define SCC_GSMRH_RTSM		((uint)0x00000002)
+#define SCC_GSMRH_RSYN		((uint)0x00000001)
+
+#define SCC_GSMRL_SIR		((uint)0x80000000)	/* SCC2 only */
+#define SCC_GSMRL_EDGE_NONE	((uint)0x60000000)
+#define SCC_GSMRL_EDGE_NEG	((uint)0x40000000)
+#define SCC_GSMRL_EDGE_POS	((uint)0x20000000)
+#define SCC_GSMRL_EDGE_BOTH	((uint)0x00000000)
+#define SCC_GSMRL_TCI		((uint)0x10000000)
+#define SCC_GSMRL_TSNC_3	((uint)0x0c000000)
+#define SCC_GSMRL_TSNC_4	((uint)0x08000000)
+#define SCC_GSMRL_TSNC_14	((uint)0x04000000)
+#define SCC_GSMRL_TSNC_INF	((uint)0x00000000)
+#define SCC_GSMRL_RINV		((uint)0x02000000)
+#define SCC_GSMRL_TINV		((uint)0x01000000)
+#define SCC_GSMRL_TPL_128	((uint)0x00c00000)
+#define SCC_GSMRL_TPL_64	((uint)0x00a00000)
+#define SCC_GSMRL_TPL_48	((uint)0x00800000)
+#define SCC_GSMRL_TPL_32	((uint)0x00600000)
+#define SCC_GSMRL_TPL_16	((uint)0x00400000)
+#define SCC_GSMRL_TPL_8		((uint)0x00200000)
+#define SCC_GSMRL_TPL_NONE	((uint)0x00000000)
+#define SCC_GSMRL_TPP_ALL1	((uint)0x00180000)
+#define SCC_GSMRL_TPP_01	((uint)0x00100000)
+#define SCC_GSMRL_TPP_10	((uint)0x00080000)
+#define SCC_GSMRL_TPP_ZEROS	((uint)0x00000000)
+#define SCC_GSMRL_TEND		((uint)0x00040000)
+#define SCC_GSMRL_TDCR_32	((uint)0x00030000)
+#define SCC_GSMRL_TDCR_16	((uint)0x00020000)
+#define SCC_GSMRL_TDCR_8	((uint)0x00010000)
+#define SCC_GSMRL_TDCR_1	((uint)0x00000000)
+#define SCC_GSMRL_RDCR_32	((uint)0x0000c000)
+#define SCC_GSMRL_RDCR_16	((uint)0x00008000)
+#define SCC_GSMRL_RDCR_8	((uint)0x00004000)
+#define SCC_GSMRL_RDCR_1	((uint)0x00000000)
+#define SCC_GSMRL_RENC_DFMAN	((uint)0x00003000)
+#define SCC_GSMRL_RENC_MANCH	((uint)0x00002000)
+#define SCC_GSMRL_RENC_FM0	((uint)0x00001000)
+#define SCC_GSMRL_RENC_NRZI	((uint)0x00000800)
+#define SCC_GSMRL_RENC_NRZ	((uint)0x00000000)
+#define SCC_GSMRL_TENC_DFMAN	((uint)0x00000600)
+#define SCC_GSMRL_TENC_MANCH	((uint)0x00000400)
+#define SCC_GSMRL_TENC_FM0	((uint)0x00000200)
+#define SCC_GSMRL_TENC_NRZI	((uint)0x00000100)
+#define SCC_GSMRL_TENC_NRZ	((uint)0x00000000)
+#define SCC_GSMRL_DIAG_LE	((uint)0x000000c0)	/* Loop and echo */
+#define SCC_GSMRL_DIAG_ECHO	((uint)0x00000080)
+#define SCC_GSMRL_DIAG_LOOP	((uint)0x00000040)
+#define SCC_GSMRL_DIAG_NORM	((uint)0x00000000)
+#define SCC_GSMRL_ENR		((uint)0x00000020)
+#define SCC_GSMRL_ENT		((uint)0x00000010)
+#define SCC_GSMRL_MODE_ENET	((uint)0x0000000c)
+#define SCC_GSMRL_MODE_QMC	((uint)0x0000000a)
+#define SCC_GSMRL_MODE_DDCMP	((uint)0x00000009)
+#define SCC_GSMRL_MODE_BISYNC	((uint)0x00000008)
+#define SCC_GSMRL_MODE_V14	((uint)0x00000007)
+#define SCC_GSMRL_MODE_AHDLC	((uint)0x00000006)
+#define SCC_GSMRL_MODE_PROFIBUS	((uint)0x00000005)
+#define SCC_GSMRL_MODE_UART	((uint)0x00000004)
+#define SCC_GSMRL_MODE_SS7	((uint)0x00000003)
+#define SCC_GSMRL_MODE_ATALK	((uint)0x00000002)
+#define SCC_GSMRL_MODE_HDLC	((uint)0x00000000)
+
+#define SCC_TODR_TOD		((ushort)0x8000)
+
+/* SCC Event and Mask register.
+*/
+#define	SCCM_TXE	((unsigned char)0x10)
+#define	SCCM_BSY	((unsigned char)0x04)
+#define	SCCM_TX		((unsigned char)0x02)
+#define	SCCM_RX		((unsigned char)0x01)
+
+typedef struct scc_param {
+	ushort	scc_rbase;	/* Rx Buffer descriptor base address */
+	ushort	scc_tbase;	/* Tx Buffer descriptor base address */
+	u_char	scc_rfcr;	/* Rx function code */
+	u_char	scc_tfcr;	/* Tx function code */
+	ushort	scc_mrblr;	/* Max receive buffer length */
+	uint	scc_rstate;	/* Internal */
+	uint	scc_idp;	/* Internal */
+	ushort	scc_rbptr;	/* Internal */
+	ushort	scc_ibc;	/* Internal */
+	uint	scc_rxtmp;	/* Internal */
+	uint	scc_tstate;	/* Internal */
+	uint	scc_tdp;	/* Internal */
+	ushort	scc_tbptr;	/* Internal */
+	ushort	scc_tbc;	/* Internal */
+	uint	scc_txtmp;	/* Internal */
+	uint	scc_rcrc;	/* Internal */
+	uint	scc_tcrc;	/* Internal */
+} sccp_t;
+
+/* Function code bits.
+*/
+#define SCC_EB	((u_char)0x10)	/* Set big endian byte order */
+
+/* CPM Ethernet through SCCx.
+ */
+typedef struct scc_enet {
+	sccp_t	sen_genscc;
+	uint	sen_cpres;	/* Preset CRC */
+	uint	sen_cmask;	/* Constant mask for CRC */
+	uint	sen_crcec;	/* CRC Error counter */
+	uint	sen_alec;	/* alignment error counter */
+	uint	sen_disfc;	/* discard frame counter */
+	ushort	sen_pads;	/* Tx short frame pad character */
+	ushort	sen_retlim;	/* Retry limit threshold */
+	ushort	sen_retcnt;	/* Retry limit counter */
+	ushort	sen_maxflr;	/* maximum frame length register */
+	ushort	sen_minflr;	/* minimum frame length register */
+	ushort	sen_maxd1;	/* maximum DMA1 length */
+	ushort	sen_maxd2;	/* maximum DMA2 length */
+	ushort	sen_maxd;	/* Rx max DMA */
+	ushort	sen_dmacnt;	/* Rx DMA counter */
+	ushort	sen_maxb;	/* Max BD byte count */
+	ushort	sen_gaddr1;	/* Group address filter */
+	ushort	sen_gaddr2;
+	ushort	sen_gaddr3;
+	ushort	sen_gaddr4;
+	uint	sen_tbuf0data0;	/* Save area 0 - current frame */
+	uint	sen_tbuf0data1;	/* Save area 1 - current frame */
+	uint	sen_tbuf0rba;	/* Internal */
+	uint	sen_tbuf0crc;	/* Internal */
+	ushort	sen_tbuf0bcnt;	/* Internal */
+	ushort	sen_paddrh;	/* physical address (MSB) */
+	ushort	sen_paddrm;
+	ushort	sen_paddrl;	/* physical address (LSB) */
+	ushort	sen_pper;	/* persistence */
+	ushort	sen_rfbdptr;	/* Rx first BD pointer */
+	ushort	sen_tfbdptr;	/* Tx first BD pointer */
+	ushort	sen_tlbdptr;	/* Tx last BD pointer */
+	uint	sen_tbuf1data0;	/* Save area 0 - current frame */
+	uint	sen_tbuf1data1;	/* Save area 1 - current frame */
+	uint	sen_tbuf1rba;	/* Internal */
+	uint	sen_tbuf1crc;	/* Internal */
+	ushort	sen_tbuf1bcnt;	/* Internal */
+	ushort	sen_txlen;	/* Tx Frame length counter */
+	ushort	sen_iaddr1;	/* Individual address filter */
+	ushort	sen_iaddr2;
+	ushort	sen_iaddr3;
+	ushort	sen_iaddr4;
+	ushort	sen_boffcnt;	/* Backoff counter */
+
+	/* NOTE: Some versions of the manual have the following items
+	 * incorrectly documented.  Below is the proper order.
+	 */
+	ushort	sen_taddrh;	/* temp address (MSB) */
+	ushort	sen_taddrm;
+	ushort	sen_taddrl;	/* temp address (LSB) */
+} scc_enet_t;
+
+/* SCC Event register as used by Ethernet.
+*/
+#define SCCE_ENET_GRA	((ushort)0x0080)	/* Graceful stop complete */
+#define SCCE_ENET_TXE	((ushort)0x0010)	/* Transmit Error */
+#define SCCE_ENET_RXF	((ushort)0x0008)	/* Full frame received */
+#define SCCE_ENET_BSY	((ushort)0x0004)	/* All incoming buffers full */
+#define SCCE_ENET_TXB	((ushort)0x0002)	/* A buffer was transmitted */
+#define SCCE_ENET_RXB	((ushort)0x0001)	/* A buffer was received */
+
+/* SCC Mode Register (PMSR) as used by Ethernet.
+*/
+#define SCC_PSMR_HBC	((ushort)0x8000)	/* Enable heartbeat */
+#define SCC_PSMR_FC	((ushort)0x4000)	/* Force collision */
+#define SCC_PSMR_RSH	((ushort)0x2000)	/* Receive short frames */
+#define SCC_PSMR_IAM	((ushort)0x1000)	/* Check individual hash */
+#define SCC_PSMR_ENCRC	((ushort)0x0800)	/* Ethernet CRC mode */
+#define SCC_PSMR_PRO	((ushort)0x0200)	/* Promiscuous mode */
+#define SCC_PSMR_BRO	((ushort)0x0100)	/* Catch broadcast pkts */
+#define SCC_PSMR_SBT	((ushort)0x0080)	/* Special backoff timer */
+#define SCC_PSMR_LPB	((ushort)0x0040)	/* Set Loopback mode */
+#define SCC_PSMR_SIP	((ushort)0x0020)	/* Sample Input Pins */
+#define SCC_PSMR_LCW	((ushort)0x0010)	/* Late collision window */
+#define SCC_PSMR_NIB22	((ushort)0x000a)	/* Start frame search */
+#define SCC_PSMR_FDE	((ushort)0x0001)	/* Full duplex enable */
+
+/* SCC as UART
+*/
+typedef struct scc_uart {
+	sccp_t	scc_genscc;
+	char	res1[8];	/* Reserved */
+	ushort	scc_maxidl;	/* Maximum idle chars */
+	ushort	scc_idlc;	/* temp idle counter */
+	ushort	scc_brkcr;	/* Break count register */
+	ushort	scc_parec;	/* receive parity error counter */
+	ushort	scc_frmec;	/* receive framing error counter */
+	ushort	scc_nosec;	/* receive noise counter */
+	ushort	scc_brkec;	/* receive break condition counter */
+	ushort	scc_brkln;	/* last received break length */
+	ushort	scc_uaddr1;	/* UART address character 1 */
+	ushort	scc_uaddr2;	/* UART address character 2 */
+	ushort	scc_rtemp;	/* Temp storage */
+	ushort	scc_toseq;	/* Transmit out of sequence char */
+	ushort	scc_char1;	/* control character 1 */
+	ushort	scc_char2;	/* control character 2 */
+	ushort	scc_char3;	/* control character 3 */
+	ushort	scc_char4;	/* control character 4 */
+	ushort	scc_char5;	/* control character 5 */
+	ushort	scc_char6;	/* control character 6 */
+	ushort	scc_char7;	/* control character 7 */
+	ushort	scc_char8;	/* control character 8 */
+	ushort	scc_rccm;	/* receive control character mask */
+	ushort	scc_rccr;	/* receive control character register */
+	ushort	scc_rlbc;	/* receive last break character */
+} scc_uart_t;
+
+/* SCC Event and Mask registers when it is used as a UART.
+*/
+#define UART_SCCM_GLR		((ushort)0x1000)
+#define UART_SCCM_GLT		((ushort)0x0800)
+#define UART_SCCM_AB		((ushort)0x0200)
+#define UART_SCCM_IDL		((ushort)0x0100)
+#define UART_SCCM_GRA		((ushort)0x0080)
+#define UART_SCCM_BRKE		((ushort)0x0040)
+#define UART_SCCM_BRKS		((ushort)0x0020)
+#define UART_SCCM_CCR		((ushort)0x0008)
+#define UART_SCCM_BSY		((ushort)0x0004)
+#define UART_SCCM_TX		((ushort)0x0002)
+#define UART_SCCM_RX		((ushort)0x0001)
+
+/* The SCC PMSR when used as a UART.
+*/
+#define SCU_PSMR_FLC		((ushort)0x8000)
+#define SCU_PSMR_SL		((ushort)0x4000)
+#define SCU_PSMR_CL		((ushort)0x3000)
+#define SCU_PSMR_UM		((ushort)0x0c00)
+#define SCU_PSMR_FRZ		((ushort)0x0200)
+#define SCU_PSMR_RZS		((ushort)0x0100)
+#define SCU_PSMR_SYN		((ushort)0x0080)
+#define SCU_PSMR_DRT		((ushort)0x0040)
+#define SCU_PSMR_PEN		((ushort)0x0010)
+#define SCU_PSMR_RPM		((ushort)0x000c)
+#define SCU_PSMR_REVP		((ushort)0x0008)
+#define SCU_PSMR_TPM		((ushort)0x0003)
+#define SCU_PSMR_TEVP		((ushort)0x0002)
+
+/* CPM Transparent mode SCC.
+ */
+typedef struct scc_trans {
+	sccp_t	st_genscc;
+	uint	st_cpres;	/* Preset CRC */
+	uint	st_cmask;	/* Constant mask for CRC */
+} scc_trans_t;
+
+/* IIC parameter RAM.
+*/
+typedef struct iic {
+	ushort	iic_rbase;	/* Rx Buffer descriptor base address */
+	ushort	iic_tbase;	/* Tx Buffer descriptor base address */
+	u_char	iic_rfcr;	/* Rx function code */
+	u_char	iic_tfcr;	/* Tx function code */
+	ushort	iic_mrblr;	/* Max receive buffer length */
+	uint	iic_rstate;	/* Internal */
+	uint	iic_rdp;	/* Internal */
+	ushort	iic_rbptr;	/* Internal */
+	ushort	iic_rbc;	/* Internal */
+	uint	iic_rxtmp;	/* Internal */
+	uint	iic_tstate;	/* Internal */
+	uint	iic_tdp;	/* Internal */
+	ushort	iic_tbptr;	/* Internal */
+	ushort	iic_tbc;	/* Internal */
+	uint	iic_txtmp;	/* Internal */
+	char	res1[4];	/* Reserved */
+	ushort	iic_rpbase;	/* Relocation pointer */
+	char	res2[2];	/* Reserved */
+} iic_t;
+
+/*
+ * RISC Controller Configuration Register definitons
+ */
+#define RCCR_TIME	0x8000			/* RISC Timer Enable */
+#define RCCR_TIMEP(t)	(((t) & 0x3F)<<8)	/* RISC Timer Period */
+#define RCCR_TIME_MASK	0x00FF			/* not RISC Timer related bits */
+
+/* RISC Timer Parameter RAM offset */
+#define PROFF_RTMR	((uint)0x01B0)
+
+typedef struct risc_timer_pram {
+	unsigned short	tm_base;	/* RISC Timer Table Base Address */
+	unsigned short	tm_ptr;		/* RISC Timer Table Pointer (internal) */
+	unsigned short	r_tmr;		/* RISC Timer Mode Register */
+	unsigned short	r_tmv;		/* RISC Timer Valid Register */
+	unsigned long	tm_cmd;		/* RISC Timer Command Register */
+	unsigned long	tm_cnt;		/* RISC Timer Internal Count */
+} rt_pram_t;
+
+/* Bits in RISC Timer Command Register */
+#define TM_CMD_VALID	0x80000000	/* Valid - Enables the timer */
+#define TM_CMD_RESTART	0x40000000	/* Restart - for automatic restart */
+#define TM_CMD_PWM	0x20000000	/* Run in Pulse Width Modulation Mode */
+#define TM_CMD_NUM(n)	(((n)&0xF)<<16)	/* Timer Number */
+#define TM_CMD_PERIOD(p) ((p)&0xFFFF)	/* Timer Period */
+
+/* CPM interrupts.  There are nearly 32 interrupts generated by CPM
+ * channels or devices.  All of these are presented to the PPC core
+ * as a single interrupt.  The CPM interrupt handler dispatches its
+ * own handlers, in a similar fashion to the PPC core handler.  We
+ * use the table as defined in the manuals (i.e. no special high
+ * priority and SCC1 == SCCa, etc...).
+ */
+#define CPMVEC_NR		32
+#define	CPMVEC_PIO_PC15		((ushort)0x1f)
+#define	CPMVEC_SCC1		((ushort)0x1e)
+#define	CPMVEC_SCC2		((ushort)0x1d)
+#define	CPMVEC_SCC3		((ushort)0x1c)
+#define	CPMVEC_SCC4		((ushort)0x1b)
+#define	CPMVEC_PIO_PC14		((ushort)0x1a)
+#define	CPMVEC_TIMER1		((ushort)0x19)
+#define	CPMVEC_PIO_PC13		((ushort)0x18)
+#define	CPMVEC_PIO_PC12		((ushort)0x17)
+#define	CPMVEC_SDMA_CB_ERR	((ushort)0x16)
+#define CPMVEC_IDMA1		((ushort)0x15)
+#define CPMVEC_IDMA2		((ushort)0x14)
+#define CPMVEC_TIMER2		((ushort)0x12)
+#define CPMVEC_RISCTIMER	((ushort)0x11)
+#define CPMVEC_I2C		((ushort)0x10)
+#define	CPMVEC_PIO_PC11		((ushort)0x0f)
+#define	CPMVEC_PIO_PC10		((ushort)0x0e)
+#define CPMVEC_TIMER3		((ushort)0x0c)
+#define	CPMVEC_PIO_PC9		((ushort)0x0b)
+#define	CPMVEC_PIO_PC8		((ushort)0x0a)
+#define	CPMVEC_PIO_PC7		((ushort)0x09)
+#define CPMVEC_TIMER4		((ushort)0x07)
+#define	CPMVEC_PIO_PC6		((ushort)0x06)
+#define	CPMVEC_SPI		((ushort)0x05)
+#define	CPMVEC_SMC1		((ushort)0x04)
+#define	CPMVEC_SMC2		((ushort)0x03)
+#define	CPMVEC_PIO_PC5		((ushort)0x02)
+#define	CPMVEC_PIO_PC4		((ushort)0x01)
+#define	CPMVEC_ERROR		((ushort)0x00)
+
+/* CPM interrupt configuration vector.
+*/
+#define	CICR_SCD_SCC4		((uint)0x00c00000)	/* SCC4 @ SCCd */
+#define	CICR_SCC_SCC3		((uint)0x00200000)	/* SCC3 @ SCCc */
+#define	CICR_SCB_SCC2		((uint)0x00040000)	/* SCC2 @ SCCb */
+#define	CICR_SCA_SCC1		((uint)0x00000000)	/* SCC1 @ SCCa */
+#define CICR_IRL_MASK		((uint)0x0000e000)	/* Core interrupt */
+#define CICR_HP_MASK		((uint)0x00001f00)	/* Hi-pri int. */
+#define CICR_IEN		((uint)0x00000080)	/* Int. enable */
+#define CICR_SPS		((uint)0x00000001)	/* SCC Spread */
+
+#define CPM_PIN_INPUT     0
+#define CPM_PIN_OUTPUT    1
+#define CPM_PIN_PRIMARY   0
+#define CPM_PIN_SECONDARY 2
+#define CPM_PIN_GPIO      4
+#define CPM_PIN_OPENDRAIN 8
+#define CPM_PIN_FALLEDGE  16
+#define CPM_PIN_ANYEDGE   0
+
+enum cpm_port {
+	CPM_PORTA,
+	CPM_PORTB,
+	CPM_PORTC,
+	CPM_PORTD,
+	CPM_PORTE,
+};
+
+void cpm1_set_pin(enum cpm_port port, int pin, int flags);
+
+enum cpm_clk_dir {
+	CPM_CLK_RX,
+	CPM_CLK_TX,
+	CPM_CLK_RTX
+};
+
+enum cpm_clk_target {
+	CPM_CLK_SCC1,
+	CPM_CLK_SCC2,
+	CPM_CLK_SCC3,
+	CPM_CLK_SCC4,
+	CPM_CLK_SMC1,
+	CPM_CLK_SMC2,
+};
+
+enum cpm_clk {
+	CPM_BRG1,	/* Baud Rate Generator  1 */
+	CPM_BRG2,	/* Baud Rate Generator  2 */
+	CPM_BRG3,	/* Baud Rate Generator  3 */
+	CPM_BRG4,	/* Baud Rate Generator  4 */
+	CPM_CLK1,	/* Clock  1 */
+	CPM_CLK2,	/* Clock  2 */
+	CPM_CLK3,	/* Clock  3 */
+	CPM_CLK4,	/* Clock  4 */
+	CPM_CLK5,	/* Clock  5 */
+	CPM_CLK6,	/* Clock  6 */
+	CPM_CLK7,	/* Clock  7 */
+	CPM_CLK8,	/* Clock  8 */
+};
+
+int cpm1_clk_setup(enum cpm_clk_target target, int clock, int mode);
+int cpm1_gpiochip_add16(struct device *dev);
+int cpm1_gpiochip_add32(struct device *dev);
+
+#endif /* __CPM1__ */

linux-7.2.3/arch/powerpc/include/asm/cpu_has_feature.h

@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_POWERPC_CPU_HAS_FEATURE_H
+#define __ASM_POWERPC_CPU_HAS_FEATURE_H
+
+#ifndef __ASSEMBLER__
+
+#include <linux/bug.h>
+#include <asm/cputable.h>
+
+static __always_inline bool early_cpu_has_feature(unsigned long feature)
+{
+	return !!((CPU_FTRS_ALWAYS & feature) ||
+		  (CPU_FTRS_POSSIBLE & cur_cpu_spec->cpu_features & feature));
+}
+
+#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS
+#include <linux/jump_label.h>
+
+#define NUM_CPU_FTR_KEYS	BITS_PER_LONG
+
+extern struct static_key_true cpu_feature_keys[NUM_CPU_FTR_KEYS];
+
+static __always_inline bool cpu_has_feature(unsigned long feature)
+{
+	int i;
+
+	BUILD_BUG_ON(!__builtin_constant_p(feature));
+	BUILD_BUG_ON(__builtin_popcountl(feature) > 1);
+
+#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECK_DEBUG
+	if (!static_key_feature_checks_initialized) {
+		printk("Warning! cpu_has_feature() used prior to jump label init!\n");
+		dump_stack();
+		return early_cpu_has_feature(feature);
+	}
+#endif
+
+	if (CPU_FTRS_ALWAYS & feature)
+		return true;
+
+	if (!(CPU_FTRS_POSSIBLE & feature))
+		return false;
+
+	i = __builtin_ctzl(feature);
+	return static_branch_likely(&cpu_feature_keys[i]);
+}
+#else
+static __always_inline bool cpu_has_feature(unsigned long feature)
+{
+	return early_cpu_has_feature(feature);
+}
+#endif
+
+#endif /* __ASSEMBLER__ */
+#endif /* __ASM_POWERPC_CPU_HAS_FEATURE_H */

linux-7.2.3/arch/powerpc/include/asm/cpu_setup.h

@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2020 IBM Corporation
+ */
+
+#ifndef _ASM_POWERPC_CPU_SETUP_H
+#define _ASM_POWERPC_CPU_SETUP_H
+void __setup_cpu_power7(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_power8(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_power9(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_power10(unsigned long offset, struct cpu_spec *spec);
+void __restore_cpu_power7(void);
+void __restore_cpu_power8(void);
+void __restore_cpu_power9(void);
+void __restore_cpu_power10(void);
+
+void __setup_cpu_e500v1(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_e500v2(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_e500mc(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_440ep(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_440epx(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_440gx(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_440grx(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_440spe(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_440x5(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_460ex(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_460gt(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_460sx(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_apm821xx(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_603(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_604(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_750(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_750cx(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_750fx(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_7400(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_7410(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_745x(unsigned long offset, struct cpu_spec *spec);
+
+void __setup_cpu_ppc970(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_ppc970MP(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_pa6t(unsigned long offset, struct cpu_spec *spec);
+void __restore_cpu_pa6t(void);
+void __restore_cpu_ppc970(void);
+
+void __setup_cpu_e5500(unsigned long offset, struct cpu_spec *spec);
+void __setup_cpu_e6500(unsigned long offset, struct cpu_spec *spec);
+void __restore_cpu_e5500(void);
+void __restore_cpu_e6500(void);
+#endif /* _ASM_POWERPC_CPU_SETUP_H */

linux-7.2.3/arch/powerpc/include/asm/cpufeature.h

@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * CPU feature definitions for module loading, used by
+ * module_cpu_feature_match(), see asm/cputable.h for powerpc CPU features.
+ *
+ * Copyright 2016 Alastair D'Silva, IBM Corporation.
+ */
+
+#ifndef __ASM_POWERPC_CPUFEATURE_H
+#define __ASM_POWERPC_CPUFEATURE_H
+
+#include <asm/cputable.h>
+
+/* Keep these in step with powerpc/include/asm/cputable.h */
+#define MAX_CPU_FEATURES (2 * 32)
+
+/*
+ * Currently we don't have a need for any of the feature bits defined in
+ * cpu_user_features. When we do, they should be defined such as:
+ *
+ * #define PPC_MODULE_FEATURE_32 (ilog2(PPC_FEATURE_32))
+ */
+
+#define PPC_MODULE_FEATURE_VEC_CRYPTO			(32 + ilog2(PPC_FEATURE2_VEC_CRYPTO))
+#define PPC_MODULE_FEATURE_P10				(32 + ilog2(PPC_FEATURE2_ARCH_3_1))
+
+#define cpu_feature(x)		(x)
+
+static inline bool cpu_have_feature(unsigned int num)
+{
+	if (num < 32)
+		return !!(cur_cpu_spec->cpu_user_features & 1UL << num);
+	else
+		return !!(cur_cpu_spec->cpu_user_features2 & 1UL << (num - 32));
+}
+
+#endif /* __ASM_POWERPC_CPUFEATURE_H */

linux-7.2.3/arch/powerpc/include/asm/cpuidle.h

@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_CPUIDLE_H
+#define _ASM_POWERPC_CPUIDLE_H
+
+#ifdef CONFIG_PPC_POWERNV
+/* Thread state used in powernv idle state management */
+#define PNV_THREAD_RUNNING              0
+#define PNV_THREAD_NAP                  1
+#define PNV_THREAD_SLEEP                2
+#define PNV_THREAD_WINKLE               3
+
+/*
+ * Core state used in powernv idle for POWER8.
+ *
+ * The lock bit synchronizes updates to the state, as well as parts of the
+ * sleep/wake code (see kernel/idle_book3s.S).
+ *
+ * Bottom 8 bits track the idle state of each thread. Bit is cleared before
+ * the thread executes an idle instruction (nap/sleep/winkle).
+ *
+ * Then there is winkle tracking. A core does not lose complete state
+ * until every thread is in winkle. So the winkle count field counts the
+ * number of threads in winkle (small window of false positives is okay
+ * around the sleep/wake, so long as there are no false negatives).
+ *
+ * When the winkle count reaches 8 (the COUNT_ALL_BIT becomes set), then
+ * the THREAD_WINKLE_BITS are set, which indicate which threads have not
+ * yet woken from the winkle state.
+ */
+#define NR_PNV_CORE_IDLE_LOCK_BIT		28
+#define PNV_CORE_IDLE_LOCK_BIT			(1ULL << NR_PNV_CORE_IDLE_LOCK_BIT)
+
+#define PNV_CORE_IDLE_WINKLE_COUNT_SHIFT	16
+#define PNV_CORE_IDLE_WINKLE_COUNT		0x00010000
+#define PNV_CORE_IDLE_WINKLE_COUNT_BITS		0x000F0000
+#define PNV_CORE_IDLE_THREAD_WINKLE_BITS_SHIFT	8
+#define PNV_CORE_IDLE_THREAD_WINKLE_BITS	0x0000FF00
+
+#define PNV_CORE_IDLE_THREAD_BITS       	0x000000FF
+
+/*
+ * ============================ NOTE =================================
+ * The older firmware populates only the RL field in the psscr_val and
+ * sets the psscr_mask to 0xf. On such a firmware, the kernel sets the
+ * remaining PSSCR fields to default values as follows:
+ *
+ * - ESL and EC bits are to 1. So wakeup from any stop state will be
+ *   at vector 0x100.
+ *
+ * - MTL and PSLL are set to the maximum allowed value as per the ISA,
+ *    i.e. 15.
+ *
+ * - The Transition Rate, TR is set to the Maximum value 3.
+ */
+#define PSSCR_HV_DEFAULT_VAL    (PSSCR_ESL | PSSCR_EC |		    \
+				PSSCR_PSLL_MASK | PSSCR_TR_MASK |   \
+				PSSCR_MTL_MASK)
+
+#define PSSCR_HV_DEFAULT_MASK   (PSSCR_ESL | PSSCR_EC |		    \
+				PSSCR_PSLL_MASK | PSSCR_TR_MASK |   \
+				PSSCR_MTL_MASK | PSSCR_RL_MASK)
+#define PSSCR_EC_SHIFT    20
+#define PSSCR_ESL_SHIFT   21
+#define GET_PSSCR_EC(x)   (((x) & PSSCR_EC) >> PSSCR_EC_SHIFT)
+#define GET_PSSCR_ESL(x)  (((x) & PSSCR_ESL) >> PSSCR_ESL_SHIFT)
+#define GET_PSSCR_RL(x)   ((x) & PSSCR_RL_MASK)
+
+#define ERR_EC_ESL_MISMATCH		-1
+#define ERR_DEEP_STATE_ESL_MISMATCH	-2
+
+#ifndef __ASSEMBLER__
+
+#define PNV_IDLE_NAME_LEN    16
+struct pnv_idle_states_t {
+	char name[PNV_IDLE_NAME_LEN];
+	u32 latency_ns;
+	u32 residency_ns;
+	u64 psscr_val;
+	u64 psscr_mask;
+	u32 flags;
+	bool valid;
+};
+
+extern struct pnv_idle_states_t *pnv_idle_states;
+extern int nr_pnv_idle_states;
+
+unsigned long pnv_cpu_offline(unsigned int cpu);
+int __init validate_psscr_val_mask(u64 *psscr_val, u64 *psscr_mask, u32 flags);
+static inline void report_invalid_psscr_val(u64 psscr_val, int err)
+{
+	switch (err) {
+	case ERR_EC_ESL_MISMATCH:
+		pr_warn("Invalid psscr 0x%016llx : ESL,EC bits unequal",
+			psscr_val);
+		break;
+	case ERR_DEEP_STATE_ESL_MISMATCH:
+		pr_warn("Invalid psscr 0x%016llx : ESL cleared for deep stop-state",
+			psscr_val);
+	}
+}
+#endif
+
+#endif
+
+#endif

linux-7.2.3/arch/powerpc/include/asm/cputable.h

@@ -0,0 +1,607 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_POWERPC_CPUTABLE_H
+#define __ASM_POWERPC_CPUTABLE_H
+
+
+#include <linux/types.h>
+#include <uapi/asm/cputable.h>
+#include <asm/asm-const.h>
+
+#ifndef __ASSEMBLER__
+
+/* This structure can grow, it's real size is used by head.S code
+ * via the mkdefs mechanism.
+ */
+struct cpu_spec;
+
+typedef	void (*cpu_setup_t)(unsigned long offset, struct cpu_spec* spec);
+typedef	void (*cpu_restore_t)(void);
+
+enum powerpc_pmc_type {
+	PPC_PMC_DEFAULT = 0,
+	PPC_PMC_IBM = 1,
+	PPC_PMC_PA6T = 2,
+	PPC_PMC_G4 = 3,
+};
+
+struct pt_regs;
+
+extern int machine_check_generic(struct pt_regs *regs);
+extern int machine_check_4xx(struct pt_regs *regs);
+extern int machine_check_440A(struct pt_regs *regs);
+extern int machine_check_e500mc(struct pt_regs *regs);
+extern int machine_check_e500(struct pt_regs *regs);
+extern int machine_check_47x(struct pt_regs *regs);
+int machine_check_8xx(struct pt_regs *regs);
+int machine_check_83xx(struct pt_regs *regs);
+
+extern void cpu_down_flush_e500v2(void);
+extern void cpu_down_flush_e500mc(void);
+extern void cpu_down_flush_e5500(void);
+extern void cpu_down_flush_e6500(void);
+
+/* NOTE WELL: Update identify_cpu() if fields are added or removed! */
+struct cpu_spec {
+	/* CPU is matched via (PVR & pvr_mask) == pvr_value */
+	unsigned int	pvr_mask;
+	unsigned int	pvr_value;
+
+	char		*cpu_name;
+	unsigned long	cpu_features;		/* Kernel features */
+	unsigned int	cpu_user_features;	/* Userland features */
+	unsigned int	cpu_user_features2;	/* Userland features v2 */
+	unsigned int	mmu_features;		/* MMU features */
+
+	/* cache line sizes */
+	unsigned int	icache_bsize;
+	unsigned int	dcache_bsize;
+
+	/* flush caches inside the current cpu */
+	void (*cpu_down_flush)(void);
+
+	/* number of performance monitor counters */
+	unsigned int	num_pmcs;
+	enum powerpc_pmc_type pmc_type;
+
+	/* this is called to initialize various CPU bits like L1 cache,
+	 * BHT, SPD, etc... from head.S before branching to identify_machine
+	 */
+	cpu_setup_t	cpu_setup;
+	/* Used to restore cpu setup on secondary processors and at resume */
+	cpu_restore_t	cpu_restore;
+
+	/* Name of processor class, for the ELF AT_PLATFORM entry */
+	char		*platform;
+
+	/* Processor specific machine check handling. Return negative
+	 * if the error is fatal, 1 if it was fully recovered and 0 to
+	 * pass up (not CPU originated) */
+	int		(*machine_check)(struct pt_regs *regs);
+
+	/*
+	 * Processor specific early machine check handler which is
+	 * called in real mode to handle SLB and TLB errors.
+	 */
+	long		(*machine_check_early)(struct pt_regs *regs);
+};
+
+extern struct cpu_spec		*cur_cpu_spec;
+
+extern unsigned int __start___ftr_fixup, __stop___ftr_fixup;
+
+extern void set_cur_cpu_spec(struct cpu_spec *s);
+extern struct cpu_spec *identify_cpu(unsigned long offset, unsigned int pvr);
+extern void identify_cpu_name(unsigned int pvr);
+extern void do_feature_fixups(unsigned long value, void *fixup_start,
+			      void *fixup_end);
+
+extern const char *powerpc_base_platform;
+
+#ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS
+extern void cpu_feature_keys_init(void);
+#else
+static inline void cpu_feature_keys_init(void) { }
+#endif
+
+#endif /* __ASSEMBLER__ */
+
+/* CPU kernel features */
+
+/* Definitions for features that we have on both 32-bit and 64-bit chips */
+#define CPU_FTR_COHERENT_ICACHE		ASM_CONST(0x00000001)
+#define CPU_FTR_ALTIVEC			ASM_CONST(0x00000002)
+#define CPU_FTR_DBELL			ASM_CONST(0x00000004)
+#define CPU_FTR_CAN_NAP			ASM_CONST(0x00000008)
+#define CPU_FTR_DEBUG_LVL_EXC		ASM_CONST(0x00000010)
+// ASM_CONST(0x00000020) Free
+#define CPU_FTR_FPU_UNAVAILABLE		ASM_CONST(0x00000040)
+#define CPU_FTR_LWSYNC			ASM_CONST(0x00000080)
+#define CPU_FTR_NOEXECUTE		ASM_CONST(0x00000100)
+#define CPU_FTR_EMB_HV			ASM_CONST(0x00000200)
+
+/* Definitions for features that only exist on 32-bit chips */
+#ifdef CONFIG_PPC32
+#define CPU_FTR_L2CR			ASM_CONST(0x00002000)
+#define CPU_FTR_SPEC7450		ASM_CONST(0x00004000)
+#define CPU_FTR_TAU			ASM_CONST(0x00008000)
+#define CPU_FTR_CAN_DOZE		ASM_CONST(0x00010000)
+#define CPU_FTR_L3CR			ASM_CONST(0x00040000)
+#define CPU_FTR_L3_DISABLE_NAP		ASM_CONST(0x00080000)
+#define CPU_FTR_NAP_DISABLE_L2_PR	ASM_CONST(0x00100000)
+#define CPU_FTR_DUAL_PLL_750FX		ASM_CONST(0x00200000)
+#define CPU_FTR_NO_DPM			ASM_CONST(0x00400000)
+#define CPU_FTR_476_DD2			ASM_CONST(0x00800000)
+#define CPU_FTR_NEED_COHERENT		ASM_CONST(0x01000000)
+#define CPU_FTR_NO_BTIC			ASM_CONST(0x02000000)
+#define CPU_FTR_PPC_LE			ASM_CONST(0x04000000)
+#define CPU_FTR_SPE			ASM_CONST(0x10000000)
+#define CPU_FTR_NEED_PAIRED_STWCX	ASM_CONST(0x20000000)
+#define CPU_FTR_INDEXED_DCR		ASM_CONST(0x40000000)
+
+#else	/* CONFIG_PPC32 */
+/* Define these to 0 for the sake of tests in common code */
+#define CPU_FTR_PPC_LE			(0)
+#define CPU_FTR_SPE			(0)
+#endif
+
+/*
+ * Definitions for the 64-bit processor unique features;
+ * on 32-bit, make the names available but defined to be 0.
+ */
+#ifdef __powerpc64__
+#define LONG_ASM_CONST(x)		ASM_CONST(x)
+#else
+#define LONG_ASM_CONST(x)		0
+#endif
+
+#define CPU_FTR_REAL_LE			LONG_ASM_CONST(0x0000000000001000)
+#define CPU_FTR_HVMODE			LONG_ASM_CONST(0x0000000000002000)
+#define CPU_FTR_ARCH_206		LONG_ASM_CONST(0x0000000000008000)
+#define CPU_FTR_ARCH_207S		LONG_ASM_CONST(0x0000000000010000)
+#define CPU_FTR_ARCH_300		LONG_ASM_CONST(0x0000000000020000)
+#define CPU_FTR_MMCRA			LONG_ASM_CONST(0x0000000000040000)
+#define CPU_FTR_CTRL			LONG_ASM_CONST(0x0000000000080000)
+#define CPU_FTR_SMT			LONG_ASM_CONST(0x0000000000100000)
+#define CPU_FTR_PAUSE_ZERO		LONG_ASM_CONST(0x0000000000200000)
+#define CPU_FTR_PURR			LONG_ASM_CONST(0x0000000000400000)
+#define CPU_FTR_CELL_TB_BUG		LONG_ASM_CONST(0x0000000000800000)
+#define CPU_FTR_SPURR			LONG_ASM_CONST(0x0000000001000000)
+#define CPU_FTR_DSCR			LONG_ASM_CONST(0x0000000002000000)
+#define CPU_FTR_VSX			LONG_ASM_CONST(0x0000000004000000)
+#define CPU_FTR_SAO			LONG_ASM_CONST(0x0000000008000000)
+#define CPU_FTR_CP_USE_DCBTZ		LONG_ASM_CONST(0x0000000010000000)
+#define CPU_FTR_UNALIGNED_LD_STD	LONG_ASM_CONST(0x0000000020000000)
+#define CPU_FTR_ASYM_SMT		LONG_ASM_CONST(0x0000000040000000)
+#define CPU_FTR_STCX_CHECKS_ADDRESS	LONG_ASM_CONST(0x0000000080000000)
+#define CPU_FTR_POPCNTB			LONG_ASM_CONST(0x0000000100000000)
+#define CPU_FTR_POPCNTD			LONG_ASM_CONST(0x0000000200000000)
+/* LONG_ASM_CONST(0x0000000400000000) Free */
+#define CPU_FTR_VMX_COPY		LONG_ASM_CONST(0x0000000800000000)
+#define CPU_FTR_TM			LONG_ASM_CONST(0x0000001000000000)
+#define CPU_FTR_CFAR			LONG_ASM_CONST(0x0000002000000000)
+#define	CPU_FTR_HAS_PPR			LONG_ASM_CONST(0x0000004000000000)
+#define CPU_FTR_DAWR			LONG_ASM_CONST(0x0000008000000000)
+#define CPU_FTR_DABRX			LONG_ASM_CONST(0x0000010000000000)
+#define CPU_FTR_PMAO_BUG		LONG_ASM_CONST(0x0000020000000000)
+#define CPU_FTR_POWER9_DD2_1		LONG_ASM_CONST(0x0000080000000000)
+#define CPU_FTR_P9_TM_HV_ASSIST		LONG_ASM_CONST(0x0000100000000000)
+#define CPU_FTR_P9_TM_XER_SO_BUG	LONG_ASM_CONST(0x0000200000000000)
+#define CPU_FTR_P9_TLBIE_STQ_BUG	LONG_ASM_CONST(0x0000400000000000)
+#define CPU_FTR_P9_TIDR			LONG_ASM_CONST(0x0000800000000000)
+#define CPU_FTR_P9_TLBIE_ERAT_BUG	LONG_ASM_CONST(0x0001000000000000)
+#define CPU_FTR_P9_RADIX_PREFETCH_BUG	LONG_ASM_CONST(0x0002000000000000)
+#define CPU_FTR_ARCH_31			LONG_ASM_CONST(0x0004000000000000)
+#define CPU_FTR_DAWR1			LONG_ASM_CONST(0x0008000000000000)
+#define CPU_FTR_DEXCR_NPHIE		LONG_ASM_CONST(0x0010000000000000)
+#define CPU_FTR_P11_PVR			LONG_ASM_CONST(0x0020000000000000)
+
+#ifndef __ASSEMBLER__
+
+#define CPU_FTR_PPCAS_ARCH_V2	(CPU_FTR_NOEXECUTE)
+
+/* We only set the altivec features if the kernel was compiled with altivec
+ * support
+ */
+#ifdef CONFIG_ALTIVEC
+#define CPU_FTR_ALTIVEC_COMP	CPU_FTR_ALTIVEC
+#define PPC_FEATURE_HAS_ALTIVEC_COMP PPC_FEATURE_HAS_ALTIVEC
+#else
+#define CPU_FTR_ALTIVEC_COMP	0
+#define PPC_FEATURE_HAS_ALTIVEC_COMP    0
+#endif
+
+/* We only set the VSX features if the kernel was compiled with VSX
+ * support
+ */
+#ifdef CONFIG_VSX
+#define CPU_FTR_VSX_COMP	CPU_FTR_VSX
+#define PPC_FEATURE_HAS_VSX_COMP PPC_FEATURE_HAS_VSX
+#else
+#define CPU_FTR_VSX_COMP	0
+#define PPC_FEATURE_HAS_VSX_COMP    0
+#endif
+
+/* We only set the spe features if the kernel was compiled with spe
+ * support
+ */
+#ifdef CONFIG_SPE
+#define CPU_FTR_SPE_COMP	CPU_FTR_SPE
+#define PPC_FEATURE_HAS_SPE_COMP PPC_FEATURE_HAS_SPE
+#define PPC_FEATURE_HAS_EFP_SINGLE_COMP PPC_FEATURE_HAS_EFP_SINGLE
+#define PPC_FEATURE_HAS_EFP_DOUBLE_COMP PPC_FEATURE_HAS_EFP_DOUBLE
+#else
+#define CPU_FTR_SPE_COMP	0
+#define PPC_FEATURE_HAS_SPE_COMP    0
+#define PPC_FEATURE_HAS_EFP_SINGLE_COMP 0
+#define PPC_FEATURE_HAS_EFP_DOUBLE_COMP 0
+#endif
+
+/* We only set the TM feature if the kernel was compiled with TM supprt */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+#define CPU_FTR_TM_COMP			CPU_FTR_TM
+#define PPC_FEATURE2_HTM_COMP		PPC_FEATURE2_HTM
+#define PPC_FEATURE2_HTM_NOSC_COMP	PPC_FEATURE2_HTM_NOSC
+#else
+#define CPU_FTR_TM_COMP			0
+#define PPC_FEATURE2_HTM_COMP		0
+#define PPC_FEATURE2_HTM_NOSC_COMP	0
+#endif
+
+/* We need to mark all pages as being coherent if we're SMP or we have a
+ * 74[45]x and an MPC107 host bridge. Also 83xx and PowerQUICC II
+ * require it for PCI "streaming/prefetch" to work properly.
+ * This is also required by 52xx family.
+ */
+#if defined(CONFIG_SMP) || defined(CONFIG_MPC10X_BRIDGE) \
+	|| defined(CONFIG_PPC_83xx) || defined(CONFIG_PPC_82xx) \
+	|| defined(CONFIG_PPC_MPC52xx)
+#define CPU_FTR_COMMON                  CPU_FTR_NEED_COHERENT
+#else
+#define CPU_FTR_COMMON                  0
+#endif
+
+/* The powersave features NAP & DOZE seems to confuse BDI when
+   debugging. So if a BDI is used, disable theses
+ */
+#ifndef CONFIG_BDI_SWITCH
+#define CPU_FTR_MAYBE_CAN_DOZE	CPU_FTR_CAN_DOZE
+#define CPU_FTR_MAYBE_CAN_NAP	CPU_FTR_CAN_NAP
+#else
+#define CPU_FTR_MAYBE_CAN_DOZE	0
+#define CPU_FTR_MAYBE_CAN_NAP	0
+#endif
+
+#define CPU_FTRS_603	(CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \
+	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE | CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_604	(CPU_FTR_COMMON | CPU_FTR_PPC_LE)
+#define CPU_FTRS_740_NOTAU	(CPU_FTR_COMMON | \
+	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_L2CR | \
+	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
+#define CPU_FTRS_740	(CPU_FTR_COMMON | \
+	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_L2CR | \
+	    CPU_FTR_TAU | CPU_FTR_MAYBE_CAN_NAP | \
+	    CPU_FTR_PPC_LE)
+#define CPU_FTRS_750	(CPU_FTR_COMMON | \
+	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_L2CR | \
+	    CPU_FTR_TAU | CPU_FTR_MAYBE_CAN_NAP | \
+	    CPU_FTR_PPC_LE)
+#define CPU_FTRS_750CL	(CPU_FTRS_750)
+#define CPU_FTRS_750FX1	(CPU_FTRS_750 | CPU_FTR_DUAL_PLL_750FX | CPU_FTR_NO_DPM)
+#define CPU_FTRS_750FX2	(CPU_FTRS_750 | CPU_FTR_NO_DPM)
+#define CPU_FTRS_750FX	(CPU_FTRS_750 | CPU_FTR_DUAL_PLL_750FX)
+#define CPU_FTRS_750GX	(CPU_FTRS_750FX)
+#define CPU_FTRS_7400_NOTAU	(CPU_FTR_COMMON | \
+	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_L2CR | \
+	    CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
+#define CPU_FTRS_7400	(CPU_FTR_COMMON | \
+	    CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_L2CR | \
+	    CPU_FTR_TAU | CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_PPC_LE)
+#define CPU_FTRS_7450_20	(CPU_FTR_COMMON | \
+	    CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \
+	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
+#define CPU_FTRS_7450_21	(CPU_FTR_COMMON | \
+	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \
+	    CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_L3_DISABLE_NAP | \
+	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
+#define CPU_FTRS_7450_23	(CPU_FTR_COMMON | \
+	    CPU_FTR_NEED_PAIRED_STWCX | \
+	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \
+	    CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE)
+#define CPU_FTRS_7455_1	(CPU_FTR_COMMON | \
+	    CPU_FTR_NEED_PAIRED_STWCX | \
+	    CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | CPU_FTR_L3CR | \
+	    CPU_FTR_SPEC7450 | CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE)
+#define CPU_FTRS_7455_20	(CPU_FTR_COMMON | \
+	    CPU_FTR_NEED_PAIRED_STWCX | \
+	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | \
+	    CPU_FTR_NAP_DISABLE_L2_PR | CPU_FTR_L3_DISABLE_NAP | \
+	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE)
+#define CPU_FTRS_7455	(CPU_FTR_COMMON | \
+	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
+	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
+#define CPU_FTRS_7447_10	(CPU_FTR_COMMON | \
+	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
+	    CPU_FTR_NEED_COHERENT | CPU_FTR_NO_BTIC | CPU_FTR_PPC_LE | \
+	    CPU_FTR_NEED_PAIRED_STWCX)
+#define CPU_FTRS_7447	(CPU_FTR_COMMON | \
+	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_L3CR | CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
+	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
+#define CPU_FTRS_7447A	(CPU_FTR_COMMON | \
+	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
+	    CPU_FTR_NEED_COHERENT | CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
+#define CPU_FTRS_7448	(CPU_FTR_COMMON | \
+	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_L2CR | CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_SPEC7450 | CPU_FTR_NAP_DISABLE_L2_PR | \
+	    CPU_FTR_PPC_LE | CPU_FTR_NEED_PAIRED_STWCX)
+#define CPU_FTRS_82XX	(CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_G2_LE	(CPU_FTR_COMMON | CPU_FTR_MAYBE_CAN_DOZE | \
+	    CPU_FTR_MAYBE_CAN_NAP | CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_E300	(CPU_FTR_MAYBE_CAN_DOZE | \
+	    CPU_FTR_MAYBE_CAN_NAP | \
+	    CPU_FTR_COMMON  | CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_E300C2	(CPU_FTR_MAYBE_CAN_DOZE | \
+	    CPU_FTR_MAYBE_CAN_NAP | \
+	    CPU_FTR_COMMON | CPU_FTR_FPU_UNAVAILABLE  | CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_CLASSIC32	(CPU_FTR_COMMON)
+#define CPU_FTRS_8XX	(CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_44X	(CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_440x6	(CPU_FTR_NOEXECUTE | \
+	    CPU_FTR_INDEXED_DCR)
+#define CPU_FTRS_47X	(CPU_FTRS_440x6)
+#define CPU_FTRS_E500	(CPU_FTR_MAYBE_CAN_DOZE | \
+	    CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | \
+	    CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_E500_2	(CPU_FTR_MAYBE_CAN_DOZE | \
+	    CPU_FTR_SPE_COMP | CPU_FTR_MAYBE_CAN_NAP | \
+	    CPU_FTR_NOEXECUTE)
+#define CPU_FTRS_E500MC	( \
+	    CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
+	    CPU_FTR_DBELL | CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV)
+/*
+ * e5500/e6500 erratum A-006958 is a timebase bug that can use the
+ * same workaround as CPU_FTR_CELL_TB_BUG.
+ */
+#define CPU_FTRS_E5500	( \
+	    CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
+	    CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
+	    CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV | CPU_FTR_CELL_TB_BUG)
+#define CPU_FTRS_E6500	( \
+	    CPU_FTR_LWSYNC | CPU_FTR_NOEXECUTE | \
+	    CPU_FTR_DBELL | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
+	    CPU_FTR_DEBUG_LVL_EXC | CPU_FTR_EMB_HV | CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_CELL_TB_BUG | CPU_FTR_SMT)
+
+/* 64-bit CPUs */
+#define CPU_FTRS_PPC970	(CPU_FTR_LWSYNC | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_CAN_NAP | CPU_FTR_MMCRA | \
+	    CPU_FTR_CP_USE_DCBTZ | CPU_FTR_STCX_CHECKS_ADDRESS | \
+	    CPU_FTR_HVMODE | CPU_FTR_DABRX)
+#define CPU_FTRS_POWER5	(CPU_FTR_LWSYNC | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
+	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_PURR | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_DABRX)
+#define CPU_FTRS_POWER6 (CPU_FTR_LWSYNC | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
+	    CPU_FTR_COHERENT_ICACHE | \
+	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
+	    CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_CFAR | \
+	    CPU_FTR_DABRX)
+#define CPU_FTRS_POWER7 (CPU_FTR_LWSYNC | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\
+	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
+	    CPU_FTR_COHERENT_ICACHE | \
+	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
+	    CPU_FTR_CFAR | CPU_FTR_HVMODE | \
+	    CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX )
+#define CPU_FTRS_POWER8 (CPU_FTR_LWSYNC | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\
+	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
+	    CPU_FTR_COHERENT_ICACHE | \
+	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
+	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
+	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
+	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP )
+#define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG)
+#define CPU_FTRS_POWER9 (CPU_FTR_LWSYNC | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\
+	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
+	    CPU_FTR_COHERENT_ICACHE | \
+	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
+	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
+	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
+	    CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_P9_TLBIE_STQ_BUG | \
+	    CPU_FTR_P9_TLBIE_ERAT_BUG | CPU_FTR_P9_TIDR)
+#define CPU_FTRS_POWER9_DD2_0 (CPU_FTRS_POWER9 | CPU_FTR_P9_RADIX_PREFETCH_BUG)
+#define CPU_FTRS_POWER9_DD2_1 (CPU_FTRS_POWER9 | \
+			       CPU_FTR_P9_RADIX_PREFETCH_BUG | \
+			       CPU_FTR_POWER9_DD2_1)
+#define CPU_FTRS_POWER9_DD2_2 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1 | \
+			       CPU_FTR_P9_TM_HV_ASSIST | \
+			       CPU_FTR_P9_TM_XER_SO_BUG)
+#define CPU_FTRS_POWER9_DD2_3 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1 | \
+			       CPU_FTR_P9_TM_HV_ASSIST | \
+			       CPU_FTR_P9_TM_XER_SO_BUG | \
+			       CPU_FTR_DAWR)
+#define CPU_FTRS_POWER10 (CPU_FTR_LWSYNC | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\
+	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
+	    CPU_FTR_COHERENT_ICACHE | \
+	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
+	    CPU_FTR_DSCR | CPU_FTR_SAO  | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
+	    CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
+	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
+	    CPU_FTR_ARCH_300 | CPU_FTR_ARCH_31 | \
+	    CPU_FTR_DAWR | CPU_FTR_DAWR1 | \
+	    CPU_FTR_DEXCR_NPHIE)
+
+#define CPU_FTRS_POWER11	(CPU_FTRS_POWER10 | CPU_FTR_P11_PVR)
+
+#define CPU_FTRS_CELL	(CPU_FTR_LWSYNC | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
+	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
+	    CPU_FTR_PAUSE_ZERO  | CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ | \
+	    CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_DABRX)
+#define CPU_FTRS_PA6T (CPU_FTR_LWSYNC | \
+	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_ALTIVEC_COMP | \
+	    CPU_FTR_PURR | CPU_FTR_REAL_LE | CPU_FTR_DABRX)
+#define CPU_FTRS_COMPATIBLE	(CPU_FTR_PPCAS_ARCH_V2)
+
+#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3E_64
+#define CPU_FTRS_POSSIBLE	(CPU_FTRS_E6500 | CPU_FTRS_E5500)
+#else
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+#define CPU_FTRS_POSSIBLE	\
+	    (CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | CPU_FTRS_POWER8 | \
+	     CPU_FTR_ALTIVEC_COMP | CPU_FTR_VSX_COMP | CPU_FTRS_POWER9 | \
+	     CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2 | \
+	     CPU_FTRS_POWER9_DD2_3 | CPU_FTRS_POWER10 | CPU_FTRS_POWER11)
+#else
+#define CPU_FTRS_POSSIBLE	\
+	    (CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | \
+	     CPU_FTRS_POWER6 | CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | \
+	     CPU_FTRS_POWER8 | CPU_FTRS_CELL | CPU_FTRS_PA6T | \
+	     CPU_FTR_VSX_COMP | CPU_FTR_ALTIVEC_COMP | CPU_FTRS_POWER9 | \
+	     CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2 | \
+	     CPU_FTRS_POWER9_DD2_3 | CPU_FTRS_POWER10 | CPU_FTRS_POWER11)
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+#endif
+#else
+enum {
+	CPU_FTRS_POSSIBLE =
+#ifdef CONFIG_PPC_BOOK3S_604
+	    CPU_FTRS_604 | CPU_FTRS_740_NOTAU |
+	    CPU_FTRS_740 | CPU_FTRS_750 | CPU_FTRS_750FX1 |
+	    CPU_FTRS_750FX2 | CPU_FTRS_750FX | CPU_FTRS_750GX |
+	    CPU_FTRS_7400_NOTAU | CPU_FTRS_7400 | CPU_FTRS_7450_20 |
+	    CPU_FTRS_7450_21 | CPU_FTRS_7450_23 | CPU_FTRS_7455_1 |
+	    CPU_FTRS_7455_20 | CPU_FTRS_7455 | CPU_FTRS_7447_10 |
+	    CPU_FTRS_7447 | CPU_FTRS_7447A |
+	    CPU_FTRS_CLASSIC32 |
+#endif
+#ifdef CONFIG_PPC_BOOK3S_603
+	    CPU_FTRS_603 | CPU_FTRS_82XX |
+	    CPU_FTRS_G2_LE | CPU_FTRS_E300 | CPU_FTRS_E300C2 |
+#endif
+#ifdef CONFIG_PPC_8xx
+	    CPU_FTRS_8XX |
+#endif
+#ifdef CONFIG_PPC_47x
+	    CPU_FTRS_47X | CPU_FTR_476_DD2 |
+#elif defined(CONFIG_44x)
+	    CPU_FTRS_44X | CPU_FTRS_440x6 |
+#endif
+#ifdef CONFIG_PPC_E500
+	    CPU_FTRS_E500 | CPU_FTRS_E500_2 |
+#endif
+#ifdef CONFIG_PPC_E500MC
+	    CPU_FTRS_E500MC | CPU_FTRS_E5500 | CPU_FTRS_E6500 |
+#endif
+	    0,
+};
+#endif /* __powerpc64__ */
+
+#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3E_64
+#define CPU_FTRS_ALWAYS		(CPU_FTRS_E6500 & CPU_FTRS_E5500)
+#else
+
+#ifdef CONFIG_PPC_DT_CPU_FTRS
+#define CPU_FTRS_DT_CPU_BASE			\
+	(CPU_FTR_LWSYNC |			\
+	 CPU_FTR_FPU_UNAVAILABLE |		\
+	 CPU_FTR_NOEXECUTE |			\
+	 CPU_FTR_COHERENT_ICACHE |		\
+	 CPU_FTR_STCX_CHECKS_ADDRESS |		\
+	 CPU_FTR_POPCNTB | CPU_FTR_POPCNTD |	\
+	 CPU_FTR_DAWR |				\
+	 CPU_FTR_ARCH_206 |			\
+	 CPU_FTR_ARCH_207S)
+#else
+#define CPU_FTRS_DT_CPU_BASE	(~0ul)
+#endif
+
+/* pseries may disable DBELL with ibm,pi-features */
+#ifdef CONFIG_CPU_LITTLE_ENDIAN
+#define CPU_FTRS_ALWAYS \
+	    (CPU_FTRS_POSSIBLE & ~CPU_FTR_HVMODE & ~CPU_FTR_DBELL & \
+	     CPU_FTRS_POWER7 & CPU_FTRS_POWER8E & CPU_FTRS_POWER8 & \
+	     CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_POWER9_DD2_2 & \
+	     CPU_FTRS_POWER10 & CPU_FTRS_POWER11 & CPU_FTRS_DT_CPU_BASE)
+#else
+#define CPU_FTRS_ALWAYS		\
+	    (CPU_FTRS_PPC970 & CPU_FTRS_POWER5 & \
+	     CPU_FTRS_POWER6 & CPU_FTRS_POWER7 & CPU_FTRS_CELL & \
+	     CPU_FTRS_PA6T & CPU_FTRS_POWER8 & CPU_FTRS_POWER8E & \
+	     ~CPU_FTR_HVMODE & ~CPU_FTR_DBELL & CPU_FTRS_POSSIBLE & \
+	     CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD2_1 & CPU_FTRS_POWER9_DD2_2 & \
+	     CPU_FTRS_POWER10 & CPU_FTRS_POWER11 & CPU_FTRS_DT_CPU_BASE)
+#endif /* CONFIG_CPU_LITTLE_ENDIAN */
+#endif
+#else
+enum {
+	CPU_FTRS_ALWAYS =
+#ifdef CONFIG_PPC_BOOK3S_604
+	    CPU_FTRS_604 & CPU_FTRS_740_NOTAU &
+	    CPU_FTRS_740 & CPU_FTRS_750 & CPU_FTRS_750FX1 &
+	    CPU_FTRS_750FX2 & CPU_FTRS_750FX & CPU_FTRS_750GX &
+	    CPU_FTRS_7400_NOTAU & CPU_FTRS_7400 & CPU_FTRS_7450_20 &
+	    CPU_FTRS_7450_21 & CPU_FTRS_7450_23 & CPU_FTRS_7455_1 &
+	    CPU_FTRS_7455_20 & CPU_FTRS_7455 & CPU_FTRS_7447_10 &
+	    CPU_FTRS_7447 & CPU_FTRS_7447A &
+	    CPU_FTRS_CLASSIC32 &
+#endif
+#ifdef CONFIG_PPC_BOOK3S_603
+	    CPU_FTRS_603 & CPU_FTRS_82XX &
+	    CPU_FTRS_G2_LE & CPU_FTRS_E300 & CPU_FTRS_E300C2 &
+#endif
+#ifdef CONFIG_PPC_8xx
+	    CPU_FTRS_8XX &
+#endif
+#ifdef CONFIG_PPC_47x
+	    CPU_FTRS_47X &
+#elif defined(CONFIG_44x)
+	    CPU_FTRS_44X & CPU_FTRS_440x6 &
+#endif
+#ifdef CONFIG_PPC_E500
+	    CPU_FTRS_E500 & CPU_FTRS_E500_2 &
+#endif
+#ifdef CONFIG_PPC_E500MC
+	    CPU_FTRS_E500MC & CPU_FTRS_E5500 & CPU_FTRS_E6500 &
+#endif
+	    ~CPU_FTR_EMB_HV &	/* can be removed at runtime */
+	    CPU_FTRS_POSSIBLE,
+};
+#endif /* __powerpc64__ */
+
+/*
+ * Maximum number of hw breakpoint supported on powerpc. Number of
+ * breakpoints supported by actual hw might be less than this, which
+ * is decided at run time in nr_wp_slots().
+ */
+#define HBP_NUM_MAX	2
+
+#endif /* !__ASSEMBLER__ */
+
+#endif /* __ASM_POWERPC_CPUTABLE_H */

linux-7.2.3/arch/powerpc/include/asm/cputhreads.h

@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_CPUTHREADS_H
+#define _ASM_POWERPC_CPUTHREADS_H
+
+#ifndef __ASSEMBLER__
+#include <linux/cpumask.h>
+#include <asm/cpu_has_feature.h>
+
+/*
+ * Mapping of threads to cores
+ *
+ * Note: This implementation is limited to a power of 2 number of
+ * threads per core and the same number for each core in the system
+ * (though it would work if some processors had less threads as long
+ * as the CPU numbers are still allocated, just not brought online).
+ *
+ * However, the API allows for a different implementation in the future
+ * if needed, as long as you only use the functions and not the variables
+ * directly.
+ */
+
+#ifdef CONFIG_SMP
+extern int threads_per_core;
+extern int threads_per_subcore;
+extern int threads_shift;
+extern cpumask_t threads_core_mask;
+#else
+#define threads_per_core	1
+#define threads_per_subcore	1
+#define threads_shift		0
+#define has_big_cores		0
+#define threads_core_mask	(*get_cpu_mask(0))
+#endif
+
+static inline int cpu_nr_cores(void)
+{
+	return nr_cpu_ids >> threads_shift;
+}
+
+#ifdef CONFIG_SMP
+int cpu_core_index_of_thread(int cpu);
+int cpu_first_thread_of_core(int core);
+#else
+static inline int cpu_core_index_of_thread(int cpu) { return cpu; }
+static inline int cpu_first_thread_of_core(int core) { return core; }
+#endif
+
+static inline int cpu_thread_in_core(int cpu)
+{
+	return cpu & (threads_per_core - 1);
+}
+
+static inline int cpu_thread_in_subcore(int cpu)
+{
+	return cpu & (threads_per_subcore - 1);
+}
+
+static inline int cpu_first_thread_sibling(int cpu)
+{
+	return cpu & ~(threads_per_core - 1);
+}
+
+static inline int cpu_last_thread_sibling(int cpu)
+{
+	return cpu | (threads_per_core - 1);
+}
+
+/*
+ * tlb_thread_siblings are siblings which share a TLB. This is not
+ * architected, is not something a hypervisor could emulate and a future
+ * CPU may change behaviour even in compat mode, so this should only be
+ * used on PowerNV, and only with care.
+ */
+static inline int cpu_first_tlb_thread_sibling(int cpu)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+		return cpu & ~0x6;	/* Big Core */
+	else
+		return cpu_first_thread_sibling(cpu);
+}
+
+static inline int cpu_last_tlb_thread_sibling(int cpu)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+		return cpu | 0x6;	/* Big Core */
+	else
+		return cpu_last_thread_sibling(cpu);
+}
+
+static inline int cpu_tlb_thread_sibling_step(void)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_300) && (threads_per_core == 8))
+		return 2;		/* Big Core */
+	else
+		return 1;
+}
+
+static inline u32 get_tensr(void)
+{
+#ifdef	CONFIG_BOOKE
+	if (cpu_has_feature(CPU_FTR_SMT))
+		return mfspr(SPRN_TENSR);
+#endif
+	return 1;
+}
+
+void book3e_start_thread(int thread, unsigned long addr);
+void book3e_stop_thread(int thread);
+
+#endif /* __ASSEMBLER__ */
+
+#define INVALID_THREAD_HWID	0x0fff
+
+#endif /* _ASM_POWERPC_CPUTHREADS_H */
+

linux-7.2.3/arch/powerpc/include/asm/cputime.h

@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Definitions for measuring cputime on powerpc machines.
+ *
+ * Copyright (C) 2006 Paul Mackerras, IBM Corp.
+ *
+ * If we have CONFIG_VIRT_CPU_ACCOUNTING_NATIVE, we measure cpu time in
+ * the same units as the timebase.  Otherwise we measure cpu time
+ * in jiffies using the generic definitions.
+ */
+
+#ifndef __POWERPC_CPUTIME_H
+#define __POWERPC_CPUTIME_H
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+
+#include <linux/types.h>
+#include <linux/time.h>
+#include <asm/div64.h>
+#include <asm/time.h>
+#include <asm/param.h>
+#include <asm/firmware.h>
+
+#ifdef __KERNEL__
+#define cputime_to_nsecs(cputime) tb_to_ns(cputime)
+
+/*
+ * PPC64 uses PACA which is task independent for storing accounting data while
+ * PPC32 uses struct thread_info, therefore at task switch the accounting data
+ * has to be populated in the new task
+ */
+#ifdef CONFIG_PPC64
+#define get_accounting(tsk)	(&get_paca()->accounting)
+#define raw_get_accounting(tsk)	(&local_paca->accounting)
+
+#else
+#define get_accounting(tsk)	(&task_thread_info(tsk)->accounting)
+#define raw_get_accounting(tsk)	get_accounting(tsk)
+#endif
+
+/*
+ * account_cpu_user_entry/exit runs "unreconciled", so can't trace,
+ * can't use get_paca()
+ */
+static notrace inline void account_cpu_user_entry(void)
+{
+	unsigned long tb = mftb();
+	struct cpu_accounting_data *acct = raw_get_accounting(current);
+
+	acct->utime += (tb - acct->starttime_user);
+	acct->starttime = tb;
+}
+
+static notrace inline void account_cpu_user_exit(void)
+{
+	unsigned long tb = mftb();
+	struct cpu_accounting_data *acct = raw_get_accounting(current);
+
+	acct->stime += (tb - acct->starttime);
+	acct->starttime_user = tb;
+}
+
+static notrace inline void account_stolen_time(void)
+{
+#ifdef CONFIG_PPC_SPLPAR
+	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
+		struct lppaca *lp = local_paca->lppaca_ptr;
+
+		if (unlikely(local_paca->dtl_ridx != be64_to_cpu(lp->dtl_idx)))
+			pseries_accumulate_stolen_time();
+	}
+#endif
+}
+
+#endif /* __KERNEL__ */
+#else /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
+static inline void account_cpu_user_entry(void)
+{
+}
+static inline void account_cpu_user_exit(void)
+{
+}
+static notrace inline void account_stolen_time(void)
+{
+}
+#endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
+#endif /* __POWERPC_CPUTIME_H */

linux-7.2.3/arch/powerpc/include/asm/crash_reserve.h

@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_CRASH_RESERVE_H
+#define _ASM_POWERPC_CRASH_RESERVE_H
+
+/* crash kernel regions are Page size agliged */
+#define CRASH_ALIGN             PAGE_SIZE
+
+#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
+static inline bool arch_add_crash_res_to_iomem(void)
+{
+	return false;
+}
+#define arch_add_crash_res_to_iomem arch_add_crash_res_to_iomem
+#endif
+
+#endif /* _ASM_POWERPC_CRASH_RESERVE_H */

linux-7.2.3/arch/powerpc/include/asm/crashdump-ppc64.h

@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_POWERPC_CRASHDUMP_PPC64_H
+#define _ASM_POWERPC_CRASHDUMP_PPC64_H
+
+/*
+ * Backup region - first 64KB of System RAM
+ *
+ * If ever the below macros are to be changed, please be judicious.
+ * The implicit assumptions are:
+ *     - start, end & size are less than UINT32_MAX.
+ *     - start & size are at least 8 byte aligned.
+ *
+ * For implementation details: arch/powerpc/purgatory/trampoline_64.S
+ */
+#define BACKUP_SRC_START	0
+#define BACKUP_SRC_END		0xffff
+#define BACKUP_SRC_SIZE		(BACKUP_SRC_END - BACKUP_SRC_START + 1)
+
+#endif /* __ASM_POWERPC_CRASHDUMP_PPC64_H */

linux-7.2.3/arch/powerpc/include/asm/current.h

@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ASM_POWERPC_CURRENT_H
+#define _ASM_POWERPC_CURRENT_H
+#ifdef __KERNEL__
+
+/*
+ */
+
+struct task_struct;
+
+#ifdef __powerpc64__
+#include <linux/stddef.h>
+#include <asm/paca.h>
+
+static inline struct task_struct *get_current(void)
+{
+	struct task_struct *task;
+
+	/* get_current can be cached by the compiler, so no volatile */
+	asm ("ld %0,%1(13)"
+	: "=r" (task)
+	: "i" (offsetof(struct paca_struct, __current)));
+
+	return task;
+}
+#define current	get_current()
+
+#else
+
+/*
+ * We keep `current' in r2 for speed.
+ */
+register struct task_struct *current asm ("r2");
+
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_CURRENT_H */

linux-7.2.3/arch/powerpc/include/asm/dbdma.h

@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Definitions for using the Apple Descriptor-Based DMA controller
+ * in Power Macintosh computers.
+ *
+ * Copyright (C) 1996 Paul Mackerras.
+ */
+
+#ifdef __KERNEL__
+#ifndef _ASM_DBDMA_H_
+#define _ASM_DBDMA_H_
+/*
+ * DBDMA control/status registers.  All little-endian.
+ */
+struct dbdma_regs {
+    unsigned int control;	/* lets you change bits in status */
+    unsigned int status;	/* DMA and device status bits (see below) */
+    unsigned int cmdptr_hi;	/* upper 32 bits of command address */
+    unsigned int cmdptr;	/* (lower 32 bits of) command address (phys) */
+    unsigned int intr_sel;	/* select interrupt condition bit */
+    unsigned int br_sel;	/* select branch condition bit */
+    unsigned int wait_sel;	/* select wait condition bit */
+    unsigned int xfer_mode;
+    unsigned int data2ptr_hi;
+    unsigned int data2ptr;
+    unsigned int res1;
+    unsigned int address_hi;
+    unsigned int br_addr_hi;
+    unsigned int res2[3];
+};
+
+/* Bits in control and status registers */
+#define RUN	0x8000
+#define PAUSE	0x4000
+#define FLUSH	0x2000
+#define WAKE	0x1000
+#define DEAD	0x0800
+#define ACTIVE	0x0400
+#define BT	0x0100
+#define DEVSTAT	0x00ff
+
+/*
+ * DBDMA command structure.  These fields are all little-endian!
+ */
+struct dbdma_cmd {
+	__le16 req_count;	/* requested byte transfer count */
+	__le16 command;		/* command word (has bit-fields) */
+	__le32 phy_addr;	/* physical data address */
+	__le32 cmd_dep;		/* command-dependent field */
+	__le16 res_count;	/* residual count after completion */
+	__le16 xfer_status;	/* transfer status */
+};
+
+/* DBDMA command values in command field */
+#define OUTPUT_MORE	0	/* transfer memory data to stream */
+#define OUTPUT_LAST	0x1000	/* ditto followed by end marker */
+#define INPUT_MORE	0x2000	/* transfer stream data to memory */
+#define INPUT_LAST	0x3000	/* ditto, expect end marker */
+#define STORE_WORD	0x4000	/* write word (4 bytes) to device reg */
+#define LOAD_WORD	0x5000	/* read word (4 bytes) from device reg */
+#define DBDMA_NOP	0x6000	/* do nothing */
+#define DBDMA_STOP	0x7000	/* suspend processing */
+
+/* Key values in command field */
+#define KEY_STREAM0	0	/* usual data stream */
+#define KEY_STREAM1	0x100	/* control/status stream */
+#define KEY_STREAM2	0x200	/* device-dependent stream */
+#define KEY_STREAM3	0x300	/* device-dependent stream */
+#define KEY_REGS	0x500	/* device register space */
+#define KEY_SYSTEM	0x600	/* system memory-mapped space */
+#define KEY_DEVICE	0x700	/* device memory-mapped space */
+
+/* Interrupt control values in command field */
+#define INTR_NEVER	0	/* don't interrupt */
+#define INTR_IFSET	0x10	/* intr if condition bit is 1 */
+#define INTR_IFCLR	0x20	/* intr if condition bit is 0 */
+#define INTR_ALWAYS	0x30	/* always interrupt */
+
+/* Branch control values in command field */
+#define BR_NEVER	0	/* don't branch */
+#define BR_IFSET	0x4	/* branch if condition bit is 1 */
+#define BR_IFCLR	0x8	/* branch if condition bit is 0 */
+#define BR_ALWAYS	0xc	/* always branch */
+
+/* Wait control values in command field */
+#define WAIT_NEVER	0	/* don't wait */
+#define WAIT_IFSET	1	/* wait if condition bit is 1 */
+#define WAIT_IFCLR	2	/* wait if condition bit is 0 */
+#define WAIT_ALWAYS	3	/* always wait */
+
+/* Align an address for a DBDMA command structure */
+#define DBDMA_ALIGN(x)	(((unsigned long)(x) + sizeof(struct dbdma_cmd) - 1) \
+			 & -sizeof(struct dbdma_cmd))
+
+/* Useful macros */
+#define DBDMA_DO_STOP(regs) do {				\
+	out_le32(&((regs)->control), (RUN|FLUSH)<<16);		\
+	while(in_le32(&((regs)->status)) & (ACTIVE|FLUSH))	\
+		; \
+} while(0)
+
+#define DBDMA_DO_RESET(regs) do {				\
+	out_le32(&((regs)->control), (ACTIVE|DEAD|WAKE|FLUSH|PAUSE|RUN)<<16);\
+	while(in_le32(&((regs)->status)) & (RUN)) \
+		; \
+} while(0)
+
+#endif /* _ASM_DBDMA_H_ */
+#endif /* __KERNEL__ */

linux-7.2.3/arch/powerpc/include/asm/dbell.h

@@ -0,0 +1,155 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright 2009 Freescale Semiconductor, Inc.
+ *
+ * provides masks and opcode images for use by code generation, emulation
+ * and for instructions that older assemblers might not know about
+ */
+#ifndef _ASM_POWERPC_DBELL_H
+#define _ASM_POWERPC_DBELL_H
+
+#include <linux/smp.h>
+#include <linux/threads.h>
+
+#include <asm/cputhreads.h>
+#include <asm/ppc-opcode.h>
+#include <asm/feature-fixups.h>
+#include <asm/kvm_ppc.h>
+
+#define PPC_DBELL_MSG_BRDCAST	(0x04000000)
+#define PPC_DBELL_TYPE(x)	(((x) & 0xf) << (63-36))
+#define PPC_DBELL_TYPE_MASK	PPC_DBELL_TYPE(0xf)
+#define PPC_DBELL_LPID(x)	((x) << (63 - 49))
+#define PPC_DBELL_PIR_MASK	0x3fff
+enum ppc_dbell {
+	PPC_DBELL = 0,		/* doorbell */
+	PPC_DBELL_CRIT = 1,	/* critical doorbell */
+	PPC_G_DBELL = 2,	/* guest doorbell */
+	PPC_G_DBELL_CRIT = 3,	/* guest critical doorbell */
+	PPC_G_DBELL_MC = 4,	/* guest mcheck doorbell */
+	PPC_DBELL_SERVER = 5,	/* doorbell on server */
+};
+
+#ifdef CONFIG_PPC_BOOK3S
+
+#define PPC_DBELL_MSGTYPE		PPC_DBELL_SERVER
+
+static inline void _ppc_msgsnd(u32 msg)
+{
+	__asm__ __volatile__ (ASM_FTR_IFSET(PPC_MSGSND(%1), PPC_MSGSNDP(%1), %0)
+				: : "i" (CPU_FTR_HVMODE), "r" (msg));
+}
+
+/* sync after taking message interrupt */
+static inline void ppc_msgsync(void)
+{
+	/* sync is not required when taking messages from the same core */
+	__asm__ __volatile__ (ASM_FTR_IFSET(PPC_MSGSYNC " ; lwsync", "", %0)
+				: : "i" (CPU_FTR_HVMODE|CPU_FTR_ARCH_300));
+}
+
+static inline void _ppc_msgclr(u32 msg)
+{
+	__asm__ __volatile__ (ASM_FTR_IFSET(PPC_MSGCLR(%1), PPC_MSGCLRP(%1), %0)
+				: : "i" (CPU_FTR_HVMODE), "r" (msg));
+}
+
+static inline void ppc_msgclr(enum ppc_dbell type)
+{
+	u32 msg = PPC_DBELL_TYPE(type);
+
+	_ppc_msgclr(msg);
+}
+
+#else /* CONFIG_PPC_BOOK3S */
+
+#define PPC_DBELL_MSGTYPE		PPC_DBELL
+
+static inline void _ppc_msgsnd(u32 msg)
+{
+	__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
+}
+
+/* sync after taking message interrupt */
+static inline void ppc_msgsync(void)
+{
+}
+
+#endif /* CONFIG_PPC_BOOK3S */
+
+extern void doorbell_exception(struct pt_regs *regs);
+
+/* sync before sending message */
+static inline void ppc_msgsnd_sync(void)
+{
+	__asm__ __volatile__ ("sync" : : : "memory");
+}
+
+static inline void ppc_msgsnd(enum ppc_dbell type, u32 flags, u32 tag)
+{
+	u32 msg = PPC_DBELL_TYPE(type) | (flags & PPC_DBELL_MSG_BRDCAST) |
+			(tag & 0x07ffffff);
+
+	_ppc_msgsnd(msg);
+}
+
+#ifdef CONFIG_SMP
+
+/*
+ * Doorbells must only be used if CPU_FTR_DBELL is available.
+ * msgsnd is used in HV, and msgsndp is used in !HV.
+ *
+ * These should be used by platform code that is aware of restrictions.
+ * Other arch code should use ->cause_ipi.
+ *
+ * doorbell_global_ipi() sends a dbell to any target CPU.
+ * Must be used only by architectures that address msgsnd target
+ * by PIR/get_hard_smp_processor_id.
+ */
+static inline void doorbell_global_ipi(int cpu)
+{
+	u32 tag = get_hard_smp_processor_id(cpu);
+
+	kvmppc_set_host_ipi(cpu);
+	/* Order previous accesses vs. msgsnd, which is treated as a store */
+	ppc_msgsnd_sync();
+	ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
+}
+
+/*
+ * doorbell_core_ipi() sends a dbell to a target CPU in the same core.
+ * Must be used only by architectures that address msgsnd target
+ * by TIR/cpu_thread_in_core.
+ */
+static inline void doorbell_core_ipi(int cpu)
+{
+	u32 tag = cpu_thread_in_core(cpu);
+
+	kvmppc_set_host_ipi(cpu);
+	/* Order previous accesses vs. msgsnd, which is treated as a store */
+	ppc_msgsnd_sync();
+	ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
+}
+
+/*
+ * Attempt to cause a core doorbell if destination is on the same core.
+ * Returns 1 on success, 0 on failure.
+ */
+static inline int doorbell_try_core_ipi(int cpu)
+{
+	int this_cpu = get_cpu();
+	int ret = 0;
+
+	if (cpumask_test_cpu(cpu, cpu_sibling_mask(this_cpu))) {
+		doorbell_core_ipi(cpu);
+		ret = 1;
+	}
+
+	put_cpu();
+
+	return ret;
+}
+
+#endif /* CONFIG_SMP */
+
+#endif /* _ASM_POWERPC_DBELL_H */

linux-7.2.3/arch/powerpc/include/asm/dcr-native.h

@@ -0,0 +1,144 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * (c) Copyright 2006 Benjamin Herrenschmidt, IBM Corp.
+ *                    <benh@kernel.crashing.org>
+ */
+
+#ifndef _ASM_POWERPC_DCR_NATIVE_H
+#define _ASM_POWERPC_DCR_NATIVE_H
+#ifdef __KERNEL__
+#ifndef __ASSEMBLER__
+
+#include <linux/spinlock.h>
+#include <asm/cputable.h>
+#include <asm/cpu_has_feature.h>
+#include <linux/stringify.h>
+
+typedef struct {
+	unsigned int base;
+} dcr_host_native_t;
+
+static inline bool dcr_map_ok_native(dcr_host_native_t host)
+{
+	return true;
+}
+
+#define dcr_map_native(dev, dcr_n, dcr_c) \
+	((dcr_host_native_t){ .base = (dcr_n) })
+#define dcr_unmap_native(host, dcr_c)		do {} while (0)
+#define dcr_read_native(host, dcr_n)		mfdcr(dcr_n + host.base)
+#define dcr_write_native(host, dcr_n, value)	mtdcr(dcr_n + host.base, value)
+
+/* Table based DCR accessors */
+extern void __mtdcr(unsigned int reg, unsigned int val);
+extern unsigned int __mfdcr(unsigned int reg);
+
+/* mfdcrx/mtdcrx instruction based accessors. We hand code
+ * the opcodes in order not to depend on newer binutils
+ */
+static inline unsigned int mfdcrx(unsigned int reg)
+{
+	unsigned int ret;
+	asm volatile(".long 0x7c000206 | (%0 << 21) | (%1 << 16)"
+		     : "=r" (ret) : "r" (reg));
+	return ret;
+}
+
+static inline void mtdcrx(unsigned int reg, unsigned int val)
+{
+	asm volatile(".long 0x7c000306 | (%0 << 21) | (%1 << 16)"
+		     : : "r" (val), "r" (reg));
+}
+
+#define mfdcr(rn)						\
+	({unsigned int rval;					\
+	if (__builtin_constant_p(rn) && rn < 1024)		\
+		asm volatile("mfdcr %0, %1" : "=r" (rval)	\
+			      : "n" (rn));			\
+	else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR)))	\
+		rval = mfdcrx(rn);				\
+	else							\
+		rval = __mfdcr(rn);				\
+	rval;})
+
+#define mtdcr(rn, v)						\
+do {								\
+	if (__builtin_constant_p(rn) && rn < 1024)		\
+		asm volatile("mtdcr %0, %1"			\
+			      : : "n" (rn), "r" (v));		\
+	else if (likely(cpu_has_feature(CPU_FTR_INDEXED_DCR)))	\
+		mtdcrx(rn, v);					\
+	else							\
+		__mtdcr(rn, v);					\
+} while (0)
+
+/* R/W of indirect DCRs make use of standard naming conventions for DCRs */
+extern spinlock_t dcr_ind_lock;
+
+static inline unsigned __mfdcri(int base_addr, int base_data, int reg)
+{
+	unsigned long flags;
+	unsigned int val;
+
+	spin_lock_irqsave(&dcr_ind_lock, flags);
+	if (cpu_has_feature(CPU_FTR_INDEXED_DCR)) {
+		mtdcrx(base_addr, reg);
+		val = mfdcrx(base_data);
+	} else {
+		__mtdcr(base_addr, reg);
+		val = __mfdcr(base_data);
+	}
+	spin_unlock_irqrestore(&dcr_ind_lock, flags);
+	return val;
+}
+
+static inline void __mtdcri(int base_addr, int base_data, int reg,
+			    unsigned val)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dcr_ind_lock, flags);
+	if (cpu_has_feature(CPU_FTR_INDEXED_DCR)) {
+		mtdcrx(base_addr, reg);
+		mtdcrx(base_data, val);
+	} else {
+		__mtdcr(base_addr, reg);
+		__mtdcr(base_data, val);
+	}
+	spin_unlock_irqrestore(&dcr_ind_lock, flags);
+}
+
+static inline void __dcri_clrset(int base_addr, int base_data, int reg,
+				 unsigned clr, unsigned set)
+{
+	unsigned long flags;
+	unsigned int val;
+
+	spin_lock_irqsave(&dcr_ind_lock, flags);
+	if (cpu_has_feature(CPU_FTR_INDEXED_DCR)) {
+		mtdcrx(base_addr, reg);
+		val = (mfdcrx(base_data) & ~clr) | set;
+		mtdcrx(base_data, val);
+	} else {
+		__mtdcr(base_addr, reg);
+		val = (__mfdcr(base_data) & ~clr) | set;
+		__mtdcr(base_data, val);
+	}
+	spin_unlock_irqrestore(&dcr_ind_lock, flags);
+}
+
+#define mfdcri(base, reg)	__mfdcri(DCRN_ ## base ## _CONFIG_ADDR,	\
+					 DCRN_ ## base ## _CONFIG_DATA,	\
+					 reg)
+
+#define mtdcri(base, reg, data)	__mtdcri(DCRN_ ## base ## _CONFIG_ADDR,	\
+					 DCRN_ ## base ## _CONFIG_DATA,	\
+					 reg, data)
+
+#define dcri_clrset(base, reg, clr, set)	__dcri_clrset(DCRN_ ## base ## _CONFIG_ADDR,	\
+							      DCRN_ ## base ## _CONFIG_DATA,	\
+							      reg, clr, set)
+
+#endif /* __ASSEMBLER__ */
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_DCR_NATIVE_H */

linux-7.2.3/arch/powerpc/include/asm/dcr-regs.h

@@ -0,0 +1,184 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common DCR / SDR / CPR register definitions used on various IBM/AMCC
+ * 4xx processors
+ *
+ *    Copyright 2007 Benjamin Herrenschmidt, IBM Corp
+ *                   <benh@kernel.crashing.org>
+ *
+ * Mostly lifted from asm-ppc/ibm4xx.h by
+ *
+ *    Copyright (c) 1999 Grant Erickson <grant@lcse.umn.edu>
+ *
+ */
+
+#ifndef __DCR_REGS_H__
+#define __DCR_REGS_H__
+
+/*
+ * Most DCRs used for controlling devices such as the MAL, DMA engine,
+ * etc... are obtained for the device tree.
+ *
+ * The definitions in this files are fixed DCRs and indirect DCRs that
+ * are commonly used outside of specific drivers or refer to core
+ * common registers that may occasionally have to be tweaked outside
+ * of the driver main register set
+ */
+
+/* CPRs (440GX and 440SP/440SPe) */
+#define DCRN_CPR0_CONFIG_ADDR	0xc
+#define DCRN_CPR0_CONFIG_DATA	0xd
+
+/* SDRs (440GX and 440SP/440SPe) */
+#define DCRN_SDR0_CONFIG_ADDR 	0xe
+#define DCRN_SDR0_CONFIG_DATA	0xf
+
+#define SDR0_PFC0		0x4100
+#define SDR0_PFC1		0x4101
+#define SDR0_PFC1_EPS		0x1c00000
+#define SDR0_PFC1_EPS_SHIFT	22
+#define SDR0_PFC1_RMII		0x02000000
+#define SDR0_MFR		0x4300
+#define SDR0_MFR_TAH0 		0x80000000  	/* TAHOE0 Enable */
+#define SDR0_MFR_TAH1 		0x40000000  	/* TAHOE1 Enable */
+#define SDR0_MFR_PCM  		0x10000000  	/* PPC440GP irq compat mode */
+#define SDR0_MFR_ECS  		0x08000000  	/* EMAC int clk */
+#define SDR0_MFR_T0TXFL		0x00080000
+#define SDR0_MFR_T0TXFH		0x00040000
+#define SDR0_MFR_T1TXFL		0x00020000
+#define SDR0_MFR_T1TXFH		0x00010000
+#define SDR0_MFR_E0TXFL		0x00008000
+#define SDR0_MFR_E0TXFH		0x00004000
+#define SDR0_MFR_E0RXFL		0x00002000
+#define SDR0_MFR_E0RXFH		0x00001000
+#define SDR0_MFR_E1TXFL		0x00000800
+#define SDR0_MFR_E1TXFH		0x00000400
+#define SDR0_MFR_E1RXFL		0x00000200
+#define SDR0_MFR_E1RXFH		0x00000100
+#define SDR0_MFR_E2TXFL		0x00000080
+#define SDR0_MFR_E2TXFH		0x00000040
+#define SDR0_MFR_E2RXFL		0x00000020
+#define SDR0_MFR_E2RXFH		0x00000010
+#define SDR0_MFR_E3TXFL		0x00000008
+#define SDR0_MFR_E3TXFH		0x00000004
+#define SDR0_MFR_E3RXFL		0x00000002
+#define SDR0_MFR_E3RXFH		0x00000001
+#define SDR0_UART0		0x0120
+#define SDR0_UART1		0x0121
+#define SDR0_UART2		0x0122
+#define SDR0_UART3		0x0123
+#define SDR0_CUST0		0x4000
+
+/* SDR for 405EZ */
+#define DCRN_SDR_ICINTSTAT	0x4510
+#define ICINTSTAT_ICRX	0x80000000
+#define ICINTSTAT_ICTX0	0x40000000
+#define ICINTSTAT_ICTX1 0x20000000
+#define ICINTSTAT_ICTX	0x60000000
+
+/* SDRs (460EX/460GT) */
+#define SDR0_ETH_CFG		0x4103
+#define SDR0_ETH_CFG_ECS	0x00000100	/* EMAC int clk source */
+
+/*
+ * All those DCR register addresses are offsets from the base address
+ * for the SRAM0 controller (e.g. 0x20 on 440GX). The base address is
+ * excluded here and configured in the device tree.
+ */
+#define DCRN_SRAM0_SB0CR	0x00
+#define DCRN_SRAM0_SB1CR	0x01
+#define DCRN_SRAM0_SB2CR	0x02
+#define DCRN_SRAM0_SB3CR	0x03
+#define  SRAM_SBCR_BU_MASK	0x00000180
+#define  SRAM_SBCR_BS_64KB	0x00000800
+#define  SRAM_SBCR_BU_RO	0x00000080
+#define  SRAM_SBCR_BU_RW	0x00000180
+#define DCRN_SRAM0_BEAR		0x04
+#define DCRN_SRAM0_BESR0	0x05
+#define DCRN_SRAM0_BESR1	0x06
+#define DCRN_SRAM0_PMEG		0x07
+#define DCRN_SRAM0_CID		0x08
+#define DCRN_SRAM0_REVID	0x09
+#define DCRN_SRAM0_DPC		0x0a
+#define  SRAM_DPC_ENABLE	0x80000000
+
+/*
+ * All those DCR register addresses are offsets from the base address
+ * for the SRAM0 controller (e.g. 0x30 on 440GX). The base address is
+ * excluded here and configured in the device tree.
+ */
+#define DCRN_L2C0_CFG		0x00
+#define  L2C_CFG_L2M		0x80000000
+#define  L2C_CFG_ICU		0x40000000
+#define  L2C_CFG_DCU		0x20000000
+#define  L2C_CFG_DCW_MASK	0x1e000000
+#define  L2C_CFG_TPC		0x01000000
+#define  L2C_CFG_CPC		0x00800000
+#define  L2C_CFG_FRAN		0x00200000
+#define  L2C_CFG_SS_MASK	0x00180000
+#define  L2C_CFG_SS_256		0x00000000
+#define  L2C_CFG_CPIM		0x00040000
+#define  L2C_CFG_TPIM		0x00020000
+#define  L2C_CFG_LIM		0x00010000
+#define  L2C_CFG_PMUX_MASK	0x00007000
+#define  L2C_CFG_PMUX_SNP	0x00000000
+#define  L2C_CFG_PMUX_IF	0x00001000
+#define  L2C_CFG_PMUX_DF	0x00002000
+#define  L2C_CFG_PMUX_DS	0x00003000
+#define  L2C_CFG_PMIM		0x00000800
+#define  L2C_CFG_TPEI		0x00000400
+#define  L2C_CFG_CPEI		0x00000200
+#define  L2C_CFG_NAM		0x00000100
+#define  L2C_CFG_SMCM		0x00000080
+#define  L2C_CFG_NBRM		0x00000040
+#define  L2C_CFG_RDBW		0x00000008	/* only 460EX/GT */
+#define DCRN_L2C0_CMD		0x01
+#define  L2C_CMD_CLR		0x80000000
+#define  L2C_CMD_DIAG		0x40000000
+#define  L2C_CMD_INV		0x20000000
+#define  L2C_CMD_CCP		0x10000000
+#define  L2C_CMD_CTE		0x08000000
+#define  L2C_CMD_STRC		0x04000000
+#define  L2C_CMD_STPC		0x02000000
+#define  L2C_CMD_RPMC		0x01000000
+#define  L2C_CMD_HCC		0x00800000
+#define DCRN_L2C0_ADDR		0x02
+#define DCRN_L2C0_DATA		0x03
+#define DCRN_L2C0_SR		0x04
+#define  L2C_SR_CC		0x80000000
+#define  L2C_SR_CPE		0x40000000
+#define  L2C_SR_TPE		0x20000000
+#define  L2C_SR_LRU		0x10000000
+#define  L2C_SR_PCS		0x08000000
+#define DCRN_L2C0_REVID		0x05
+#define DCRN_L2C0_SNP0		0x06
+#define DCRN_L2C0_SNP1		0x07
+#define  L2C_SNP_BA_MASK	0xffff0000
+#define  L2C_SNP_SSR_MASK	0x0000f000
+#define  L2C_SNP_SSR_32G	0x0000f000
+#define  L2C_SNP_ESR		0x00000800
+
+/*
+ * DCR register offsets for 440SP/440SPe I2O/DMA controller.
+ * The base address is configured in the device tree.
+ */
+#define DCRN_I2O0_IBAL		0x006
+#define DCRN_I2O0_IBAH		0x007
+#define I2O_REG_ENABLE		0x00000001	/* Enable I2O/DMA access */
+
+/* 440SP/440SPe Software Reset DCR */
+#define DCRN_SDR0_SRST		0x0200
+#define DCRN_SDR0_SRST_I2ODMA	(0x80000000 >> 15)	/* Reset I2O/DMA */
+
+/* 440SP/440SPe Memory Queue DCR offsets */
+#define DCRN_MQ0_XORBA		0x04
+#define DCRN_MQ0_CF2H		0x06
+#define DCRN_MQ0_CFBHL		0x0f
+#define DCRN_MQ0_BAUH		0x10
+
+/* HB/LL Paths Configuration Register */
+#define MQ0_CFBHL_TPLM		28
+#define MQ0_CFBHL_HBCL		23
+#define MQ0_CFBHL_POLY		15
+
+#endif /* __DCR_REGS_H__ */

linux-7.2.3/arch/powerpc/include/asm/dcr.h

@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * (c) Copyright 2006 Benjamin Herrenschmidt, IBM Corp.
+ *                    <benh@kernel.crashing.org>
+ */
+
+#ifndef _ASM_POWERPC_DCR_H
+#define _ASM_POWERPC_DCR_H
+#ifdef __KERNEL__
+#ifndef __ASSEMBLER__
+#ifdef CONFIG_PPC_DCR
+
+#include <asm/dcr-native.h>
+
+typedef dcr_host_native_t dcr_host_t;
+#define DCR_MAP_OK(host)	dcr_map_ok_native(host)
+#define dcr_map(dev, dcr_n, dcr_c) dcr_map_native(dev, dcr_n, dcr_c)
+#define dcr_unmap(host, dcr_c) dcr_unmap_native(host, dcr_c)
+#define dcr_read(host, dcr_n) dcr_read_native(host, dcr_n)
+#define dcr_write(host, dcr_n, value) dcr_write_native(host, dcr_n, value)
+
+/*
+ * additional helpers to read the DCR * base from the device-tree
+ */
+struct device_node;
+extern unsigned int dcr_resource_start(const struct device_node *np,
+				       unsigned int index);
+extern unsigned int dcr_resource_len(const struct device_node *np,
+				     unsigned int index);
+#endif /* CONFIG_PPC_DCR */
+#endif /* __ASSEMBLER__ */
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_DCR_H */

linux-7.2.3/arch/powerpc/include/asm/debug.h

@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
+ */
+#ifndef _ASM_POWERPC_DEBUG_H
+#define _ASM_POWERPC_DEBUG_H
+
+#include <asm/hw_breakpoint.h>
+
+struct pt_regs;
+
+#if defined(CONFIG_DEBUGGER) || defined(CONFIG_KEXEC_CORE)
+
+extern int (*__debugger)(struct pt_regs *regs);
+extern int (*__debugger_ipi)(struct pt_regs *regs);
+extern int (*__debugger_bpt)(struct pt_regs *regs);
+extern int (*__debugger_sstep)(struct pt_regs *regs);
+extern int (*__debugger_iabr_match)(struct pt_regs *regs);
+extern int (*__debugger_break_match)(struct pt_regs *regs);
+extern int (*__debugger_fault_handler)(struct pt_regs *regs);
+
+#define DEBUGGER_BOILERPLATE(__NAME) \
+static inline int __NAME(struct pt_regs *regs) \
+{ \
+	if (unlikely(__ ## __NAME)) \
+		return __ ## __NAME(regs); \
+	return 0; \
+}
+
+DEBUGGER_BOILERPLATE(debugger)
+DEBUGGER_BOILERPLATE(debugger_ipi)
+DEBUGGER_BOILERPLATE(debugger_bpt)
+DEBUGGER_BOILERPLATE(debugger_sstep)
+DEBUGGER_BOILERPLATE(debugger_iabr_match)
+DEBUGGER_BOILERPLATE(debugger_break_match)
+DEBUGGER_BOILERPLATE(debugger_fault_handler)
+
+#else
+static inline int debugger(struct pt_regs *regs) { return 0; }
+static inline int debugger_ipi(struct pt_regs *regs) { return 0; }
+static inline int debugger_bpt(struct pt_regs *regs) { return 0; }
+static inline int debugger_sstep(struct pt_regs *regs) { return 0; }
+static inline int debugger_iabr_match(struct pt_regs *regs) { return 0; }
+static inline int debugger_break_match(struct pt_regs *regs) { return 0; }
+static inline int debugger_fault_handler(struct pt_regs *regs) { return 0; }
+#endif
+
+void __set_breakpoint(int nr, struct arch_hw_breakpoint *brk);
+void suspend_breakpoints(void);
+void restore_breakpoints(void);
+bool ppc_breakpoint_available(void);
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+extern void do_send_trap(struct pt_regs *regs, unsigned long address,
+			 unsigned long error_code, int brkpt);
+#endif
+
+#endif /* _ASM_POWERPC_DEBUG_H */

linux-7.2.3/arch/powerpc/include/asm/delay.h

@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ASM_POWERPC_DELAY_H
+#define _ASM_POWERPC_DELAY_H
+#ifdef __KERNEL__
+
+#include <linux/processor.h>
+#include <asm/time.h>
+
+/*
+ * Copyright 1996, Paul Mackerras.
+ * Copyright (C) 2009 Freescale Semiconductor, Inc. All rights reserved.
+ *
+ * PPC64 Support added by Dave Engebretsen, Todd Inglett, Mike Corrigan,
+ * Anton Blanchard.
+ */
+
+extern void __delay(unsigned long loops);
+extern void udelay(unsigned long usecs);
+
+/*
+ * On shared processor machines the generic implementation of mdelay can
+ * result in large errors. While each iteration of the loop inside mdelay
+ * is supposed to take 1ms, the hypervisor could sleep our partition for
+ * longer (eg 10ms). With the right timing these errors can add up.
+ *
+ * Since there is no 32bit overflow issue on 64bit kernels, just call
+ * udelay directly.
+ */
+#ifdef CONFIG_PPC64
+#define mdelay(n)	udelay((n) * 1000)
+#endif
+
+/**
+ * spin_event_timeout - spin until a condition gets true or a timeout elapses
+ * @condition: a C expression to evalate
+ * @timeout: timeout, in microseconds
+ * @delay: the number of microseconds to delay between each evaluation of
+ *         @condition
+ *
+ * The process spins until the condition evaluates to true (non-zero) or the
+ * timeout elapses.  The return value of this macro is the value of
+ * @condition when the loop terminates. This allows you to determine the cause
+ * of the loop terminates.  If the return value is zero, then you know a
+ * timeout has occurred.
+ *
+ * This primary purpose of this macro is to poll on a hardware register
+ * until a status bit changes.  The timeout ensures that the loop still
+ * terminates even if the bit never changes.  The delay is for devices that
+ * need a delay in between successive reads.
+ *
+ * gcc will optimize out the if-statement if @delay is a constant.
+ */
+#define spin_event_timeout(condition, timeout, delay)                          \
+({                                                                             \
+	typeof(condition) __ret;                                               \
+	unsigned long __loops = tb_ticks_per_usec * timeout;                   \
+	unsigned long __start = mftb();                                     \
+                                                                               \
+	if (delay) {                                                           \
+		while (!(__ret = (condition)) &&                               \
+				(tb_ticks_since(__start) <= __loops))          \
+			udelay(delay);                                         \
+	} else {                                                               \
+		spin_begin();                                                  \
+		while (!(__ret = (condition)) &&                               \
+				(tb_ticks_since(__start) <= __loops))          \
+			spin_cpu_relax();                                      \
+		spin_end();                                                    \
+	}                                                                      \
+	if (!__ret)                                                            \
+		__ret = (condition);                                           \
+	__ret;		                                                       \
+})
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_POWERPC_DELAY_H */

linux-7.2.3/arch/powerpc/include/asm/device.h

@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Arch specific extensions to struct device
+ */
+#ifndef _ASM_POWERPC_DEVICE_H
+#define _ASM_POWERPC_DEVICE_H
+
+struct device_node;
+#ifdef CONFIG_PPC64
+struct pci_dn;
+struct iommu_table;
+#endif
+
+/*
+ * Arch extensions to struct device.
+ *
+ * When adding fields, consider macio_add_one_device in
+ * drivers/macintosh/macio_asic.c
+ */
+struct dev_archdata {
+	/*
+	 * These two used to be a union. However, with the hybrid ops we need
+	 * both so here we store both a DMA offset for direct mappings and
+	 * an iommu_table for remapped DMA.
+	 */
+	dma_addr_t		dma_offset;
+
+#ifdef CONFIG_PPC64
+	struct iommu_table	*iommu_table_base;
+#endif
+
+#ifdef CONFIG_PPC64
+	struct pci_dn		*pci_data;
+#endif
+#ifdef CONFIG_EEH
+	struct eeh_dev		*edev;
+#endif
+#ifdef CONFIG_FAIL_IOMMU
+	int fail_iommu;
+#endif
+#ifdef CONFIG_PCI_IOV
+	void *iov_data;
+#endif
+};
+
+struct pdev_archdata {
+	u64 dma_mask;
+	/*
+	 * Pointer to nvdimm_pmu structure, to handle the unregistering
+	 * of pmu device
+	 */
+	void *priv;
+};
+
+#endif /* _ASM_POWERPC_DEVICE_H */

linux-7.2.3/arch/powerpc/include/asm/disassemble.h

@@ -0,0 +1,117 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *
+ * Copyright IBM Corp. 2008
+ *
+ * Authors: Hollis Blanchard <hollisb@us.ibm.com>
+ */
+
+#ifndef __ASM_PPC_DISASSEMBLE_H__
+#define __ASM_PPC_DISASSEMBLE_H__
+
+#include <linux/types.h>
+
+static inline unsigned int get_op(u32 inst)
+{
+	return inst >> 26;
+}
+
+static inline unsigned int get_xop(u32 inst)
+{
+	return (inst >> 1) & 0x3ff;
+}
+
+static inline unsigned int get_sprn(u32 inst)
+{
+	return ((inst >> 16) & 0x1f) | ((inst >> 6) & 0x3e0);
+}
+
+static inline unsigned int get_dcrn(u32 inst)
+{
+	return ((inst >> 16) & 0x1f) | ((inst >> 6) & 0x3e0);
+}
+
+static inline unsigned int get_tmrn(u32 inst)
+{
+	return ((inst >> 16) & 0x1f) | ((inst >> 6) & 0x3e0);
+}
+
+static inline unsigned int get_rt(u32 inst)
+{
+	return (inst >> 21) & 0x1f;
+}
+
+static inline unsigned int get_rs(u32 inst)
+{
+	return (inst >> 21) & 0x1f;
+}
+
+static inline unsigned int get_ra(u32 inst)
+{
+	return (inst >> 16) & 0x1f;
+}
+
+static inline unsigned int get_rb(u32 inst)
+{
+	return (inst >> 11) & 0x1f;
+}
+
+static inline unsigned int get_rc(u32 inst)
+{
+	return inst & 0x1;
+}
+
+static inline unsigned int get_ws(u32 inst)
+{
+	return (inst >> 11) & 0x1f;
+}
+
+static inline unsigned int get_d(u32 inst)
+{
+	return inst & 0xffff;
+}
+
+static inline unsigned int get_oc(u32 inst)
+{
+	return (inst >> 11) & 0x7fff;
+}
+
+static inline unsigned int get_tx_or_sx(u32 inst)
+{
+	return (inst) & 0x1;
+}
+
+#define IS_XFORM(inst)	(get_op(inst)  == 31)
+#define IS_DSFORM(inst)	(get_op(inst) >= 56)
+
+/*
+ * Create a DSISR value from the instruction
+ */
+static inline unsigned make_dsisr(unsigned instr)
+{
+	unsigned dsisr;
+
+
+	/* bits  6:15 --> 22:31 */
+	dsisr = (instr & 0x03ff0000) >> 16;
+
+	if (IS_XFORM(instr)) {
+		/* bits 29:30 --> 15:16 */
+		dsisr |= (instr & 0x00000006) << 14;
+		/* bit     25 -->    17 */
+		dsisr |= (instr & 0x00000040) << 8;
+		/* bits 21:24 --> 18:21 */
+		dsisr |= (instr & 0x00000780) << 3;
+	} else {
+		/* bit      5 -->    17 */
+		dsisr |= (instr & 0x04000000) >> 12;
+		/* bits  1: 4 --> 18:21 */
+		dsisr |= (instr & 0x78000000) >> 17;
+		/* bits 30:31 --> 12:13 */
+		if (IS_DSFORM(instr))
+			dsisr |= (instr & 0x00000003) << 18;
+	}
+
+	return dsisr;
+}
+#endif /* __ASM_PPC_DISASSEMBLE_H__ */

linux-7.2.3/arch/powerpc/include/asm/dma-direct.h

@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ASM_POWERPC_DMA_DIRECT_H
+#define ASM_POWERPC_DMA_DIRECT_H 1
+
+static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	return paddr + dev->archdata.dma_offset;
+}
+
+static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
+{
+	return daddr - dev->archdata.dma_offset;
+}
+#endif /* ASM_POWERPC_DMA_DIRECT_H */

linux-7.2.3/arch/powerpc/include/asm/dma.h

@@ -0,0 +1,344 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_DMA_H
+#define _ASM_POWERPC_DMA_H
+#ifdef __KERNEL__
+
+/*
+ * Defines for using and allocating dma channels.
+ * Written by Hennus Bergman, 1992.
+ * High DMA channel support & info by Hannu Savolainen
+ * and John Boyd, Nov. 1992.
+ * Changes for ppc sound by Christoph Nadig
+ */
+
+/*
+ * Note: Adapted for PowerPC by Gary Thomas
+ * Modified by Cort Dougan <cort@cs.nmt.edu>
+ *
+ * None of this really applies for Power Macintoshes.  There is
+ * basically just enough here to get kernel/dma.c to compile.
+ */
+
+#include <asm/io.h>
+#include <linux/spinlock.h>
+
+#ifndef MAX_DMA_CHANNELS
+#define MAX_DMA_CHANNELS	8
+#endif
+
+/* The maximum address that we can perform a DMA transfer to on this platform */
+/* Doesn't really apply... */
+#define MAX_DMA_ADDRESS		(~0UL)
+
+#ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER
+#define dma_outb	outb_p
+#else
+#define dma_outb	outb
+#endif
+
+#define dma_inb		inb
+
+/*
+ * NOTES about DMA transfers:
+ *
+ *  controller 1: channels 0-3, byte operations, ports 00-1F
+ *  controller 2: channels 4-7, word operations, ports C0-DF
+ *
+ *  - ALL registers are 8 bits only, regardless of transfer size
+ *  - channel 4 is not used - cascades 1 into 2.
+ *  - channels 0-3 are byte - addresses/counts are for physical bytes
+ *  - channels 5-7 are word - addresses/counts are for physical words
+ *  - transfers must not cross physical 64K (0-3) or 128K (5-7) boundaries
+ *  - transfer count loaded to registers is 1 less than actual count
+ *  - controller 2 offsets are all even (2x offsets for controller 1)
+ *  - page registers for 5-7 don't use data bit 0, represent 128K pages
+ *  - page registers for 0-3 use bit 0, represent 64K pages
+ *
+ * On CHRP, the W83C553F (and VLSI Tollgate?) support full 32 bit addressing.
+ * Note that addresses loaded into registers must be _physical_ addresses,
+ * not logical addresses (which may differ if paging is active).
+ *
+ *  Address mapping for channels 0-3:
+ *
+ *   A23 ... A16 A15 ... A8  A7 ... A0    (Physical addresses)
+ *    |  ...  |   |  ... |   |  ... |
+ *    |  ...  |   |  ... |   |  ... |
+ *    |  ...  |   |  ... |   |  ... |
+ *   P7  ...  P0  A7 ... A0  A7 ... A0
+ * |    Page    | Addr MSB | Addr LSB |   (DMA registers)
+ *
+ *  Address mapping for channels 5-7:
+ *
+ *   A23 ... A17 A16 A15 ... A9 A8 A7 ... A1 A0    (Physical addresses)
+ *    |  ...  |   \   \   ... \  \  \  ... \  \
+ *    |  ...  |    \   \   ... \  \  \  ... \  (not used)
+ *    |  ...  |     \   \   ... \  \  \  ... \
+ *   P7  ...  P1 (0) A7 A6  ... A0 A7 A6 ... A0
+ * |      Page      |  Addr MSB   |  Addr LSB  |   (DMA registers)
+ *
+ * Again, channels 5-7 transfer _physical_ words (16 bits), so addresses
+ * and counts _must_ be word-aligned (the lowest address bit is _ignored_ at
+ * the hardware level, so odd-byte transfers aren't possible).
+ *
+ * Transfer count (_not # bytes_) is limited to 64K, represented as actual
+ * count - 1 : 64K => 0xFFFF, 1 => 0x0000.  Thus, count is always 1 or more,
+ * and up to 128K bytes may be transferred on channels 5-7 in one operation.
+ *
+ */
+
+/* 8237 DMA controllers */
+#define IO_DMA1_BASE	0x00	/* 8 bit slave DMA, channels 0..3 */
+#define IO_DMA2_BASE	0xC0	/* 16 bit master DMA, ch 4(=slave input)..7 */
+
+/* DMA controller registers */
+#define DMA1_CMD_REG		0x08	/* command register (w) */
+#define DMA1_STAT_REG		0x08	/* status register (r) */
+#define DMA1_REQ_REG		0x09	/* request register (w) */
+#define DMA1_MASK_REG		0x0A	/* single-channel mask (w) */
+#define DMA1_MODE_REG		0x0B	/* mode register (w) */
+#define DMA1_CLEAR_FF_REG	0x0C	/* clear pointer flip-flop (w) */
+#define DMA1_TEMP_REG		0x0D	/* Temporary Register (r) */
+#define DMA1_RESET_REG		0x0D	/* Master Clear (w) */
+#define DMA1_CLR_MASK_REG	0x0E	/* Clear Mask */
+#define DMA1_MASK_ALL_REG	0x0F	/* all-channels mask (w) */
+
+#define DMA2_CMD_REG		0xD0	/* command register (w) */
+#define DMA2_STAT_REG		0xD0	/* status register (r) */
+#define DMA2_REQ_REG		0xD2	/* request register (w) */
+#define DMA2_MASK_REG		0xD4	/* single-channel mask (w) */
+#define DMA2_MODE_REG		0xD6	/* mode register (w) */
+#define DMA2_CLEAR_FF_REG	0xD8	/* clear pointer flip-flop (w) */
+#define DMA2_TEMP_REG		0xDA	/* Temporary Register (r) */
+#define DMA2_RESET_REG		0xDA	/* Master Clear (w) */
+#define DMA2_CLR_MASK_REG	0xDC	/* Clear Mask */
+#define DMA2_MASK_ALL_REG	0xDE	/* all-channels mask (w) */
+
+#define DMA_ADDR_0		0x00	/* DMA address registers */
+#define DMA_ADDR_1		0x02
+#define DMA_ADDR_2		0x04
+#define DMA_ADDR_3		0x06
+#define DMA_ADDR_4		0xC0
+#define DMA_ADDR_5		0xC4
+#define DMA_ADDR_6		0xC8
+#define DMA_ADDR_7		0xCC
+
+#define DMA_CNT_0		0x01	/* DMA count registers */
+#define DMA_CNT_1		0x03
+#define DMA_CNT_2		0x05
+#define DMA_CNT_3		0x07
+#define DMA_CNT_4		0xC2
+#define DMA_CNT_5		0xC6
+#define DMA_CNT_6		0xCA
+#define DMA_CNT_7		0xCE
+
+#define DMA_LO_PAGE_0		0x87	/* DMA page registers */
+#define DMA_LO_PAGE_1		0x83
+#define DMA_LO_PAGE_2		0x81
+#define DMA_LO_PAGE_3		0x82
+#define DMA_LO_PAGE_5		0x8B
+#define DMA_LO_PAGE_6		0x89
+#define DMA_LO_PAGE_7		0x8A
+
+#define DMA_HI_PAGE_0		0x487	/* DMA page registers */
+#define DMA_HI_PAGE_1		0x483
+#define DMA_HI_PAGE_2		0x481
+#define DMA_HI_PAGE_3		0x482
+#define DMA_HI_PAGE_5		0x48B
+#define DMA_HI_PAGE_6		0x489
+#define DMA_HI_PAGE_7		0x48A
+
+#define DMA1_EXT_REG		0x40B
+#define DMA2_EXT_REG		0x4D6
+
+#ifndef __powerpc64__
+    /* in arch/powerpc/kernel/setup_32.c -- Cort */
+    extern unsigned int DMA_MODE_WRITE;
+    extern unsigned int DMA_MODE_READ;
+#else
+    #define DMA_MODE_READ	0x44	/* I/O to memory, no autoinit, increment, single mode */
+    #define DMA_MODE_WRITE	0x48	/* memory to I/O, no autoinit, increment, single mode */
+#endif
+
+#define DMA_MODE_CASCADE	0xC0	/* pass thru DREQ->HRQ, DACK<-HLDA only */
+
+#define DMA_AUTOINIT		0x10
+
+extern spinlock_t dma_spin_lock;
+
+static __inline__ unsigned long claim_dma_lock(void)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&dma_spin_lock, flags);
+	return flags;
+}
+
+static __inline__ void release_dma_lock(unsigned long flags)
+{
+	spin_unlock_irqrestore(&dma_spin_lock, flags);
+}
+
+/* enable/disable a specific DMA channel */
+static __inline__ void enable_dma(unsigned int dmanr)
+{
+	unsigned char ucDmaCmd = 0x00;
+
+	if (dmanr != 4) {
+		dma_outb(0, DMA2_MASK_REG);	/* This may not be enabled */
+		dma_outb(ucDmaCmd, DMA2_CMD_REG);	/* Enable group */
+	}
+	if (dmanr <= 3) {
+		dma_outb(dmanr, DMA1_MASK_REG);
+		dma_outb(ucDmaCmd, DMA1_CMD_REG);	/* Enable group */
+	} else {
+		dma_outb(dmanr & 3, DMA2_MASK_REG);
+	}
+}
+
+static __inline__ void disable_dma(unsigned int dmanr)
+{
+	if (dmanr <= 3)
+		dma_outb(dmanr | 4, DMA1_MASK_REG);
+	else
+		dma_outb((dmanr & 3) | 4, DMA2_MASK_REG);
+}
+
+/* Clear the 'DMA Pointer Flip Flop'.
+ * Write 0 for LSB/MSB, 1 for MSB/LSB access.
+ * Use this once to initialize the FF to a known state.
+ * After that, keep track of it. :-)
+ * --- In order to do that, the DMA routines below should ---
+ * --- only be used while interrupts are disabled! ---
+ */
+static __inline__ void clear_dma_ff(unsigned int dmanr)
+{
+	if (dmanr <= 3)
+		dma_outb(0, DMA1_CLEAR_FF_REG);
+	else
+		dma_outb(0, DMA2_CLEAR_FF_REG);
+}
+
+/* set mode (above) for a specific DMA channel */
+static __inline__ void set_dma_mode(unsigned int dmanr, char mode)
+{
+	if (dmanr <= 3)
+		dma_outb(mode | dmanr, DMA1_MODE_REG);
+	else
+		dma_outb(mode | (dmanr & 3), DMA2_MODE_REG);
+}
+
+/* Set only the page register bits of the transfer address.
+ * This is used for successive transfers when we know the contents of
+ * the lower 16 bits of the DMA current address register, but a 64k boundary
+ * may have been crossed.
+ */
+static __inline__ void set_dma_page(unsigned int dmanr, int pagenr)
+{
+	switch (dmanr) {
+	case 0:
+		dma_outb(pagenr, DMA_LO_PAGE_0);
+		dma_outb(pagenr >> 8, DMA_HI_PAGE_0);
+		break;
+	case 1:
+		dma_outb(pagenr, DMA_LO_PAGE_1);
+		dma_outb(pagenr >> 8, DMA_HI_PAGE_1);
+		break;
+	case 2:
+		dma_outb(pagenr, DMA_LO_PAGE_2);
+		dma_outb(pagenr >> 8, DMA_HI_PAGE_2);
+		break;
+	case 3:
+		dma_outb(pagenr, DMA_LO_PAGE_3);
+		dma_outb(pagenr >> 8, DMA_HI_PAGE_3);
+		break;
+	case 5:
+		dma_outb(pagenr & 0xfe, DMA_LO_PAGE_5);
+		dma_outb(pagenr >> 8, DMA_HI_PAGE_5);
+		break;
+	case 6:
+		dma_outb(pagenr & 0xfe, DMA_LO_PAGE_6);
+		dma_outb(pagenr >> 8, DMA_HI_PAGE_6);
+		break;
+	case 7:
+		dma_outb(pagenr & 0xfe, DMA_LO_PAGE_7);
+		dma_outb(pagenr >> 8, DMA_HI_PAGE_7);
+		break;
+	}
+}
+
+/* Set transfer address & page bits for specific DMA channel.
+ * Assumes dma flipflop is clear.
+ */
+static __inline__ void set_dma_addr(unsigned int dmanr, unsigned int phys)
+{
+	if (dmanr <= 3) {
+		dma_outb(phys & 0xff,
+			 ((dmanr & 3) << 1) + IO_DMA1_BASE);
+		dma_outb((phys >> 8) & 0xff,
+			 ((dmanr & 3) << 1) + IO_DMA1_BASE);
+	} else {
+		dma_outb((phys >> 1) & 0xff,
+			 ((dmanr & 3) << 2) + IO_DMA2_BASE);
+		dma_outb((phys >> 9) & 0xff,
+			 ((dmanr & 3) << 2) + IO_DMA2_BASE);
+	}
+	set_dma_page(dmanr, phys >> 16);
+}
+
+
+/* Set transfer size (max 64k for DMA1..3, 128k for DMA5..7) for
+ * a specific DMA channel.
+ * You must ensure the parameters are valid.
+ * NOTE: from a manual: "the number of transfers is one more
+ * than the initial word count"! This is taken into account.
+ * Assumes dma flip-flop is clear.
+ * NOTE 2: "count" represents _bytes_ and must be even for channels 5-7.
+ */
+static __inline__ void set_dma_count(unsigned int dmanr, unsigned int count)
+{
+	count--;
+	if (dmanr <= 3) {
+		dma_outb(count & 0xff,
+			 ((dmanr & 3) << 1) + 1 + IO_DMA1_BASE);
+		dma_outb((count >> 8) & 0xff,
+			 ((dmanr & 3) << 1) + 1 + IO_DMA1_BASE);
+	} else {
+		dma_outb((count >> 1) & 0xff,
+			 ((dmanr & 3) << 2) + 2 + IO_DMA2_BASE);
+		dma_outb((count >> 9) & 0xff,
+			 ((dmanr & 3) << 2) + 2 + IO_DMA2_BASE);
+	}
+}
+
+
+/* Get DMA residue count. After a DMA transfer, this
+ * should return zero. Reading this while a DMA transfer is
+ * still in progress will return unpredictable results.
+ * If called before the channel has been used, it may return 1.
+ * Otherwise, it returns the number of _bytes_ left to transfer.
+ *
+ * Assumes DMA flip-flop is clear.
+ */
+static __inline__ int get_dma_residue(unsigned int dmanr)
+{
+	unsigned int io_port = (dmanr <= 3)
+	    ? ((dmanr & 3) << 1) + 1 + IO_DMA1_BASE
+	    : ((dmanr & 3) << 2) + 2 + IO_DMA2_BASE;
+
+	/* using short to get 16-bit wrap around */
+	unsigned short count;
+
+	count = 1 + dma_inb(io_port);
+	count += dma_inb(io_port) << 8;
+
+	return (dmanr <= 3) ? count : (count << 1);
+}
+
+/* These are in kernel/dma.c: */
+
+/* reserve a DMA channel */
+extern int request_dma(unsigned int dmanr, const char *device_id);
+/* release it again */
+extern void free_dma(unsigned int dmanr);
+
+#endif /* __KERNEL__ */
+#endif	/* _ASM_POWERPC_DMA_H */

linux-7.2.3/arch/powerpc/include/asm/drmem.h

@@ -0,0 +1,125 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * drmem.h: Power specific logical memory block representation
+ *
+ * Copyright 2017 IBM Corporation
+ */
+
+#ifndef _ASM_POWERPC_LMB_H
+#define _ASM_POWERPC_LMB_H
+
+#include <linux/sched.h>
+
+struct drmem_lmb {
+	u64     base_addr;
+	u32     drc_index;
+	u32     aa_index;
+	u32     flags;
+};
+
+struct drmem_lmb_info {
+	struct drmem_lmb        *lmbs;
+	int                     n_lmbs;
+	u64                     lmb_size;
+};
+
+struct device_node;
+struct property;
+
+extern struct drmem_lmb_info *drmem_info;
+
+static inline struct drmem_lmb *drmem_lmb_next(struct drmem_lmb *lmb,
+					       const struct drmem_lmb *start)
+{
+	/*
+	 * DLPAR code paths can take several milliseconds per element
+	 * when interacting with firmware. Ensure that we don't
+	 * unfairly monopolize the CPU.
+	 */
+	if (((++lmb - start) % 16) == 0)
+		cond_resched();
+
+	return lmb;
+}
+
+#define for_each_drmem_lmb_in_range(lmb, start, end)		\
+	for ((lmb) = (start); (lmb) < (end); lmb = drmem_lmb_next(lmb, start))
+
+#define for_each_drmem_lmb(lmb)					\
+	for_each_drmem_lmb_in_range((lmb),			\
+		&drmem_info->lmbs[0],				\
+		&drmem_info->lmbs[drmem_info->n_lmbs])
+
+/*
+ * The of_drconf_cell_v1 struct defines the layout of the LMB data
+ * specified in the ibm,dynamic-memory device tree property.
+ * The property itself is a 32-bit value specifying the number of
+ * LMBs followed by an array of of_drconf_cell_v1 entries, one
+ * per LMB.
+ */
+struct of_drconf_cell_v1 {
+	__be64	base_addr;
+	__be32	drc_index;
+	__be32	reserved;
+	__be32	aa_index;
+	__be32	flags;
+};
+
+/*
+ * Version 2 of the ibm,dynamic-memory property is defined as a
+ * 32-bit value specifying the number of LMB sets followed by an
+ * array of of_drconf_cell_v2 entries, one per LMB set.
+ */
+struct of_drconf_cell_v2 {
+	u32	seq_lmbs;
+	u64	base_addr;
+	u32	drc_index;
+	u32	aa_index;
+	u32	flags;
+} __packed;
+
+#define DRCONF_MEM_ASSIGNED	0x00000008
+#define DRCONF_MEM_AI_INVALID	0x00000040
+#define DRCONF_MEM_RESERVED	0x00000080
+#define DRCONF_MEM_HOTREMOVABLE	0x00000100
+
+static inline u64 drmem_lmb_size(void)
+{
+	return drmem_info->lmb_size;
+}
+
+#define DRMEM_LMB_RESERVED	0x80000000
+
+static inline void drmem_mark_lmb_reserved(struct drmem_lmb *lmb)
+{
+	lmb->flags |= DRMEM_LMB_RESERVED;
+}
+
+static inline void drmem_remove_lmb_reservation(struct drmem_lmb *lmb)
+{
+	lmb->flags &= ~DRMEM_LMB_RESERVED;
+}
+
+static inline bool drmem_lmb_reserved(struct drmem_lmb *lmb)
+{
+	return lmb->flags & DRMEM_LMB_RESERVED;
+}
+
+u64 drmem_lmb_memory_max(void);
+int walk_drmem_lmbs(struct device_node *dn, void *data,
+		    int (*func)(struct drmem_lmb *, const __be32 **, void *));
+int drmem_update_dt(void);
+
+#ifdef CONFIG_PPC_PSERIES
+int __init
+walk_drmem_lmbs_early(unsigned long node, void *data,
+		      int (*func)(struct drmem_lmb *, const __be32 **, void *));
+void drmem_update_lmbs(struct property *prop);
+#endif
+
+static inline void invalidate_lmb_associativity_index(struct drmem_lmb *lmb)
+{
+	lmb->aa_index = 0xffffffff;
+}
+
+#endif /* _ASM_POWERPC_LMB_H */

linux-7.2.3/arch/powerpc/include/asm/dt_cpu_ftrs.h

@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_POWERPC_DT_CPU_FTRS_H
+#define __ASM_POWERPC_DT_CPU_FTRS_H
+
+/*
+ *  Copyright 2017, IBM Corporation
+ *  cpufeatures is the new way to discover CPU features with /cpus/features
+ *  devicetree. This supersedes PVR based discovery ("cputable"), and older
+ *  device tree feature advertisement.
+ */
+
+#include <linux/types.h>
+#include <uapi/asm/cputable.h>
+
+#ifdef CONFIG_PPC_DT_CPU_FTRS
+bool dt_cpu_ftrs_init(void *fdt);
+void dt_cpu_ftrs_scan(void);
+bool dt_cpu_ftrs_in_use(void);
+#else
+static inline bool dt_cpu_ftrs_init(void *fdt) { return false; }
+static inline void dt_cpu_ftrs_scan(void) { }
+static inline bool dt_cpu_ftrs_in_use(void) { return false; }
+#endif
+
+#endif /* __ASM_POWERPC_DT_CPU_FTRS_H */

linux-7.2.3/arch/powerpc/include/asm/dtl.h

@@ -0,0 +1,43 @@
+#ifndef _ASM_POWERPC_DTL_H
+#define _ASM_POWERPC_DTL_H
+
+#include <linux/rwsem.h>
+#include <asm/lppaca.h>
+
+/*
+ * Layout of entries in the hypervisor's dispatch trace log buffer.
+ */
+struct dtl_entry {
+	u8	dispatch_reason;
+	u8	preempt_reason;
+	__be16	processor_id;
+	__be32	enqueue_to_dispatch_time;
+	__be32	ready_to_enqueue_time;
+	__be32	waiting_to_ready_time;
+	__be64	timebase;
+	__be64	fault_addr;
+	__be64	srr0;
+	__be64	srr1;
+};
+
+#define DISPATCH_LOG_BYTES	4096	/* bytes per cpu */
+#define N_DISPATCH_LOG		(DISPATCH_LOG_BYTES / sizeof(struct dtl_entry))
+
+/*
+ * Dispatch trace log event enable mask:
+ *   0x1: voluntary virtual processor waits
+ *   0x2: time-slice preempts
+ *   0x4: virtual partition memory page faults
+ */
+#define DTL_LOG_CEDE		0x1
+#define DTL_LOG_PREEMPT		0x2
+#define DTL_LOG_FAULT		0x4
+#define DTL_LOG_ALL		(DTL_LOG_CEDE | DTL_LOG_PREEMPT | DTL_LOG_FAULT)
+
+extern struct kmem_cache *dtl_cache;
+extern struct rw_semaphore dtl_access_lock;
+
+extern void register_dtl_buffer(int cpu);
+extern void alloc_dtl_buffers(unsigned long *time_limit);
+
+#endif /* _ASM_POWERPC_DTL_H */

linux-7.2.3/arch/powerpc/include/asm/edac.h

@@ -0,0 +1,40 @@
+/*
+ * PPC EDAC common defs
+ *
+ * Author: Dave Jiang <djiang@mvista.com>
+ *
+ * 2007 (c) MontaVista Software, Inc. This file is licensed under
+ * the terms of the GNU General Public License version 2. This program
+ * is licensed "as is" without any warranty of any kind, whether express
+ * or implied.
+ */
+#ifndef ASM_EDAC_H
+#define ASM_EDAC_H
+/*
+ * ECC atomic, DMA, SMP and interrupt safe scrub function.
+ * Implements the per arch edac_atomic_scrub() that EDAC use for software
+ * ECC scrubbing.  It reads memory and then writes back the original
+ * value, allowing the hardware to detect and correct memory errors.
+ */
+static __inline__ void edac_atomic_scrub(void *va, u32 size)
+{
+	unsigned int *virt_addr = va;
+	unsigned int temp;
+	unsigned int i;
+
+	for (i = 0; i < size / sizeof(*virt_addr); i++, virt_addr++) {
+		/* Very carefully read and write to memory atomically
+		 * so we are interrupt, DMA and SMP safe.
+		 */
+		__asm__ __volatile__ ("\n\
+				1:	lwarx	%0,0,%1\n\
+					stwcx.	%0,0,%1\n\
+					bne-	1b\n\
+					isync"
+					: "=&r"(temp)
+					: "r"(virt_addr)
+					: "cr0", "memory");
+	}
+}
+
+#endif

linux-7.2.3/arch/powerpc/include/asm/eeh.h

@@ -0,0 +1,464 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2001  Dave Engebretsen & Todd Inglett IBM Corporation.
+ * Copyright 2001-2012 IBM Corporation.
+ */
+
+#ifndef _POWERPC_EEH_H
+#define _POWERPC_EEH_H
+#ifdef __KERNEL__
+
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/string.h>
+#include <linux/time.h>
+#include <linux/atomic.h>
+
+#include <uapi/asm/eeh.h>
+
+struct pci_dev;
+struct pci_bus;
+struct pci_dn;
+
+#ifdef CONFIG_EEH
+
+/* EEH subsystem flags */
+#define EEH_ENABLED		0x01	/* EEH enabled			     */
+#define EEH_FORCE_DISABLED	0x02	/* EEH disabled			     */
+#define EEH_PROBE_MODE_DEV	0x04	/* From PCI device		     */
+#define EEH_PROBE_MODE_DEVTREE	0x08	/* From device tree		     */
+#define EEH_ENABLE_IO_FOR_LOG	0x20	/* Enable IO for log		     */
+#define EEH_EARLY_DUMP_LOG	0x40	/* Dump log immediately		     */
+
+/*
+ * Delay for PE reset, all in ms
+ *
+ * PCI specification has reset hold time of 100 milliseconds.
+ * We have 250 milliseconds here. The PCI bus settlement time
+ * is specified as 1.5 seconds and we have 1.8 seconds.
+ */
+#define EEH_PE_RST_HOLD_TIME		250
+#define EEH_PE_RST_SETTLE_TIME		1800
+
+/*
+ * The struct is used to trace PE related EEH functionality.
+ * In theory, there will have one instance of the struct to
+ * be created against particular PE. In nature, PEs correlate
+ * to each other. the struct has to reflect that hierarchy in
+ * order to easily pick up those affected PEs when one particular
+ * PE has EEH errors.
+ *
+ * Also, one particular PE might be composed of PCI device, PCI
+ * bus and its subordinate components. The struct also need ship
+ * the information. Further more, one particular PE is only meaingful
+ * in the corresponding PHB. Therefore, the root PEs should be created
+ * against existing PHBs in on-to-one fashion.
+ */
+#define EEH_PE_INVALID	(1 << 0)	/* Invalid   */
+#define EEH_PE_PHB	(1 << 1)	/* PHB PE    */
+#define EEH_PE_DEVICE 	(1 << 2)	/* Device PE */
+#define EEH_PE_BUS	(1 << 3)	/* Bus PE    */
+#define EEH_PE_VF	(1 << 4)	/* VF PE     */
+
+#define EEH_PE_ISOLATED		(1 << 0)	/* Isolated PE		*/
+#define EEH_PE_RECOVERING	(1 << 1)	/* Recovering PE	*/
+#define EEH_PE_CFG_BLOCKED	(1 << 2)	/* Block config access	*/
+#define EEH_PE_RESET		(1 << 3)	/* PE reset in progress */
+
+#define EEH_PE_KEEP		(1 << 8)	/* Keep PE on hotplug	*/
+#define EEH_PE_CFG_RESTRICTED	(1 << 9)	/* Block config on error */
+#define EEH_PE_REMOVED		(1 << 10)	/* Removed permanently	*/
+#define EEH_PE_PRI_BUS		(1 << 11)	/* Cached primary bus   */
+
+struct eeh_pe {
+	int type;			/* PE type: PHB/Bus/Device	*/
+	int state;			/* PE EEH dependent mode	*/
+	int addr;			/* PE configuration address	*/
+	struct pci_controller *phb;	/* Associated PHB		*/
+	struct pci_bus *bus;		/* Top PCI bus for bus PE	*/
+	int check_count;		/* Times of ignored error	*/
+	int freeze_count;		/* Times of froze up		*/
+	time64_t tstamp;		/* Time on first-time freeze	*/
+	int false_positives;		/* Times of reported #ff's	*/
+	atomic_t pass_dev_cnt;		/* Count of passed through devs	*/
+	struct eeh_pe *parent;		/* Parent PE			*/
+	void *data;			/* PE auxiliary data		*/
+	struct list_head child_list;	/* List of PEs below this PE	*/
+	struct list_head child;		/* Memb. child_list/eeh_phb_pe	*/
+	struct list_head edevs;		/* List of eeh_dev in this PE	*/
+
+#ifdef CONFIG_STACKTRACE
+	/*
+	 * Saved stack trace. When we find a PE freeze in eeh_dev_check_failure
+	 * the stack trace is saved here so we can print it in the recovery
+	 * thread if it turns out to due to a real problem rather than
+	 * a hot-remove.
+	 *
+	 * A max of 64 entries might be overkill, but it also might not be.
+	 */
+	unsigned long stack_trace[64];
+	int trace_entries;
+#endif /* CONFIG_STACKTRACE */
+};
+
+#define eeh_pe_for_each_dev(pe, edev, tmp) \
+		list_for_each_entry_safe(edev, tmp, &pe->edevs, entry)
+
+#define eeh_for_each_pe(root, pe) \
+	for (pe = root; pe; pe = eeh_pe_next(pe, root))
+
+static inline bool eeh_pe_passed(struct eeh_pe *pe)
+{
+	return pe ? !!atomic_read(&pe->pass_dev_cnt) : false;
+}
+
+/*
+ * The struct is used to trace EEH state for the associated
+ * PCI device node or PCI device. In future, it might
+ * represent PE as well so that the EEH device to form
+ * another tree except the currently existing tree of PCI
+ * buses and PCI devices
+ */
+#define EEH_DEV_BRIDGE		(1 << 0)	/* PCI bridge		*/
+#define EEH_DEV_ROOT_PORT	(1 << 1)	/* PCIe root port	*/
+#define EEH_DEV_DS_PORT		(1 << 2)	/* Downstream port	*/
+#define EEH_DEV_IRQ_DISABLED	(1 << 3)	/* Interrupt disabled	*/
+#define EEH_DEV_DISCONNECTED	(1 << 4)	/* Removing from PE	*/
+
+#define EEH_DEV_NO_HANDLER	(1 << 8)	/* No error handler	*/
+#define EEH_DEV_SYSFS		(1 << 9)	/* Sysfs created	*/
+#define EEH_DEV_REMOVED		(1 << 10)	/* Removed permanently	*/
+
+struct eeh_dev {
+	int mode;			/* EEH mode			*/
+	int bdfn;			/* bdfn of device (for cfg ops) */
+	struct pci_controller *controller;
+	int pe_config_addr;		/* PE config address		*/
+	u32 config_space[16];		/* Saved PCI config space	*/
+	int pcix_cap;			/* Saved PCIx capability	*/
+	int pcie_cap;			/* Saved PCIe capability	*/
+	int aer_cap;			/* Saved AER capability		*/
+	int af_cap;			/* Saved AF capability		*/
+	struct eeh_pe *pe;		/* Associated PE		*/
+	struct list_head entry;		/* Membership in eeh_pe.edevs	*/
+	struct list_head rmv_entry;	/* Membership in rmv_list	*/
+	struct pci_dn *pdn;		/* Associated PCI device node	*/
+	struct pci_dev *pdev;		/* Associated PCI device	*/
+	bool in_error;			/* Error flag for edev		*/
+
+	/* VF specific properties */
+	struct pci_dev *physfn;		/* Associated SRIOV PF		*/
+	int vf_index;			/* Index of this VF 		*/
+};
+
+/* "fmt" must be a simple literal string */
+#define EEH_EDEV_PRINT(level, edev, fmt, ...) \
+	pr_##level("PCI %04x:%02x:%02x.%x#%04x: EEH: " fmt, \
+	(edev)->controller->global_number, PCI_BUSNO((edev)->bdfn), \
+	PCI_SLOT((edev)->bdfn), PCI_FUNC((edev)->bdfn), \
+	((edev)->pe ? (edev)->pe_config_addr : 0xffff), ##__VA_ARGS__)
+#define eeh_edev_dbg(edev, fmt, ...) EEH_EDEV_PRINT(debug, (edev), fmt, ##__VA_ARGS__)
+#define eeh_edev_info(edev, fmt, ...) EEH_EDEV_PRINT(info, (edev), fmt, ##__VA_ARGS__)
+#define eeh_edev_warn(edev, fmt, ...) EEH_EDEV_PRINT(warn, (edev), fmt, ##__VA_ARGS__)
+#define eeh_edev_err(edev, fmt, ...) EEH_EDEV_PRINT(err, (edev), fmt, ##__VA_ARGS__)
+
+static inline struct pci_dn *eeh_dev_to_pdn(struct eeh_dev *edev)
+{
+	return edev ? edev->pdn : NULL;
+}
+
+static inline struct pci_dev *eeh_dev_to_pci_dev(struct eeh_dev *edev)
+{
+	return edev ? edev->pdev : NULL;
+}
+
+static inline struct eeh_pe *eeh_dev_to_pe(struct eeh_dev* edev)
+{
+	return edev ? edev->pe : NULL;
+}
+
+/* Return values from eeh_ops::next_error */
+enum {
+	EEH_NEXT_ERR_NONE = 0,
+	EEH_NEXT_ERR_INF,
+	EEH_NEXT_ERR_FROZEN_PE,
+	EEH_NEXT_ERR_FENCED_PHB,
+	EEH_NEXT_ERR_DEAD_PHB,
+	EEH_NEXT_ERR_DEAD_IOC
+};
+
+/*
+ * The struct is used to trace the registered EEH operation
+ * callback functions. Actually, those operation callback
+ * functions are heavily platform dependent. That means the
+ * platform should register its own EEH operation callback
+ * functions before any EEH further operations.
+ */
+#define EEH_OPT_DISABLE		0	/* EEH disable	*/
+#define EEH_OPT_ENABLE		1	/* EEH enable	*/
+#define EEH_OPT_THAW_MMIO	2	/* MMIO enable	*/
+#define EEH_OPT_THAW_DMA	3	/* DMA enable	*/
+#define EEH_OPT_FREEZE_PE	4	/* Freeze PE	*/
+#define EEH_STATE_UNAVAILABLE	(1 << 0)	/* State unavailable	*/
+#define EEH_STATE_NOT_SUPPORT	(1 << 1)	/* EEH not supported	*/
+#define EEH_STATE_RESET_ACTIVE	(1 << 2)	/* Active reset		*/
+#define EEH_STATE_MMIO_ACTIVE	(1 << 3)	/* Active MMIO		*/
+#define EEH_STATE_DMA_ACTIVE	(1 << 4)	/* Active DMA		*/
+#define EEH_STATE_MMIO_ENABLED	(1 << 5)	/* MMIO enabled		*/
+#define EEH_STATE_DMA_ENABLED	(1 << 6)	/* DMA enabled		*/
+#define EEH_RESET_DEACTIVATE	0	/* Deactivate the PE reset	*/
+#define EEH_RESET_HOT		1	/* Hot reset			*/
+#define EEH_RESET_FUNDAMENTAL	3	/* Fundamental reset		*/
+#define EEH_LOG_TEMP		1	/* EEH temporary error log	*/
+#define EEH_LOG_PERM		2	/* EEH permanent error log	*/
+
+struct eeh_ops {
+	char *name;
+	struct eeh_dev *(*probe)(struct pci_dev *pdev);
+	int (*set_option)(struct eeh_pe *pe, int option);
+	int (*get_state)(struct eeh_pe *pe, int *delay);
+	int (*reset)(struct eeh_pe *pe, int option);
+	int (*get_log)(struct eeh_pe *pe, int severity, char *drv_log, unsigned long len);
+	int (*configure_bridge)(struct eeh_pe *pe);
+	int (*err_inject)(struct eeh_pe *pe, int type, int func,
+			  unsigned long addr, unsigned long mask);
+	int (*read_config)(struct eeh_dev *edev, int where, int size, u32 *val);
+	int (*write_config)(struct eeh_dev *edev, int where, int size, u32 val);
+	int (*next_error)(struct eeh_pe **pe);
+	int (*restore_config)(struct eeh_dev *edev);
+	int (*notify_resume)(struct eeh_dev *edev);
+};
+
+extern int eeh_subsystem_flags;
+extern u32 eeh_max_freezes;
+extern bool eeh_debugfs_no_recover;
+extern struct eeh_ops *eeh_ops;
+extern raw_spinlock_t confirm_error_lock;
+
+static inline void eeh_add_flag(int flag)
+{
+	eeh_subsystem_flags |= flag;
+}
+
+static inline void eeh_clear_flag(int flag)
+{
+	eeh_subsystem_flags &= ~flag;
+}
+
+static inline bool eeh_has_flag(int flag)
+{
+        return !!(eeh_subsystem_flags & flag);
+}
+
+static inline bool eeh_enabled(void)
+{
+	return eeh_has_flag(EEH_ENABLED) && !eeh_has_flag(EEH_FORCE_DISABLED);
+}
+
+static inline void eeh_serialize_lock(unsigned long *flags)
+{
+	raw_spin_lock_irqsave(&confirm_error_lock, *flags);
+}
+
+static inline void eeh_serialize_unlock(unsigned long flags)
+{
+	raw_spin_unlock_irqrestore(&confirm_error_lock, flags);
+}
+
+static inline bool eeh_state_active(int state)
+{
+	return (state & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE))
+	== (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
+}
+
+typedef void (*eeh_edev_traverse_func)(struct eeh_dev *edev, void *flag);
+typedef void *(*eeh_pe_traverse_func)(struct eeh_pe *pe, void *flag);
+void eeh_set_pe_aux_size(int size);
+int eeh_phb_pe_create(struct pci_controller *phb);
+int eeh_wait_state(struct eeh_pe *pe, int max_wait);
+struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb);
+struct eeh_pe *eeh_pe_next(struct eeh_pe *pe, struct eeh_pe *root);
+struct eeh_pe *eeh_pe_get(struct pci_controller *phb, int pe_no);
+int eeh_pe_tree_insert(struct eeh_dev *edev, struct eeh_pe *new_pe_parent);
+int eeh_pe_tree_remove(struct eeh_dev *edev);
+void eeh_pe_update_time_stamp(struct eeh_pe *pe);
+void *eeh_pe_traverse(struct eeh_pe *root,
+		      eeh_pe_traverse_func fn, void *flag);
+void eeh_pe_dev_traverse(struct eeh_pe *root,
+			 eeh_edev_traverse_func fn, void *flag);
+void eeh_pe_restore_bars(struct eeh_pe *pe);
+const char *eeh_pe_loc_get(struct eeh_pe *pe);
+struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe);
+const char *eeh_pe_loc_get_bus(struct pci_bus *bus);
+struct pci_bus *eeh_pe_bus_get_nolock(struct eeh_pe *pe);
+
+void eeh_show_enabled(void);
+int __init eeh_init(struct eeh_ops *ops);
+int eeh_check_failure(const volatile void __iomem *token);
+int eeh_dev_check_failure(struct eeh_dev *edev);
+void eeh_addr_cache_init(void);
+void eeh_probe_device(struct pci_dev *pdev);
+void eeh_remove_device(struct pci_dev *);
+int eeh_unfreeze_pe(struct eeh_pe *pe);
+int eeh_pe_reset_and_recover(struct eeh_pe *pe);
+int eeh_dev_open(struct pci_dev *pdev);
+void eeh_dev_release(struct pci_dev *pdev);
+struct eeh_pe *eeh_iommu_group_to_pe(struct iommu_group *group);
+int eeh_pe_set_option(struct eeh_pe *pe, int option);
+int eeh_pe_get_state(struct eeh_pe *pe);
+int eeh_pe_reset(struct eeh_pe *pe, int option, bool include_passed);
+int eeh_pe_configure(struct eeh_pe *pe);
+int eeh_pe_inject_err(struct eeh_pe *pe, int type, int func,
+		      unsigned long addr, unsigned long mask);
+int eeh_pe_inject_mmio_error(struct pci_dev *pdev);
+
+/**
+ * EEH_POSSIBLE_ERROR() -- test for possible MMIO failure.
+ *
+ * If this macro yields TRUE, the caller relays to eeh_check_failure()
+ * which does further tests out of line.
+ */
+#define EEH_POSSIBLE_ERROR(val, type)	((val) == (type)~0 && eeh_enabled())
+
+/*
+ * Reads from a device which has been isolated by EEH will return
+ * all 1s.  This macro gives an all-1s value of the given size (in
+ * bytes: 1, 2, or 4) for comparing with the result of a read.
+ */
+#define EEH_IO_ERROR_VALUE(size)	(~0U >> ((4 - (size)) * 8))
+
+#else /* !CONFIG_EEH */
+
+static inline bool eeh_enabled(void)
+{
+        return false;
+}
+
+static inline void eeh_show_enabled(void) { }
+
+static inline int eeh_check_failure(const volatile void __iomem *token)
+{
+	return 0;
+}
+
+#define eeh_dev_check_failure(x) (0)
+
+static inline void eeh_addr_cache_init(void) { }
+
+static inline void eeh_probe_device(struct pci_dev *dev) { }
+
+static inline void eeh_remove_device(struct pci_dev *dev) { }
+
+#define EEH_POSSIBLE_ERROR(val, type) (0)
+#define EEH_IO_ERROR_VALUE(size) (-1UL)
+static inline int eeh_phb_pe_create(struct pci_controller *phb) { return 0; }
+#endif /* CONFIG_EEH */
+
+#if defined(CONFIG_PPC_PSERIES) && defined(CONFIG_EEH)
+void pseries_eeh_init_edev_recursive(struct pci_dn *pdn);
+#endif
+
+#ifdef CONFIG_PPC64
+/*
+ * MMIO read/write operations with EEH support.
+ */
+static inline u8 eeh_readb(const volatile void __iomem *addr)
+{
+	u8 val = in_8(addr);
+	if (EEH_POSSIBLE_ERROR(val, u8))
+		eeh_check_failure(addr);
+	return val;
+}
+
+static inline u16 eeh_readw(const volatile void __iomem *addr)
+{
+	u16 val = in_le16(addr);
+	if (EEH_POSSIBLE_ERROR(val, u16))
+		eeh_check_failure(addr);
+	return val;
+}
+
+static inline u32 eeh_readl(const volatile void __iomem *addr)
+{
+	u32 val = in_le32(addr);
+	if (EEH_POSSIBLE_ERROR(val, u32))
+		eeh_check_failure(addr);
+	return val;
+}
+
+static inline u64 eeh_readq(const volatile void __iomem *addr)
+{
+	u64 val = in_le64(addr);
+	if (EEH_POSSIBLE_ERROR(val, u64))
+		eeh_check_failure(addr);
+	return val;
+}
+
+static inline u16 eeh_readw_be(const volatile void __iomem *addr)
+{
+	u16 val = in_be16(addr);
+	if (EEH_POSSIBLE_ERROR(val, u16))
+		eeh_check_failure(addr);
+	return val;
+}
+
+static inline u32 eeh_readl_be(const volatile void __iomem *addr)
+{
+	u32 val = in_be32(addr);
+	if (EEH_POSSIBLE_ERROR(val, u32))
+		eeh_check_failure(addr);
+	return val;
+}
+
+static inline u64 eeh_readq_be(const volatile void __iomem *addr)
+{
+	u64 val = in_be64(addr);
+	if (EEH_POSSIBLE_ERROR(val, u64))
+		eeh_check_failure(addr);
+	return val;
+}
+
+static inline void eeh_memcpy_fromio(void *dest, const
+				     volatile void __iomem *src,
+				     unsigned long n)
+{
+	_memcpy_fromio(dest, src, n);
+
+	/* Look for ffff's here at dest[n].  Assume that at least 4 bytes
+	 * were copied. Check all four bytes.
+	 */
+	if (n >= 4 && EEH_POSSIBLE_ERROR(*((u32 *)(dest + n - 4)), u32))
+		eeh_check_failure(src);
+}
+
+/* in-string eeh macros */
+static inline void eeh_readsb(const volatile void __iomem *addr, void * buf,
+			      int ns)
+{
+	_insb(addr, buf, ns);
+	if (EEH_POSSIBLE_ERROR((*(((u8*)buf)+ns-1)), u8))
+		eeh_check_failure(addr);
+}
+
+static inline void eeh_readsw(const volatile void __iomem *addr, void * buf,
+			      int ns)
+{
+	_insw(addr, buf, ns);
+	if (EEH_POSSIBLE_ERROR((*(((u16*)buf)+ns-1)), u16))
+		eeh_check_failure(addr);
+}
+
+static inline void eeh_readsl(const volatile void __iomem *addr, void * buf,
+			      int nl)
+{
+	_insl(addr, buf, nl);
+	if (EEH_POSSIBLE_ERROR((*(((u32*)buf)+nl-1)), u32))
+		eeh_check_failure(addr);
+}
+
+
+void __init eeh_cache_debugfs_init(void);
+
+#endif /* CONFIG_PPC64 */
+#endif /* __KERNEL__ */
+#endif /* _POWERPC_EEH_H */

linux-7.2.3/arch/powerpc/include/asm/eeh_event.h

@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ *
+ * Copyright (c) 2005 Linas Vepstas <linas@linas.org>
+ */
+
+#ifndef ASM_POWERPC_EEH_EVENT_H
+#define ASM_POWERPC_EEH_EVENT_H
+#ifdef __KERNEL__
+
+/*
+ * structure holding pci controller data that describes a
+ * change in the isolation status of a PCI slot.  A pointer
+ * to this struct is passed as the data pointer in a notify
+ * callback.
+ */
+struct eeh_event {
+	struct list_head	list;	/* to form event queue	*/
+	struct eeh_pe		*pe;	/* EEH PE		*/
+};
+
+int eeh_event_init(void);
+int eeh_send_failure_event(struct eeh_pe *pe);
+int __eeh_send_failure_event(struct eeh_pe *pe);
+void eeh_remove_event(struct eeh_pe *pe, bool force);
+void eeh_handle_normal_event(struct eeh_pe *pe);
+void eeh_handle_special_event(void);
+
+#endif /* __KERNEL__ */
+#endif /* ASM_POWERPC_EEH_EVENT_H */

linux-7.2.3/arch/powerpc/include/asm/ehv_pic.h

@@ -0,0 +1,40 @@
+/*
+ * EHV_PIC private definitions and structure.
+ *
+ * Copyright 2008-2010 Freescale Semiconductor, Inc.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+#ifndef __EHV_PIC_H__
+#define __EHV_PIC_H__
+
+#include <linux/irq.h>
+
+#define NR_EHV_PIC_INTS 1024
+
+#define EHV_PIC_INFO(name) EHV_PIC_##name
+
+#define EHV_PIC_VECPRI_POLARITY_NEGATIVE 0
+#define EHV_PIC_VECPRI_POLARITY_POSITIVE 1
+#define EHV_PIC_VECPRI_SENSE_EDGE 0
+#define EHV_PIC_VECPRI_SENSE_LEVEL 0x2
+#define EHV_PIC_VECPRI_POLARITY_MASK 0x1
+#define EHV_PIC_VECPRI_SENSE_MASK 0x2
+
+struct ehv_pic {
+	/* The remapper for this EHV_PIC */
+	struct irq_domain	*irqhost;
+
+	/* The "linux" controller struct */
+	struct irq_chip	hc_irq;
+
+	/* core int flag */
+	int coreint_flag;
+};
+
+void ehv_pic_init(void);
+unsigned int ehv_pic_get_irq(void);
+
+#endif /* __EHV_PIC_H__ */

linux-7.2.3/arch/powerpc/include/asm/elf.h

@@ -0,0 +1,195 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * ELF register definitions..
+ */
+#ifndef _ASM_POWERPC_ELF_H
+#define _ASM_POWERPC_ELF_H
+
+#include <linux/sched.h>	/* for task_struct */
+#include <asm/page.h>
+#include <asm/string.h>
+#include <uapi/asm/elf.h>
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x) ((x)->e_machine == ELF_ARCH)
+#define compat_elf_check_arch(x)	((x)->e_machine == EM_PPC)
+
+#define CORE_DUMP_USE_REGSET
+#define ELF_EXEC_PAGESIZE	PAGE_SIZE
+
+/*
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
+ */
+#define ELF_ET_DYN_BASE		(is_32bit_task() ? 0x000400000UL : \
+						   0x100000000UL)
+
+#define ELF_CORE_EFLAGS (is_elf2_task() ? 2 : 0)
+
+/*
+ * Our registers are always unsigned longs, whether we're a 32 bit
+ * process or 64 bit, on either a 64 bit or 32 bit kernel.
+ *
+ * This macro relies on elf_regs[i] having the right type to truncate to,
+ * either u32 or u64.  It defines the body of the elf_core_copy_regs
+ * function, either the native one with elf_gregset_t elf_regs or
+ * the 32-bit one with elf_gregset_t32 elf_regs.
+ */
+#define PPC_ELF_CORE_COPY_REGS(elf_regs, regs) \
+	int i, nregs = min(sizeof(*regs) / sizeof(unsigned long), \
+			   (size_t)ELF_NGREG);			  \
+	for (i = 0; i < nregs; i++) \
+		elf_regs[i] = ((unsigned long *) regs)[i]; \
+	memset(&elf_regs[i], 0, (ELF_NGREG - i) * sizeof(elf_regs[0]))
+
+/* Common routine for both 32-bit and 64-bit native processes */
+static inline void ppc_elf_core_copy_regs(elf_gregset_t elf_regs,
+					  struct pt_regs *regs)
+{
+	PPC_ELF_CORE_COPY_REGS(elf_regs, regs);
+}
+#define ELF_CORE_COPY_REGS(gregs, regs) ppc_elf_core_copy_regs(gregs, regs);
+
+/* ELF_HWCAP yields a mask that user programs can use to figure out what
+   instruction set this cpu supports.  This could be done in userspace,
+   but it's not easy, and we've already done it here.  */
+# define ELF_HWCAP	(cur_cpu_spec->cpu_user_features)
+# define ELF_HWCAP2	(cur_cpu_spec->cpu_user_features2)
+
+/* This yields a string that ld.so will use to load implementation
+   specific libraries for optimization.  This is more specific in
+   intent than poking at uname or /proc/cpuinfo.  */
+
+#define ELF_PLATFORM	(cur_cpu_spec->platform)
+
+/* While ELF_PLATFORM indicates the ISA supported by the platform, it
+ * may not accurately reflect the underlying behavior of the hardware
+ * (as in the case of running in Power5+ compatibility mode on a
+ * Power6 machine).  ELF_BASE_PLATFORM allows ld.so to load libraries
+ * that are tuned for the real hardware.
+ */
+#define ELF_BASE_PLATFORM (powerpc_base_platform)
+
+#ifdef __powerpc64__
+# define ELF_PLAT_INIT(_r, load_addr)	do {	\
+	_r->gpr[2] = load_addr; 		\
+} while (0)
+#endif /* __powerpc64__ */
+
+#ifdef __powerpc64__
+# define SET_PERSONALITY(ex)					\
+do {								\
+	if (((ex).e_flags & 0x3) == 2)				\
+		set_thread_flag(TIF_ELF2ABI);			\
+	else							\
+		clear_thread_flag(TIF_ELF2ABI);			\
+	if ((ex).e_ident[EI_CLASS] == ELFCLASS32)		\
+		set_thread_flag(TIF_32BIT);			\
+	else							\
+		clear_thread_flag(TIF_32BIT);			\
+	if (personality(current->personality) != PER_LINUX32)	\
+		set_personality(PER_LINUX |			\
+			(current->personality & (~PER_MASK)));	\
+} while (0)
+/*
+ * An executable for which elf_read_implies_exec() returns TRUE will
+ * have the READ_IMPLIES_EXEC personality flag set automatically. This
+ * is only required to work around bugs in old 32bit toolchains. Since
+ * the 64bit ABI has never had these issues dont enable the workaround
+ * even if we have an executable stack.
+ */
+# define elf_read_implies_exec(ex, exec_stk) (is_32bit_task() ? \
+		(exec_stk == EXSTACK_DEFAULT) : 0)
+#else 
+# define elf_read_implies_exec(ex, exec_stk) (exec_stk == EXSTACK_DEFAULT)
+#endif /* __powerpc64__ */
+
+extern int dcache_bsize;
+extern int icache_bsize;
+extern int ucache_bsize;
+
+/* vDSO has arch_setup_additional_pages */
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES
+struct linux_binprm;
+extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+				       int uses_interp);
+#define VDSO_AUX_ENT(a,b) NEW_AUX_ENT(a,b)
+
+/* 1GB for 64bit, 8MB for 32bit */
+#define STACK_RND_MASK (is_32bit_task() ? \
+	(0x7ff >> (PAGE_SHIFT - 12)) : \
+	(0x3ffff >> (PAGE_SHIFT - 12)))
+
+#ifdef CONFIG_SPU_BASE
+/* Notes used in ET_CORE. Note name is "SPU/<fd>/<filename>". */
+#define NT_SPU		1
+
+#endif /* CONFIG_SPU_BASE */
+
+#ifdef CONFIG_PPC64
+
+#define get_cache_geometry(level) \
+	(ppc64_caches.level.assoc << 16 | ppc64_caches.level.line_size)
+
+#define ARCH_DLINFO_CACHE_GEOMETRY					\
+	NEW_AUX_ENT(AT_L1I_CACHESIZE, ppc64_caches.l1i.size);		\
+	NEW_AUX_ENT(AT_L1I_CACHEGEOMETRY, get_cache_geometry(l1i));	\
+	NEW_AUX_ENT(AT_L1D_CACHESIZE, ppc64_caches.l1d.size);		\
+	NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, get_cache_geometry(l1d));	\
+	NEW_AUX_ENT(AT_L2_CACHESIZE, ppc64_caches.l2.size);		\
+	NEW_AUX_ENT(AT_L2_CACHEGEOMETRY, get_cache_geometry(l2));	\
+	NEW_AUX_ENT(AT_L3_CACHESIZE, ppc64_caches.l3.size);		\
+	NEW_AUX_ENT(AT_L3_CACHEGEOMETRY, get_cache_geometry(l3))
+
+#else
+#define ARCH_DLINFO_CACHE_GEOMETRY
+#endif
+
+/*
+ * The requirements here are:
+ * - keep the final alignment of sp (sp & 0xf)
+ * - make sure the 32-bit value at the first 16 byte aligned position of
+ *   AUXV is greater than 16 for glibc compatibility.
+ *   AT_IGNOREPPC is used for that.
+ * - for compatibility with glibc ARCH_DLINFO must always be defined on PPC,
+ *   even if DLINFO_ARCH_ITEMS goes to zero or is undefined.
+ * update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes
+ */
+#define COMMON_ARCH_DLINFO						\
+do {									\
+	/* Handle glibc compatibility. */				\
+	NEW_AUX_ENT(AT_IGNOREPPC, AT_IGNOREPPC);			\
+	NEW_AUX_ENT(AT_IGNOREPPC, AT_IGNOREPPC);			\
+	/* Cache size items */						\
+	NEW_AUX_ENT(AT_DCACHEBSIZE, dcache_bsize);			\
+	NEW_AUX_ENT(AT_ICACHEBSIZE, icache_bsize);			\
+	NEW_AUX_ENT(AT_UCACHEBSIZE, 0);					\
+	VDSO_AUX_ENT(AT_SYSINFO_EHDR, (unsigned long)current->mm->context.vdso);\
+	ARCH_DLINFO_CACHE_GEOMETRY;					\
+} while (0)
+
+#define ARCH_DLINFO							\
+do {									\
+	COMMON_ARCH_DLINFO;						\
+	NEW_AUX_ENT(AT_MINSIGSTKSZ, get_min_sigframe_size());		\
+} while (0)
+
+#define COMPAT_ARCH_DLINFO						\
+do {									\
+	COMMON_ARCH_DLINFO;						\
+	NEW_AUX_ENT(AT_MINSIGSTKSZ, get_min_sigframe_size_compat());	\
+} while (0)
+
+/* Relocate the kernel image to @final_address */
+void relocate(unsigned long final_address);
+
+struct func_desc {
+	unsigned long addr;
+	unsigned long toc;
+	unsigned long env;
+};
+
+#endif /* _ASM_POWERPC_ELF_H */

linux-7.2.3/arch/powerpc/include/asm/elfnote.h

@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * PowerPC ELF notes.
+ *
+ * Copyright 2019, IBM Corporation
+ */
+
+#ifndef __ASM_POWERPC_ELFNOTE_H__
+#define __ASM_POWERPC_ELFNOTE_H__
+
+/*
+ * These note types should live in a SHT_NOTE segment and have
+ * "PowerPC" in the name field.
+ */
+
+/*
+ * The capabilities supported/required by this kernel (bitmap).
+ *
+ * This type uses a bitmap as "desc" field. Each bit is described
+ * in arch/powerpc/kernel/note.S
+ */
+#define PPC_ELFNOTE_CAPABILITIES 1
+
+#endif /* __ASM_POWERPC_ELFNOTE_H__ */

linux-7.2.3/arch/powerpc/include/asm/emergency-restart.h

@@ -0,0 +1 @@
+#include <asm-generic/emergency-restart.h>

linux-7.2.3/arch/powerpc/include/asm/emulated_ops.h

@@ -0,0 +1,84 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  Copyright 2007 Sony Corporation
+ */
+
+#ifndef _ASM_POWERPC_EMULATED_OPS_H
+#define _ASM_POWERPC_EMULATED_OPS_H
+
+#include <linux/atomic.h>
+#include <linux/perf_event.h>
+
+
+#ifdef CONFIG_PPC_EMULATED_STATS
+
+struct ppc_emulated_entry {
+	const char *name;
+	atomic_t val;
+};
+
+extern struct ppc_emulated {
+#ifdef CONFIG_ALTIVEC
+	struct ppc_emulated_entry altivec;
+#endif
+	struct ppc_emulated_entry dcba;
+	struct ppc_emulated_entry dcbz;
+	struct ppc_emulated_entry fp_pair;
+	struct ppc_emulated_entry isel;
+	struct ppc_emulated_entry mcrxr;
+	struct ppc_emulated_entry mfpvr;
+	struct ppc_emulated_entry multiple;
+	struct ppc_emulated_entry popcntb;
+	struct ppc_emulated_entry spe;
+	struct ppc_emulated_entry string;
+	struct ppc_emulated_entry sync;
+	struct ppc_emulated_entry unaligned;
+#ifdef CONFIG_MATH_EMULATION
+	struct ppc_emulated_entry math;
+#endif
+#ifdef CONFIG_VSX
+	struct ppc_emulated_entry vsx;
+#endif
+#ifdef CONFIG_PPC64
+	struct ppc_emulated_entry mfdscr;
+	struct ppc_emulated_entry mtdscr;
+	struct ppc_emulated_entry lq_stq;
+	struct ppc_emulated_entry lxvw4x;
+	struct ppc_emulated_entry lxvh8x;
+	struct ppc_emulated_entry lxvd2x;
+	struct ppc_emulated_entry lxvb16x;
+#endif
+} ppc_emulated;
+
+extern u32 ppc_warn_emulated;
+
+extern void ppc_warn_emulated_print(const char *type);
+
+#define __PPC_WARN_EMULATED(type)					 \
+	do {								 \
+		atomic_inc(&ppc_emulated.type.val);			 \
+		if (ppc_warn_emulated)					 \
+			ppc_warn_emulated_print(ppc_emulated.type.name); \
+	} while (0)
+
+#else /* !CONFIG_PPC_EMULATED_STATS */
+
+#define __PPC_WARN_EMULATED(type)	do { } while (0)
+
+#endif /* !CONFIG_PPC_EMULATED_STATS */
+
+#define PPC_WARN_EMULATED(type, regs)					\
+	do {								\
+		perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS,		\
+			1, regs, 0);					\
+		__PPC_WARN_EMULATED(type);				\
+	} while (0)
+
+#define PPC_WARN_ALIGNMENT(type, regs)					\
+	do {								\
+		perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS,		\
+			1, regs, regs->dar);				\
+		__PPC_WARN_EMULATED(type);				\
+	} while (0)
+
+#endif /* _ASM_POWERPC_EMULATED_OPS_H */

linux-7.2.3/arch/powerpc/include/asm/entry-common.h

@@ -0,0 +1,533 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_PPC_ENTRY_COMMON_H
+#define _ASM_PPC_ENTRY_COMMON_H
+
+#include <asm/cputime.h>
+#include <asm/interrupt.h>
+#include <asm/runlatch.h>
+#include <asm/stacktrace.h>
+#include <asm/switch_to.h>
+#include <asm/tm.h>
+
+#ifdef CONFIG_PPC_IRQ_SOFT_MASK_DEBUG
+/*
+ * WARN/BUG is handled with a program interrupt so minimise checks here to
+ * avoid recursion and maximise the chance of getting the first oops handled.
+ */
+#define INT_SOFT_MASK_BUG_ON(regs, cond)				\
+do {									\
+	if ((user_mode(regs) || (TRAP(regs) != INTERRUPT_PROGRAM)))	\
+		BUG_ON(cond);						\
+} while (0)
+#else
+#define INT_SOFT_MASK_BUG_ON(regs, cond)
+#endif
+
+#ifdef CONFIG_PPC_BOOK3S_64
+extern char __end_soft_masked[];
+bool search_kernel_soft_mask_table(unsigned long addr);
+unsigned long search_kernel_restart_table(unsigned long addr);
+
+DECLARE_STATIC_KEY_FALSE(interrupt_exit_not_reentrant);
+
+static inline bool is_implicit_soft_masked(struct pt_regs *regs)
+{
+	if (user_mode(regs))
+		return false;
+
+	if (regs->nip >= (unsigned long)__end_soft_masked)
+		return false;
+
+	return search_kernel_soft_mask_table(regs->nip);
+}
+
+static inline void srr_regs_clobbered(void)
+{
+	local_paca->srr_valid = 0;
+	local_paca->hsrr_valid = 0;
+}
+#else
+static inline unsigned long search_kernel_restart_table(unsigned long addr)
+{
+	return 0;
+}
+
+static inline bool is_implicit_soft_masked(struct pt_regs *regs)
+{
+	return false;
+}
+
+static inline void srr_regs_clobbered(void)
+{
+}
+#endif
+
+static inline void nap_adjust_return(struct pt_regs *regs)
+{
+#ifdef CONFIG_PPC_970_NAP
+	/*
+	 * Adjust the nap return address before irq_exit_rcu(). irq_exit_rcu()
+	 * may invoke softirqs with interrupts re-enabled, allowing a nested
+	 * async interrupt to arrive. If _TLF_NAPPING is still set at that
+	 * point, the nested interrupt would erroneously redirect its own
+	 * return address to power4_idle_nap_return, corrupting the stack.
+	 */
+	if (unlikely(test_thread_local_flags(_TLF_NAPPING))) {
+		/* Can avoid a test-and-clear because NMIs do not call this */
+		clear_thread_local_flags(_TLF_NAPPING);
+		regs_set_return_ip(regs, (unsigned long)power4_idle_nap_return);
+	}
+#endif
+}
+
+static __always_inline void booke_load_dbcr0(void)
+{
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+	unsigned long dbcr0 = current->thread.debug.dbcr0;
+
+	if (likely(!(dbcr0 & DBCR0_IDM)))
+		return;
+
+	/*
+	 * Check to see if the dbcr0 register is set up to debug.
+	 * Use the internal debug mode bit to do this.
+	 */
+	mtmsr(mfmsr() & ~MSR_DE);
+	if (IS_ENABLED(CONFIG_PPC32)) {
+		isync();
+		global_dbcr0[smp_processor_id()] = mfspr(SPRN_DBCR0);
+	}
+	mtspr(SPRN_DBCR0, dbcr0);
+	mtspr(SPRN_DBSR, -1);
+#endif
+}
+
+static inline void booke_restore_dbcr0(void)
+{
+#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+	unsigned long dbcr0 = current->thread.debug.dbcr0;
+
+	if (IS_ENABLED(CONFIG_PPC32) && unlikely(dbcr0 & DBCR0_IDM)) {
+		mtspr(SPRN_DBSR, -1);
+		mtspr(SPRN_DBCR0, global_dbcr0[smp_processor_id()]);
+	}
+#endif
+}
+
+static inline void check_return_regs_valid(struct pt_regs *regs)
+{
+#ifdef CONFIG_PPC_BOOK3S_64
+	unsigned long trap, srr0, srr1;
+	static bool warned;
+	u8 *validp;
+	char *h;
+
+	if (trap_is_scv(regs))
+		return;
+
+	trap = TRAP(regs);
+	// EE in HV mode sets HSRRs like 0xea0
+	if (cpu_has_feature(CPU_FTR_HVMODE) && trap == INTERRUPT_EXTERNAL)
+		trap = 0xea0;
+
+	switch (trap) {
+	case 0x980:
+	case INTERRUPT_H_DATA_STORAGE:
+	case 0xe20:
+	case 0xe40:
+	case INTERRUPT_HMI:
+	case 0xe80:
+	case 0xea0:
+	case INTERRUPT_H_FAC_UNAVAIL:
+	case 0x1200:
+	case 0x1500:
+	case 0x1600:
+	case 0x1800:
+		validp = &local_paca->hsrr_valid;
+		if (!READ_ONCE(*validp))
+			return;
+
+		srr0 = mfspr(SPRN_HSRR0);
+		srr1 = mfspr(SPRN_HSRR1);
+		h = "H";
+
+		break;
+	default:
+		validp = &local_paca->srr_valid;
+		if (!READ_ONCE(*validp))
+			return;
+
+		srr0 = mfspr(SPRN_SRR0);
+		srr1 = mfspr(SPRN_SRR1);
+		h = "";
+		break;
+	}
+
+	if (srr0 == regs->nip && srr1 == regs->msr)
+		return;
+
+	/*
+	 * A NMI / soft-NMI interrupt may have come in after we found
+	 * srr_valid and before the SRRs are loaded. The interrupt then
+	 * comes in and clobbers SRRs and clears srr_valid. Then we load
+	 * the SRRs here and test them above and find they don't match.
+	 *
+	 * Test validity again after that, to catch such false positives.
+	 *
+	 * This test in general will have some window for false negatives
+	 * and may not catch and fix all such cases if an NMI comes in
+	 * later and clobbers SRRs without clearing srr_valid, but hopefully
+	 * such things will get caught most of the time, statistically
+	 * enough to be able to get a warning out.
+	 */
+	if (!READ_ONCE(*validp))
+		return;
+
+	if (!data_race(warned)) {
+		data_race(warned = true);
+		pr_warn("%sSRR0 was: %lx should be: %lx\n", h, srr0, regs->nip);
+		pr_warn("%sSRR1 was: %lx should be: %lx\n", h, srr1, regs->msr);
+		show_regs(regs);
+	}
+
+	WRITE_ONCE(*validp, 0); /* fixup */
+#endif
+}
+
+static inline void arch_interrupt_enter_prepare(struct pt_regs *regs)
+{
+#ifdef CONFIG_PPC64
+	irq_soft_mask_set(IRQS_ALL_DISABLED);
+
+	/*
+	 * If the interrupt was taken with HARD_DIS clear, then enable MSR[EE].
+	 * Asynchronous interrupts get here with HARD_DIS set (see below), so
+	 * this enables MSR[EE] for synchronous interrupts. IRQs remain
+	 * soft-masked. The interrupt handler may later call
+	 * interrupt_cond_local_irq_enable() to achieve a regular process
+	 * context.
+	 */
+	if (!(local_paca->irq_happened & PACA_IRQ_HARD_DIS)) {
+		INT_SOFT_MASK_BUG_ON(regs, !(regs->msr & MSR_EE));
+		__hard_irq_enable();
+	} else {
+		__hard_RI_enable();
+	}
+	/* Enable MSR[RI] early, to support kernel SLB and hash faults */
+#endif
+
+	if (!regs_irqs_disabled(regs))
+		trace_hardirqs_off();
+
+	if (user_mode(regs)) {
+		kuap_lock();
+		account_cpu_user_entry();
+		account_stolen_time();
+	} else {
+		kuap_save_and_lock(regs);
+		/*
+		 * CT_WARN_ON comes here via program_check_exception,
+		 * so avoid recursion.
+		 */
+		if (TRAP(regs) != INTERRUPT_PROGRAM)
+			CT_WARN_ON(ct_state() != CT_STATE_KERNEL &&
+				   ct_state() != CT_STATE_IDLE);
+		INT_SOFT_MASK_BUG_ON(regs, is_implicit_soft_masked(regs));
+		INT_SOFT_MASK_BUG_ON(regs, regs_irqs_disabled(regs) &&
+				     search_kernel_restart_table(regs->nip));
+	}
+	INT_SOFT_MASK_BUG_ON(regs, !regs_irqs_disabled(regs) &&
+			     !(regs->msr & MSR_EE));
+
+	booke_restore_dbcr0();
+}
+
+/*
+ * Care should be taken to note that arch_interrupt_exit_prepare and
+ * arch_interrupt_async_exit_prepare do not necessarily return immediately to
+ * regs context (e.g., if regs is usermode, we don't necessarily return to
+ * user mode). Other interrupts might be taken between here and return,
+ * context switch / preemption may occur in the exit path after this, or a
+ * signal may be delivered, etc.
+ *
+ * The real interrupt exit code is platform specific, e.g.,
+ * interrupt_exit_user_prepare / interrupt_exit_kernel_prepare for 64s.
+ *
+ * However arch_interrupt_nmi_exit_prepare does return directly to regs, because
+ * NMIs do not do "exit work" or replay soft-masked interrupts.
+ */
+static inline void arch_interrupt_exit_prepare(struct pt_regs *regs)
+{
+	if (user_mode(regs)) {
+		BUG_ON(regs_is_unrecoverable(regs));
+		BUG_ON(regs_irqs_disabled(regs));
+		/*
+		 * We don't need to restore AMR on the way back to userspace for KUAP.
+		 * AMR can only have been unlocked if we interrupted the kernel.
+		 */
+		kuap_assert_locked();
+	}
+
+	/* irqentry_exit expects to be called with interrupts disabled */
+	local_irq_disable();
+}
+
+static inline void arch_interrupt_async_enter_prepare(struct pt_regs *regs)
+{
+#ifdef CONFIG_PPC64
+	/* Ensure arch_interrupt_enter_prepare does not enable MSR[EE] */
+	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+#endif
+	arch_interrupt_enter_prepare(regs);
+#ifdef CONFIG_PPC_BOOK3S_64
+	/*
+	 * RI=1 is set by arch_interrupt_enter_prepare, so this thread flags access
+	 * has to come afterward (it can cause SLB faults).
+	 */
+	if (cpu_has_feature(CPU_FTR_CTRL) &&
+	    !test_thread_local_flags(_TLF_RUNLATCH))
+		__ppc64_runlatch_on();
+#endif
+}
+
+static inline void arch_interrupt_async_exit_prepare(struct pt_regs *regs)
+{
+	arch_interrupt_exit_prepare(regs);
+}
+
+struct interrupt_nmi_state {
+#ifdef CONFIG_PPC64
+	u8 irq_soft_mask;
+	u8 irq_happened;
+	u8 ftrace_enabled;
+	u64 softe;
+#endif
+};
+
+static inline bool nmi_disables_ftrace(struct pt_regs *regs)
+{
+	/* Allow DEC and PMI to be traced when they are soft-NMI */
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64)) {
+		if (TRAP(regs) == INTERRUPT_DECREMENTER)
+			return false;
+		if (TRAP(regs) == INTERRUPT_PERFMON)
+			return false;
+	}
+	if (IS_ENABLED(CONFIG_PPC_BOOK3E_64)) {
+		if (TRAP(regs) == INTERRUPT_PERFMON)
+			return false;
+	}
+
+	return true;
+}
+
+static inline void arch_interrupt_nmi_enter_prepare(struct pt_regs *regs,
+						    struct interrupt_nmi_state *state)
+{
+#ifdef CONFIG_PPC64
+	state->irq_soft_mask = local_paca->irq_soft_mask;
+	state->irq_happened = local_paca->irq_happened;
+	state->softe = regs->softe;
+
+	/*
+	 * Set IRQS_ALL_DISABLED unconditionally so irqs_disabled() does
+	 * the right thing, and set IRQ_HARD_DIS. We do not want to reconcile
+	 * because that goes through irq tracing which we don't want in NMI.
+	 */
+	local_paca->irq_soft_mask = IRQS_ALL_DISABLED;
+	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;
+
+	if (!(regs->msr & MSR_EE) || is_implicit_soft_masked(regs)) {
+		/*
+		 * Adjust regs->softe to be soft-masked if it had not been
+		 * reconcied (e.g., interrupt entry with MSR[EE]=0 but softe
+		 * not yet set disabled), or if it was in an implicit soft
+		 * masked state. This makes regs_irqs_disabled(regs)
+		 * behave as expected.
+		 */
+		regs->softe = IRQS_ALL_DISABLED;
+	}
+
+	__hard_RI_enable();
+
+	/* Don't do any per-CPU operations until interrupt state is fixed */
+
+	if (nmi_disables_ftrace(regs)) {
+		state->ftrace_enabled = this_cpu_get_ftrace_enabled();
+		this_cpu_set_ftrace_enabled(0);
+	}
+#endif
+}
+
+static inline void arch_interrupt_nmi_exit_prepare(struct pt_regs *regs,
+						   struct interrupt_nmi_state *state)
+{
+	/*
+	 * nmi does not call nap_adjust_return because nmi should not create
+	 * new work to do (must use irq_work for that).
+	 */
+
+#ifdef CONFIG_PPC64
+#ifdef CONFIG_PPC_BOOK3S
+	if (regs_irqs_disabled(regs)) {
+		unsigned long rst = search_kernel_restart_table(regs->nip);
+
+		if (rst)
+			regs_set_return_ip(regs, rst);
+	}
+#endif
+
+	if (nmi_disables_ftrace(regs))
+		this_cpu_set_ftrace_enabled(state->ftrace_enabled);
+
+	/* Check we didn't change the pending interrupt mask. */
+	WARN_ON_ONCE((state->irq_happened | PACA_IRQ_HARD_DIS) != local_paca->irq_happened);
+	regs->softe = state->softe;
+	local_paca->irq_happened = state->irq_happened;
+	local_paca->irq_soft_mask = state->irq_soft_mask;
+#endif
+}
+
+static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs)
+{
+	kuap_lock();
+
+	if (IS_ENABLED(CONFIG_PPC_IRQ_SOFT_MASK_DEBUG))
+		BUG_ON(irq_soft_mask_return() != IRQS_ALL_DISABLED);
+
+	BUG_ON(regs_is_unrecoverable(regs));
+	BUG_ON(!user_mode(regs));
+	BUG_ON(regs_irqs_disabled(regs));
+
+#ifdef CONFIG_PPC_PKEY
+	if (mmu_has_feature(MMU_FTR_PKEY) && trap_is_syscall(regs)) {
+		unsigned long amr, iamr;
+		bool flush_needed = false;
+		/*
+		 * When entering from userspace we mostly have the AMR/IAMR
+		 * different from kernel default values. Hence don't compare.
+		 */
+		amr = mfspr(SPRN_AMR);
+		iamr = mfspr(SPRN_IAMR);
+		regs->amr  = amr;
+		regs->iamr = iamr;
+		if (mmu_has_feature(MMU_FTR_KUAP)) {
+			mtspr(SPRN_AMR, AMR_KUAP_BLOCKED);
+			flush_needed = true;
+		}
+		if (mmu_has_feature(MMU_FTR_BOOK3S_KUEP)) {
+			mtspr(SPRN_IAMR, AMR_KUEP_BLOCKED);
+			flush_needed = true;
+		}
+		if (flush_needed)
+			isync();
+	}
+#endif
+	kuap_assert_locked();
+	booke_restore_dbcr0();
+	account_cpu_user_entry();
+	account_stolen_time();
+
+	/*
+	 * This is not required for the syscall exit path, but makes the
+	 * stack frame look nicer. If this was initialised in the first stack
+	 * frame, or if the unwinder was taught the first stack frame always
+	 * returns to user with IRQS_ENABLED, this store could be avoided!
+	 */
+	irq_soft_mask_regs_set_state(regs, IRQS_ENABLED);
+
+	/*
+	 * If system call is called with TM active, set _TIF_RESTOREALL to
+	 * prevent RFSCV being used to return to userspace, because POWER9
+	 * TM implementation has problems with this instruction returning to
+	 * transactional state. Final register values are not relevant because
+	 * the transaction will be aborted upon return anyway. Or in the case
+	 * of unsupported_scv SIGILL fault, the return state does not much
+	 * matter because it's an edge case.
+	 */
+	if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
+	    unlikely(MSR_TM_TRANSACTIONAL(regs->msr)))
+		set_bits(_TIF_RESTOREALL, &current_thread_info()->flags);
+
+	/*
+	 * If the system call was made with a transaction active, doom it and
+	 * return without performing the system call. Unless it was an
+	 * unsupported scv vector, in which case it's treated like an illegal
+	 * instruction.
+	 */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	if (unlikely(MSR_TM_TRANSACTIONAL(regs->msr)) &&
+	    !trap_is_unsupported_scv(regs)) {
+		/* Enable TM in the kernel, and disable EE (for scv) */
+		hard_irq_disable();
+		mtmsr(mfmsr() | MSR_TM);
+
+		/* tabort, this dooms the transaction, nothing else */
+		asm volatile(".long 0x7c00071d | ((%0) << 16)"
+			     :: "r"(TM_CAUSE_SYSCALL | TM_CAUSE_PERSISTENT));
+
+		/*
+		 * Userspace will never see the return value. Execution will
+		 * resume after the tbegin. of the aborted transaction with the
+		 * checkpointed register state. A context switch could occur
+		 * or signal delivered to the process before resuming the
+		 * doomed transaction context, but that should all be handled
+		 * as expected.
+		 */
+		return;
+	}
+#endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
+}
+
+#define arch_enter_from_user_mode arch_enter_from_user_mode
+
+static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
+						  unsigned long ti_work)
+{
+	unsigned long mathflags;
+
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_64) && IS_ENABLED(CONFIG_PPC_FPU)) {
+		if (IS_ENABLED(CONFIG_PPC_TRANSACTIONAL_MEM) &&
+		    unlikely((ti_work & _TIF_RESTORE_TM))) {
+			restore_tm_state(regs);
+		} else {
+			mathflags = MSR_FP;
+
+			if (cpu_has_feature(CPU_FTR_VSX))
+				mathflags |= MSR_VEC | MSR_VSX;
+			else if (cpu_has_feature(CPU_FTR_ALTIVEC))
+				mathflags |= MSR_VEC;
+
+			/*
+			 * If userspace MSR has all available FP bits set,
+			 * then they are live and no need to restore. If not,
+			 * it means the regs were given up and restore_math
+			 * may decide to restore them (to avoid taking an FP
+			 * fault).
+			 */
+			if ((regs->msr & mathflags) != mathflags)
+				restore_math(regs);
+		}
+	}
+
+	check_return_regs_valid(regs);
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	local_paca->tm_scratch = regs->msr;
+#endif
+	/* Restore user access locks last */
+	kuap_user_restore(regs);
+}
+
+#define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare
+
+static __always_inline void arch_exit_to_user_mode(void)
+{
+	booke_load_dbcr0();
+
+	account_cpu_user_exit();
+}
+
+#define arch_exit_to_user_mode arch_exit_to_user_mode
+
+#endif /* _ASM_PPC_ENTRY_COMMON_H */

linux-7.2.3/arch/powerpc/include/asm/epapr_hcalls.h

@@ -0,0 +1,575 @@
+/*
+ * ePAPR hcall interface
+ *
+ * Copyright 2008-2011 Freescale Semiconductor, Inc.
+ *
+ * Author: Timur Tabi <timur@freescale.com>
+ *
+ * This file is provided under a dual BSD/GPL license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in the
+ *       documentation and/or other materials provided with the distribution.
+ *     * Neither the name of Freescale Semiconductor nor the
+ *       names of its contributors may be used to endorse or promote products
+ *       derived from this software without specific prior written permission.
+ *
+ *
+ * ALTERNATIVELY, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") as published by the Free Software
+ * Foundation, either version 2 of that License or (at your option) any
+ * later version.
+ *
+ * THIS SOFTWARE IS PROVIDED BY Freescale Semiconductor ``AS IS'' AND ANY
+ * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ * DISCLAIMED. IN NO EVENT SHALL Freescale Semiconductor BE LIABLE FOR ANY
+ * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
+ * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
+ * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/* A "hypercall" is an "sc 1" instruction.  This header file provides C
+ * wrapper functions for the ePAPR hypervisor interface.  It is inteded
+ * for use by Linux device drivers and other operating systems.
+ *
+ * The hypercalls are implemented as inline assembly, rather than assembly
+ * language functions in a .S file, for optimization.  It allows
+ * the caller to issue the hypercall instruction directly, improving both
+ * performance and memory footprint.
+ */
+
+#ifndef _EPAPR_HCALLS_H
+#define _EPAPR_HCALLS_H
+
+#include <uapi/asm/epapr_hcalls.h>
+
+#ifndef __ASSEMBLER__
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <asm/byteorder.h>
+
+/*
+ * Hypercall register clobber list
+ *
+ * These macros are used to define the list of clobbered registers during a
+ * hypercall.  Technically, registers r0 and r3-r12 are always clobbered,
+ * but the gcc inline assembly syntax does not allow us to specify registers
+ * on the clobber list that are also on the input/output list.  Therefore,
+ * the lists of clobbered registers depends on the number of register
+ * parameters ("+r" and "=r") passed to the hypercall.
+ *
+ * Each assembly block should use one of the HCALL_CLOBBERSx macros.  As a
+ * general rule, 'x' is the number of parameters passed to the assembly
+ * block *except* for r11.
+ *
+ * If you're not sure, just use the smallest value of 'x' that does not
+ * generate a compilation error.  Because these are static inline functions,
+ * the compiler will only check the clobber list for a function if you
+ * compile code that calls that function.
+ *
+ * r3 and r11 are not included in any clobbers list because they are always
+ * listed as output registers.
+ *
+ * XER, CTR, and LR are currently listed as clobbers because it's uncertain
+ * whether they will be clobbered.
+ *
+ * Note that r11 can be used as an output parameter.
+ *
+ * The "memory" clobber is only necessary for hcalls where the Hypervisor
+ * will read or write guest memory. However, we add it to all hcalls because
+ * the impact is minimal, and we want to ensure that it's present for the
+ * hcalls that need it.
+*/
+
+/* List of common clobbered registers.  Do not use this macro. */
+#define EV_HCALL_CLOBBERS "r0", "r12", "xer", "ctr", "lr", "cc", "memory"
+
+#define EV_HCALL_CLOBBERS8 EV_HCALL_CLOBBERS
+#define EV_HCALL_CLOBBERS7 EV_HCALL_CLOBBERS8, "r10"
+#define EV_HCALL_CLOBBERS6 EV_HCALL_CLOBBERS7, "r9"
+#define EV_HCALL_CLOBBERS5 EV_HCALL_CLOBBERS6, "r8"
+#define EV_HCALL_CLOBBERS4 EV_HCALL_CLOBBERS5, "r7"
+#define EV_HCALL_CLOBBERS3 EV_HCALL_CLOBBERS4, "r6"
+#define EV_HCALL_CLOBBERS2 EV_HCALL_CLOBBERS3, "r5"
+#define EV_HCALL_CLOBBERS1 EV_HCALL_CLOBBERS2, "r4"
+
+extern bool epapr_paravirt_enabled;
+extern u32 epapr_hypercall_start[];
+
+#ifdef CONFIG_EPAPR_PARAVIRT
+int __init epapr_paravirt_early_init(void);
+#else
+static inline int epapr_paravirt_early_init(void) { return 0; }
+#endif
+
+/*
+ * We use "uintptr_t" to define a register because it's guaranteed to be a
+ * 32-bit integer on a 32-bit platform, and a 64-bit integer on a 64-bit
+ * platform.
+ *
+ * All registers are either input/output or output only.  Registers that are
+ * initialized before making the hypercall are input/output.  All
+ * input/output registers are represented with "+r".  Output-only registers
+ * are represented with "=r".  Do not specify any unused registers.  The
+ * clobber list will tell the compiler that the hypercall modifies those
+ * registers, which is good enough.
+ */
+
+/**
+ * ev_int_set_config - configure the specified interrupt
+ * @interrupt: the interrupt number
+ * @config: configuration for this interrupt
+ * @priority: interrupt priority
+ * @destination: destination CPU number
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int ev_int_set_config(unsigned int interrupt,
+	uint32_t config, unsigned int priority, uint32_t destination)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+	register uintptr_t r5 __asm__("r5");
+	register uintptr_t r6 __asm__("r6");
+
+	r11 = EV_HCALL_TOKEN(EV_INT_SET_CONFIG);
+	r3  = interrupt;
+	r4  = config;
+	r5  = priority;
+	r6  = destination;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3), "+r" (r4), "+r" (r5), "+r" (r6)
+		: : EV_HCALL_CLOBBERS4
+	);
+
+	return r3;
+}
+
+/**
+ * ev_int_get_config - return the config of the specified interrupt
+ * @interrupt: the interrupt number
+ * @config: returned configuration for this interrupt
+ * @priority: returned interrupt priority
+ * @destination: returned destination CPU number
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int ev_int_get_config(unsigned int interrupt,
+	uint32_t *config, unsigned int *priority, uint32_t *destination)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+	register uintptr_t r5 __asm__("r5");
+	register uintptr_t r6 __asm__("r6");
+
+	r11 = EV_HCALL_TOKEN(EV_INT_GET_CONFIG);
+	r3 = interrupt;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3), "=r" (r4), "=r" (r5), "=r" (r6)
+		: : EV_HCALL_CLOBBERS4
+	);
+
+	*config = r4;
+	*priority = r5;
+	*destination = r6;
+
+	return r3;
+}
+
+/**
+ * ev_int_set_mask - sets the mask for the specified interrupt source
+ * @interrupt: the interrupt number
+ * @mask: 0=enable interrupts, 1=disable interrupts
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int ev_int_set_mask(unsigned int interrupt,
+	unsigned int mask)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+
+	r11 = EV_HCALL_TOKEN(EV_INT_SET_MASK);
+	r3 = interrupt;
+	r4 = mask;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3), "+r" (r4)
+		: : EV_HCALL_CLOBBERS2
+	);
+
+	return r3;
+}
+
+/**
+ * ev_int_get_mask - returns the mask for the specified interrupt source
+ * @interrupt: the interrupt number
+ * @mask: returned mask for this interrupt (0=enabled, 1=disabled)
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int ev_int_get_mask(unsigned int interrupt,
+	unsigned int *mask)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+
+	r11 = EV_HCALL_TOKEN(EV_INT_GET_MASK);
+	r3 = interrupt;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3), "=r" (r4)
+		: : EV_HCALL_CLOBBERS2
+	);
+
+	*mask = r4;
+
+	return r3;
+}
+
+/**
+ * ev_int_eoi - signal the end of interrupt processing
+ * @interrupt: the interrupt number
+ *
+ * This function signals the end of processing for the specified
+ * interrupt, which must be the interrupt currently in service. By
+ * definition, this is also the highest-priority interrupt.
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int ev_int_eoi(unsigned int interrupt)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+
+	r11 = EV_HCALL_TOKEN(EV_INT_EOI);
+	r3 = interrupt;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3)
+		: : EV_HCALL_CLOBBERS1
+	);
+
+	return r3;
+}
+
+/**
+ * ev_byte_channel_send - send characters to a byte stream
+ * @handle: byte stream handle
+ * @count: (input) num of chars to send, (output) num chars sent
+ * @buffer: pointer to a 16-byte buffer
+ *
+ * @buffer must be at least 16 bytes long, because all 16 bytes will be
+ * read from memory into registers, even if count < 16.
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int ev_byte_channel_send(unsigned int handle,
+	unsigned int *count, const char buffer[EV_BYTE_CHANNEL_MAX_BYTES])
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+	register uintptr_t r5 __asm__("r5");
+	register uintptr_t r6 __asm__("r6");
+	register uintptr_t r7 __asm__("r7");
+	register uintptr_t r8 __asm__("r8");
+	const uint32_t *p = (const uint32_t *) buffer;
+
+	r11 = EV_HCALL_TOKEN(EV_BYTE_CHANNEL_SEND);
+	r3 = handle;
+	r4 = *count;
+	r5 = be32_to_cpu(p[0]);
+	r6 = be32_to_cpu(p[1]);
+	r7 = be32_to_cpu(p[2]);
+	r8 = be32_to_cpu(p[3]);
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3),
+		  "+r" (r4), "+r" (r5), "+r" (r6), "+r" (r7), "+r" (r8)
+		: : EV_HCALL_CLOBBERS6
+	);
+
+	*count = r4;
+
+	return r3;
+}
+
+/**
+ * ev_byte_channel_receive - fetch characters from a byte channel
+ * @handle: byte channel handle
+ * @count: (input) max num of chars to receive, (output) num chars received
+ * @buffer: pointer to a 16-byte buffer
+ *
+ * The size of @buffer must be at least 16 bytes, even if you request fewer
+ * than 16 characters, because we always write 16 bytes to @buffer.  This is
+ * for performance reasons.
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int ev_byte_channel_receive(unsigned int handle,
+	unsigned int *count, char buffer[EV_BYTE_CHANNEL_MAX_BYTES])
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+	register uintptr_t r5 __asm__("r5");
+	register uintptr_t r6 __asm__("r6");
+	register uintptr_t r7 __asm__("r7");
+	register uintptr_t r8 __asm__("r8");
+	uint32_t *p = (uint32_t *) buffer;
+
+	r11 = EV_HCALL_TOKEN(EV_BYTE_CHANNEL_RECEIVE);
+	r3 = handle;
+	r4 = *count;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3), "+r" (r4),
+		  "=r" (r5), "=r" (r6), "=r" (r7), "=r" (r8)
+		: : EV_HCALL_CLOBBERS6
+	);
+
+	*count = r4;
+	p[0] = cpu_to_be32(r5);
+	p[1] = cpu_to_be32(r6);
+	p[2] = cpu_to_be32(r7);
+	p[3] = cpu_to_be32(r8);
+
+	return r3;
+}
+
+/**
+ * ev_byte_channel_poll - returns the status of the byte channel buffers
+ * @handle: byte channel handle
+ * @rx_count: returned count of bytes in receive queue
+ * @tx_count: returned count of free space in transmit queue
+ *
+ * This function reports the amount of data in the receive queue (i.e. the
+ * number of bytes you can read), and the amount of free space in the transmit
+ * queue (i.e. the number of bytes you can write).
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int ev_byte_channel_poll(unsigned int handle,
+	unsigned int *rx_count,	unsigned int *tx_count)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+	register uintptr_t r5 __asm__("r5");
+
+	r11 = EV_HCALL_TOKEN(EV_BYTE_CHANNEL_POLL);
+	r3 = handle;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3), "=r" (r4), "=r" (r5)
+		: : EV_HCALL_CLOBBERS3
+	);
+
+	*rx_count = r4;
+	*tx_count = r5;
+
+	return r3;
+}
+
+/**
+ * ev_int_iack - acknowledge an interrupt
+ * @handle: handle to the target interrupt controller
+ * @vector: returned interrupt vector
+ *
+ * If handle is zero, the function returns the next interrupt source
+ * number to be handled irrespective of the hierarchy or cascading
+ * of interrupt controllers. If non-zero, specifies a handle to the
+ * interrupt controller that is the target of the acknowledge.
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int ev_int_iack(unsigned int handle,
+	unsigned int *vector)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+	register uintptr_t r4 __asm__("r4");
+
+	r11 = EV_HCALL_TOKEN(EV_INT_IACK);
+	r3 = handle;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3), "=r" (r4)
+		: : EV_HCALL_CLOBBERS2
+	);
+
+	*vector = r4;
+
+	return r3;
+}
+
+/**
+ * ev_doorbell_send - send a doorbell to another partition
+ * @handle: doorbell send handle
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int ev_doorbell_send(unsigned int handle)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+
+	r11 = EV_HCALL_TOKEN(EV_DOORBELL_SEND);
+	r3 = handle;
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "+r" (r3)
+		: : EV_HCALL_CLOBBERS1
+	);
+
+	return r3;
+}
+
+/**
+ * ev_idle -- wait for next interrupt on this core
+ *
+ * Returns 0 for success, or an error code.
+ */
+static inline unsigned int ev_idle(void)
+{
+	register uintptr_t r11 __asm__("r11");
+	register uintptr_t r3 __asm__("r3");
+
+	r11 = EV_HCALL_TOKEN(EV_IDLE);
+
+	asm volatile("bl	epapr_hypercall_start"
+		: "+r" (r11), "=r" (r3)
+		: : EV_HCALL_CLOBBERS1
+	);
+
+	return r3;
+}
+
+#ifdef CONFIG_EPAPR_PARAVIRT
+static inline unsigned long epapr_hypercall(unsigned long *in,
+			    unsigned long *out,
+			    unsigned long nr)
+{
+	register unsigned long r0 asm("r0");
+	register unsigned long r3 asm("r3") = in[0];
+	register unsigned long r4 asm("r4") = in[1];
+	register unsigned long r5 asm("r5") = in[2];
+	register unsigned long r6 asm("r6") = in[3];
+	register unsigned long r7 asm("r7") = in[4];
+	register unsigned long r8 asm("r8") = in[5];
+	register unsigned long r9 asm("r9") = in[6];
+	register unsigned long r10 asm("r10") = in[7];
+	register unsigned long r11 asm("r11") = nr;
+	register unsigned long r12 asm("r12");
+
+	asm volatile("bl	epapr_hypercall_start"
+		     : "=r"(r0), "=r"(r3), "=r"(r4), "=r"(r5), "=r"(r6),
+		       "=r"(r7), "=r"(r8), "=r"(r9), "=r"(r10), "=r"(r11),
+		       "=r"(r12)
+		     : "r"(r3), "r"(r4), "r"(r5), "r"(r6), "r"(r7), "r"(r8),
+		       "r"(r9), "r"(r10), "r"(r11)
+		     : "memory", "cc", "xer", "ctr", "lr");
+
+	out[0] = r4;
+	out[1] = r5;
+	out[2] = r6;
+	out[3] = r7;
+	out[4] = r8;
+	out[5] = r9;
+	out[6] = r10;
+	out[7] = r11;
+
+	return r3;
+}
+#else
+static unsigned long epapr_hypercall(unsigned long *in,
+				   unsigned long *out,
+				   unsigned long nr)
+{
+	return EV_UNIMPLEMENTED;
+}
+#endif
+
+static inline long epapr_hypercall0_1(unsigned int nr, unsigned long *r2)
+{
+	unsigned long in[8] = {0};
+	unsigned long out[8];
+	unsigned long r;
+
+	r = epapr_hypercall(in, out, nr);
+	*r2 = out[0];
+
+	return r;
+}
+
+static inline long epapr_hypercall0(unsigned int nr)
+{
+	unsigned long in[8] = {0};
+	unsigned long out[8];
+
+	return epapr_hypercall(in, out, nr);
+}
+
+static inline long epapr_hypercall1(unsigned int nr, unsigned long p1)
+{
+	unsigned long in[8] = {0};
+	unsigned long out[8];
+
+	in[0] = p1;
+	return epapr_hypercall(in, out, nr);
+}
+
+static inline long epapr_hypercall2(unsigned int nr, unsigned long p1,
+				    unsigned long p2)
+{
+	unsigned long in[8] = {0};
+	unsigned long out[8];
+
+	in[0] = p1;
+	in[1] = p2;
+	return epapr_hypercall(in, out, nr);
+}
+
+static inline long epapr_hypercall3(unsigned int nr, unsigned long p1,
+				    unsigned long p2, unsigned long p3)
+{
+	unsigned long in[8] = {0};
+	unsigned long out[8];
+
+	in[0] = p1;
+	in[1] = p2;
+	in[2] = p3;
+	return epapr_hypercall(in, out, nr);
+}
+
+static inline long epapr_hypercall4(unsigned int nr, unsigned long p1,
+				    unsigned long p2, unsigned long p3,
+				    unsigned long p4)
+{
+	unsigned long in[8] = {0};
+	unsigned long out[8];
+
+	in[0] = p1;
+	in[1] = p2;
+	in[2] = p3;
+	in[3] = p4;
+	return epapr_hypercall(in, out, nr);
+}
+#endif /* !__ASSEMBLER__ */
+#endif /* _EPAPR_HCALLS_H */

linux-7.2.3/arch/powerpc/include/asm/exception-64e.h

@@ -0,0 +1,172 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ *  Definitions for use by exception code on Book3-E
+ *
+ *  Copyright (C) 2008 Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp.
+ */
+#ifndef _ASM_POWERPC_EXCEPTION_64E_H
+#define _ASM_POWERPC_EXCEPTION_64E_H
+
+/*
+ * SPRGs usage an other considerations...
+ *
+ * Since TLB miss and other standard exceptions can be interrupted by
+ * critical exceptions which can themselves be interrupted by machine
+ * checks, and since the two later can themselves cause a TLB miss when
+ * hitting the linear mapping for the kernel stacks, we need to be a bit
+ * creative on how we use SPRGs.
+ *
+ * The base idea is that we have one SRPG reserved for critical and one
+ * for machine check interrupts. Those are used to save a GPR that can
+ * then be used to get the PACA, and store as much context as we need
+ * to save in there. That includes saving the SPRGs used by the TLB miss
+ * handler for linear mapping misses and the associated SRR0/1 due to
+ * the above re-entrancy issue.
+ *
+ * So here's the current usage pattern. It's done regardless of which
+ * SPRGs are user-readable though, thus we might have to change some of
+ * this later. In order to do that more easily, we use special constants
+ * for naming them
+ *
+ * WARNING: Some of these SPRGs are user readable. We need to do something
+ * about it as some point by making sure they can't be used to leak kernel
+ * critical data
+ */
+
+#define PACA_EXGDBELL PACA_EXGEN
+
+/* We are out of SPRGs so we save some things in the PACA. The normal
+ * exception frame is smaller than the CRIT or MC one though
+ */
+#define EX_R1		(0 * 8)
+#define EX_CR		(1 * 8)
+#define EX_R10		(2 * 8)
+#define EX_R11		(3 * 8)
+#define EX_R14		(4 * 8)
+#define EX_R15		(5 * 8)
+
+/*
+ * The TLB miss exception uses different slots.
+ *
+ * The bolted variant uses only the first six fields,
+ * which in combination with pgd and kernel_pgd fits in
+ * one 64-byte cache line.
+ */
+
+#define EX_TLB_R10	( 0 * 8)
+#define EX_TLB_R11	( 1 * 8)
+#define EX_TLB_R14	( 2 * 8)
+#define EX_TLB_R15	( 3 * 8)
+#define EX_TLB_R16	( 4 * 8)
+#define EX_TLB_CR	( 5 * 8)
+#define EX_TLB_R12	( 6 * 8)
+#define EX_TLB_R13	( 7 * 8)
+#define EX_TLB_DEAR	( 8 * 8) /* Level 0 and 2 only */
+#define EX_TLB_ESR	( 9 * 8) /* Level 0 and 2 only */
+#define EX_TLB_SRR0	(10 * 8)
+#define EX_TLB_SRR1	(11 * 8)
+#define EX_TLB_R7	(12 * 8)
+#define EX_TLB_SIZE	(13 * 8)
+
+#define	START_EXCEPTION(label)						\
+	.globl exc_##label##_book3e;					\
+exc_##label##_book3e:
+
+/* TLB miss exception prolog
+ *
+ * This prolog handles re-entrancy (up to 3 levels supported in the PACA
+ * though we currently don't test for overflow). It provides you with a
+ * re-entrancy safe working space of r10...r16 and CR with r12 being used
+ * as the exception area pointer in the PACA for that level of re-entrancy
+ * and r13 containing the PACA pointer.
+ *
+ * SRR0 and SRR1 are saved, but DEAR and ESR are not, since they don't apply
+ * as-is for instruction exceptions. It's up to the actual exception code
+ * to save them as well if required.
+ */
+#define TLB_MISS_PROLOG							    \
+	mtspr	SPRN_SPRG_TLB_SCRATCH,r12;				    \
+	mfspr	r12,SPRN_SPRG_TLB_EXFRAME;				    \
+	std	r10,EX_TLB_R10(r12);					    \
+	mfcr	r10;							    \
+	std	r11,EX_TLB_R11(r12);					    \
+	mfspr	r11,SPRN_SPRG_TLB_SCRATCH;				    \
+	std	r13,EX_TLB_R13(r12);					    \
+	mfspr	r13,SPRN_SPRG_PACA;					    \
+	std	r14,EX_TLB_R14(r12);					    \
+	addi	r14,r12,EX_TLB_SIZE;					    \
+	std	r15,EX_TLB_R15(r12);					    \
+	mfspr	r15,SPRN_SRR1;						    \
+	std	r16,EX_TLB_R16(r12);					    \
+	mfspr	r16,SPRN_SRR0;						    \
+	std	r10,EX_TLB_CR(r12);					    \
+	std	r11,EX_TLB_R12(r12);					    \
+	mtspr	SPRN_SPRG_TLB_EXFRAME,r14;				    \
+	std	r15,EX_TLB_SRR1(r12);					    \
+	std	r16,EX_TLB_SRR0(r12);
+
+/* And these are the matching epilogs that restores things
+ *
+ * There are 3 epilogs:
+ *
+ * - SUCCESS       : Unwinds one level
+ * - ERROR         : restore from level 0 and reset
+ * - ERROR_SPECIAL : restore from current level and reset
+ *
+ * Normal errors use ERROR, that is, they restore the initial fault context
+ * and trigger a fault. However, there is a special case for linear mapping
+ * errors. Those should basically never happen, but if they do happen, we
+ * want the error to point out the context that did that linear mapping
+ * fault, not the initial level 0 (basically, we got a bogus PGF or something
+ * like that). For userland errors on the linear mapping, there is no
+ * difference since those are always level 0 anyway
+ */
+
+#define TLB_MISS_RESTORE(freg)						    \
+	ld	r14,EX_TLB_CR(r12);					    \
+	ld	r10,EX_TLB_R10(r12);					    \
+	ld	r15,EX_TLB_SRR0(r12);					    \
+	ld	r16,EX_TLB_SRR1(r12);					    \
+	mtspr	SPRN_SPRG_TLB_EXFRAME,freg;				    \
+	ld	r11,EX_TLB_R11(r12);					    \
+	mtcr	r14;							    \
+	ld	r13,EX_TLB_R13(r12);					    \
+	ld	r14,EX_TLB_R14(r12);					    \
+	mtspr	SPRN_SRR0,r15;						    \
+	ld	r15,EX_TLB_R15(r12);					    \
+	mtspr	SPRN_SRR1,r16;						    \
+	ld	r16,EX_TLB_R16(r12);					    \
+	ld	r12,EX_TLB_R12(r12);					    \
+
+#define TLB_MISS_EPILOG_SUCCESS						    \
+	TLB_MISS_RESTORE(r12)
+
+#define TLB_MISS_EPILOG_ERROR						    \
+	addi	r12,r13,PACA_EXTLB;					    \
+	TLB_MISS_RESTORE(r12)
+
+#define TLB_MISS_EPILOG_ERROR_SPECIAL					    \
+	addi	r11,r13,PACA_EXTLB;					    \
+	TLB_MISS_RESTORE(r11)
+
+#ifndef __ASSEMBLER__
+extern unsigned int interrupt_base_book3e;
+#endif
+
+#define SET_IVOR(vector_number, vector_offset)	\
+	LOAD_REG_ADDR(r3,interrupt_base_book3e);\
+	ori	r3,r3,vector_offset@l;		\
+	mtspr	SPRN_IVOR##vector_number,r3;
+/*
+ * powerpc relies on return from interrupt/syscall being context synchronising
+ * (which rfi is) to support ARCH_HAS_MEMBARRIER_SYNC_CORE without additional
+ * synchronisation instructions.
+ */
+#define RFI_TO_KERNEL							\
+	rfi
+
+#define RFI_TO_USER							\
+	rfi
+
+#endif /* _ASM_POWERPC_EXCEPTION_64E_H */
+

linux-7.2.3/arch/powerpc/include/asm/exception-64s.h

@@ -0,0 +1,178 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ASM_POWERPC_EXCEPTION_H
+#define _ASM_POWERPC_EXCEPTION_H
+/*
+ * Extracted from head_64.S
+ *
+ *  PowerPC version
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ *  Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
+ *    Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
+ *  Adapted for Power Macintosh by Paul Mackerras.
+ *  Low-level exception handlers and MMU support
+ *  rewritten by Paul Mackerras.
+ *    Copyright (C) 1996 Paul Mackerras.
+ *
+ *  Adapted for 64bit PowerPC by Dave Engebretsen, Peter Bergner, and
+ *    Mike Corrigan {engebret|bergner|mikejc}@us.ibm.com
+ *
+ *  This file contains the low-level support and setup for the
+ *  PowerPC-64 platform, including trap and interrupt dispatch.
+ */
+/*
+ * The following macros define the code that appears as
+ * the prologue to each of the exception handlers.  They
+ * are split into two parts to allow a single kernel binary
+ * to be used for pSeries and iSeries.
+ *
+ * We make as much of the exception code common between native
+ * exception handlers (including pSeries LPAR) and iSeries LPAR
+ * implementations as possible.
+ */
+#include <asm/feature-fixups.h>
+
+/* PACA save area size in u64 units (exgen, exmc, etc) */
+#define EX_SIZE		10
+
+/* PACA save area offsets */
+#define EX_R9		0
+#define EX_R10		8
+#define EX_R11		16
+#define EX_R12		24
+#define EX_R13		32
+#define EX_DAR		40
+#define EX_DSISR	48
+#define EX_CCR		52
+#define EX_CFAR		56
+#define EX_PPR		64
+#define EX_CTR		72
+
+/*
+ * maximum recursive depth of MCE exceptions
+ */
+#define MAX_MCE_DEPTH	4
+
+#ifdef __ASSEMBLER__
+
+#define STF_ENTRY_BARRIER_SLOT						\
+	STF_ENTRY_BARRIER_FIXUP_SECTION;				\
+	nop;								\
+	nop;								\
+	nop
+
+#define STF_EXIT_BARRIER_SLOT						\
+	STF_EXIT_BARRIER_FIXUP_SECTION;					\
+	nop;								\
+	nop;								\
+	nop;								\
+	nop;								\
+	nop;								\
+	nop
+
+#define ENTRY_FLUSH_SLOT						\
+	ENTRY_FLUSH_FIXUP_SECTION;					\
+	nop;								\
+	nop;								\
+	nop;
+
+#define SCV_ENTRY_FLUSH_SLOT						\
+	SCV_ENTRY_FLUSH_FIXUP_SECTION;					\
+	nop;								\
+	nop;								\
+	nop;
+
+/*
+ * r10 must be free to use, r13 must be paca
+ */
+#define INTERRUPT_TO_KERNEL						\
+	STF_ENTRY_BARRIER_SLOT;						\
+	ENTRY_FLUSH_SLOT
+
+/*
+ * r10, ctr must be free to use, r13 must be paca
+ */
+#define SCV_INTERRUPT_TO_KERNEL						\
+	STF_ENTRY_BARRIER_SLOT;						\
+	SCV_ENTRY_FLUSH_SLOT
+
+/*
+ * Macros for annotating the expected destination of (h)rfid
+ *
+ * The nop instructions allow us to insert one or more instructions to flush the
+ * L1-D cache when returning to userspace or a guest.
+ *
+ * powerpc relies on return from interrupt/syscall being context synchronising
+ * (which hrfid, rfid, and rfscv are) to support ARCH_HAS_MEMBARRIER_SYNC_CORE
+ * without additional synchronisation instructions.
+ *
+ * soft-masked interrupt replay does not include a context-synchronising rfid,
+ * but those always return to kernel, the sync is only required when returning
+ * to user.
+ */
+#define RFI_FLUSH_SLOT							\
+	RFI_FLUSH_FIXUP_SECTION;					\
+	nop;								\
+	nop;								\
+	nop
+
+#define RFI_TO_KERNEL							\
+	rfid
+
+#define RFI_TO_USER							\
+	STF_EXIT_BARRIER_SLOT;						\
+	RFI_FLUSH_SLOT;							\
+	rfid;								\
+	b	rfi_flush_fallback
+
+#define RFI_TO_USER_OR_KERNEL						\
+	STF_EXIT_BARRIER_SLOT;						\
+	RFI_FLUSH_SLOT;							\
+	rfid;								\
+	b	rfi_flush_fallback
+
+#define RFI_TO_GUEST							\
+	STF_EXIT_BARRIER_SLOT;						\
+	RFI_FLUSH_SLOT;							\
+	rfid;								\
+	b	rfi_flush_fallback
+
+#define HRFI_TO_KERNEL							\
+	hrfid
+
+#define HRFI_TO_USER							\
+	STF_EXIT_BARRIER_SLOT;						\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
+#define HRFI_TO_USER_OR_KERNEL						\
+	STF_EXIT_BARRIER_SLOT;						\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
+#define HRFI_TO_GUEST							\
+	STF_EXIT_BARRIER_SLOT;						\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
+#define HRFI_TO_UNKNOWN							\
+	STF_EXIT_BARRIER_SLOT;						\
+	RFI_FLUSH_SLOT;							\
+	hrfid;								\
+	b	hrfi_flush_fallback
+
+#define RFSCV_TO_USER							\
+	STF_EXIT_BARRIER_SLOT;						\
+	RFI_FLUSH_SLOT;							\
+	RFSCV;								\
+	b	rfscv_flush_fallback
+
+#else /* __ASSEMBLER__ */
+/* Prototype for function defined in exceptions-64s.S */
+void do_uaccess_flush(void);
+#endif /* __ASSEMBLER__ */
+
+#endif	/* _ASM_POWERPC_EXCEPTION_H */

linux-7.2.3/arch/powerpc/include/asm/exec.h

@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 1999 Cort Dougan <cort@cs.nmt.edu>
+ */
+#ifndef _ASM_POWERPC_EXEC_H
+#define _ASM_POWERPC_EXEC_H
+
+extern unsigned long arch_align_stack(unsigned long sp);
+
+#endif /* _ASM_POWERPC_EXEC_H */

linux-7.2.3/arch/powerpc/include/asm/extable.h

@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ARCH_POWERPC_EXTABLE_H
+#define _ARCH_POWERPC_EXTABLE_H
+
+/*
+ * The exception table consists of pairs of relative addresses: the first is
+ * the address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue.  No registers are
+ * modified, so it is entirely up to the continuation code to figure out what
+ * to do.
+ *
+ * All the routines below use bits of fixup code that are out of line with the
+ * main instruction path.  This means when everything is well, we don't even
+ * have to jump over them.  Further, they do not intrude on our cache or tlb
+ * entries.
+ */
+
+#define ARCH_HAS_RELATIVE_EXTABLE
+
+#ifndef __ASSEMBLER__
+
+struct exception_table_entry {
+	int insn;
+	int fixup;
+};
+
+static inline unsigned long extable_fixup(const struct exception_table_entry *x)
+{
+	return (unsigned long)&x->fixup + x->fixup;
+}
+
+#endif
+
+/*
+ * Helper macro for exception table entries
+ */
+#define EX_TABLE(_fault, _target)		\
+	stringify_in_c(.section __ex_table,"a";)\
+	stringify_in_c(.balign 4;)		\
+	stringify_in_c(.long (_fault) - . ;)	\
+	stringify_in_c(.long (_target) - . ;)	\
+	stringify_in_c(.previous)
+
+#endif

linux-7.2.3/arch/powerpc/include/asm/fadump-internal.h

@@ -0,0 +1,196 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Firmware-Assisted Dump internal code.
+ *
+ * Copyright 2011, Mahesh Salgaonkar, IBM Corporation.
+ * Copyright 2019, Hari Bathini, IBM Corporation.
+ */
+
+#ifndef _ASM_POWERPC_FADUMP_INTERNAL_H
+#define _ASM_POWERPC_FADUMP_INTERNAL_H
+
+/* Maximum number of memory regions kernel supports */
+#define FADUMP_MAX_MEM_REGS			128
+
+#ifndef CONFIG_PRESERVE_FA_DUMP
+
+/* The upper limit percentage for user specified boot memory size (25%) */
+#define MAX_BOOT_MEM_RATIO			4
+
+#define memblock_num_regions(memblock_type)	(memblock.memblock_type.cnt)
+
+/* FAD commands */
+#define FADUMP_REGISTER			1
+#define FADUMP_UNREGISTER		2
+#define FADUMP_INVALIDATE		3
+
+/*
+ * Copy the ascii values for first 8 characters from a string into u64
+ * variable at their respective indexes.
+ * e.g.
+ *  The string "FADMPINF" will be converted into 0x4641444d50494e46
+ */
+static inline u64 fadump_str_to_u64(const char *str)
+{
+	u64 val = 0;
+	int i;
+
+	for (i = 0; i < sizeof(val); i++)
+		val = (*str) ? (val << 8) | *str++ : val << 8;
+	return val;
+}
+
+#define FADUMP_CPU_UNKNOWN		(~((u32)0))
+
+/*
+ * The introduction of new fields in the fadump crash info header has
+ * led to a change in the magic key from `FADMPINF` to `FADMPSIG` for
+ * identifying a kernel crash from an old kernel.
+ *
+ * To prevent the need for further changes to the magic number in the
+ * event of future modifications to the fadump crash info header, a
+ * version field has been introduced to track the fadump crash info
+ * header version.
+ *
+ * Consider a few points before adding new members to the fadump crash info
+ * header structure:
+ *
+ *  - Append new members; avoid adding them in between.
+ *  - Non-primitive members should have a size member as well.
+ *  - For every change in the fadump header, increment the
+ *    fadump header version. This helps the updated kernel decide how to
+ *    handle kernel dumps from older kernels.
+ */
+#define FADUMP_CRASH_INFO_MAGIC_OLD	fadump_str_to_u64("FADMPINF")
+#define FADUMP_CRASH_INFO_MAGIC		fadump_str_to_u64("FADMPSIG")
+#define FADUMP_HEADER_VERSION		1
+
+/* fadump crash info structure */
+struct fadump_crash_info_header {
+	u64		magic_number;
+	u32		version;
+	u32		crashing_cpu;
+	u64		vmcoreinfo_raddr;
+	u64		vmcoreinfo_size;
+	u32		pt_regs_sz;
+	u32		cpu_mask_sz;
+	struct pt_regs	regs;
+	struct cpumask	cpu_mask;
+};
+
+struct fadump_memory_range {
+	u64	base;
+	u64	size;
+};
+
+/* fadump memory ranges info */
+#define RNG_NAME_SZ			16
+struct fadump_mrange_info {
+	char				name[RNG_NAME_SZ];
+	struct fadump_memory_range	*mem_ranges;
+	u32				mem_ranges_sz;
+	u32				mem_range_cnt;
+	u32				max_mem_ranges;
+	bool				is_static;
+};
+
+/* Platform specific callback functions */
+struct fadump_ops;
+
+/* Firmware-assisted dump configuration details. */
+struct fw_dump {
+	unsigned long	reserve_dump_area_start;
+	unsigned long	reserve_dump_area_size;
+	/* cmd line option during boot */
+	unsigned long	reserve_bootvar;
+
+	unsigned long	cpu_state_data_size;
+	u64		cpu_state_dest_vaddr;
+	u32		cpu_state_data_version;
+	u32		cpu_state_entry_size;
+
+	unsigned long	hpte_region_size;
+
+	unsigned long	boot_memory_size;
+	u64		boot_mem_dest_addr;
+	u64		boot_mem_addr[FADUMP_MAX_MEM_REGS];
+	u64		boot_mem_sz[FADUMP_MAX_MEM_REGS];
+	u64		boot_mem_top;
+	u64		boot_mem_regs_cnt;
+
+	unsigned long	fadumphdr_addr;
+	u64		elfcorehdr_addr;
+	u64		elfcorehdr_size;
+	unsigned long	cpu_notes_buf_vaddr;
+	unsigned long	cpu_notes_buf_size;
+
+	unsigned long	param_area;
+
+	/*
+	 * Maximum size supported by firmware to copy from source to
+	 * destination address per entry.
+	 */
+	u64		max_copy_size;
+	u64		kernel_metadata;
+
+	int		ibm_configure_kernel_dump;
+
+	unsigned long	fadump_enabled:1;
+	unsigned long	fadump_supported:1;
+	unsigned long	dump_active:1;
+	unsigned long	dump_registered:1;
+	unsigned long	nocma:1;
+	unsigned long	param_area_supported:1;
+
+	struct fadump_ops	*ops;
+};
+
+struct fadump_ops {
+	u64	(*fadump_init_mem_struct)(struct fw_dump *fadump_conf);
+	u64	(*fadump_get_metadata_size)(void);
+	int	(*fadump_setup_metadata)(struct fw_dump *fadump_conf);
+	u64	(*fadump_get_bootmem_min)(void);
+	int	(*fadump_register)(struct fw_dump *fadump_conf);
+	int	(*fadump_unregister)(struct fw_dump *fadump_conf);
+	int	(*fadump_invalidate)(struct fw_dump *fadump_conf);
+	void	(*fadump_cleanup)(struct fw_dump *fadump_conf);
+	int	(*fadump_process)(struct fw_dump *fadump_conf);
+	void	(*fadump_region_show)(struct fw_dump *fadump_conf,
+				      struct seq_file *m);
+	void	(*fadump_trigger)(struct fadump_crash_info_header *fdh,
+				  const char *msg);
+	int	(*fadump_max_boot_mem_rgns)(void);
+};
+
+/* Helper functions */
+s32 __init fadump_setup_cpu_notes_buf(u32 num_cpus);
+void fadump_free_cpu_notes_buf(void);
+u32 *__init fadump_regs_to_elf_notes(u32 *buf, struct pt_regs *regs);
+void __init fadump_update_elfcore_header(char *bufp);
+bool is_fadump_reserved_mem_contiguous(void);
+
+#else /* !CONFIG_PRESERVE_FA_DUMP */
+
+/* Firmware-assisted dump configuration details. */
+struct fw_dump {
+	u64	boot_mem_top;
+	u64	dump_active;
+};
+
+#endif /* CONFIG_PRESERVE_FA_DUMP */
+
+#ifdef CONFIG_PPC_PSERIES
+extern void rtas_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node);
+#else
+static inline void
+rtas_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node) { }
+#endif
+
+#ifdef CONFIG_PPC_POWERNV
+extern void opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node);
+#else
+static inline void
+opal_fadump_dt_scan(struct fw_dump *fadump_conf, u64 node) { }
+#endif
+
+#endif /* _ASM_POWERPC_FADUMP_INTERNAL_H */

linux-7.2.3/arch/powerpc/include/asm/fadump.h

@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Firmware Assisted dump header file.
+ *
+ * Copyright 2011 IBM Corporation
+ * Author: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
+ */
+
+#ifndef _ASM_POWERPC_FADUMP_H
+#define _ASM_POWERPC_FADUMP_H
+
+#ifdef CONFIG_FA_DUMP
+
+extern int crashing_cpu;
+
+extern int is_fadump_memory_area(u64 addr, ulong size);
+extern int setup_fadump(void);
+extern int is_fadump_active(void);
+extern int should_fadump_crash(void);
+extern void crash_fadump(struct pt_regs *, const char *);
+extern void fadump_cleanup(void);
+void fadump_setup_param_area(void);
+extern void fadump_append_bootargs(void);
+
+#else	/* CONFIG_FA_DUMP */
+static inline int is_fadump_active(void) { return 0; }
+static inline int should_fadump_crash(void) { return 0; }
+static inline void crash_fadump(struct pt_regs *regs, const char *str) { }
+static inline void fadump_cleanup(void) { }
+static inline void fadump_setup_param_area(void) { }
+static inline void fadump_append_bootargs(void) { }
+#endif /* !CONFIG_FA_DUMP */
+
+#if defined(CONFIG_FA_DUMP) || defined(CONFIG_PRESERVE_FA_DUMP)
+extern int early_init_dt_scan_fw_dump(unsigned long node, const char *uname,
+				      int depth, void *data);
+extern int fadump_reserve_mem(void);
+#endif
+
+#if defined(CONFIG_FA_DUMP) && defined(CONFIG_CMA)
+void fadump_cma_init(void);
+#else
+static inline void fadump_cma_init(void) { }
+#endif
+
+#endif /* _ASM_POWERPC_FADUMP_H */