From fd615f69a18a9d4aa5ef02a1dc83f319f75da8e7 Mon Sep 17 00:00:00 2001 From: LiuHailong Date: Tue, 7 Feb 2017 10:35:52 +0800 Subject: powerpc/64e: Fix hang when debugging programs with relocated kernel Debug interrupts can be taken during interrupt entry, since interrupt entry does not automatically turn them off. The kernel will check whether the faulting instruction is between [interrupt_base_book3e, __end_interrupts], and if so clear MSR[DE] and return. However, when the kernel is built with CONFIG_RELOCATABLE, it can't use LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e) and LOAD_REG_IMMEDIATE(r15,__end_interrupts), as they ignore relocation. Thus, if the kernel is actually running at a different address than it was built at, the address comparison will fail, and the exception entry code will hang at kernel_dbg_exc. r2(toc) is also not usable here, as r2 still holds data from the interrupted context, so LOAD_REG_ADDR() doesn't work either. So we use the *name@got* to get the EV of two labels directly. Test programs test.c shows as follows: int main(int argc, char *argv[]) { if (access("/proc/sys/kernel/perf_event_paranoid", F_OK) == -1) printf("Kernel doesn't have perf_event support\n"); } Steps to reproduce the bug, for example: 1) ./gdb ./test 2) (gdb) b access 3) (gdb) r 4) (gdb) s Signed-off-by: Liu Hailong Signed-off-by: Jiang Xuexin Reviewed-by: Jiang Biao Reviewed-by: Liu Song Reviewed-by: Huang Jian [scottwood: cleaned up commit message, and specified bad behavior as a hang rather than an oops to correspond to mainline kernel behavior] Fixes: 1cb6e0649248 ("powerpc/book3e: support CONFIG_RELOCATABLE") Cc: # 4.4.x- Signed-off-by: Scott Wood --- arch/powerpc/kernel/exceptions-64e.S | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 45b453e4d0c8..acd8ca76233e 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -735,8 +735,14 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC) andis. r15,r14,(DBSR_IC|DBSR_BT)@h beq+ 1f +#ifdef CONFIG_RELOCATABLE + ld r15,PACATOC(r13) + ld r14,interrupt_base_book3e@got(r15) + ld r15,__end_interrupts@got(r15) +#else LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e) LOAD_REG_IMMEDIATE(r15,__end_interrupts) +#endif cmpld cr0,r10,r14 cmpld cr1,r10,r15 blt+ cr0,1f @@ -799,8 +805,14 @@ kernel_dbg_exc: andis. r15,r14,(DBSR_IC|DBSR_BT)@h beq+ 1f +#ifdef CONFIG_RELOCATABLE + ld r15,PACATOC(r13) + ld r14,interrupt_base_book3e@got(r15) + ld r15,__end_interrupts@got(r15) +#else LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e) LOAD_REG_IMMEDIATE(r15,__end_interrupts) +#endif cmpld cr0,r10,r14 cmpld cr1,r10,r15 blt+ cr0,1f -- cgit v1.2.3-59-g8ed1b From 8b8642af15ed14b9a7a34d3401afbcc274533e13 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 7 Feb 2017 10:05:09 +0100 Subject: net: ethernet: ucc_geth: fix MEM_PART_MURAM mode Since commit 5093bb965a163 ("powerpc/QE: switch to the cpm_muram implementation"), muram area is not part of immrbar mapping anymore so immrbar_virt_to_phys() is not usable anymore. Fixes: 5093bb965a163 ("powerpc/QE: switch to the cpm_muram implementation") Signed-off-by: Christophe Leroy Acked-by: David S. Miller Acked-by: Li Yang Signed-off-by: Scott Wood --- drivers/net/ethernet/freescale/ucc_geth.c | 8 +++----- include/soc/fsl/qe/qe.h | 1 + 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index 3f7ae9f64cd8..f77ba9fa257b 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -2594,11 +2594,10 @@ static int ucc_geth_startup(struct ucc_geth_private *ugeth) } else if (ugeth->ug_info->uf_info.bd_mem_part == MEM_PART_MURAM) { out_be32(&ugeth->p_send_q_mem_reg->sqqd[i].bd_ring_base, - (u32) immrbar_virt_to_phys(ugeth-> - p_tx_bd_ring[i])); + (u32)qe_muram_dma(ugeth->p_tx_bd_ring[i])); out_be32(&ugeth->p_send_q_mem_reg->sqqd[i]. last_bd_completed_address, - (u32) immrbar_virt_to_phys(endOfRing)); + (u32)qe_muram_dma(endOfRing)); } } @@ -2844,8 +2843,7 @@ static int ucc_geth_startup(struct ucc_geth_private *ugeth) } else if (ugeth->ug_info->uf_info.bd_mem_part == MEM_PART_MURAM) { out_be32(&ugeth->p_rx_bd_qs_tbl[i].externalbdbaseptr, - (u32) immrbar_virt_to_phys(ugeth-> - p_rx_bd_ring[i])); + (u32)qe_muram_dma(ugeth->p_rx_bd_ring[i])); } /* rest of fields handled by QE */ } diff --git a/include/soc/fsl/qe/qe.h b/include/soc/fsl/qe/qe.h index 70339d7958c0..0cd4c11479b1 100644 --- a/include/soc/fsl/qe/qe.h +++ b/include/soc/fsl/qe/qe.h @@ -243,6 +243,7 @@ static inline int qe_alive_during_sleep(void) #define qe_muram_free cpm_muram_free #define qe_muram_addr cpm_muram_addr #define qe_muram_offset cpm_muram_offset +#define qe_muram_dma cpm_muram_dma #define qe_setbits32(_addr, _v) iowrite32be(ioread32be(_addr) | (_v), (_addr)) #define qe_clrbits32(_addr, _v) iowrite32be(ioread32be(_addr) & ~(_v), (_addr)) -- cgit v1.2.3-59-g8ed1b From b54ea82f01282253c85eb7e2fd2b6c96f7a027d8 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Tue, 7 Feb 2017 10:05:11 +0100 Subject: soc/fsl/qe: get rid of immrbar_virt_to_phys() immrbar_virt_to_phys() is not used anymore Signed-off-by: Christophe Leroy Acked-by: Li Yang Signed-off-by: Scott Wood --- drivers/soc/fsl/qe/qe.c | 4 +--- include/soc/fsl/qe/immap_qe.h | 19 ------------------- 2 files changed, 1 insertion(+), 22 deletions(-) diff --git a/drivers/soc/fsl/qe/qe.c b/drivers/soc/fsl/qe/qe.c index ade168f5328e..d9c04f588f7f 100644 --- a/drivers/soc/fsl/qe/qe.c +++ b/drivers/soc/fsl/qe/qe.c @@ -66,7 +66,7 @@ static unsigned int qe_num_of_snum; static phys_addr_t qebase = -1; -phys_addr_t get_qe_base(void) +static phys_addr_t get_qe_base(void) { struct device_node *qe; int ret; @@ -90,8 +90,6 @@ phys_addr_t get_qe_base(void) return qebase; } -EXPORT_SYMBOL(get_qe_base); - void qe_reset(void) { if (qe_immr == NULL) diff --git a/include/soc/fsl/qe/immap_qe.h b/include/soc/fsl/qe/immap_qe.h index c76ef30b05ba..7baaabd5ec2c 100644 --- a/include/soc/fsl/qe/immap_qe.h +++ b/include/soc/fsl/qe/immap_qe.h @@ -464,25 +464,6 @@ struct qe_immap { } __attribute__ ((packed)); extern struct qe_immap __iomem *qe_immr; -extern phys_addr_t get_qe_base(void); - -/* - * Returns the offset within the QE address space of the given pointer. - * - * Note that the QE does not support 36-bit physical addresses, so if - * get_qe_base() returns a number above 4GB, the caller will probably fail. - */ -static inline phys_addr_t immrbar_virt_to_phys(void *address) -{ - void *q = (void *)qe_immr; - - /* Is it a MURAM address? */ - if ((address >= q) && (address < (q + QE_IMMAP_SIZE))) - return get_qe_base() + (address - q); - - /* It's an address returned by kmalloc */ - return virt_to_phys(address); -} #endif /* __KERNEL__ */ #endif /* _ASM_POWERPC_IMMAP_QE_H */ -- cgit v1.2.3-59-g8ed1b From 2ccf80b7566cc035d903dd0ac5d7ebd25c2c1060 Mon Sep 17 00:00:00 2001 From: Valentin Longchamp Date: Fri, 17 Feb 2017 11:29:45 +0100 Subject: soc/fsl/qe: round brg_freq to 1kHz granularity Because of integer computation rounding in u-boot (that sets the QE brg-frequency DTS prop), the clk value is 99999999 Hz even though it is 100 MHz. When setting brg clks that are exact divisors of 100 MHz, this small differnce plays a role and can result in lower clks to be output (for instance 20 MHz - divide by 5 - results in 16.666 MHz - divide by 6). This patch fixes that by "forcing" the brg_clk to the nearest kHz when the difference is below 2 integer rounding errors (i.e. 4). Signed-off-by: Valentin Longchamp Signed-off-by: Scott Wood --- drivers/soc/fsl/qe/qe.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/drivers/soc/fsl/qe/qe.c b/drivers/soc/fsl/qe/qe.c index d9c04f588f7f..31a094573a9d 100644 --- a/drivers/soc/fsl/qe/qe.c +++ b/drivers/soc/fsl/qe/qe.c @@ -161,11 +161,15 @@ EXPORT_SYMBOL(qe_issue_cmd); */ static unsigned int brg_clk = 0; +#define CLK_GRAN (1000) +#define CLK_GRAN_LIMIT (5) + unsigned int qe_get_brg_clk(void) { struct device_node *qe; int size; const u32 *prop; + unsigned int mod; if (brg_clk) return brg_clk; @@ -183,6 +187,15 @@ unsigned int qe_get_brg_clk(void) of_node_put(qe); + /* round this if near to a multiple of CLK_GRAN */ + mod = brg_clk % CLK_GRAN; + if (mod) { + if (mod < CLK_GRAN_LIMIT) + brg_clk -= mod; + else if (mod > (CLK_GRAN - CLK_GRAN_LIMIT)) + brg_clk += CLK_GRAN - mod; + } + return brg_clk; } EXPORT_SYMBOL(qe_get_brg_clk); -- cgit v1.2.3-59-g8ed1b From e5c5c8d23fef2a976afe724f30e34da31be09769 Mon Sep 17 00:00:00 2001 From: Valentin Longchamp Date: Fri, 17 Feb 2017 11:29:46 +0100 Subject: soc/fsl/qe: only apply QE_General4 workaround on affected SoCs The QE_General4 workaround is only valid for the MPC832x and MPC836x SoCs. The other SoCs that embed a QUICC engine are not affected by this hardware bug and thus can use the computed divisors (this was successfully tested on the T1040). Similalry to what was done in commit 8ce795cb0c6b ("i2c: mpc: assign the correct prescaler from SVR") in order to avoid changes in the device tree nodes of the QE (with maybe a variant of the compatible property), the PVR reg is read out to find out if the workaround must be applied or not. Signed-off-by: Valentin Longchamp Signed-off-by: Scott Wood --- drivers/soc/fsl/qe/qe.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/soc/fsl/qe/qe.c b/drivers/soc/fsl/qe/qe.c index 31a094573a9d..2ef6fc6487c1 100644 --- a/drivers/soc/fsl/qe/qe.c +++ b/drivers/soc/fsl/qe/qe.c @@ -200,6 +200,9 @@ unsigned int qe_get_brg_clk(void) } EXPORT_SYMBOL(qe_get_brg_clk); +#define PVR_VER_836x 0x8083 +#define PVR_VER_832x 0x8084 + /* Program the BRG to the given sampling rate and multiplier * * @brg: the BRG, QE_BRG1 - QE_BRG16 @@ -226,8 +229,9 @@ int qe_setbrg(enum qe_clock brg, unsigned int rate, unsigned int multiplier) /* Errata QE_General4, which affects some MPC832x and MPC836x SOCs, says that the BRG divisor must be even if you're not using divide-by-16 mode. */ - if (!div16 && (divisor & 1) && (divisor > 3)) - divisor++; + if (pvr_version_is(PVR_VER_836x) || pvr_version_is(PVR_VER_832x)) + if (!div16 && (divisor & 1) && (divisor > 3)) + divisor++; tempval = ((divisor - 1) << QE_BRGC_DIVISOR_SHIFT) | QE_BRGC_ENABLE | div16; -- cgit v1.2.3-59-g8ed1b From 4ba251626ff1ac3447f9a05ecfcec7f85b6c8a91 Mon Sep 17 00:00:00 2001 From: Valentin Longchamp Date: Fri, 17 Feb 2017 11:29:47 +0100 Subject: soc/fsl/qe: add EXPORT_SYMBOL for the 2 qe_tdm functions This allows to build the fsl_ucc_hdlc driver as a module. Signed-off-by: Valentin Longchamp Signed-off-by: Scott Wood --- drivers/soc/fsl/qe/qe_tdm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/soc/fsl/qe/qe_tdm.c b/drivers/soc/fsl/qe/qe_tdm.c index a1048b44e6b9..f744c214f680 100644 --- a/drivers/soc/fsl/qe/qe_tdm.c +++ b/drivers/soc/fsl/qe/qe_tdm.c @@ -177,6 +177,7 @@ err_miss_siram_property: devm_iounmap(&pdev->dev, utdm->si_regs); return ret; } +EXPORT_SYMBOL(ucc_of_parse_tdm); void ucc_tdm_init(struct ucc_tdm *utdm, struct ucc_tdm_info *ut_info) { @@ -274,3 +275,4 @@ void ucc_tdm_init(struct ucc_tdm *utdm, struct ucc_tdm_info *ut_info) break; } } +EXPORT_SYMBOL(ucc_tdm_init); -- cgit v1.2.3-59-g8ed1b From e21c7316d8ddcf1fd679591d1427e937999a7cf5 Mon Sep 17 00:00:00 2001 From: Roy Pledge Date: Mon, 17 Apr 2017 16:55:19 -0400 Subject: soc/fsl/qbman: Disable IRQs for deferred QBMan work Work for Congestion State Notifications (CSCN) and Message Ring (MR) handling is handled via the workqueue mechanism. This requires the driver to disable those IRQs before scheduling the work and re-enabling it once the work is completed so that the interrupt doesn't continually fire. Signed-off-by: Roy Pledge Signed-off-by: Scott Wood --- drivers/soc/fsl/qbman/qman.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index 6f509f68085e..2827a65aa25a 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -1344,6 +1344,7 @@ static void qm_congestion_task(struct work_struct *work) if (!qm_mc_result_timeout(&p->p, &mcr)) { spin_unlock(&p->cgr_lock); dev_crit(p->config->dev, "QUERYCONGESTION timeout\n"); + qman_p_irqsource_add(p, QM_PIRQ_CSCI); return; } /* mask out the ones I'm not interested in */ @@ -1358,6 +1359,7 @@ static void qm_congestion_task(struct work_struct *work) if (cgr->cb && qman_cgrs_get(&c, cgr->cgrid)) cgr->cb(p, cgr, qman_cgrs_get(&rr, cgr->cgrid)); spin_unlock(&p->cgr_lock); + qman_p_irqsource_add(p, QM_PIRQ_CSCI); } static void qm_mr_process_task(struct work_struct *work) @@ -1417,12 +1419,14 @@ static void qm_mr_process_task(struct work_struct *work) } qm_mr_cci_consume(&p->p, num); + qman_p_irqsource_add(p, QM_PIRQ_MRI); preempt_enable(); } static u32 __poll_portal_slow(struct qman_portal *p, u32 is) { if (is & QM_PIRQ_CSCI) { + qman_p_irqsource_remove(p, QM_PIRQ_CSCI); queue_work_on(smp_processor_id(), qm_portal_wq, &p->congestion_work); } @@ -1434,6 +1438,7 @@ static u32 __poll_portal_slow(struct qman_portal *p, u32 is) } if (is & QM_PIRQ_MRI) { + qman_p_irqsource_remove(p, QM_PIRQ_MRI); queue_work_on(smp_processor_id(), qm_portal_wq, &p->mr_work); } -- cgit v1.2.3-59-g8ed1b From 726bd223105c04f7bf5eacdc2540819c301061f7 Mon Sep 17 00:00:00 2001 From: Christophe Leroy Date: Mon, 1 May 2017 09:38:13 +0200 Subject: powerpc/8xx: Adding support of IRQ in MPC8xx GPIO This patch allows the use of IRQ to notify the change of GPIO status on MPC8xx CPM IO ports. This then allows to associate IRQs to GPIOs in the Device Tree. Ex: CPM1_PIO_C: gpio-controller@960 { #gpio-cells = <2>; compatible = "fsl,cpm1-pario-bank-c"; reg = <0x960 0x10>; fsl,cpm1-gpio-irq-mask = <0x0fff>; interrupts = <1 2 6 9 10 11 14 15 23 24 26 31>; interrupt-parent = <&CPM_PIC>; gpio-controller; }; The property 'fsl,cpm1-gpio-irq-mask' defines which of the 16 GPIOs have the associated interrupts defined in the 'interrupts' property. Signed-off-by: Christophe Leroy Signed-off-by: Scott Wood --- .../devicetree/bindings/soc/fsl/cpm_qe/gpio.txt | 21 +++++++++++++++++- arch/powerpc/include/asm/cpm1.h | 2 ++ arch/powerpc/sysdev/cpm1.c | 25 ++++++++++++++++++++++ 3 files changed, 47 insertions(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/gpio.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/gpio.txt index 349f79fd7076..626e1afa64a6 100644 --- a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/gpio.txt +++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/gpio.txt @@ -13,8 +13,17 @@ Required properties: - #gpio-cells : Should be two. The first cell is the pin number and the second cell is used to specify optional parameters (currently unused). - gpio-controller : Marks the port as GPIO controller. +Optional properties: +- fsl,cpm1-gpio-irq-mask : For banks having interrupt capability (like port C + on CPM1), this item tells which ports have an associated interrupt (ports are + listed in the same order as in PCINT register) +- interrupts : This property provides the list of interrupt for each GPIO having + one as described by the fsl,cpm1-gpio-irq-mask property. There should be as + many interrupts as number of ones in the mask property. The first interrupt in + the list corresponds to the most significant bit of the mask. +- interrupt-parent : Parent for the above interrupt property. -Example of three SOC GPIO banks defined as gpio-controller nodes: +Example of four SOC GPIO banks defined as gpio-controller nodes: CPM1_PIO_A: gpio-controller@950 { #gpio-cells = <2>; @@ -30,6 +39,16 @@ Example of three SOC GPIO banks defined as gpio-controller nodes: gpio-controller; }; + CPM1_PIO_C: gpio-controller@960 { + #gpio-cells = <2>; + compatible = "fsl,cpm1-pario-bank-c"; + reg = <0x960 0x10>; + fsl,cpm1-gpio-irq-mask = <0x0fff>; + interrupts = <1 2 6 9 10 11 14 15 23 24 26 31>; + interrupt-parent = <&CPM_PIC>; + gpio-controller; + }; + CPM1_PIO_E: gpio-controller@ac8 { #gpio-cells = <2>; compatible = "fsl,cpm1-pario-bank-e"; diff --git a/arch/powerpc/include/asm/cpm1.h b/arch/powerpc/include/asm/cpm1.h index 8ee4211ca0c6..14ad37865000 100644 --- a/arch/powerpc/include/asm/cpm1.h +++ b/arch/powerpc/include/asm/cpm1.h @@ -560,6 +560,8 @@ typedef struct risc_timer_pram { #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, diff --git a/arch/powerpc/sysdev/cpm1.c b/arch/powerpc/sysdev/cpm1.c index 986cd111d4df..c651e668996b 100644 --- a/arch/powerpc/sysdev/cpm1.c +++ b/arch/powerpc/sysdev/cpm1.c @@ -377,6 +377,10 @@ static void cpm1_set_pin16(int port, int pin, int flags) setbits16(&iop->odr_sor, pin); else clrbits16(&iop->odr_sor, pin); + if (flags & CPM_PIN_FALLEDGE) + setbits16(&iop->intr, pin); + else + clrbits16(&iop->intr, pin); } } @@ -528,6 +532,9 @@ struct cpm1_gpio16_chip { /* shadowed data register to clear/set bits safely */ u16 cpdata; + + /* IRQ associated with Pins when relevant */ + int irq[16]; }; static void cpm1_gpio16_save_regs(struct of_mm_gpio_chip *mm_gc) @@ -578,6 +585,14 @@ static void cpm1_gpio16_set(struct gpio_chip *gc, unsigned int gpio, int value) spin_unlock_irqrestore(&cpm1_gc->lock, flags); } +static int cpm1_gpio16_to_irq(struct gpio_chip *gc, unsigned int gpio) +{ + struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); + struct cpm1_gpio16_chip *cpm1_gc = gpiochip_get_data(&mm_gc->gc); + + return cpm1_gc->irq[gpio] ? : -ENXIO; +} + static int cpm1_gpio16_dir_out(struct gpio_chip *gc, unsigned int gpio, int val) { struct of_mm_gpio_chip *mm_gc = to_of_mm_gpio_chip(gc); @@ -618,6 +633,7 @@ int cpm1_gpiochip_add16(struct device_node *np) struct cpm1_gpio16_chip *cpm1_gc; struct of_mm_gpio_chip *mm_gc; struct gpio_chip *gc; + u16 mask; cpm1_gc = kzalloc(sizeof(*cpm1_gc), GFP_KERNEL); if (!cpm1_gc) @@ -625,6 +641,14 @@ int cpm1_gpiochip_add16(struct device_node *np) spin_lock_init(&cpm1_gc->lock); + if (!of_property_read_u16(np, "fsl,cpm1-gpio-irq-mask", &mask)) { + int i, j; + + for (i = 0, j = 0; i < 16; i++) + if (mask & (1 << (15 - i))) + cpm1_gc->irq[i] = irq_of_parse_and_map(np, j++); + } + mm_gc = &cpm1_gc->mm_gc; gc = &mm_gc->gc; @@ -634,6 +658,7 @@ int cpm1_gpiochip_add16(struct device_node *np) gc->direction_output = cpm1_gpio16_dir_out; gc->get = cpm1_gpio16_get; gc->set = cpm1_gpio16_set; + gc->to_irq = cpm1_gpio16_to_irq; return of_mm_gpiochip_add_data(np, mm_gc, cpm1_gc); } -- cgit v1.2.3-59-g8ed1b From c374ed27c93698c794f99c5d41d9ad3062c4c207 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Wed, 19 Apr 2017 14:46:24 +1000 Subject: powerpc/powernv: Block PCI config access on BCM5718 during EEH recovery Similar to what is done in commit b6541db13952 ("powerpc/eeh: Block PCI config access upon frozen PE"), we need block PCI config access for BCM5719 when recovering frozen error on them. Otherwise, an unexpected recursive fenced PHB error is observed. 0001:06:00.0 Ethernet controller: Broadcom Corporation \ NetXtreme BCM5718 Gigabit Ethernet PCIe (rev 10) 0001:06:00.1 Ethernet controller: Broadcom Corporation \ NetXtreme BCM5718 Gigabit Ethernet PCIe (rev 10) Signed-off-by: Gavin Shan Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/powernv/eeh-powernv.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index d2f19821d71d..d12ea7b9fd47 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -412,11 +412,14 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) * been set for the PE, we will set EEH_PE_CFG_BLOCKED for * that PE to block its config space. * + * Broadcom BCM5718 2-ports NICs (14e4:1656) * Broadcom Austin 4-ports NICs (14e4:1657) * Broadcom Shiner 4-ports 1G NICs (14e4:168a) * Broadcom Shiner 2-ports 10G NICs (14e4:168e) */ if ((pdn->vendor_id == PCI_VENDOR_ID_BROADCOM && + pdn->device_id == 0x1656) || + (pdn->vendor_id == PCI_VENDOR_ID_BROADCOM && pdn->device_id == 0x1657) || (pdn->vendor_id == PCI_VENDOR_ID_BROADCOM && pdn->device_id == 0x168a) || -- cgit v1.2.3-59-g8ed1b From 61baf15555129f69720334f232b153890895ef71 Mon Sep 17 00:00:00 2001 From: Scott Wood Date: Fri, 5 May 2017 01:22:06 -0500 Subject: powerpc/64e: Don't place the stack beyond TASK_SIZE Commit f4ea6dcb08ea ("powerpc/mm: Enable mappings above 128TB") increased the task size on book3s, and introduced a mechanism to dynamically control whether a task uses these larger addresses. While the change to the task size itself was ifdef-protected to only apply on book3s, the change to STACK_TOP_USER64 was not. On book3e, this had the effect of trying to use addresses up to 128TiB for the stack despite a 64TiB task size limit -- which broke 64-bit userspace producing the following errors: Starting init: /sbin/init exists but couldn't execute it (error -14) Starting init: /bin/sh exists but couldn't execute it (error -14) Kernel panic - not syncing: No working init found. Try passing init= option to kernel. See Linux Documentation/admin-guide/init.rst for guidance. Fixes: f4ea6dcb08ea ("powerpc/mm: Enable mappings above 128TB") Cc: Aneesh Kumar K.V Signed-off-by: Scott Wood --- arch/powerpc/include/asm/processor.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h index a4b1d8d6b793..a2123f291ab0 100644 --- a/arch/powerpc/include/asm/processor.h +++ b/arch/powerpc/include/asm/processor.h @@ -151,8 +151,13 @@ void release_thread(struct task_struct *); #ifdef __powerpc64__ +#ifdef CONFIG_PPC_BOOK3S_64 /* Limit stack to 128TB */ #define STACK_TOP_USER64 TASK_SIZE_128TB +#else +#define STACK_TOP_USER64 TASK_SIZE_USER64 +#endif + #define STACK_TOP_USER32 TASK_SIZE_USER32 #define STACK_TOP (is_32bit_task() ? \ -- cgit v1.2.3-59-g8ed1b From 24e0bfbf63bac18495b0ad76115269f2158e9234 Mon Sep 17 00:00:00 2001 From: Horia Geantă Date: Mon, 8 May 2017 11:50:16 +0300 Subject: powerpc: Fix distclean with Makefile.postlink MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Makefile.postlink always includes include/config/auto.conf, however this file is not present in a clean kernel tree, causing make to fail: $ git clone linuxppc.git $ cd linuxppc.git $ make distclean arch/powerpc/Makefile.postlink:10: include/config/auto.conf: No such file or directory make[1]: *** No rule to make target `include/config/auto.conf'. Stop. make: *** [vmlinuxclean] Error 2 Equally running 'make distclean; make distclean' will trip the error case. Change the inclusion such that file not being found does not trigger an error. Fixes: f188d0524d7e ("powerpc: Use the new post-link pass to check relocations") Reported-by: Mircea Pop Signed-off-by: Horia Geantă Tested-by: Justin M. Forbes Signed-off-by: Michael Ellerman --- arch/powerpc/Makefile.postlink | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/Makefile.postlink b/arch/powerpc/Makefile.postlink index 3c22d64b2de9..eccfcc88afae 100644 --- a/arch/powerpc/Makefile.postlink +++ b/arch/powerpc/Makefile.postlink @@ -7,7 +7,7 @@ PHONY := __archpost __archpost: -include include/config/auto.conf +-include include/config/auto.conf include scripts/Kbuild.include quiet_cmd_relocs_check = CHKREL $@ -- cgit v1.2.3-59-g8ed1b From ba95b5d0359609b4ec8010f77c40ab3c595a6ac6 Mon Sep 17 00:00:00 2001 From: Michael Ellerman Date: Tue, 9 May 2017 15:39:04 +1000 Subject: powerpc/mm/book3s/64: Rework page table geometry for lower memory usage Recently in commit f6eedbba7a26 ("powerpc/mm/hash: Increase VA range to 128TB") we increased the virtual address space for user processes to 128TB by default, and up to 512TB if user space opts in. This obviously required expanding the range of the Linux page tables. For Book3s 64-bit using hash and with PAGE_SIZE=64K, we increased the PGD to 2^15 entries. This meant we could cover the full address range, while still being able to insert a 16G hugepage at the PGD level and a 16M hugepage in the PMD. The downside of that geometry is that it uses a lot of memory for the PGD, and in particular makes the PGD a 4-page allocation, which means it's much more likely to fail under memory pressure. Instead we can make the PMD larger, so that a single PUD entry maps 16G, allowing the 16G hugepages to sit at that level in the tree. We're then able to split the remaining bits between the PUG and PGD. We make the PGD slightly larger as that results in lower memory usage for typical programs. When THP is enabled the PMD actually doubles in size, to 2^11 entries, or 2^14 bytes, which is large but still < PAGE_SIZE. Signed-off-by: Michael Ellerman Reviewed-by: Balbir Singh Reviewed-by: Aneesh Kumar K.V --- arch/powerpc/include/asm/book3s/64/hash-64k.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index 214219dff87c..9732837aaae8 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -2,9 +2,9 @@ #define _ASM_POWERPC_BOOK3S_64_HASH_64K_H #define H_PTE_INDEX_SIZE 8 -#define H_PMD_INDEX_SIZE 5 -#define H_PUD_INDEX_SIZE 5 -#define H_PGD_INDEX_SIZE 15 +#define H_PMD_INDEX_SIZE 10 +#define H_PUD_INDEX_SIZE 7 +#define H_PGD_INDEX_SIZE 8 /* * 64k aligned address free up few of the lower bits of RPN for us -- cgit v1.2.3-59-g8ed1b From 6102c005a71b4a7a6433d43b887662fb0780746d Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 4 May 2017 20:41:12 +1000 Subject: powerpc/64s: Fix unnecessary machine check handler relocation branch Similarly to commit 2563a70c3b ("powerpc/64s: Remove unnecessary relocation branch from idle handler"), the machine check handler has a BRANCH_TO from relocated to relocated code, which is unnecessary. It has also caused build errors with some toolchains: arch/powerpc/kernel/exceptions-64s.S: Assembler messages: arch/powerpc/kernel/exceptions-64s.S:395: Error: operand out of range (0xffffffffffff8280 is not between 0x0000000000000000 and 0x000000000000ffff) Fixes: 1945bc4549e5 ("powerpc/64s: Fix POWER9 machine check handler from stop state") Signed-off-by: Nicholas Piggin Reported-and-tested-by : Abdul Haleem Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/exceptions-64s.S | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S index 3840a7700285..ef72065f684c 100644 --- a/arch/powerpc/kernel/exceptions-64s.S +++ b/arch/powerpc/kernel/exceptions-64s.S @@ -391,9 +391,7 @@ EXC_COMMON_BEGIN(machine_check_handle_early) */ BEGIN_FTR_SECTION rlwinm. r11,r12,47-31,30,31 - beq- 4f - BRANCH_TO_COMMON(r10, machine_check_idle_common) -4: + bne machine_check_idle_common END_FTR_SECTION_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206) #endif -- cgit v1.2.3-59-g8ed1b From ea47dd191d543f81e0912b5dc0471b48346b016e Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 19 Apr 2017 05:12:18 +1000 Subject: of/fdt: introduce of_scan_flat_dt_subnodes and of_get_flat_dt_phandle Introduce primitives for FDT parsing. These will be used for powerpc cpufeatures node scanning, which has quite complex structure but should be processed early. Cc: devicetree@vger.kernel.org Acked-by: Rob Herring Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- drivers/of/fdt.c | 38 ++++++++++++++++++++++++++++++++++++++ include/linux/of_fdt.h | 6 ++++++ 2 files changed, 44 insertions(+) diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index e5ce4b59e162..961ca97072a9 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -753,6 +753,36 @@ int __init of_scan_flat_dt(int (*it)(unsigned long node, return rc; } +/** + * of_scan_flat_dt_subnodes - scan sub-nodes of a node call callback on each. + * @it: callback function + * @data: context data pointer + * + * This function is used to scan sub-nodes of a node. + */ +int __init of_scan_flat_dt_subnodes(unsigned long parent, + int (*it)(unsigned long node, + const char *uname, + void *data), + void *data) +{ + const void *blob = initial_boot_params; + int node; + + fdt_for_each_subnode(node, blob, parent) { + const char *pathp; + int rc; + + pathp = fdt_get_name(blob, node, NULL); + if (*pathp == '/') + pathp = kbasename(pathp); + rc = it(node, pathp, data); + if (rc) + return rc; + } + return 0; +} + /** * of_get_flat_dt_subnode_by_name - get the subnode by given name * @@ -812,6 +842,14 @@ int __init of_flat_dt_match(unsigned long node, const char *const *compat) return of_fdt_match(initial_boot_params, node, compat); } +/** + * of_get_flat_dt_prop - Given a node in the flat blob, return the phandle + */ +uint32_t __init of_get_flat_dt_phandle(unsigned long node) +{ + return fdt_get_phandle(initial_boot_params, node); +} + struct fdt_scan_status { const char *name; int namelen; diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h index 271b3fdf0070..1dfbfd0d8040 100644 --- a/include/linux/of_fdt.h +++ b/include/linux/of_fdt.h @@ -54,6 +54,11 @@ extern char __dtb_end[]; extern int of_scan_flat_dt(int (*it)(unsigned long node, const char *uname, int depth, void *data), void *data); +extern int of_scan_flat_dt_subnodes(unsigned long node, + int (*it)(unsigned long node, + const char *uname, + void *data), + void *data); extern int of_get_flat_dt_subnode_by_name(unsigned long node, const char *uname); extern const void *of_get_flat_dt_prop(unsigned long node, const char *name, @@ -62,6 +67,7 @@ extern int of_flat_dt_is_compatible(unsigned long node, const char *name); extern int of_flat_dt_match(unsigned long node, const char *const *matches); extern unsigned long of_get_flat_dt_root(void); extern int of_get_flat_dt_size(void); +extern uint32_t of_get_flat_dt_phandle(unsigned long node); extern int early_init_dt_scan_chosen(unsigned long node, const char *uname, int depth, void *data); -- cgit v1.2.3-59-g8ed1b From 75bda95048a4d2c5ff04036bd0181bc84085d8b2 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 9 May 2017 13:17:08 +1000 Subject: powerpc: Don't print cpu_spec->cpu_name if it's NULL Currently we assume that if the cpu_spec has a pvr_mask then it must also have a cpu_name. But that will change in a subsequent commit when we do CPU feature discovery via the device tree, so check explicitly if cpu_name is NULL. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/setup-common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 5c10b5925ac2..b57df7fc9e5f 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -256,7 +256,7 @@ static int show_cpuinfo(struct seq_file *m, void *v) seq_printf(m, "processor\t: %lu\n", cpu_id); seq_printf(m, "cpu\t\t: "); - if (cur_cpu_spec->pvr_mask) + if (cur_cpu_spec->pvr_mask && cur_cpu_spec->cpu_name) seq_printf(m, "%s", cur_cpu_spec->cpu_name); else seq_printf(m, "unknown (%08x)", pvr); -- cgit v1.2.3-59-g8ed1b From 5a61ef74f269f2573f48fa53607a8911216c3326 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Tue, 9 May 2017 13:16:52 +1000 Subject: powerpc/64s: Support new device tree binding for discovering CPU features The ibm,powerpc-cpu-features device tree binding describes CPU features with ASCII names and extensible compatibility, privilege, and enablement metadata that allows improved flexibility and compatibility with new hardware. The interface is described in detail in ibm,powerpc-cpu-features.txt in this patch. Currently this code is not enabled by default, and there are no released firmwares that provide the binding. Signed-off-by: Nicholas Piggin Signed-off-by: Michael Ellerman --- .../bindings/powerpc/ibm,powerpc-cpu-features.txt | 248 +++++ arch/powerpc/Kconfig | 16 + arch/powerpc/include/asm/cpu_has_feature.h | 6 +- arch/powerpc/include/asm/cputable.h | 2 + arch/powerpc/include/asm/dt_cpu_ftrs.h | 26 + arch/powerpc/include/asm/reg.h | 1 + arch/powerpc/include/uapi/asm/cputable.h | 7 + arch/powerpc/kernel/Makefile | 1 + arch/powerpc/kernel/cputable.c | 37 +- arch/powerpc/kernel/dt_cpu_ftrs.c | 1031 ++++++++++++++++++++ arch/powerpc/kernel/prom.c | 29 +- arch/powerpc/kernel/setup_64.c | 10 +- 12 files changed, 1398 insertions(+), 16 deletions(-) create mode 100644 Documentation/devicetree/bindings/powerpc/ibm,powerpc-cpu-features.txt create mode 100644 arch/powerpc/include/asm/dt_cpu_ftrs.h create mode 100644 arch/powerpc/kernel/dt_cpu_ftrs.c diff --git a/Documentation/devicetree/bindings/powerpc/ibm,powerpc-cpu-features.txt b/Documentation/devicetree/bindings/powerpc/ibm,powerpc-cpu-features.txt new file mode 100644 index 000000000000..5af426e13334 --- /dev/null +++ b/Documentation/devicetree/bindings/powerpc/ibm,powerpc-cpu-features.txt @@ -0,0 +1,248 @@ +*** NOTE *** +This document is copied from OPAL firmware +(skiboot/doc/device-tree/ibm,powerpc-cpu-features/binding.txt) + +There is more complete overview and documentation of features in that +source tree. All patches and modifications should go there. +************ + +ibm,powerpc-cpu-features binding +================================ + +This device tree binding describes CPU features available to software, with +enablement, privilege, and compatibility metadata. + +More general description of design and implementation of this binding is +found in design.txt, which also points to documentation of specific features. + + +/cpus/ibm,powerpc-cpu-features node binding +------------------------------------------- + +Node: ibm,powerpc-cpu-features + +Description: Container of CPU feature nodes. + +The node name must be "ibm,powerpc-cpu-features". + +It is implemented as a child of the node "/cpus", but this must not be +assumed by parsers. + +The node is optional but should be provided by new OPAL firmware. + +Properties: + +- compatible + Usage: required + Value type: string + Definition: "ibm,powerpc-cpu-features" + + This compatibility refers to backwards compatibility of the overall + design with parsers that behave according to these guidelines. This can + be extended in a backward compatible manner which would not warrant a + revision of the compatible property. + +- isa + Usage: required + Value type: + Definition: + + isa that the CPU is currently running in. This provides instruction set + compatibility, less the individual feature nodes. For example, an ISA v3.0 + implementation that lacks the "transactional-memory" cpufeature node + should not use transactional memory facilities. + + Value corresponds to the "Power ISA Version" multiplied by 1000. + For example, <3000> corresponds to Version 3.0, <2070> to Version 2.07. + The minor digit is available for revisions. + +- display-name + Usage: optional + Value type: string + Definition: + + A human readable name for the CPU. + +/cpus/ibm,powerpc-cpu-features/example-feature node bindings +---------------------------------------------------------------- + +Each child node of cpu-features represents a CPU feature / capability. + +Node: A string describing an architected CPU feature, e.g., "floating-point". + +Description: A feature or capability supported by the CPUs. + +The name of the node is a human readable string that forms the interface +used to describe features to software. Features are currently documented +in the code where they are implemented in skiboot/core/cpufeatures.c + +Presence of the node indicates the feature is available. + +Properties: + +- isa + Usage: required + Value type: + Definition: + + First level of the Power ISA that the feature appears in. + Software should filter out features when constraining the + environment to a particular ISA version. + + Value is defined similarly to /cpus/features/isa + +- usable-privilege + Usage: required + Value type: bit mask + Definition: + Bit numbers are LSB0 + bit 0 - PR (problem state / user mode) + bit 1 - OS (privileged state) + bit 2 - HV (hypervisor state) + All other bits reserved and should be zero. + + This property describes the privilege levels and/or software components + that can use the feature. + + If bit 0 is set, then the hwcap-bit-nr property will exist. + + +- hv-support + Usage: optional + Value type: bit mask + Definition: + Bit numbers are LSB0 + bit 0 - HFSCR + All other bits reserved and should be zero. + + This property describes the HV privilege support required to enable the + feature to lesser privilege levels. If the property does not exist then no + support is required. + + If no bits are set, the hypervisor must have explicit/custom support for + this feature. + + If the HFSCR bit is set, then the hfscr-bit-nr property will exist and + the feature may be enabled by setting this bit in the HFSCR register. + + +- os-support + Usage: optional + Value type: bit mask + Definition: + Bit numbers are LSB0 + bit 0 - FSCR + All other bits reserved and should be zero. + + This property describes the OS privilege support required to enable the + feature to lesser privilege levels. If the property does not exist then no + support is required. + + If no bits are set, the operating system must have explicit/custom support + for this feature. + + If the FSCR bit is set, then the fscr-bit-nr property will exist and + the feature may be enabled by setting this bit in the FSCR register. + + +- hfscr-bit-nr + Usage: optional + Value type: + Definition: HFSCR bit position (LSB0) + + This property exists when the hv-support property HFSCR bit is set. This + property describes the bit number in the HFSCR register that the + hypervisor must set in order to enable this feature. + + This property also exists if an HFSCR bit corresponds with this feature. + This makes CPU feature parsing slightly simpler. + + +- fscr-bit-nr + Usage: optional + Value type: + Definition: FSCR bit position (LSB0) + + This property exists when the os-support property FSCR bit is set. This + property describes the bit number in the FSCR register that the + operating system must set in order to enable this feature. + + This property also exists if an FSCR bit corresponds with this feature. + This makes CPU feature parsing slightly simpler. + + +- hwcap-bit-nr + Usage: optional + Value type: + Definition: Linux ELF AUX vector bit position (LSB0) + + This property may exist when the usable-privilege property value has PR bit set. + This property describes the bit number that should be set in the ELF AUX + hardware capability vectors in order to advertise this feature to userspace. + Bits 0-31 correspond to bits 0-31 in AT_HWCAP vector. Bits 32-63 correspond + to 0-31 in AT_HWCAP2 vector, and so on. Missing AT_HWCAPx vectors implies + that the feature is not enabled or can not be advertised. Operating systems + may provide a number of unassigned hardware capability bits to allow for new + features to be advertised. + + Some properties representing features created before this binding are + advertised to userspace without a one-to-one hwcap bit number may not specify + this bit. Operating system will handle those bits specifically. All new + features usable by userspace will have a hwcap-bit-nr property. + + +- dependencies + Usage: optional + Value type: + Definition: + + If this property exists then it is a list of phandles to cpu feature + nodes that must be enabled for this feature to be enabled. + + +Example +------- + + /cpus/ibm,powerpc-cpu-features { + compatible = "ibm,powerpc-cpu-features"; + + isa = <3020>; + + darn { + isa = <3000>; + usable-privilege = <1 | 2 | 4>; + hwcap-bit-nr = ; + }; + + scv { + isa = <3000>; + usable-privilege = <1 | 2>; + os-support = <0>; + hwcap-bit-nr = ; + }; + + stop { + isa = <3000>; + usable-privilege = <2 | 4>; + hv-support = <0>; + os-support = <0>; + }; + + vsx2 (hypothetical) { + isa = <3010>; + usable-privilege = <1 | 2 | 4>; + hv-support = <0>; + os-support = <0>; + hwcap-bit-nr = ; + }; + + vsx2-newinsns { + isa = <3020>; + usable-privilege = <1 | 2 | 4>; + os-support = <1>; + fscr-bit-nr = ; + hwcap-bit-nr = ; + dependencies = <&vsx2>; + }; + + }; diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 67ee6731f4e9..5bd868f2e813 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -380,6 +380,22 @@ source "arch/powerpc/platforms/Kconfig" menu "Kernel options" +config PPC_DT_CPU_FTRS + bool "Device-tree based CPU feature discovery & setup" + depends on PPC_BOOK3S_64 + default n + help + This enables code to use a new device tree binding for describing CPU + compatibility and features. Saying Y here will attempt to use the new + binding if the firmware provides it. Currently only the skiboot + firmware provides this binding. + If you're not sure say Y. + +config PPC_CPUFEATURES_ENABLE_UNKNOWN + bool "cpufeatures pass through unknown features to guest/userspace" + depends on PPC_DT_CPU_FTRS + default y + config HIGHMEM bool "High memory support" depends on PPC32 diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h index 6e834caa3720..0d1df02bf99d 100644 --- a/arch/powerpc/include/asm/cpu_has_feature.h +++ b/arch/powerpc/include/asm/cpu_has_feature.h @@ -1,5 +1,5 @@ -#ifndef __ASM_POWERPC_CPUFEATURES_H -#define __ASM_POWERPC_CPUFEATURES_H +#ifndef __ASM_POWERPC_CPU_HAS_FEATURE_H +#define __ASM_POWERPC_CPU_HAS_FEATURE_H #ifndef __ASSEMBLY__ @@ -52,4 +52,4 @@ static inline bool cpu_has_feature(unsigned long feature) #endif #endif /* __ASSEMBLY__ */ -#endif /* __ASM_POWERPC_CPUFEATURE_H */ +#endif /* __ASM_POWERPC_CPU_HAS_FEATURE_H */ diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h index 1f6847b107e4..c2d509584a98 100644 --- a/arch/powerpc/include/asm/cputable.h +++ b/arch/powerpc/include/asm/cputable.h @@ -118,7 +118,9 @@ 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); diff --git a/arch/powerpc/include/asm/dt_cpu_ftrs.h b/arch/powerpc/include/asm/dt_cpu_ftrs.h new file mode 100644 index 000000000000..7a34fc11bf63 --- /dev/null +++ b/arch/powerpc/include/asm/dt_cpu_ftrs.h @@ -0,0 +1,26 @@ +#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 +#include +#include +#include + +#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 */ diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h index d4f653c9259a..7e50e47375d6 100644 --- a/arch/powerpc/include/asm/reg.h +++ b/arch/powerpc/include/asm/reg.h @@ -1229,6 +1229,7 @@ #define PVR_POWER8E 0x004B #define PVR_POWER8NVL 0x004C #define PVR_POWER8 0x004D +#define PVR_POWER9 0x004E #define PVR_BE 0x0070 #define PVR_PA6T 0x0090 diff --git a/arch/powerpc/include/uapi/asm/cputable.h b/arch/powerpc/include/uapi/asm/cputable.h index f63c96cd3608..3e7ce86d5c13 100644 --- a/arch/powerpc/include/uapi/asm/cputable.h +++ b/arch/powerpc/include/uapi/asm/cputable.h @@ -47,4 +47,11 @@ #define PPC_FEATURE2_ARCH_3_00 0x00800000 /* ISA 3.00 */ #define PPC_FEATURE2_HAS_IEEE128 0x00400000 /* VSX IEEE Binary Float 128-bit */ +/* + * IMPORTANT! + * All future PPC_FEATURE definitions should be allocated in cooperation with + * OPAL / skiboot firmware, in accordance with the ibm,powerpc-cpu-features + * device tree binding. + */ + #endif /* _UAPI__ASM_POWERPC_CPUTABLE_H */ diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index b9db46ae545b..e132902e1f14 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -56,6 +56,7 @@ obj-$(CONFIG_PPC_RTAS) += rtas.o rtas-rtc.o $(rtaspci-y-y) obj-$(CONFIG_PPC_RTAS_DAEMON) += rtasd.o obj-$(CONFIG_RTAS_FLASH) += rtas_flash.o obj-$(CONFIG_RTAS_PROC) += rtas-proc.o +obj-$(CONFIG_PPC_DT_CPU_FTRS) += dt_cpu_ftrs.o obj-$(CONFIG_EEH) += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \ eeh_driver.o eeh_event.o eeh_sysfs.o obj-$(CONFIG_GENERIC_TBSYNC) += smp-tbsync.o diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index e79b9daa873c..9b3e88b1a9c8 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -23,7 +23,9 @@ #include #include -struct cpu_spec* cur_cpu_spec = NULL; +static struct cpu_spec the_cpu_spec __read_mostly; + +struct cpu_spec* cur_cpu_spec __read_mostly = NULL; EXPORT_SYMBOL(cur_cpu_spec); /* The platform string corresponding to the real PVR */ @@ -2179,7 +2181,15 @@ static struct cpu_spec __initdata cpu_specs[] = { #endif /* CONFIG_E500 */ }; -static struct cpu_spec the_cpu_spec; +void __init set_cur_cpu_spec(struct cpu_spec *s) +{ + struct cpu_spec *t = &the_cpu_spec; + + t = PTRRELOC(t); + *t = *s; + + *PTRRELOC(&cur_cpu_spec) = &the_cpu_spec; +} static struct cpu_spec * __init setup_cpu_spec(unsigned long offset, struct cpu_spec *s) @@ -2266,6 +2276,29 @@ struct cpu_spec * __init identify_cpu(unsigned long offset, unsigned int pvr) return NULL; } +/* + * Used by cpufeatures to get the name for CPUs with a PVR table. + * If they don't hae a PVR table, cpufeatures gets the name from + * cpu device-tree node. + */ +void __init identify_cpu_name(unsigned int pvr) +{ + struct cpu_spec *s = cpu_specs; + struct cpu_spec *t = &the_cpu_spec; + int i; + + s = PTRRELOC(s); + t = PTRRELOC(t); + + for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++) { + if ((pvr & s->pvr_mask) == s->pvr_value) { + t->cpu_name = s->cpu_name; + return; + } + } +} + + #ifdef CONFIG_JUMP_LABEL_FEATURE_CHECKS struct static_key_true cpu_feature_keys[NUM_CPU_FTR_KEYS] = { [0 ... NUM_CPU_FTR_KEYS - 1] = STATIC_KEY_TRUE_INIT diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c new file mode 100644 index 000000000000..fcc7588a96d6 --- /dev/null +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -0,0 +1,1031 @@ +/* + * Copyright 2017, Nicholas Piggin, IBM Corporation + * Licensed under GPLv2. + */ + +#define pr_fmt(fmt) "dt-cpu-ftrs: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + + +/* Device-tree visible constants follow */ +#define ISA_V2_07B 2070 +#define ISA_V3_0B 3000 + +#define USABLE_PR (1U << 0) +#define USABLE_OS (1U << 1) +#define USABLE_HV (1U << 2) + +#define HV_SUPPORT_HFSCR (1U << 0) +#define OS_SUPPORT_FSCR (1U << 0) + +/* For parsing, we define all bits set as "NONE" case */ +#define HV_SUPPORT_NONE 0xffffffffU +#define OS_SUPPORT_NONE 0xffffffffU + +struct dt_cpu_feature { + const char *name; + uint32_t isa; + uint32_t usable_privilege; + uint32_t hv_support; + uint32_t os_support; + uint32_t hfscr_bit_nr; + uint32_t fscr_bit_nr; + uint32_t hwcap_bit_nr; + /* fdt parsing */ + unsigned long node; + int enabled; + int disabled; +}; + +#define CPU_FTRS_BASE \ + (CPU_FTR_USE_TB | \ + CPU_FTR_LWSYNC | \ + CPU_FTR_FPU_UNAVAILABLE |\ + CPU_FTR_NODSISRALIGN |\ + 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) + +#define MMU_FTRS_HASH_BASE (MMU_FTRS_POWER8) + +#define COMMON_USER_BASE (PPC_FEATURE_32 | PPC_FEATURE_64 | \ + PPC_FEATURE_ARCH_2_06 |\ + PPC_FEATURE_ICACHE_SNOOP) +#define COMMON_USER2_BASE (PPC_FEATURE2_ARCH_2_07 | \ + PPC_FEATURE2_ISEL) +/* + * Set up the base CPU + */ + +extern void __flush_tlb_power8(unsigned int action); +extern void __flush_tlb_power9(unsigned int action); +extern long __machine_check_early_realmode_p8(struct pt_regs *regs); +extern long __machine_check_early_realmode_p9(struct pt_regs *regs); + +static int hv_mode; + +static struct { + u64 lpcr; + u64 hfscr; + u64 fscr; +} system_registers; + +static void (*init_pmu_registers)(void); + +static void cpufeatures_flush_tlb(void) +{ + unsigned long rb; + unsigned int i, num_sets; + + /* + * This is a temporary measure to keep equivalent TLB flush as the + * cputable based setup code. + */ + switch (PVR_VER(mfspr(SPRN_PVR))) { + case PVR_POWER8: + case PVR_POWER8E: + case PVR_POWER8NVL: + num_sets = POWER8_TLB_SETS; + break; + case PVR_POWER9: + num_sets = POWER9_TLB_SETS_HASH; + break; + default: + num_sets = 1; + pr_err("unknown CPU version for boot TLB flush\n"); + break; + } + + asm volatile("ptesync" : : : "memory"); + rb = TLBIEL_INVAL_SET; + for (i = 0; i < num_sets; i++) { + asm volatile("tlbiel %0" : : "r" (rb)); + rb += 1 << TLBIEL_INVAL_SET_SHIFT; + } + asm volatile("ptesync" : : : "memory"); +} + +static void __restore_cpu_cpufeatures(void) +{ + /* + * LPCR is restored by the power on engine already. It can be changed + * after early init e.g., by radix enable, and we have no unified API + * for saving and restoring such SPRs. + * + * This ->restore hook should really be removed from idle and register + * restore moved directly into the idle restore code, because this code + * doesn't know how idle is implemented or what it needs restored here. + * + * The best we can do to accommodate secondary boot and idle restore + * for now is "or" LPCR with existing. + */ + + mtspr(SPRN_LPCR, system_registers.lpcr | mfspr(SPRN_LPCR)); + if (hv_mode) { + mtspr(SPRN_LPID, 0); + mtspr(SPRN_HFSCR, system_registers.hfscr); + } + mtspr(SPRN_FSCR, system_registers.fscr); + + if (init_pmu_registers) + init_pmu_registers(); + + cpufeatures_flush_tlb(); +} + +static char dt_cpu_name[64]; + +static struct cpu_spec __initdata base_cpu_spec = { + .cpu_name = NULL, + .cpu_features = CPU_FTRS_BASE, + .cpu_user_features = COMMON_USER_BASE, + .cpu_user_features2 = COMMON_USER2_BASE, + .mmu_features = 0, + .icache_bsize = 32, /* minimum block size, fixed by */ + .dcache_bsize = 32, /* cache info init. */ + .num_pmcs = 0, + .pmc_type = PPC_PMC_DEFAULT, + .oprofile_cpu_type = NULL, + .oprofile_type = PPC_OPROFILE_INVALID, + .cpu_setup = NULL, + .cpu_restore = __restore_cpu_cpufeatures, + .flush_tlb = NULL, + .machine_check_early = NULL, + .platform = NULL, +}; + +static void __init cpufeatures_setup_cpu(void) +{ + set_cur_cpu_spec(&base_cpu_spec); + + cur_cpu_spec->pvr_mask = -1; + cur_cpu_spec->pvr_value = mfspr(SPRN_PVR); + + /* Initialize the base environment -- clear FSCR/HFSCR. */ + hv_mode = !!(mfmsr() & MSR_HV); + if (hv_mode) { + /* CPU_FTR_HVMODE is used early in PACA setup */ + cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE; + mtspr(SPRN_HFSCR, 0); + } + mtspr(SPRN_FSCR, 0); + + /* + * LPCR does not get cleared, to match behaviour with secondaries + * in __restore_cpu_cpufeatures. Once the idle code is fixed, this + * could clear LPCR too. + */ +} + +static int __init feat_try_enable_unknown(struct dt_cpu_feature *f) +{ + if (f->hv_support == HV_SUPPORT_NONE) { + } else if (f->hv_support & HV_SUPPORT_HFSCR) { + u64 hfscr = mfspr(SPRN_HFSCR); + hfscr |= 1UL << f->hfscr_bit_nr; + mtspr(SPRN_HFSCR, hfscr); + } else { + /* Does not have a known recipe */ + return 0; + } + + if (f->os_support == OS_SUPPORT_NONE) { + } else if (f->os_support & OS_SUPPORT_FSCR) { + u64 fscr = mfspr(SPRN_FSCR); + fscr |= 1UL << f->fscr_bit_nr; + mtspr(SPRN_FSCR, fscr); + } else { + /* Does not have a known recipe */ + return 0; + } + + if ((f->usable_privilege & USABLE_PR) && (f->hwcap_bit_nr != -1)) { + uint32_t word = f->hwcap_bit_nr / 32; + uint32_t bit = f->hwcap_bit_nr % 32; + + if (word == 0) + cur_cpu_spec->cpu_user_features |= 1U << bit; + else if (word == 1) + cur_cpu_spec->cpu_user_features2 |= 1U << bit; + else + pr_err("%s could not advertise to user (no hwcap bits)\n", f->name); + } + + return 1; +} + +static int __init feat_enable(struct dt_cpu_feature *f) +{ + if (f->hv_support != HV_SUPPORT_NONE) { + if (f->hfscr_bit_nr != -1) { + u64 hfscr = mfspr(SPRN_HFSCR); + hfscr |= 1UL << f->hfscr_bit_nr; + mtspr(SPRN_HFSCR, hfscr); + } + } + + if (f->os_support != OS_SUPPORT_NONE) { + if (f->fscr_bit_nr != -1) { + u64 fscr = mfspr(SPRN_FSCR); + fscr |= 1UL << f->fscr_bit_nr; + mtspr(SPRN_FSCR, fscr); + } + } + + if ((f->usable_privilege & USABLE_PR) && (f->hwcap_bit_nr != -1)) { + uint32_t word = f->hwcap_bit_nr / 32; + uint32_t bit = f->hwcap_bit_nr % 32; + + if (word == 0) + cur_cpu_spec->cpu_user_features |= 1U << bit; + else if (word == 1) + cur_cpu_spec->cpu_user_features2 |= 1U << bit; + else + pr_err("CPU feature: %s could not advertise to user (no hwcap bits)\n", f->name); + } + + return 1; +} + +static int __init feat_disable(struct dt_cpu_feature *f) +{ + return 0; +} + +static int __init feat_enable_hv(struct dt_cpu_feature *f) +{ + u64 lpcr; + + if (!hv_mode) { + pr_err("CPU feature hypervisor present in device tree but HV mode not enabled in the CPU. Ignoring.\n"); + return 0; + } + + mtspr(SPRN_LPID, 0); + + lpcr = mfspr(SPRN_LPCR); + lpcr &= ~LPCR_LPES0; /* HV external interrupts */ + mtspr(SPRN_LPCR, lpcr); + + cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE; + + return 1; +} + +static int __init feat_enable_le(struct dt_cpu_feature *f) +{ + cur_cpu_spec->cpu_user_features |= PPC_FEATURE_TRUE_LE; + return 1; +} + +static int __init feat_enable_smt(struct dt_cpu_feature *f) +{ + cur_cpu_spec->cpu_features |= CPU_FTR_SMT; + cur_cpu_spec->cpu_user_features |= PPC_FEATURE_SMT; + return 1; +} + +static int __init feat_enable_idle_nap(struct dt_cpu_feature *f) +{ + u64 lpcr; + + /* Set PECE wakeup modes for ISA 207 */ + lpcr = mfspr(SPRN_LPCR); + lpcr |= LPCR_PECE0; + lpcr |= LPCR_PECE1; + lpcr |= LPCR_PECE2; + mtspr(SPRN_LPCR, lpcr); + + return 1; +} + +static int __init feat_enable_align_dsisr(struct dt_cpu_feature *f) +{ + cur_cpu_spec->cpu_features &= ~CPU_FTR_NODSISRALIGN; + + return 1; +} + +static int __init feat_enable_idle_stop(struct dt_cpu_feature *f) +{ + u64 lpcr; + + /* Set PECE wakeup modes for ISAv3.0B */ + lpcr = mfspr(SPRN_LPCR); + lpcr |= LPCR_PECE0; + lpcr |= LPCR_PECE1; + lpcr |= LPCR_PECE2; + mtspr(SPRN_LPCR, lpcr); + + return 1; +} + +static int __init feat_enable_mmu_hash(struct dt_cpu_feature *f) +{ + u64 lpcr; + + lpcr = mfspr(SPRN_LPCR); + lpcr &= ~LPCR_ISL; + + /* VRMASD */ + lpcr |= LPCR_VPM0; + lpcr &= ~LPCR_VPM1; + lpcr |= 0x10UL << LPCR_VRMASD_SH; /* L=1 LP=00 */ + mtspr(SPRN_LPCR, lpcr); + + cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE; + cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU; + + return 1; +} + +static int __init feat_enable_mmu_hash_v3(struct dt_cpu_feature *f) +{ + u64 lpcr; + + lpcr = mfspr(SPRN_LPCR); + lpcr &= ~LPCR_ISL; + mtspr(SPRN_LPCR, lpcr); + + cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE; + cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU; + + return 1; +} + + +static int __init feat_enable_mmu_radix(struct dt_cpu_feature *f) +{ +#ifdef CONFIG_PPC_RADIX_MMU + cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX; + cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE; + cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU; + + return 1; +#endif + return 0; +} + +static int __init feat_enable_dscr(struct dt_cpu_feature *f) +{ + u64 lpcr; + + feat_enable(f); + + lpcr = mfspr(SPRN_LPCR); + lpcr &= ~LPCR_DPFD; + lpcr |= (4UL << LPCR_DPFD_SH); + mtspr(SPRN_LPCR, lpcr); + + return 1; +} + +static void hfscr_pmu_enable(void) +{ + u64 hfscr = mfspr(SPRN_HFSCR); + hfscr |= PPC_BIT(60); + mtspr(SPRN_HFSCR, hfscr); +} + +static void init_pmu_power8(void) +{ + if (hv_mode) { + mtspr(SPRN_MMCRC, 0); + mtspr(SPRN_MMCRH, 0); + } + + mtspr(SPRN_MMCRA, 0); + mtspr(SPRN_MMCR0, 0); + mtspr(SPRN_MMCR1, 0); + mtspr(SPRN_MMCR2, 0); + mtspr(SPRN_MMCRS, 0); +} + +static int __init feat_enable_mce_power8(struct dt_cpu_feature *f) +{ + cur_cpu_spec->platform = "power8"; + cur_cpu_spec->flush_tlb = __flush_tlb_power8; + cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p8; + + return 1; +} + +static int __init feat_enable_pmu_power8(struct dt_cpu_feature *f) +{ + hfscr_pmu_enable(); + + init_pmu_power8(); + init_pmu_registers = init_pmu_power8; + + cur_cpu_spec->cpu_features |= CPU_FTR_MMCRA; + cur_cpu_spec->cpu_user_features |= PPC_FEATURE_PSERIES_PERFMON_COMPAT; + if (pvr_version_is(PVR_POWER8E)) + cur_cpu_spec->cpu_features |= CPU_FTR_PMAO_BUG; + + cur_cpu_spec->num_pmcs = 6; + cur_cpu_spec->pmc_type = PPC_PMC_IBM; + cur_cpu_spec->oprofile_cpu_type = "ppc64/power8"; + + return 1; +} + +static void init_pmu_power9(void) +{ + if (hv_mode) + mtspr(SPRN_MMCRC, 0); + + mtspr(SPRN_MMCRA, 0); + mtspr(SPRN_MMCR0, 0); + mtspr(SPRN_MMCR1, 0); + mtspr(SPRN_MMCR2, 0); +} + +static int __init feat_enable_mce_power9(struct dt_cpu_feature *f) +{ + cur_cpu_spec->platform = "power9"; + cur_cpu_spec->flush_tlb = __flush_tlb_power9; + cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p9; + + return 1; +} + +static int __init feat_enable_pmu_power9(struct dt_cpu_feature *f) +{ + hfscr_pmu_enable(); + + init_pmu_power9(); + init_pmu_registers = init_pmu_power9; + + cur_cpu_spec->cpu_features |= CPU_FTR_MMCRA; + cur_cpu_spec->cpu_user_features |= PPC_FEATURE_PSERIES_PERFMON_COMPAT; + + cur_cpu_spec->num_pmcs = 6; + cur_cpu_spec->pmc_type = PPC_PMC_IBM; + cur_cpu_spec->oprofile_cpu_type = "ppc64/power9"; + + return 1; +} + +static int __init feat_enable_tm(struct dt_cpu_feature *f) +{ +#ifdef CONFIG_PPC_TRANSACTIONAL_MEM + feat_enable(f); + cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_HTM_NOSC; + return 1; +#endif + return 0; +} + +static int __init feat_enable_fp(struct dt_cpu_feature *f) +{ + feat_enable(f); + cur_cpu_spec->cpu_features &= ~CPU_FTR_FPU_UNAVAILABLE; + + return 1; +} + +static int __init feat_enable_vector(struct dt_cpu_feature *f) +{ +#ifdef CONFIG_ALTIVEC + feat_enable(f); + cur_cpu_spec->cpu_features |= CPU_FTR_ALTIVEC; + cur_cpu_spec->cpu_features |= CPU_FTR_VMX_COPY; + cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_ALTIVEC; + + return 1; +#endif + return 0; +} + +static int __init feat_enable_vsx(struct dt_cpu_feature *f) +{ +#ifdef CONFIG_VSX + feat_enable(f); + cur_cpu_spec->cpu_features |= CPU_FTR_VSX; + cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_VSX; + + return 1; +#endif + return 0; +} + +static int __init feat_enable_purr(struct dt_cpu_feature *f) +{ + cur_cpu_spec->cpu_features |= CPU_FTR_PURR | CPU_FTR_SPURR; + + return 1; +} + +static int __init feat_enable_ebb(struct dt_cpu_feature *f) +{ + /* + * PPC_FEATURE2_EBB is enabled in PMU init code because it has + * historically been related to the PMU facility. This may have + * to be decoupled if EBB becomes more generic. For now, follow + * existing convention. + */ + f->hwcap_bit_nr = -1; + feat_enable(f); + + return 1; +} + +static int __init feat_enable_dbell(struct dt_cpu_feature *f) +{ + u64 lpcr; + + /* P9 has an HFSCR for privileged state */ + feat_enable(f); + + cur_cpu_spec->cpu_features |= CPU_FTR_DBELL; + + lpcr = mfspr(SPRN_LPCR); + lpcr |= LPCR_PECEDH; /* hyp doorbell wakeup */ + mtspr(SPRN_LPCR, lpcr); + + return 1; +} + +static int __init feat_enable_hvi(struct dt_cpu_feature *f) +{ + u64 lpcr; + + /* + * POWER9 XIVE interrupts including in OPAL XICS compatibility + * are always delivered as hypervisor virtualization interrupts (HVI) + * rather than EE. + * + * However LPES0 is not set here, in the chance that an EE does get + * delivered to the host somehow, the EE handler would not expect it + * to be delivered in LPES0 mode (e.g., using SRR[01]). This could + * happen if there is a bug in interrupt controller code, or IC is + * misconfigured in systemsim. + */ + + lpcr = mfspr(SPRN_LPCR); + lpcr |= LPCR_HVICE; /* enable hvi interrupts */ + lpcr |= LPCR_HEIC; /* disable ee interrupts when MSR_HV */ + lpcr |= LPCR_PECE_HVEE; /* hvi can wake from stop */ + mtspr(SPRN_LPCR, lpcr); + + return 1; +} + +static int __init feat_enable_large_ci(struct dt_cpu_feature *f) +{ + cur_cpu_spec->mmu_features |= MMU_FTR_CI_LARGE_PAGE; + + return 1; +} + +struct dt_cpu_feature_match { + const char *name; + int (*enable)(struct dt_cpu_feature *f); + u64 cpu_ftr_bit_mask; +}; + +static struct dt_cpu_feature_match __initdata + dt_cpu_feature_match_table[] = { + {"hypervisor", feat_enable_hv, 0}, + {"big-endian", feat_enable, 0}, + {"little-endian", feat_enable_le, CPU_FTR_REAL_LE}, + {"smt", feat_enable_smt, 0}, + {"interrupt-facilities", feat_enable, 0}, + {"timer-facilities", feat_enable, 0}, + {"timer-facilities-v3", feat_enable, 0}, + {"debug-facilities", feat_enable, 0}, + {"come-from-address-register", feat_enable, CPU_FTR_CFAR}, + {"branch-tracing", feat_enable, 0}, + {"floating-point", feat_enable_fp, 0}, + {"vector", feat_enable_vector, 0}, + {"vector-scalar", feat_enable_vsx, 0}, + {"vector-scalar-v3", feat_enable, 0}, + {"decimal-floating-point", feat_enable, 0}, + {"decimal-integer", feat_enable, 0}, + {"quadword-load-store", feat_enable, 0}, + {"vector-crypto", feat_enable, 0}, + {"mmu-hash", feat_enable_mmu_hash, 0}, + {"mmu-radix", feat_enable_mmu_radix, 0}, + {"mmu-hash-v3", feat_enable_mmu_hash_v3, 0}, + {"virtual-page-class-key-protection", feat_enable, 0}, + {"transactional-memory", feat_enable_tm, CPU_FTR_TM}, + {"transactional-memory-v3", feat_enable_tm, 0}, + {"idle-nap", feat_enable_idle_nap, 0}, + {"alignment-interrupt-dsisr", feat_enable_align_dsisr, 0}, + {"idle-stop", feat_enable_idle_stop, 0}, + {"machine-check-power8", feat_enable_mce_power8, 0}, + {"performance-monitor-power8", feat_enable_pmu_power8, 0}, + {"data-stream-control-register", feat_enable_dscr, CPU_FTR_DSCR}, + {"event-based-branch", feat_enable_ebb, 0}, + {"target-address-register", feat_enable, 0}, + {"branch-history-rolling-buffer", feat_enable, 0}, + {"control-register", feat_enable, CPU_FTR_CTRL}, + {"processor-control-facility", feat_enable_dbell, CPU_FTR_DBELL}, + {"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL}, + {"processor-utilization-of-resources-register", feat_enable_purr, 0}, + {"subcore", feat_enable, CPU_FTR_SUBCORE}, + {"no-execute", feat_enable, 0}, + {"strong-access-ordering", feat_enable, CPU_FTR_SAO}, + {"cache-inhibited-large-page", feat_enable_large_ci, 0}, + {"coprocessor-icswx", feat_enable, CPU_FTR_ICSWX}, + {"hypervisor-virtualization-interrupt", feat_enable_hvi, 0}, + {"program-priority-register", feat_enable, CPU_FTR_HAS_PPR}, + {"wait", feat_enable, 0}, + {"atomic-memory-operations", feat_enable, 0}, + {"branch-v3", feat_enable, 0}, + {"copy-paste", feat_enable, 0}, + {"decimal-floating-point-v3", feat_enable, 0}, + {"decimal-integer-v3", feat_enable, 0}, + {"fixed-point-v3", feat_enable, 0}, + {"floating-point-v3", feat_enable, 0}, + {"group-start-register", feat_enable, 0}, + {"pc-relative-addressing", feat_enable, 0}, + {"machine-check-power9", feat_enable_mce_power9, 0}, + {"performance-monitor-power9", feat_enable_pmu_power9, 0}, + {"event-based-branch-v3", feat_enable, 0}, + {"random-number-generator", feat_enable, 0}, + {"system-call-vectored", feat_disable, 0}, + {"trace-interrupt-v3", feat_enable, 0}, + {"vector-v3", feat_enable, 0}, + {"vector-binary128", feat_enable, 0}, + {"vector-binary16", feat_enable, 0}, + {"wait-v3", feat_enable, 0}, +}; + +/* XXX: how to configure this? Default + boot time? */ +#ifdef CONFIG_PPC_CPUFEATURES_ENABLE_UNKNOWN +#define CPU_FEATURE_ENABLE_UNKNOWN 1 +#else +#define CPU_FEATURE_ENABLE_UNKNOWN 0 +#endif + +static void __init cpufeatures_setup_start(u32 isa) +{ + pr_info("setup for ISA %d\n", isa); + + if (isa >= 3000) { + cur_cpu_spec->cpu_features |= CPU_FTR_ARCH_300; + cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_ARCH_3_00; + } +} + +static bool __init cpufeatures_process_feature(struct dt_cpu_feature *f) +{ + const struct dt_cpu_feature_match *m; + bool known = false; + int i; + + for (i = 0; i < ARRAY_SIZE(dt_cpu_feature_match_table); i++) { + m = &dt_cpu_feature_match_table[i]; + if (!strcmp(f->name, m->name)) { + known = true; + if (m->enable(f)) + break; + + pr_info("not enabling: %s (disabled or unsupported by kernel)\n", + f->name); + return false; + } + } + + if (!known && CPU_FEATURE_ENABLE_UNKNOWN) { + if (!feat_try_enable_unknown(f)) { + pr_info("not enabling: %s (unknown and unsupported by kernel)\n", + f->name); + return false; + } + } + + if (m->cpu_ftr_bit_mask) + cur_cpu_spec->cpu_features |= m->cpu_ftr_bit_mask; + + if (known) + pr_debug("enabling: %s\n", f->name); + else + pr_debug("enabling: %s (unknown)\n", f->name); + + return true; +} + +static __init void cpufeatures_cpu_quirks(void) +{ + int version = mfspr(SPRN_PVR); + + /* + * Not all quirks can be derived from the cpufeatures device tree. + */ + if ((version & 0xffffff00) == 0x004e0100) + cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD1; +} + +static void __init cpufeatures_setup_finished(void) +{ + cpufeatures_cpu_quirks(); + + if (hv_mode && !(cur_cpu_spec->cpu_features & CPU_FTR_HVMODE)) { + pr_err("hypervisor not present in device tree but HV mode is enabled in the CPU. Enabling.\n"); + cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE; + } + + system_registers.lpcr = mfspr(SPRN_LPCR); + system_registers.hfscr = mfspr(SPRN_HFSCR); + system_registers.fscr = mfspr(SPRN_FSCR); + + cpufeatures_flush_tlb(); + + pr_info("final cpu/mmu features = 0x%016lx 0x%08x\n", + cur_cpu_spec->cpu_features, cur_cpu_spec->mmu_features); +} + +static int __init fdt_find_cpu_features(unsigned long node, const char *uname, + int depth, void *data) +{ + if (of_flat_dt_is_compatible(node, "ibm,powerpc-cpu-features") + && of_get_flat_dt_prop(node, "isa", NULL)) + return 1; + + return 0; +} + +static bool __initdata using_dt_cpu_ftrs = false; + +bool __init dt_cpu_ftrs_in_use(void) +{ + return using_dt_cpu_ftrs; +} + +bool __init dt_cpu_ftrs_init(void *fdt) +{ + /* Setup and verify the FDT, if it fails we just bail */ + if (!early_init_dt_verify(fdt)) + return false; + + if (!of_scan_flat_dt(fdt_find_cpu_features, NULL)) + return false; + + cpufeatures_setup_cpu(); + + using_dt_cpu_ftrs = true; + return true; +} + +static int nr_dt_cpu_features; +static struct dt_cpu_feature *dt_cpu_features; + +static int __init process_cpufeatures_node(unsigned long node, + const char *uname, int i) +{ + const __be32 *prop; + struct dt_cpu_feature *f; + int len; + + f = &dt_cpu_features[i]; + memset(f, 0, sizeof(struct dt_cpu_feature)); + + f->node = node; + + f->name = uname; + + prop = of_get_flat_dt_prop(node, "isa", &len); + if (!prop) { + pr_warn("%s: missing isa property\n", uname); + return 0; + } + f->isa = be32_to_cpup(prop); + + prop = of_get_flat_dt_prop(node, "usable-privilege", &len); + if (!prop) { + pr_warn("%s: missing usable-privilege property", uname); + return 0; + } + f->usable_privilege = be32_to_cpup(prop); + + prop = of_get_flat_dt_prop(node, "hv-support", &len); + if (prop) + f->hv_support = be32_to_cpup(prop); + else + f->hv_support = HV_SUPPORT_NONE; + + prop = of_get_flat_dt_prop(node, "os-support", &len); + if (prop) + f->os_support = be32_to_cpup(prop); + else + f->os_support = OS_SUPPORT_NONE; + + prop = of_get_flat_dt_prop(node, "hfscr-bit-nr", &len); + if (prop) + f->hfscr_bit_nr = be32_to_cpup(prop); + else + f->hfscr_bit_nr = -1; + prop = of_get_flat_dt_prop(node, "fscr-bit-nr", &len); + if (prop) + f->fscr_bit_nr = be32_to_cpup(prop); + else + f->fscr_bit_nr = -1; + prop = of_get_flat_dt_prop(node, "hwcap-bit-nr", &len); + if (prop) + f->hwcap_bit_nr = be32_to_cpup(prop); + else + f->hwcap_bit_nr = -1; + + if (f->usable_privilege & USABLE_HV) { + if (!(mfmsr() & MSR_HV)) { + pr_warn("%s: HV feature passed to guest\n", uname); + return 0; + } + + if (f->hv_support == HV_SUPPORT_NONE && f->hfscr_bit_nr != -1) { + pr_warn("%s: unwanted hfscr_bit_nr\n", uname); + return 0; + } + + if (f->hv_support == HV_SUPPORT_HFSCR) { + if (f->hfscr_bit_nr == -1) { + pr_warn("%s: missing hfscr_bit_nr\n", uname); + return 0; + } + } + } else { + if (f->hv_support != HV_SUPPORT_NONE || f->hfscr_bit_nr != -1) { + pr_warn("%s: unwanted hv_support/hfscr_bit_nr\n", uname); + return 0; + } + } + + if (f->usable_privilege & USABLE_OS) { + if (f->os_support == OS_SUPPORT_NONE && f->fscr_bit_nr != -1) { + pr_warn("%s: unwanted fscr_bit_nr\n", uname); + return 0; + } + + if (f->os_support == OS_SUPPORT_FSCR) { + if (f->fscr_bit_nr == -1) { + pr_warn("%s: missing fscr_bit_nr\n", uname); + return 0; + } + } + } else { + if (f->os_support != OS_SUPPORT_NONE || f->fscr_bit_nr != -1) { + pr_warn("%s: unwanted os_support/fscr_bit_nr\n", uname); + return 0; + } + } + + if (!(f->usable_privilege & USABLE_PR)) { + if (f->hwcap_bit_nr != -1) { + pr_warn("%s: unwanted hwcap_bit_nr\n", uname); + return 0; + } + } + + /* Do all the independent features in the first pass */ + if (!of_get_flat_dt_prop(node, "dependencies", &len)) { + if (cpufeatures_process_feature(f)) + f->enabled = 1; + else + f->disabled = 1; + } + + return 0; +} + +static void __init cpufeatures_deps_enable(struct dt_cpu_feature *f) +{ + const __be32 *prop; + int len; + int nr_deps; + int i; + + if (f->enabled || f->disabled) + return; + + prop = of_get_flat_dt_prop(f->node, "dependencies", &len); + if (!prop) { + pr_warn("%s: missing dependencies property", f->name); + return; + } + + nr_deps = len / sizeof(int); + + for (i = 0; i < nr_deps; i++) { + unsigned long phandle = be32_to_cpu(prop[i]); + int j; + + for (j = 0; j < nr_dt_cpu_features; j++) { + struct dt_cpu_feature *d = &dt_cpu_features[j]; + + if (of_get_flat_dt_phandle(d->node) == phandle) { + cpufeatures_deps_enable(d); + if (d->disabled) { + f->disabled = 1; + return; + } + } + } + } + + if (cpufeatures_process_feature(f)) + f->enabled = 1; + else + f->disabled = 1; +} + +static int __init scan_cpufeatures_subnodes(unsigned long node, + const char *uname, + void *data) +{ + int *count = data; + + process_cpufeatures_node(node, uname, *count); + + (*count)++; + + return 0; +} + +static int __init count_cpufeatures_subnodes(unsigned long node, + const char *uname, + void *data) +{ + int *count = data; + + (*count)++; + + return 0; +} + +static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char + *uname, int depth, void *data) +{ + const __be32 *prop; + int count, i; + u32 isa; + + /* We are scanning "ibm,powerpc-cpu-features" nodes only */ + if (!of_flat_dt_is_compatible(node, "ibm,powerpc-cpu-features")) + return 0; + + prop = of_get_flat_dt_prop(node, "isa", NULL); + if (!prop) + /* We checked before, "can't happen" */ + return 0; + + isa = be32_to_cpup(prop); + + /* Count and allocate space for cpu features */ + of_scan_flat_dt_subnodes(node, count_cpufeatures_subnodes, + &nr_dt_cpu_features); + dt_cpu_features = __va( + memblock_alloc(sizeof(struct dt_cpu_feature)* + nr_dt_cpu_features, PAGE_SIZE)); + + cpufeatures_setup_start(isa); + + /* Scan nodes into dt_cpu_features and enable those without deps */ + count = 0; + of_scan_flat_dt_subnodes(node, scan_cpufeatures_subnodes, &count); + + /* Recursive enable remaining features with dependencies */ + for (i = 0; i < nr_dt_cpu_features; i++) { + struct dt_cpu_feature *f = &dt_cpu_features[i]; + + cpufeatures_deps_enable(f); + } + + prop = of_get_flat_dt_prop(node, "display-name", NULL); + if (prop && strlen((char *)prop) != 0) { + strlcpy(dt_cpu_name, (char *)prop, sizeof(dt_cpu_name)); + cur_cpu_spec->cpu_name = dt_cpu_name; + } + + cpufeatures_setup_finished(); + + memblock_free(__pa(dt_cpu_features), + sizeof(struct dt_cpu_feature)*nr_dt_cpu_features); + + return 0; +} + +void __init dt_cpu_ftrs_scan(void) +{ + of_scan_flat_dt(dt_cpu_ftrs_scan_callback, NULL); +} diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index d2f0afeae5a0..40c4887c27b6 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -57,6 +57,7 @@ #include #include #include +#include #include @@ -375,23 +376,31 @@ static int __init early_init_dt_scan_cpus(unsigned long node, * A POWER6 partition in "POWER6 architected" mode * uses the 0x0f000002 PVR value; in POWER5+ mode * it uses 0x0f000001. + * + * If we're using device tree CPU feature discovery then we don't + * support the cpu-version property, and it's the responsibility of the + * firmware/hypervisor to provide the correct feature set for the + * architecture level via the ibm,powerpc-cpu-features binding. */ - prop = of_get_flat_dt_prop(node, "cpu-version", NULL); - if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000) - identify_cpu(0, be32_to_cpup(prop)); + if (!dt_cpu_ftrs_in_use()) { + prop = of_get_flat_dt_prop(node, "cpu-version", NULL); + if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000) + identify_cpu(0, be32_to_cpup(prop)); - identical_pvr_fixup(node); + check_cpu_feature_properties(node); + check_cpu_pa_features(node); + } - check_cpu_feature_properties(node); - check_cpu_pa_features(node); + identical_pvr_fixup(node); init_mmu_slb_size(node); #ifdef CONFIG_PPC64 - if (nthreads > 1) - cur_cpu_spec->cpu_features |= CPU_FTR_SMT; - else + if (nthreads == 1) cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT; + else if (!dt_cpu_ftrs_in_use()) + cur_cpu_spec->cpu_features |= CPU_FTR_SMT; #endif + return 0; } @@ -721,6 +730,8 @@ void __init early_init_devtree(void *params) DBG("Scanning CPUs ...\n"); + dt_cpu_ftrs_scan(); + /* Retrieve CPU related informations from the flat tree * (altivec support, boot CPU ID, ...) */ diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 0f7b15860a06..1bf8978ec8da 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -49,6 +49,7 @@ #include #include #include +#include #include #include #include @@ -265,8 +266,10 @@ void __init early_setup(unsigned long dt_ptr) /* -------- printk is _NOT_ safe to use here ! ------- */ - /* Identify CPU type */ - identify_cpu(0, mfspr(SPRN_PVR)); + /* Try new device tree based feature discovery ... */ + if (!dt_cpu_ftrs_init(__va(dt_ptr))) + /* Otherwise use the old style CPU table */ + identify_cpu(0, mfspr(SPRN_PVR)); /* Assume we're on cpu 0 for now. Don't write to the paca yet! */ initialise_paca(&boot_paca, 0); @@ -532,6 +535,9 @@ void __init initialize_cache_info(void) dcache_bsize = ppc64_caches.l1d.block_size; icache_bsize = ppc64_caches.l1i.block_size; + cur_cpu_spec->dcache_bsize = dcache_bsize; + cur_cpu_spec->icache_bsize = icache_bsize; + DBG(" <- initialize_cache_info()\n"); } -- cgit v1.2.3-59-g8ed1b