| Message ID | 1563187987-5847-1-git-send-email-hhhawa@amazon.com (mailing list archive) |
|---|---|
| State | Not Applicable, archived |
| Delegated to: | Andy Gross |
| Headers | show |
| Series | [RFC,1/1] edac: Add a counter parameter for edac_device_handle_ue/ce() | expand |
On Mon, Jul 15, 2019 at 01:53:07PM +0300, Hanna Hawa wrote: > Add a counter parameter in order to avoid losing errors count for edac > device, the error count reports the number of errors reported by an edac > device similar to the way MC_EDAC do. > > Signed-off-by: Hanna Hawa <hhhawa@amazon.com> > --- > drivers/edac/altera_edac.c | 20 ++++++++++++-------- > drivers/edac/amd8111_edac.c | 6 +++--- > drivers/edac/cpc925_edac.c | 4 ++-- > drivers/edac/edac_device.c | 18 ++++++++++-------- > drivers/edac/edac_device.h | 8 ++++++-- > drivers/edac/highbank_l2_edac.c | 4 ++-- > drivers/edac/mpc85xx_edac.c | 4 ++-- > drivers/edac/mv64x60_edac.c | 4 ++-- > drivers/edac/octeon_edac-l2c.c | 20 ++++++++++---------- > drivers/edac/octeon_edac-pc.c | 6 +++--- > drivers/edac/qcom_edac.c | 8 ++++---- > drivers/edac/thunderx_edac.c | 10 +++++----- > drivers/edac/xgene_edac.c | 26 +++++++++++++------------- > 13 files changed, 74 insertions(+), 64 deletions(-) Hi Hanna, I'm probably missing something but this patch looks like while it adds the error_count parameter the passed values all seem to be 1. So is the new parameter used otherwise, maybe in another patch? thanks, Jan > diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c > index 8816f74..747dd43 100644 > --- a/drivers/edac/altera_edac.c > +++ b/drivers/edac/altera_edac.c > @@ -616,12 +616,12 @@ static irqreturn_t altr_edac_device_handler(int irq, void *dev_id) > if (irq == drvdata->sb_irq) { > if (priv->ce_clear_mask) > writel(priv->ce_clear_mask, drvdata->base); > - edac_device_handle_ce(dci, 0, 0, drvdata->edac_dev_name); > + edac_device_handle_ce(dci, 1, 0, 0, drvdata->edac_dev_name); > ret_value = IRQ_HANDLED; > } else if (irq == drvdata->db_irq) { > if (priv->ue_clear_mask) > writel(priv->ue_clear_mask, drvdata->base); > - edac_device_handle_ue(dci, 0, 0, drvdata->edac_dev_name); > + edac_device_handle_ue(dci, 1, 0, 0, drvdata->edac_dev_name); > panic("\nEDAC:ECC_DEVICE[Uncorrectable errors]\n"); > ret_value = IRQ_HANDLED; > } else { > @@ -919,13 +919,15 @@ static irqreturn_t __maybe_unused altr_edac_a10_ecc_irq(int irq, void *dev_id) > if (irq == dci->sb_irq) { > writel(ALTR_A10_ECC_SERRPENA, > base + ALTR_A10_ECC_INTSTAT_OFST); > - edac_device_handle_ce(dci->edac_dev, 0, 0, dci->edac_dev_name); > + edac_device_handle_ce(dci->edac_dev, 1, 0, 0, > + dci->edac_dev_name); > > return IRQ_HANDLED; > } else if (irq == dci->db_irq) { > writel(ALTR_A10_ECC_DERRPENA, > base + ALTR_A10_ECC_INTSTAT_OFST); > - edac_device_handle_ue(dci->edac_dev, 0, 0, dci->edac_dev_name); > + edac_device_handle_ue(dci->edac_dev, 1, 0, 0, > + dci->edac_dev_name); > if (dci->data->panic) > panic("\nEDAC:ECC_DEVICE[Uncorrectable errors]\n"); > > @@ -1308,14 +1310,16 @@ static irqreturn_t altr_edac_a10_l2_irq(int irq, void *dev_id) > regmap_write(dci->edac->ecc_mgr_map, > A10_SYSGMR_MPU_CLEAR_L2_ECC_OFST, > A10_SYSGMR_MPU_CLEAR_L2_ECC_SB); > - edac_device_handle_ce(dci->edac_dev, 0, 0, dci->edac_dev_name); > + edac_device_handle_ce(dci->edac_dev, 1, 0, 0, > + dci->edac_dev_name); > > return IRQ_HANDLED; > } else if (irq == dci->db_irq) { > regmap_write(dci->edac->ecc_mgr_map, > A10_SYSGMR_MPU_CLEAR_L2_ECC_OFST, > A10_SYSGMR_MPU_CLEAR_L2_ECC_MB); > - edac_device_handle_ue(dci->edac_dev, 0, 0, dci->edac_dev_name); > + edac_device_handle_ue(dci->edac_dev, 1, 0, 0, > + dci->edac_dev_name); > panic("\nEDAC:ECC_DEVICE[Uncorrectable errors]\n"); > > return IRQ_HANDLED; > @@ -1652,12 +1656,12 @@ static irqreturn_t altr_edac_a10_ecc_irq_portb(int irq, void *dev_id) > if (irq == ad->sb_irq) { > writel(priv->ce_clear_mask, > base + ALTR_A10_ECC_INTSTAT_OFST); > - edac_device_handle_ce(ad->edac_dev, 0, 0, ad->edac_dev_name); > + edac_device_handle_ce(ad->edac_dev, 1, 0, 0, ad->edac_dev_name); > return IRQ_HANDLED; > } else if (irq == ad->db_irq) { > writel(priv->ue_clear_mask, > base + ALTR_A10_ECC_INTSTAT_OFST); > - edac_device_handle_ue(ad->edac_dev, 0, 0, ad->edac_dev_name); > + edac_device_handle_ue(ad->edac_dev, 1, 0, 0, ad->edac_dev_name); > return IRQ_HANDLED; > } > > diff --git a/drivers/edac/amd8111_edac.c b/drivers/edac/amd8111_edac.c > index b5786cf..e595fab 100644 > --- a/drivers/edac/amd8111_edac.c > +++ b/drivers/edac/amd8111_edac.c > @@ -303,7 +303,7 @@ static void amd8111_lpc_bridge_check(struct edac_device_ctl_info *edac_dev) > val8 |= IO_CTRL_1_CLEAR_MASK; > edac_pci_write_byte(dev, REG_IO_CTRL_1, val8); > > - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); > } > > if (at_compat_reg_broken == 0) { > @@ -315,8 +315,8 @@ static void amd8111_lpc_bridge_check(struct edac_device_ctl_info *edac_dev) > out8 |= AT_COMPAT_CLRIOCHK; > if (out8 > 0) { > __do_outb(out8, REG_AT_COMPAT); > - edac_device_handle_ue(edac_dev, 0, 0, > - edac_dev->ctl_name); > + edac_device_handle_ue(edac_dev, 1, 0, 0, > + edac_dev->ctl_name); > } > } > } > diff --git a/drivers/edac/cpc925_edac.c b/drivers/edac/cpc925_edac.c > index 3c0881a..eb74865 100644 > --- a/drivers/edac/cpc925_edac.c > +++ b/drivers/edac/cpc925_edac.c > @@ -682,7 +682,7 @@ static void cpc925_cpu_check(struct edac_device_ctl_info *edac_dev) > cpc925_printk(KERN_INFO, "APIMASK 0x%08x\n", apimask); > cpc925_printk(KERN_INFO, "APIEXCP 0x%08x\n", apiexcp); > > - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); > } > > /******************** HT Link err device****************************/ > @@ -756,7 +756,7 @@ static void cpc925_htlink_check(struct edac_device_ctl_info *edac_dev) > __raw_writel(HT_LINKERR_DETECTED, > dev_info->vbase + REG_LINKERR_OFFSET); > > - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); > } > > static struct cpc925_dev_info cpc925_devs[] = { > diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c > index 65cf2b9..d1de296 100644 > --- a/drivers/edac/edac_device.c > +++ b/drivers/edac/edac_device.c > @@ -556,7 +556,8 @@ static inline int edac_device_get_panic_on_ue(struct edac_device_ctl_info > } > > void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, > - int inst_nr, int block_nr, const char *msg) > + u16 error_count, int inst_nr, int block_nr, > + const char *msg) > { > struct edac_device_instance *instance; > struct edac_device_block *block = NULL; > @@ -582,12 +583,12 @@ void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, > > if (instance->nr_blocks > 0) { > block = instance->blocks + block_nr; > - block->counters.ce_count++; > + block->counters.ce_count += error_count; > } > > /* Propagate the count up the 'totals' tree */ > - instance->counters.ce_count++; > - edac_dev->counters.ce_count++; > + instance->counters.ce_count += error_count; > + edac_dev->counters.ce_count += error_count; > > if (edac_device_get_log_ce(edac_dev)) > edac_device_printk(edac_dev, KERN_WARNING, > @@ -598,7 +599,8 @@ void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, > EXPORT_SYMBOL_GPL(edac_device_handle_ce); > > void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, > - int inst_nr, int block_nr, const char *msg) > + u16 error_count, int inst_nr, int block_nr, > + const char *msg) > { > struct edac_device_instance *instance; > struct edac_device_block *block = NULL; > @@ -624,12 +626,12 @@ void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, > > if (instance->nr_blocks > 0) { > block = instance->blocks + block_nr; > - block->counters.ue_count++; > + block->counters.ue_count += error_count; > } > > /* Propagate the count up the 'totals' tree */ > - instance->counters.ue_count++; > - edac_dev->counters.ue_count++; > + instance->counters.ue_count += error_count; > + edac_dev->counters.ue_count += error_count; > > if (edac_device_get_log_ue(edac_dev)) > edac_device_printk(edac_dev, KERN_EMERG, > diff --git a/drivers/edac/edac_device.h b/drivers/edac/edac_device.h > index 1aaba74..cf1a1da 100644 > --- a/drivers/edac/edac_device.h > +++ b/drivers/edac/edac_device.h > @@ -290,23 +290,27 @@ extern struct edac_device_ctl_info *edac_device_del_device(struct device *dev); > * perform a common output and handling of an 'edac_dev' UE event > * > * @edac_dev: pointer to struct &edac_device_ctl_info > + * @error_count: number of errors of the same type > * @inst_nr: number of the instance where the UE error happened > * @block_nr: number of the block where the UE error happened > * @msg: message to be printed > */ > extern void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, > - int inst_nr, int block_nr, const char *msg); > + u16 error_count, int inst_nr, int block_nr, > + const char *msg); > /** > * edac_device_handle_ce(): > * perform a common output and handling of an 'edac_dev' CE event > * > * @edac_dev: pointer to struct &edac_device_ctl_info > + * @error_count: number of errors of the same type > * @inst_nr: number of the instance where the CE error happened > * @block_nr: number of the block where the CE error happened > * @msg: message to be printed > */ > extern void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, > - int inst_nr, int block_nr, const char *msg); > + u16 error_count, int inst_nr, int block_nr, > + const char *msg); > > /** > * edac_device_alloc_index: Allocate a unique device index number > diff --git a/drivers/edac/highbank_l2_edac.c b/drivers/edac/highbank_l2_edac.c > index cd9a2bb..65f016a 100644 > --- a/drivers/edac/highbank_l2_edac.c > +++ b/drivers/edac/highbank_l2_edac.c > @@ -39,11 +39,11 @@ static irqreturn_t highbank_l2_err_handler(int irq, void *dev_id) > > if (irq == drvdata->sb_irq) { > writel(1, drvdata->base + SR_CLR_SB_ECC_INTR); > - edac_device_handle_ce(dci, 0, 0, dci->ctl_name); > + edac_device_handle_ce(dci, 1, 0, 0, dci->ctl_name); > } > if (irq == drvdata->db_irq) { > writel(1, drvdata->base + SR_CLR_DB_ECC_INTR); > - edac_device_handle_ue(dci, 0, 0, dci->ctl_name); > + edac_device_handle_ue(dci, 1, 0, 0, dci->ctl_name); > } > > return IRQ_HANDLED; > diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c > index 67f7bc3..0618a06 100644 > --- a/drivers/edac/mpc85xx_edac.c > +++ b/drivers/edac/mpc85xx_edac.c > @@ -464,10 +464,10 @@ static void mpc85xx_l2_check(struct edac_device_ctl_info *edac_dev) > out_be32(pdata->l2_vbase + MPC85XX_L2_ERRDET, err_detect); > > if (err_detect & L2_EDE_CE_MASK) > - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); > > if (err_detect & L2_EDE_UE_MASK) > - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); > } > > static irqreturn_t mpc85xx_l2_isr(int irq, void *dev_id) > diff --git a/drivers/edac/mv64x60_edac.c b/drivers/edac/mv64x60_edac.c > index 3c68bb5..005b012 100644 > --- a/drivers/edac/mv64x60_edac.c > +++ b/drivers/edac/mv64x60_edac.c > @@ -251,7 +251,7 @@ static void mv64x60_sram_check(struct edac_device_ctl_info *edac_dev) > readl(pdata->sram_vbase + MV64X60_SRAM_ERR_PARITY)); > writel(0, pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE); > > - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); > } > > static irqreturn_t mv64x60_sram_isr(int irq, void *dev_id) > @@ -417,7 +417,7 @@ static void mv64x60_cpu_check(struct edac_device_ctl_info *edac_dev) > readl(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_PARITY)); > writel(0, pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE); > > - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); > } > > static irqreturn_t mv64x60_cpu_isr(int irq, void *dev_id) > diff --git a/drivers/edac/octeon_edac-l2c.c b/drivers/edac/octeon_edac-l2c.c > index c33059e..8e58531 100644 > --- a/drivers/edac/octeon_edac-l2c.c > +++ b/drivers/edac/octeon_edac-l2c.c > @@ -28,12 +28,12 @@ static void octeon_l2c_poll_oct1(struct edac_device_ctl_info *l2c) > l2t_err_reset.u64 = 0; > l2t_err.u64 = cvmx_read_csr(CVMX_L2T_ERR); > if (l2t_err.s.sec_err) { > - edac_device_handle_ce(l2c, 0, 0, > + edac_device_handle_ce(l2c, 1, 0, 0, > "Tag Single bit error (corrected)"); > l2t_err_reset.s.sec_err = 1; > } > if (l2t_err.s.ded_err) { > - edac_device_handle_ue(l2c, 0, 0, > + edac_device_handle_ue(l2c, 1, 0, 0, > "Tag Double bit error (detected)"); > l2t_err_reset.s.ded_err = 1; > } > @@ -43,12 +43,12 @@ static void octeon_l2c_poll_oct1(struct edac_device_ctl_info *l2c) > l2d_err_reset.u64 = 0; > l2d_err.u64 = cvmx_read_csr(CVMX_L2D_ERR); > if (l2d_err.s.sec_err) { > - edac_device_handle_ce(l2c, 0, 1, > + edac_device_handle_ce(l2c, 1, 0, 1, > "Data Single bit error (corrected)"); > l2d_err_reset.s.sec_err = 1; > } > if (l2d_err.s.ded_err) { > - edac_device_handle_ue(l2c, 0, 1, > + edac_device_handle_ue(l2c, 1, 0, 1, > "Data Double bit error (detected)"); > l2d_err_reset.s.ded_err = 1; > } > @@ -76,25 +76,25 @@ static void _octeon_l2c_poll_oct2(struct edac_device_ctl_info *l2c, int tad) > snprintf(buf2, sizeof(buf2), > "L2D Double bit error (detected):%s", buf1); > err_tdtx_reset.s.dbe = 1; > - edac_device_handle_ue(l2c, tad, 1, buf2); > + edac_device_handle_ue(l2c, 1, tad, 1, buf2); > } > if (err_tdtx.s.sbe) { > snprintf(buf2, sizeof(buf2), > "L2D Single bit error (corrected):%s", buf1); > err_tdtx_reset.s.sbe = 1; > - edac_device_handle_ce(l2c, tad, 1, buf2); > + edac_device_handle_ce(l2c, 1, tad, 1, buf2); > } > if (err_tdtx.s.vdbe) { > snprintf(buf2, sizeof(buf2), > "VBF Double bit error (detected):%s", buf1); > err_tdtx_reset.s.vdbe = 1; > - edac_device_handle_ue(l2c, tad, 1, buf2); > + edac_device_handle_ue(l2c, 1, tad, 1, buf2); > } > if (err_tdtx.s.vsbe) { > snprintf(buf2, sizeof(buf2), > "VBF Single bit error (corrected):%s", buf1); > err_tdtx_reset.s.vsbe = 1; > - edac_device_handle_ce(l2c, tad, 1, buf2); > + edac_device_handle_ce(l2c, 1, tad, 1, buf2); > } > if (err_tdtx_reset.u64) > cvmx_write_csr(CVMX_L2C_ERR_TDTX(tad), err_tdtx_reset.u64); > @@ -111,13 +111,13 @@ static void _octeon_l2c_poll_oct2(struct edac_device_ctl_info *l2c, int tad) > snprintf(buf2, sizeof(buf2), > "Tag Double bit error (detected):%s", buf1); > err_ttgx_reset.s.dbe = 1; > - edac_device_handle_ue(l2c, tad, 0, buf2); > + edac_device_handle_ue(l2c, 1, tad, 0, buf2); > } > if (err_ttgx.s.sbe) { > snprintf(buf2, sizeof(buf2), > "Tag Single bit error (corrected):%s", buf1); > err_ttgx_reset.s.sbe = 1; > - edac_device_handle_ce(l2c, tad, 0, buf2); > + edac_device_handle_ce(l2c, 1, tad, 0, buf2); > } > if (err_ttgx_reset.u64) > cvmx_write_csr(CVMX_L2C_ERR_TTGX(tad), err_ttgx_reset.u64); > diff --git a/drivers/edac/octeon_edac-pc.c b/drivers/edac/octeon_edac-pc.c > index 754eced..efd0bbc 100644 > --- a/drivers/edac/octeon_edac-pc.c > +++ b/drivers/edac/octeon_edac-pc.c > @@ -59,7 +59,7 @@ static int co_cache_error_event(struct notifier_block *this, > (unsigned long long)icache_err, core, cpu, > read_c0_errorepc()); > write_octeon_c0_icacheerr(0); > - edac_device_handle_ce(p->ed, cpu, 1, "icache"); > + edac_device_handle_ce(p->ed, 1, cpu, 1, "icache"); > } > if (dcache_err & 1) { > edac_device_printk(p->ed, KERN_ERR, > @@ -67,9 +67,9 @@ static int co_cache_error_event(struct notifier_block *this, > (unsigned long long)dcache_err, core, cpu, > read_c0_errorepc()); > if (event) > - edac_device_handle_ue(p->ed, cpu, 0, "dcache"); > + edac_device_handle_ue(p->ed, 1, cpu, 0, "dcache"); > else > - edac_device_handle_ce(p->ed, cpu, 0, "dcache"); > + edac_device_handle_ce(p->ed, 1, cpu, 0, "dcache"); > > /* Clear the error indication */ > if (OCTEON_IS_OCTEON2()) > diff --git a/drivers/edac/qcom_edac.c b/drivers/edac/qcom_edac.c > index 97a27e4..8730eed 100644 > --- a/drivers/edac/qcom_edac.c > +++ b/drivers/edac/qcom_edac.c > @@ -261,19 +261,19 @@ dump_syn_reg(struct edac_device_ctl_info *edev_ctl, int err_type, u32 bank) > > switch (err_type) { > case LLCC_DRAM_CE: > - edac_device_handle_ce(edev_ctl, 0, bank, > + edac_device_handle_ce(edev_ctl, 1, 0, bank, > "LLCC Data RAM correctable Error"); > break; > case LLCC_DRAM_UE: > - edac_device_handle_ue(edev_ctl, 0, bank, > + edac_device_handle_ue(edev_ctl, 1, 0, bank, > "LLCC Data RAM uncorrectable Error"); > break; > case LLCC_TRAM_CE: > - edac_device_handle_ce(edev_ctl, 0, bank, > + edac_device_handle_ce(edev_ctl, 1, 0, bank, > "LLCC Tag RAM correctable Error"); > break; > case LLCC_TRAM_UE: > - edac_device_handle_ue(edev_ctl, 0, bank, > + edac_device_handle_ue(edev_ctl, 1, 0, bank, > "LLCC Tag RAM uncorrectable Error"); > break; > default: > diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c > index 34be60f..35a186f 100644 > --- a/drivers/edac/thunderx_edac.c > +++ b/drivers/edac/thunderx_edac.c > @@ -1151,7 +1151,7 @@ static irqreturn_t thunderx_ocx_com_threaded_isr(int irq, void *irq_id) > } > > if (ctx->reg_com_int & OCX_COM_INT_CE) > - edac_device_handle_ce(ocx->edac_dev, 0, 0, msg); > + edac_device_handle_ce(ocx->edac_dev, 1, 0, 0, msg); > > ocx->com_ring_tail++; > } > @@ -1220,9 +1220,9 @@ static irqreturn_t thunderx_ocx_lnk_threaded_isr(int irq, void *irq_id) > strncat(msg, other, OCX_MESSAGE_SIZE); > > if (ctx->reg_com_link_int & OCX_COM_LINK_INT_UE) > - edac_device_handle_ue(ocx->edac_dev, 0, 0, msg); > + edac_device_handle_ue(ocx->edac_dev, 1, 0, 0, msg); > else if (ctx->reg_com_link_int & OCX_COM_LINK_INT_CE) > - edac_device_handle_ce(ocx->edac_dev, 0, 0, msg); > + edac_device_handle_ce(ocx->edac_dev, 1, 0, 0, msg); > > ocx->link_ring_tail++; > } > @@ -1899,9 +1899,9 @@ static irqreturn_t thunderx_l2c_threaded_isr(int irq, void *irq_id) > strncat(msg, other, L2C_MESSAGE_SIZE); > > if (ctx->reg_int & mask_ue) > - edac_device_handle_ue(l2c->edac_dev, 0, 0, msg); > + edac_device_handle_ue(l2c->edac_dev, 1, 0, 0, msg); > else if (ctx->reg_int & mask_ce) > - edac_device_handle_ce(l2c->edac_dev, 0, 0, msg); > + edac_device_handle_ce(l2c->edac_dev, 1, 0, 0, msg); > > l2c->ring_tail++; > } > diff --git a/drivers/edac/xgene_edac.c b/drivers/edac/xgene_edac.c > index e8b81d7..d31a8bb 100644 > --- a/drivers/edac/xgene_edac.c > +++ b/drivers/edac/xgene_edac.c > @@ -574,7 +574,7 @@ static void xgene_edac_pmd_l1_check(struct edac_device_ctl_info *edac_dev, > > if (val & (MEMERR_CPU_ICFESR_CERR_MASK | > MEMERR_CPU_ICFESR_MULTCERR_MASK)) > - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); > > chk_lsu: > val = readl(pg_f + MEMERR_CPU_LSUESR_PAGE_OFFSET); > @@ -618,7 +618,7 @@ static void xgene_edac_pmd_l1_check(struct edac_device_ctl_info *edac_dev, > > if (val & (MEMERR_CPU_LSUESR_CERR_MASK | > MEMERR_CPU_LSUESR_MULTCERR_MASK)) > - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); > > chk_mmu: > val = readl(pg_f + MEMERR_CPU_MMUESR_PAGE_OFFSET); > @@ -665,7 +665,7 @@ static void xgene_edac_pmd_l1_check(struct edac_device_ctl_info *edac_dev, > /* Clear any HW errors */ > writel(val, pg_f + MEMERR_CPU_MMUESR_PAGE_OFFSET); > > - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); > } > > static void xgene_edac_pmd_l2_check(struct edac_device_ctl_info *edac_dev) > @@ -724,10 +724,10 @@ static void xgene_edac_pmd_l2_check(struct edac_device_ctl_info *edac_dev) > > if (val & (MEMERR_L2C_L2ESR_ERR_MASK | > MEMERR_L2C_L2ESR_MULTICERR_MASK)) > - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); > if (val & (MEMERR_L2C_L2ESR_UCERR_MASK | > MEMERR_L2C_L2ESR_MULTUCERR_MASK)) > - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); > > chk_l2c: > /* Check if any memory request timed out on L2 cache */ > @@ -1113,13 +1113,13 @@ static void xgene_edac_l3_check(struct edac_device_ctl_info *edac_dev) > > if (ctx->version <= 1 && > xgene_edac_l3_promote_to_uc_err(l3cesr, l3celr)) { > - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); > return; > } > if (l3cesr & L3C_ESR_CERR_MASK) > - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); > if (l3cesr & L3C_ESR_UCERR_MASK) > - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); > } > > static void xgene_edac_l3_hw_init(struct edac_device_ctl_info *edac_dev, > @@ -1449,7 +1449,7 @@ static void xgene_edac_iob_gic_report(struct edac_device_ctl_info *edac_dev) > writel(err_addr_hi, ctx->dev_csr + GLBL_MSEC_ERRH); > } > if (reg & (SEC_ERR_MASK | MSEC_ERR_MASK)) > - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); > > if (reg & DED_ERR_MASK) { > err_addr_lo = readl(ctx->dev_csr + GLBL_DED_ERRL); > @@ -1470,7 +1470,7 @@ static void xgene_edac_iob_gic_report(struct edac_device_ctl_info *edac_dev) > writel(err_addr_hi, ctx->dev_csr + GLBL_MDED_ERRH); > } > if (reg & (DED_ERR_MASK | MDED_ERR_MASK)) > - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); > } > > static void xgene_edac_rb_report(struct edac_device_ctl_info *edac_dev) > @@ -1675,7 +1675,7 @@ static void xgene_edac_soc_check(struct edac_device_ctl_info *edac_dev) > if (pcp_lp_stat & CSW_SWITCH_TRACE_ERR_MASK) { > dev_info(edac_dev->dev, > "CSW switch trace correctable memory parity error\n"); > - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); > } > > if (!reg) > @@ -1685,14 +1685,14 @@ static void xgene_edac_soc_check(struct edac_device_ctl_info *edac_dev) > if (!soc_mem_err) { > dev_err(edac_dev->dev, "SoC memory parity error 0x%08X\n", > reg); > - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); > return; > } > for (i = 0; i < 31; i++) { > if (reg & (1 << i)) { > dev_err(edac_dev->dev, "%s memory parity error\n", > soc_mem_err[i]); > - edac_device_handle_ue(edac_dev, 0, 0, > + edac_device_handle_ue(edac_dev, 1, 0, 0, > edac_dev->ctl_name); > } > } > -- > 2.7.4
Hi Jan, On 7/17/2019 3:06 PM, Jan Glauber wrote: > Hi Hanna, > > I'm probably missing something but this patch looks like while it adds > the error_count parameter the passed values all seem to be 1. So is the > new parameter used otherwise, maybe in another patch? Yes in another patch. In Amazon L1/L2 edac driver [1], I'm using loop to report on multiple L1 or L2 errors. After this patch I'll remove the loop and pass the errors count. [1]: https://lkml.org/lkml/2019/7/15/349 Thanks, Hanna > > thanks, > Jan
Em Mon, 15 Jul 2019 13:53:07 +0300 Hanna Hawa <hhhawa@amazon.com> escreveu: > Add a counter parameter in order to avoid losing errors count for edac > device, the error count reports the number of errors reported by an edac > device similar to the way MC_EDAC do. > > Signed-off-by: Hanna Hawa <hhhawa@amazon.com> > --- > drivers/edac/altera_edac.c | 20 ++++++++++++-------- > drivers/edac/amd8111_edac.c | 6 +++--- > drivers/edac/cpc925_edac.c | 4 ++-- > drivers/edac/edac_device.c | 18 ++++++++++-------- > drivers/edac/edac_device.h | 8 ++++++-- > drivers/edac/highbank_l2_edac.c | 4 ++-- > drivers/edac/mpc85xx_edac.c | 4 ++-- > drivers/edac/mv64x60_edac.c | 4 ++-- > drivers/edac/octeon_edac-l2c.c | 20 ++++++++++---------- > drivers/edac/octeon_edac-pc.c | 6 +++--- > drivers/edac/qcom_edac.c | 8 ++++---- > drivers/edac/thunderx_edac.c | 10 +++++----- > drivers/edac/xgene_edac.c | 26 +++++++++++++------------- > 13 files changed, 74 insertions(+), 64 deletions(-) > > diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c > index 8816f74..747dd43 100644 > --- a/drivers/edac/altera_edac.c > +++ b/drivers/edac/altera_edac.c > @@ -616,12 +616,12 @@ static irqreturn_t altr_edac_device_handler(int irq, void *dev_id) > if (irq == drvdata->sb_irq) { > if (priv->ce_clear_mask) > writel(priv->ce_clear_mask, drvdata->base); > - edac_device_handle_ce(dci, 0, 0, drvdata->edac_dev_name); > + edac_device_handle_ce(dci, 1, 0, 0, drvdata->edac_dev_name); > ret_value = IRQ_HANDLED; > } else if (irq == drvdata->db_irq) { > if (priv->ue_clear_mask) > writel(priv->ue_clear_mask, drvdata->base); > - edac_device_handle_ue(dci, 0, 0, drvdata->edac_dev_name); > + edac_device_handle_ue(dci, 1, 0, 0, drvdata->edac_dev_name); > panic("\nEDAC:ECC_DEVICE[Uncorrectable errors]\n"); > ret_value = IRQ_HANDLED; > } else { > @@ -919,13 +919,15 @@ static irqreturn_t __maybe_unused altr_edac_a10_ecc_irq(int irq, void *dev_id) > if (irq == dci->sb_irq) { > writel(ALTR_A10_ECC_SERRPENA, > base + ALTR_A10_ECC_INTSTAT_OFST); > - edac_device_handle_ce(dci->edac_dev, 0, 0, dci->edac_dev_name); > + edac_device_handle_ce(dci->edac_dev, 1, 0, 0, > + dci->edac_dev_name); > > return IRQ_HANDLED; > } else if (irq == dci->db_irq) { > writel(ALTR_A10_ECC_DERRPENA, > base + ALTR_A10_ECC_INTSTAT_OFST); > - edac_device_handle_ue(dci->edac_dev, 0, 0, dci->edac_dev_name); > + edac_device_handle_ue(dci->edac_dev, 1, 0, 0, > + dci->edac_dev_name); > if (dci->data->panic) > panic("\nEDAC:ECC_DEVICE[Uncorrectable errors]\n"); > > @@ -1308,14 +1310,16 @@ static irqreturn_t altr_edac_a10_l2_irq(int irq, void *dev_id) > regmap_write(dci->edac->ecc_mgr_map, > A10_SYSGMR_MPU_CLEAR_L2_ECC_OFST, > A10_SYSGMR_MPU_CLEAR_L2_ECC_SB); > - edac_device_handle_ce(dci->edac_dev, 0, 0, dci->edac_dev_name); > + edac_device_handle_ce(dci->edac_dev, 1, 0, 0, > + dci->edac_dev_name); > > return IRQ_HANDLED; > } else if (irq == dci->db_irq) { > regmap_write(dci->edac->ecc_mgr_map, > A10_SYSGMR_MPU_CLEAR_L2_ECC_OFST, > A10_SYSGMR_MPU_CLEAR_L2_ECC_MB); > - edac_device_handle_ue(dci->edac_dev, 0, 0, dci->edac_dev_name); > + edac_device_handle_ue(dci->edac_dev, 1, 0, 0, > + dci->edac_dev_name); > panic("\nEDAC:ECC_DEVICE[Uncorrectable errors]\n"); > > return IRQ_HANDLED; > @@ -1652,12 +1656,12 @@ static irqreturn_t altr_edac_a10_ecc_irq_portb(int irq, void *dev_id) > if (irq == ad->sb_irq) { > writel(priv->ce_clear_mask, > base + ALTR_A10_ECC_INTSTAT_OFST); > - edac_device_handle_ce(ad->edac_dev, 0, 0, ad->edac_dev_name); > + edac_device_handle_ce(ad->edac_dev, 1, 0, 0, ad->edac_dev_name); > return IRQ_HANDLED; > } else if (irq == ad->db_irq) { > writel(priv->ue_clear_mask, > base + ALTR_A10_ECC_INTSTAT_OFST); > - edac_device_handle_ue(ad->edac_dev, 0, 0, ad->edac_dev_name); > + edac_device_handle_ue(ad->edac_dev, 1, 0, 0, ad->edac_dev_name); > return IRQ_HANDLED; > } > > diff --git a/drivers/edac/amd8111_edac.c b/drivers/edac/amd8111_edac.c > index b5786cf..e595fab 100644 > --- a/drivers/edac/amd8111_edac.c > +++ b/drivers/edac/amd8111_edac.c > @@ -303,7 +303,7 @@ static void amd8111_lpc_bridge_check(struct edac_device_ctl_info *edac_dev) > val8 |= IO_CTRL_1_CLEAR_MASK; > edac_pci_write_byte(dev, REG_IO_CTRL_1, val8); > > - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); > } > > if (at_compat_reg_broken == 0) { > @@ -315,8 +315,8 @@ static void amd8111_lpc_bridge_check(struct edac_device_ctl_info *edac_dev) > out8 |= AT_COMPAT_CLRIOCHK; > if (out8 > 0) { > __do_outb(out8, REG_AT_COMPAT); > - edac_device_handle_ue(edac_dev, 0, 0, > - edac_dev->ctl_name); > + edac_device_handle_ue(edac_dev, 1, 0, 0, > + edac_dev->ctl_name); > } > } > } > diff --git a/drivers/edac/cpc925_edac.c b/drivers/edac/cpc925_edac.c > index 3c0881a..eb74865 100644 > --- a/drivers/edac/cpc925_edac.c > +++ b/drivers/edac/cpc925_edac.c > @@ -682,7 +682,7 @@ static void cpc925_cpu_check(struct edac_device_ctl_info *edac_dev) > cpc925_printk(KERN_INFO, "APIMASK 0x%08x\n", apimask); > cpc925_printk(KERN_INFO, "APIEXCP 0x%08x\n", apiexcp); > > - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); > } > > /******************** HT Link err device****************************/ > @@ -756,7 +756,7 @@ static void cpc925_htlink_check(struct edac_device_ctl_info *edac_dev) > __raw_writel(HT_LINKERR_DETECTED, > dev_info->vbase + REG_LINKERR_OFFSET); > > - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); > + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); > } > > static struct cpc925_dev_info cpc925_devs[] = { > diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c > index 65cf2b9..d1de296 100644 > --- a/drivers/edac/edac_device.c > +++ b/drivers/edac/edac_device.c > @@ -556,7 +556,8 @@ static inline int edac_device_get_panic_on_ue(struct edac_device_ctl_info > } > > void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, > - int inst_nr, int block_nr, const char *msg) > + u16 error_count, int inst_nr, int block_nr, > + const char *msg) > { > struct edac_device_instance *instance; > struct edac_device_block *block = NULL; > @@ -582,12 +583,12 @@ void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, > > if (instance->nr_blocks > 0) { > block = instance->blocks + block_nr; > - block->counters.ce_count++; > + block->counters.ce_count += error_count; > } > > /* Propagate the count up the 'totals' tree */ > - instance->counters.ce_count++; > - edac_dev->counters.ce_count++; > + instance->counters.ce_count += error_count; > + edac_dev->counters.ce_count += error_count; > > if (edac_device_get_log_ce(edac_dev)) > edac_device_printk(edac_dev, KERN_WARNING, > @@ -598,7 +599,8 @@ void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, > EXPORT_SYMBOL_GPL(edac_device_handle_ce); > > void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, > - int inst_nr, int block_nr, const char *msg) > + u16 error_count, int inst_nr, int block_nr, > + const char *msg) > { > struct edac_device_instance *instance; > struct edac_device_block *block = NULL; > @@ -624,12 +626,12 @@ void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, > > if (instance->nr_blocks > 0) { > block = instance->blocks + block_nr; > - block->counters.ue_count++; > + block->counters.ue_count += error_count; > } > > /* Propagate the count up the 'totals' tree */ > - instance->counters.ue_count++; > - edac_dev->counters.ue_count++; > + instance->counters.ue_count += error_count; > + edac_dev->counters.ue_count += error_count; Patch itself looks a good idea, but maybe it should rise a WARN() if error_count == 0. That applies for both CE and UE error logic. Thanks, Mauro
On 7/25/2019 9:36 PM, Mauro Carvalho Chehab wrote: >> /* Propagate the count up the 'totals' tree */ >> - instance->counters.ue_count++; >> - edac_dev->counters.ue_count++; >> + instance->counters.ue_count += error_count; >> + edac_dev->counters.ue_count += error_count; > Patch itself looks a good idea, but maybe it should rise a WARN() > if error_count == 0. Good point, shouldn't we use WARN_ONCE here? if the user call edac_device_handle_ue() with error count == 0, it not be change in run-time, only if the error count parameter is calculated somehow, and it'll be the *caller* issue that didn't check the error count. What you think? > > That applies for both CE and UE error logic. Sure. Thanks, Hanna > > Thanks, > Mauro
On 15.07.19 13:53:07, Hanna Hawa wrote: > Add a counter parameter in order to avoid losing errors count for edac > device, the error count reports the number of errors reported by an edac > device similar to the way MC_EDAC do. > > Signed-off-by: Hanna Hawa <hhhawa@amazon.com> > --- > drivers/edac/altera_edac.c | 20 ++++++++++++-------- > drivers/edac/amd8111_edac.c | 6 +++--- > drivers/edac/cpc925_edac.c | 4 ++-- > drivers/edac/edac_device.c | 18 ++++++++++-------- > drivers/edac/edac_device.h | 8 ++++++-- > drivers/edac/highbank_l2_edac.c | 4 ++-- > drivers/edac/mpc85xx_edac.c | 4 ++-- > drivers/edac/mv64x60_edac.c | 4 ++-- > drivers/edac/octeon_edac-l2c.c | 20 ++++++++++---------- > drivers/edac/octeon_edac-pc.c | 6 +++--- > drivers/edac/qcom_edac.c | 8 ++++---- > drivers/edac/thunderx_edac.c | 10 +++++----- > drivers/edac/xgene_edac.c | 26 +++++++++++++------------- > 13 files changed, 74 insertions(+), 64 deletions(-) > diff --git a/drivers/edac/edac_device.h b/drivers/edac/edac_device.h > index 1aaba74..cf1a1da 100644 > --- a/drivers/edac/edac_device.h > +++ b/drivers/edac/edac_device.h > @@ -290,23 +290,27 @@ extern struct edac_device_ctl_info *edac_device_del_device(struct device *dev); > * perform a common output and handling of an 'edac_dev' UE event > * > * @edac_dev: pointer to struct &edac_device_ctl_info > + * @error_count: number of errors of the same type > * @inst_nr: number of the instance where the UE error happened > * @block_nr: number of the block where the UE error happened > * @msg: message to be printed > */ > extern void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, > - int inst_nr, int block_nr, const char *msg); > + u16 error_count, int inst_nr, int block_nr, > + const char *msg); > /** > * edac_device_handle_ce(): > * perform a common output and handling of an 'edac_dev' CE event > * > * @edac_dev: pointer to struct &edac_device_ctl_info > + * @error_count: number of errors of the same type > * @inst_nr: number of the instance where the CE error happened > * @block_nr: number of the block where the CE error happened > * @msg: message to be printed > */ > extern void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, How about renaming this to __edac_device_handle_ce() and then have 2 macros for: * edac_device_handle_ce() to keep old i/f. * edac_device_handle_ce_count(), with count parameter added. Same for uncorrectable errors. Code of other driver can be kept as it is then. Thanks, -Robert > - int inst_nr, int block_nr, const char *msg); > + u16 error_count, int inst_nr, int block_nr, > + const char *msg);
On 8/1/2019 2:35 PM, Robert Richter wrote: > On 15.07.19 13:53:07, Hanna Hawa wrote: >> Add a counter parameter in order to avoid losing errors count for edac >> device, the error count reports the number of errors reported by an edac >> device similar to the way MC_EDAC do. >> >> Signed-off-by: Hanna Hawa <hhhawa@amazon.com> >> --- >> drivers/edac/altera_edac.c | 20 ++++++++++++-------- >> drivers/edac/amd8111_edac.c | 6 +++--- >> drivers/edac/cpc925_edac.c | 4 ++-- >> drivers/edac/edac_device.c | 18 ++++++++++-------- >> drivers/edac/edac_device.h | 8 ++++++-- >> drivers/edac/highbank_l2_edac.c | 4 ++-- >> drivers/edac/mpc85xx_edac.c | 4 ++-- >> drivers/edac/mv64x60_edac.c | 4 ++-- >> drivers/edac/octeon_edac-l2c.c | 20 ++++++++++---------- >> drivers/edac/octeon_edac-pc.c | 6 +++--- >> drivers/edac/qcom_edac.c | 8 ++++---- >> drivers/edac/thunderx_edac.c | 10 +++++----- >> drivers/edac/xgene_edac.c | 26 +++++++++++++------------- >> 13 files changed, 74 insertions(+), 64 deletions(-) > >> diff --git a/drivers/edac/edac_device.h b/drivers/edac/edac_device.h >> index 1aaba74..cf1a1da 100644 >> --- a/drivers/edac/edac_device.h >> +++ b/drivers/edac/edac_device.h >> @@ -290,23 +290,27 @@ extern struct edac_device_ctl_info *edac_device_del_device(struct device *dev); >> * perform a common output and handling of an 'edac_dev' UE event >> * >> * @edac_dev: pointer to struct &edac_device_ctl_info >> + * @error_count: number of errors of the same type >> * @inst_nr: number of the instance where the UE error happened >> * @block_nr: number of the block where the UE error happened >> * @msg: message to be printed >> */ >> extern void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, >> - int inst_nr, int block_nr, const char *msg); >> + u16 error_count, int inst_nr, int block_nr, >> + const char *msg); >> /** >> * edac_device_handle_ce(): >> * perform a common output and handling of an 'edac_dev' CE event >> * >> * @edac_dev: pointer to struct &edac_device_ctl_info >> + * @error_count: number of errors of the same type >> * @inst_nr: number of the instance where the CE error happened >> * @block_nr: number of the block where the CE error happened >> * @msg: message to be printed >> */ >> extern void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, > > How about renaming this to __edac_device_handle_ce() and then have 2 > macros for: > > * edac_device_handle_ce() to keep old i/f. > > * edac_device_handle_ce_count(), with count parameter added. > > Same for uncorrectable errors. > > Code of other driver can be kept as it is then. Don't you think it'll be confused to have different APIs between EDAC_MC and EDAC_DEVICE? (in MC the count passed as part of edac_mc_handle_error()) I don't have strong objection, the change for other drivers is not that hard. > > Thanks, > > -Robert > >> - int inst_nr, int block_nr, const char *msg); >> + u16 error_count, int inst_nr, int block_nr, >> + const char *msg);
On 01.08.19 15:29:03, Hawa, Hanna wrote: > On 8/1/2019 2:35 PM, Robert Richter wrote: > > On 15.07.19 13:53:07, Hanna Hawa wrote: > > > Add a counter parameter in order to avoid losing errors count for edac > > > device, the error count reports the number of errors reported by an edac > > > device similar to the way MC_EDAC do. > > > > > > Signed-off-by: Hanna Hawa <hhhawa@amazon.com> > > > --- > > > drivers/edac/altera_edac.c | 20 ++++++++++++-------- > > > drivers/edac/amd8111_edac.c | 6 +++--- > > > drivers/edac/cpc925_edac.c | 4 ++-- > > > drivers/edac/edac_device.c | 18 ++++++++++-------- > > > drivers/edac/edac_device.h | 8 ++++++-- > > > drivers/edac/highbank_l2_edac.c | 4 ++-- > > > drivers/edac/mpc85xx_edac.c | 4 ++-- > > > drivers/edac/mv64x60_edac.c | 4 ++-- > > > drivers/edac/octeon_edac-l2c.c | 20 ++++++++++---------- > > > drivers/edac/octeon_edac-pc.c | 6 +++--- > > > drivers/edac/qcom_edac.c | 8 ++++---- > > > drivers/edac/thunderx_edac.c | 10 +++++----- > > > drivers/edac/xgene_edac.c | 26 +++++++++++++------------- > > > 13 files changed, 74 insertions(+), 64 deletions(-) > > > > > diff --git a/drivers/edac/edac_device.h b/drivers/edac/edac_device.h > > > index 1aaba74..cf1a1da 100644 > > > --- a/drivers/edac/edac_device.h > > > +++ b/drivers/edac/edac_device.h > > > @@ -290,23 +290,27 @@ extern struct edac_device_ctl_info *edac_device_del_device(struct device *dev); > > > * perform a common output and handling of an 'edac_dev' UE event > > > * > > > * @edac_dev: pointer to struct &edac_device_ctl_info > > > + * @error_count: number of errors of the same type > > > * @inst_nr: number of the instance where the UE error happened > > > * @block_nr: number of the block where the UE error happened > > > * @msg: message to be printed > > > */ > > > extern void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, > > > - int inst_nr, int block_nr, const char *msg); > > > + u16 error_count, int inst_nr, int block_nr, > > > + const char *msg); > > > /** > > > * edac_device_handle_ce(): > > > * perform a common output and handling of an 'edac_dev' CE event > > > * > > > * @edac_dev: pointer to struct &edac_device_ctl_info > > > + * @error_count: number of errors of the same type > > > * @inst_nr: number of the instance where the CE error happened > > > * @block_nr: number of the block where the CE error happened > > > * @msg: message to be printed > > > */ > > > extern void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, > > > > How about renaming this to __edac_device_handle_ce() and then have 2 > > macros for: > > > > * edac_device_handle_ce() to keep old i/f. > > > > * edac_device_handle_ce_count(), with count parameter added. > > > > Same for uncorrectable errors. > > > > Code of other driver can be kept as it is then. > > Don't you think it'll be confused to have different APIs between EDAC_MC and > EDAC_DEVICE? > (in MC the count passed as part of edac_mc_handle_error()) I don't think edac_mc_handle_error() with 11 function arguments is a good reference for somethin we want to adopt. For the majority of drivers you just introduce another useless argument with the following pattern: edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev_name); IMO, the api should be improved when touching it. -Robert
On 8/1/2019 5:17 PM, Robert Richter wrote: >> Don't you think it'll be confused to have different APIs between EDAC_MC and >> EDAC_DEVICE? >> (in MC the count passed as part of edac_mc_handle_error()) > I don't think edac_mc_handle_error() with 11 function arguments is a > good reference for somethin we want to adopt. For the majority of > drivers you just introduce another useless argument with the following > pattern: > > edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev_name); > > IMO, the api should be improved when touching it. Got it, I'll update the patch as you suggested. Thanks, Hanna > > -Robert
diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 8816f74..747dd43 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -616,12 +616,12 @@ static irqreturn_t altr_edac_device_handler(int irq, void *dev_id) if (irq == drvdata->sb_irq) { if (priv->ce_clear_mask) writel(priv->ce_clear_mask, drvdata->base); - edac_device_handle_ce(dci, 0, 0, drvdata->edac_dev_name); + edac_device_handle_ce(dci, 1, 0, 0, drvdata->edac_dev_name); ret_value = IRQ_HANDLED; } else if (irq == drvdata->db_irq) { if (priv->ue_clear_mask) writel(priv->ue_clear_mask, drvdata->base); - edac_device_handle_ue(dci, 0, 0, drvdata->edac_dev_name); + edac_device_handle_ue(dci, 1, 0, 0, drvdata->edac_dev_name); panic("\nEDAC:ECC_DEVICE[Uncorrectable errors]\n"); ret_value = IRQ_HANDLED; } else { @@ -919,13 +919,15 @@ static irqreturn_t __maybe_unused altr_edac_a10_ecc_irq(int irq, void *dev_id) if (irq == dci->sb_irq) { writel(ALTR_A10_ECC_SERRPENA, base + ALTR_A10_ECC_INTSTAT_OFST); - edac_device_handle_ce(dci->edac_dev, 0, 0, dci->edac_dev_name); + edac_device_handle_ce(dci->edac_dev, 1, 0, 0, + dci->edac_dev_name); return IRQ_HANDLED; } else if (irq == dci->db_irq) { writel(ALTR_A10_ECC_DERRPENA, base + ALTR_A10_ECC_INTSTAT_OFST); - edac_device_handle_ue(dci->edac_dev, 0, 0, dci->edac_dev_name); + edac_device_handle_ue(dci->edac_dev, 1, 0, 0, + dci->edac_dev_name); if (dci->data->panic) panic("\nEDAC:ECC_DEVICE[Uncorrectable errors]\n"); @@ -1308,14 +1310,16 @@ static irqreturn_t altr_edac_a10_l2_irq(int irq, void *dev_id) regmap_write(dci->edac->ecc_mgr_map, A10_SYSGMR_MPU_CLEAR_L2_ECC_OFST, A10_SYSGMR_MPU_CLEAR_L2_ECC_SB); - edac_device_handle_ce(dci->edac_dev, 0, 0, dci->edac_dev_name); + edac_device_handle_ce(dci->edac_dev, 1, 0, 0, + dci->edac_dev_name); return IRQ_HANDLED; } else if (irq == dci->db_irq) { regmap_write(dci->edac->ecc_mgr_map, A10_SYSGMR_MPU_CLEAR_L2_ECC_OFST, A10_SYSGMR_MPU_CLEAR_L2_ECC_MB); - edac_device_handle_ue(dci->edac_dev, 0, 0, dci->edac_dev_name); + edac_device_handle_ue(dci->edac_dev, 1, 0, 0, + dci->edac_dev_name); panic("\nEDAC:ECC_DEVICE[Uncorrectable errors]\n"); return IRQ_HANDLED; @@ -1652,12 +1656,12 @@ static irqreturn_t altr_edac_a10_ecc_irq_portb(int irq, void *dev_id) if (irq == ad->sb_irq) { writel(priv->ce_clear_mask, base + ALTR_A10_ECC_INTSTAT_OFST); - edac_device_handle_ce(ad->edac_dev, 0, 0, ad->edac_dev_name); + edac_device_handle_ce(ad->edac_dev, 1, 0, 0, ad->edac_dev_name); return IRQ_HANDLED; } else if (irq == ad->db_irq) { writel(priv->ue_clear_mask, base + ALTR_A10_ECC_INTSTAT_OFST); - edac_device_handle_ue(ad->edac_dev, 0, 0, ad->edac_dev_name); + edac_device_handle_ue(ad->edac_dev, 1, 0, 0, ad->edac_dev_name); return IRQ_HANDLED; } diff --git a/drivers/edac/amd8111_edac.c b/drivers/edac/amd8111_edac.c index b5786cf..e595fab 100644 --- a/drivers/edac/amd8111_edac.c +++ b/drivers/edac/amd8111_edac.c @@ -303,7 +303,7 @@ static void amd8111_lpc_bridge_check(struct edac_device_ctl_info *edac_dev) val8 |= IO_CTRL_1_CLEAR_MASK; edac_pci_write_byte(dev, REG_IO_CTRL_1, val8); - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); } if (at_compat_reg_broken == 0) { @@ -315,8 +315,8 @@ static void amd8111_lpc_bridge_check(struct edac_device_ctl_info *edac_dev) out8 |= AT_COMPAT_CLRIOCHK; if (out8 > 0) { __do_outb(out8, REG_AT_COMPAT); - edac_device_handle_ue(edac_dev, 0, 0, - edac_dev->ctl_name); + edac_device_handle_ue(edac_dev, 1, 0, 0, + edac_dev->ctl_name); } } } diff --git a/drivers/edac/cpc925_edac.c b/drivers/edac/cpc925_edac.c index 3c0881a..eb74865 100644 --- a/drivers/edac/cpc925_edac.c +++ b/drivers/edac/cpc925_edac.c @@ -682,7 +682,7 @@ static void cpc925_cpu_check(struct edac_device_ctl_info *edac_dev) cpc925_printk(KERN_INFO, "APIMASK 0x%08x\n", apimask); cpc925_printk(KERN_INFO, "APIEXCP 0x%08x\n", apiexcp); - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); } /******************** HT Link err device****************************/ @@ -756,7 +756,7 @@ static void cpc925_htlink_check(struct edac_device_ctl_info *edac_dev) __raw_writel(HT_LINKERR_DETECTED, dev_info->vbase + REG_LINKERR_OFFSET); - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); } static struct cpc925_dev_info cpc925_devs[] = { diff --git a/drivers/edac/edac_device.c b/drivers/edac/edac_device.c index 65cf2b9..d1de296 100644 --- a/drivers/edac/edac_device.c +++ b/drivers/edac/edac_device.c @@ -556,7 +556,8 @@ static inline int edac_device_get_panic_on_ue(struct edac_device_ctl_info } void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, - int inst_nr, int block_nr, const char *msg) + u16 error_count, int inst_nr, int block_nr, + const char *msg) { struct edac_device_instance *instance; struct edac_device_block *block = NULL; @@ -582,12 +583,12 @@ void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, if (instance->nr_blocks > 0) { block = instance->blocks + block_nr; - block->counters.ce_count++; + block->counters.ce_count += error_count; } /* Propagate the count up the 'totals' tree */ - instance->counters.ce_count++; - edac_dev->counters.ce_count++; + instance->counters.ce_count += error_count; + edac_dev->counters.ce_count += error_count; if (edac_device_get_log_ce(edac_dev)) edac_device_printk(edac_dev, KERN_WARNING, @@ -598,7 +599,8 @@ void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, EXPORT_SYMBOL_GPL(edac_device_handle_ce); void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, - int inst_nr, int block_nr, const char *msg) + u16 error_count, int inst_nr, int block_nr, + const char *msg) { struct edac_device_instance *instance; struct edac_device_block *block = NULL; @@ -624,12 +626,12 @@ void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, if (instance->nr_blocks > 0) { block = instance->blocks + block_nr; - block->counters.ue_count++; + block->counters.ue_count += error_count; } /* Propagate the count up the 'totals' tree */ - instance->counters.ue_count++; - edac_dev->counters.ue_count++; + instance->counters.ue_count += error_count; + edac_dev->counters.ue_count += error_count; if (edac_device_get_log_ue(edac_dev)) edac_device_printk(edac_dev, KERN_EMERG, diff --git a/drivers/edac/edac_device.h b/drivers/edac/edac_device.h index 1aaba74..cf1a1da 100644 --- a/drivers/edac/edac_device.h +++ b/drivers/edac/edac_device.h @@ -290,23 +290,27 @@ extern struct edac_device_ctl_info *edac_device_del_device(struct device *dev); * perform a common output and handling of an 'edac_dev' UE event * * @edac_dev: pointer to struct &edac_device_ctl_info + * @error_count: number of errors of the same type * @inst_nr: number of the instance where the UE error happened * @block_nr: number of the block where the UE error happened * @msg: message to be printed */ extern void edac_device_handle_ue(struct edac_device_ctl_info *edac_dev, - int inst_nr, int block_nr, const char *msg); + u16 error_count, int inst_nr, int block_nr, + const char *msg); /** * edac_device_handle_ce(): * perform a common output and handling of an 'edac_dev' CE event * * @edac_dev: pointer to struct &edac_device_ctl_info + * @error_count: number of errors of the same type * @inst_nr: number of the instance where the CE error happened * @block_nr: number of the block where the CE error happened * @msg: message to be printed */ extern void edac_device_handle_ce(struct edac_device_ctl_info *edac_dev, - int inst_nr, int block_nr, const char *msg); + u16 error_count, int inst_nr, int block_nr, + const char *msg); /** * edac_device_alloc_index: Allocate a unique device index number diff --git a/drivers/edac/highbank_l2_edac.c b/drivers/edac/highbank_l2_edac.c index cd9a2bb..65f016a 100644 --- a/drivers/edac/highbank_l2_edac.c +++ b/drivers/edac/highbank_l2_edac.c @@ -39,11 +39,11 @@ static irqreturn_t highbank_l2_err_handler(int irq, void *dev_id) if (irq == drvdata->sb_irq) { writel(1, drvdata->base + SR_CLR_SB_ECC_INTR); - edac_device_handle_ce(dci, 0, 0, dci->ctl_name); + edac_device_handle_ce(dci, 1, 0, 0, dci->ctl_name); } if (irq == drvdata->db_irq) { writel(1, drvdata->base + SR_CLR_DB_ECC_INTR); - edac_device_handle_ue(dci, 0, 0, dci->ctl_name); + edac_device_handle_ue(dci, 1, 0, 0, dci->ctl_name); } return IRQ_HANDLED; diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c index 67f7bc3..0618a06 100644 --- a/drivers/edac/mpc85xx_edac.c +++ b/drivers/edac/mpc85xx_edac.c @@ -464,10 +464,10 @@ static void mpc85xx_l2_check(struct edac_device_ctl_info *edac_dev) out_be32(pdata->l2_vbase + MPC85XX_L2_ERRDET, err_detect); if (err_detect & L2_EDE_CE_MASK) - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); if (err_detect & L2_EDE_UE_MASK) - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); } static irqreturn_t mpc85xx_l2_isr(int irq, void *dev_id) diff --git a/drivers/edac/mv64x60_edac.c b/drivers/edac/mv64x60_edac.c index 3c68bb5..005b012 100644 --- a/drivers/edac/mv64x60_edac.c +++ b/drivers/edac/mv64x60_edac.c @@ -251,7 +251,7 @@ static void mv64x60_sram_check(struct edac_device_ctl_info *edac_dev) readl(pdata->sram_vbase + MV64X60_SRAM_ERR_PARITY)); writel(0, pdata->sram_vbase + MV64X60_SRAM_ERR_CAUSE); - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); } static irqreturn_t mv64x60_sram_isr(int irq, void *dev_id) @@ -417,7 +417,7 @@ static void mv64x60_cpu_check(struct edac_device_ctl_info *edac_dev) readl(pdata->cpu_vbase[1] + MV64x60_CPU_ERR_PARITY)); writel(0, pdata->cpu_vbase[1] + MV64x60_CPU_ERR_CAUSE); - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); } static irqreturn_t mv64x60_cpu_isr(int irq, void *dev_id) diff --git a/drivers/edac/octeon_edac-l2c.c b/drivers/edac/octeon_edac-l2c.c index c33059e..8e58531 100644 --- a/drivers/edac/octeon_edac-l2c.c +++ b/drivers/edac/octeon_edac-l2c.c @@ -28,12 +28,12 @@ static void octeon_l2c_poll_oct1(struct edac_device_ctl_info *l2c) l2t_err_reset.u64 = 0; l2t_err.u64 = cvmx_read_csr(CVMX_L2T_ERR); if (l2t_err.s.sec_err) { - edac_device_handle_ce(l2c, 0, 0, + edac_device_handle_ce(l2c, 1, 0, 0, "Tag Single bit error (corrected)"); l2t_err_reset.s.sec_err = 1; } if (l2t_err.s.ded_err) { - edac_device_handle_ue(l2c, 0, 0, + edac_device_handle_ue(l2c, 1, 0, 0, "Tag Double bit error (detected)"); l2t_err_reset.s.ded_err = 1; } @@ -43,12 +43,12 @@ static void octeon_l2c_poll_oct1(struct edac_device_ctl_info *l2c) l2d_err_reset.u64 = 0; l2d_err.u64 = cvmx_read_csr(CVMX_L2D_ERR); if (l2d_err.s.sec_err) { - edac_device_handle_ce(l2c, 0, 1, + edac_device_handle_ce(l2c, 1, 0, 1, "Data Single bit error (corrected)"); l2d_err_reset.s.sec_err = 1; } if (l2d_err.s.ded_err) { - edac_device_handle_ue(l2c, 0, 1, + edac_device_handle_ue(l2c, 1, 0, 1, "Data Double bit error (detected)"); l2d_err_reset.s.ded_err = 1; } @@ -76,25 +76,25 @@ static void _octeon_l2c_poll_oct2(struct edac_device_ctl_info *l2c, int tad) snprintf(buf2, sizeof(buf2), "L2D Double bit error (detected):%s", buf1); err_tdtx_reset.s.dbe = 1; - edac_device_handle_ue(l2c, tad, 1, buf2); + edac_device_handle_ue(l2c, 1, tad, 1, buf2); } if (err_tdtx.s.sbe) { snprintf(buf2, sizeof(buf2), "L2D Single bit error (corrected):%s", buf1); err_tdtx_reset.s.sbe = 1; - edac_device_handle_ce(l2c, tad, 1, buf2); + edac_device_handle_ce(l2c, 1, tad, 1, buf2); } if (err_tdtx.s.vdbe) { snprintf(buf2, sizeof(buf2), "VBF Double bit error (detected):%s", buf1); err_tdtx_reset.s.vdbe = 1; - edac_device_handle_ue(l2c, tad, 1, buf2); + edac_device_handle_ue(l2c, 1, tad, 1, buf2); } if (err_tdtx.s.vsbe) { snprintf(buf2, sizeof(buf2), "VBF Single bit error (corrected):%s", buf1); err_tdtx_reset.s.vsbe = 1; - edac_device_handle_ce(l2c, tad, 1, buf2); + edac_device_handle_ce(l2c, 1, tad, 1, buf2); } if (err_tdtx_reset.u64) cvmx_write_csr(CVMX_L2C_ERR_TDTX(tad), err_tdtx_reset.u64); @@ -111,13 +111,13 @@ static void _octeon_l2c_poll_oct2(struct edac_device_ctl_info *l2c, int tad) snprintf(buf2, sizeof(buf2), "Tag Double bit error (detected):%s", buf1); err_ttgx_reset.s.dbe = 1; - edac_device_handle_ue(l2c, tad, 0, buf2); + edac_device_handle_ue(l2c, 1, tad, 0, buf2); } if (err_ttgx.s.sbe) { snprintf(buf2, sizeof(buf2), "Tag Single bit error (corrected):%s", buf1); err_ttgx_reset.s.sbe = 1; - edac_device_handle_ce(l2c, tad, 0, buf2); + edac_device_handle_ce(l2c, 1, tad, 0, buf2); } if (err_ttgx_reset.u64) cvmx_write_csr(CVMX_L2C_ERR_TTGX(tad), err_ttgx_reset.u64); diff --git a/drivers/edac/octeon_edac-pc.c b/drivers/edac/octeon_edac-pc.c index 754eced..efd0bbc 100644 --- a/drivers/edac/octeon_edac-pc.c +++ b/drivers/edac/octeon_edac-pc.c @@ -59,7 +59,7 @@ static int co_cache_error_event(struct notifier_block *this, (unsigned long long)icache_err, core, cpu, read_c0_errorepc()); write_octeon_c0_icacheerr(0); - edac_device_handle_ce(p->ed, cpu, 1, "icache"); + edac_device_handle_ce(p->ed, 1, cpu, 1, "icache"); } if (dcache_err & 1) { edac_device_printk(p->ed, KERN_ERR, @@ -67,9 +67,9 @@ static int co_cache_error_event(struct notifier_block *this, (unsigned long long)dcache_err, core, cpu, read_c0_errorepc()); if (event) - edac_device_handle_ue(p->ed, cpu, 0, "dcache"); + edac_device_handle_ue(p->ed, 1, cpu, 0, "dcache"); else - edac_device_handle_ce(p->ed, cpu, 0, "dcache"); + edac_device_handle_ce(p->ed, 1, cpu, 0, "dcache"); /* Clear the error indication */ if (OCTEON_IS_OCTEON2()) diff --git a/drivers/edac/qcom_edac.c b/drivers/edac/qcom_edac.c index 97a27e4..8730eed 100644 --- a/drivers/edac/qcom_edac.c +++ b/drivers/edac/qcom_edac.c @@ -261,19 +261,19 @@ dump_syn_reg(struct edac_device_ctl_info *edev_ctl, int err_type, u32 bank) switch (err_type) { case LLCC_DRAM_CE: - edac_device_handle_ce(edev_ctl, 0, bank, + edac_device_handle_ce(edev_ctl, 1, 0, bank, "LLCC Data RAM correctable Error"); break; case LLCC_DRAM_UE: - edac_device_handle_ue(edev_ctl, 0, bank, + edac_device_handle_ue(edev_ctl, 1, 0, bank, "LLCC Data RAM uncorrectable Error"); break; case LLCC_TRAM_CE: - edac_device_handle_ce(edev_ctl, 0, bank, + edac_device_handle_ce(edev_ctl, 1, 0, bank, "LLCC Tag RAM correctable Error"); break; case LLCC_TRAM_UE: - edac_device_handle_ue(edev_ctl, 0, bank, + edac_device_handle_ue(edev_ctl, 1, 0, bank, "LLCC Tag RAM uncorrectable Error"); break; default: diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c index 34be60f..35a186f 100644 --- a/drivers/edac/thunderx_edac.c +++ b/drivers/edac/thunderx_edac.c @@ -1151,7 +1151,7 @@ static irqreturn_t thunderx_ocx_com_threaded_isr(int irq, void *irq_id) } if (ctx->reg_com_int & OCX_COM_INT_CE) - edac_device_handle_ce(ocx->edac_dev, 0, 0, msg); + edac_device_handle_ce(ocx->edac_dev, 1, 0, 0, msg); ocx->com_ring_tail++; } @@ -1220,9 +1220,9 @@ static irqreturn_t thunderx_ocx_lnk_threaded_isr(int irq, void *irq_id) strncat(msg, other, OCX_MESSAGE_SIZE); if (ctx->reg_com_link_int & OCX_COM_LINK_INT_UE) - edac_device_handle_ue(ocx->edac_dev, 0, 0, msg); + edac_device_handle_ue(ocx->edac_dev, 1, 0, 0, msg); else if (ctx->reg_com_link_int & OCX_COM_LINK_INT_CE) - edac_device_handle_ce(ocx->edac_dev, 0, 0, msg); + edac_device_handle_ce(ocx->edac_dev, 1, 0, 0, msg); ocx->link_ring_tail++; } @@ -1899,9 +1899,9 @@ static irqreturn_t thunderx_l2c_threaded_isr(int irq, void *irq_id) strncat(msg, other, L2C_MESSAGE_SIZE); if (ctx->reg_int & mask_ue) - edac_device_handle_ue(l2c->edac_dev, 0, 0, msg); + edac_device_handle_ue(l2c->edac_dev, 1, 0, 0, msg); else if (ctx->reg_int & mask_ce) - edac_device_handle_ce(l2c->edac_dev, 0, 0, msg); + edac_device_handle_ce(l2c->edac_dev, 1, 0, 0, msg); l2c->ring_tail++; } diff --git a/drivers/edac/xgene_edac.c b/drivers/edac/xgene_edac.c index e8b81d7..d31a8bb 100644 --- a/drivers/edac/xgene_edac.c +++ b/drivers/edac/xgene_edac.c @@ -574,7 +574,7 @@ static void xgene_edac_pmd_l1_check(struct edac_device_ctl_info *edac_dev, if (val & (MEMERR_CPU_ICFESR_CERR_MASK | MEMERR_CPU_ICFESR_MULTCERR_MASK)) - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); chk_lsu: val = readl(pg_f + MEMERR_CPU_LSUESR_PAGE_OFFSET); @@ -618,7 +618,7 @@ static void xgene_edac_pmd_l1_check(struct edac_device_ctl_info *edac_dev, if (val & (MEMERR_CPU_LSUESR_CERR_MASK | MEMERR_CPU_LSUESR_MULTCERR_MASK)) - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); chk_mmu: val = readl(pg_f + MEMERR_CPU_MMUESR_PAGE_OFFSET); @@ -665,7 +665,7 @@ static void xgene_edac_pmd_l1_check(struct edac_device_ctl_info *edac_dev, /* Clear any HW errors */ writel(val, pg_f + MEMERR_CPU_MMUESR_PAGE_OFFSET); - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); } static void xgene_edac_pmd_l2_check(struct edac_device_ctl_info *edac_dev) @@ -724,10 +724,10 @@ static void xgene_edac_pmd_l2_check(struct edac_device_ctl_info *edac_dev) if (val & (MEMERR_L2C_L2ESR_ERR_MASK | MEMERR_L2C_L2ESR_MULTICERR_MASK)) - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); if (val & (MEMERR_L2C_L2ESR_UCERR_MASK | MEMERR_L2C_L2ESR_MULTUCERR_MASK)) - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); chk_l2c: /* Check if any memory request timed out on L2 cache */ @@ -1113,13 +1113,13 @@ static void xgene_edac_l3_check(struct edac_device_ctl_info *edac_dev) if (ctx->version <= 1 && xgene_edac_l3_promote_to_uc_err(l3cesr, l3celr)) { - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); return; } if (l3cesr & L3C_ESR_CERR_MASK) - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); if (l3cesr & L3C_ESR_UCERR_MASK) - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); } static void xgene_edac_l3_hw_init(struct edac_device_ctl_info *edac_dev, @@ -1449,7 +1449,7 @@ static void xgene_edac_iob_gic_report(struct edac_device_ctl_info *edac_dev) writel(err_addr_hi, ctx->dev_csr + GLBL_MSEC_ERRH); } if (reg & (SEC_ERR_MASK | MSEC_ERR_MASK)) - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); if (reg & DED_ERR_MASK) { err_addr_lo = readl(ctx->dev_csr + GLBL_DED_ERRL); @@ -1470,7 +1470,7 @@ static void xgene_edac_iob_gic_report(struct edac_device_ctl_info *edac_dev) writel(err_addr_hi, ctx->dev_csr + GLBL_MDED_ERRH); } if (reg & (DED_ERR_MASK | MDED_ERR_MASK)) - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); } static void xgene_edac_rb_report(struct edac_device_ctl_info *edac_dev) @@ -1675,7 +1675,7 @@ static void xgene_edac_soc_check(struct edac_device_ctl_info *edac_dev) if (pcp_lp_stat & CSW_SWITCH_TRACE_ERR_MASK) { dev_info(edac_dev->dev, "CSW switch trace correctable memory parity error\n"); - edac_device_handle_ce(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ce(edac_dev, 1, 0, 0, edac_dev->ctl_name); } if (!reg) @@ -1685,14 +1685,14 @@ static void xgene_edac_soc_check(struct edac_device_ctl_info *edac_dev) if (!soc_mem_err) { dev_err(edac_dev->dev, "SoC memory parity error 0x%08X\n", reg); - edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name); + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); return; } for (i = 0; i < 31; i++) { if (reg & (1 << i)) { dev_err(edac_dev->dev, "%s memory parity error\n", soc_mem_err[i]); - edac_device_handle_ue(edac_dev, 0, 0, + edac_device_handle_ue(edac_dev, 1, 0, 0, edac_dev->ctl_name); } }
Add a counter parameter in order to avoid losing errors count for edac device, the error count reports the number of errors reported by an edac device similar to the way MC_EDAC do. Signed-off-by: Hanna Hawa <hhhawa@amazon.com> --- drivers/edac/altera_edac.c | 20 ++++++++++++-------- drivers/edac/amd8111_edac.c | 6 +++--- drivers/edac/cpc925_edac.c | 4 ++-- drivers/edac/edac_device.c | 18 ++++++++++-------- drivers/edac/edac_device.h | 8 ++++++-- drivers/edac/highbank_l2_edac.c | 4 ++-- drivers/edac/mpc85xx_edac.c | 4 ++-- drivers/edac/mv64x60_edac.c | 4 ++-- drivers/edac/octeon_edac-l2c.c | 20 ++++++++++---------- drivers/edac/octeon_edac-pc.c | 6 +++--- drivers/edac/qcom_edac.c | 8 ++++---- drivers/edac/thunderx_edac.c | 10 +++++----- drivers/edac/xgene_edac.c | 26 +++++++++++++------------- 13 files changed, 74 insertions(+), 64 deletions(-)